Expertise

The relevance and added value of artificial intelligence (AI) and machine learning (ML) have increased significantly in recent years. Extensive potential has emerged, particularly in the area of production. However, the high complexity of ML and the lack of evidence of its added value often mean that particularly small and medium-sized enterprises (SMEs) do not engage further with its introduction and use. For this reason, a holistic guide has been developed that accompanies manufacturing SMEs from the identification of suitable use cases and maturity level analysis through to the implementation of measures and continuous improvement processes, providing the required concepts.

Machine learning, implementation strategy, guide, production, maturity level

Process monitoring and the resulting increase in quality through AI are attracting increasing attention in large parts of the manufacturing industry. The possibilities of inline process monitoring of cross-wedge rolling are being investigated as part of the research of the Collaborative Research Center 1153. The aim is to develop a monitoring system that enables inline process control in order to compensate process deviations that occur during the forming process. Therefore, an algorithm is developed that can detect and classify process deviations within a few seconds and while the process is still running. An AI-based image recognition algorithm was applied as part of this research work. The process data was collected as part of a sensitivity study of the process parameters. A parameter study was used to determine optimized hyperparameters for AI modeling that enable a high prediction accuracy. The challenge of the necessary speed of the prediction was tested and validated. The evaluation of the algorithm including the generation of a picture requires 270 ms on average and is therefore fast enough to be used as preparation for process control. The investigations revealed a possibility for data augmentation that significantly increases the predictive accuracy of the models. Leave-One-Out Cross-Validation (LOOCV) was used to conclude the overall performance of the model.

Cross-wedge rolling, Hybrid components, Process monitoring, AI-based image recognition

Artificial intelligence (AI) can be used to reliably recognise errors, reduce defective parts and increase component quality. In the 'AutoPress' project, researchers have developed a system of sensors and AI that recognises 95 to 98 per cent of all process deviations.

Artificial intelligence, AI, process monitoring, error detection

This work explores the challenges of fully automating in-house goods transport in environments where industrial trucks like forklift trucks remain necessary due to undefined load carrier positions and shapes. Imitation Learning (IL) is identified as a promising solution for vehicle control in repetitive tasks, yet its application in intralogistics is challenging by the dynamic complexity of industrial trucks and the large dimensional space involved. A Robot Operating System 2 (ROS2) framework is introduced, enabling the acquisition of driving data from both simulation environments and real-world demonstrators. The study also presents a network architecture combining a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) network, facilitating end-to-end learning from spatial and temporal image data. The framework's effectiveness is evaluated using a dataset of expert driving maneuvers to assess the generalization potential of the IL-trained network in vehicle control in different scenarios. The research aims to demonstrate the utility of the proposed framework for data acquisition and validate IL as a control approach for industrial trucks that require generalization.

Imitation Learning, industrial truck automation, intralogistics, ROS2, load handling

The use of injection molds enables the economical mass production of products. As the interface between product development and production, tooling must be able to submit a reliable target price quotation as early as possible. Due to an increasingly intense global competition, the efforts for production of injection molds should be estimated as accurately as possible before an investment is made. 

In the present work, a method for estimating manufacturing efforts based on article data, which are available during the request for quotation, is therefore developed. The basis is a model based on machine learning methods, which is trained with the geometry data of the articles as well as with the corresponding article and tool related metadata. In addition, a system for implementing the method will be developed. This transforms the method into a self-learning system. 

In two case studies, the developed method is applied to two concrete use cases from the production world - injection molding and additive manufacturing. The system is implemented in the form of a software demonstrator and evaluated using real production data.

Tooling, injection molding, machine learning, additive manufacturing, effort estimation

Increasing the service life and process reliability of systems plays an important role in terms of sustainable and economical production. Especially in the field of energy-intensive bulk forming, low scrap rates and long tool lifetimes are business critical. This article describes a modular method for AI-supported process monitoring during hot forming within a screw press. With this method, the following deviations can be detected in an integrated process: the height of the semi-finished product, the positions of the die and the position of the semi-finished product. The method was developed using the CRISP-DM standard. A modular sensor concept was developed that can be used for different screw presses and dies. Subsequently a hot forming-optimized test plan was developed to examine individual and overlapping process deviations. By applying various methods of artificial intelligence, a method for process-integrated detection of process deviations was developed. The results of the investigation show the potential of the developed method and offer starting points for the investigation of further process parameters.

Process monitoring, Wear, Hot forming, Predictive maintenance, Quality management

Automated industrial trucks master difficult driving situations worse than humans – for now. New approaches based on artificial intelligence (AI) are intended to replicate human driving behavior and give automated systems more flexibility.

artificial intelligence, intralogistics, industrial trucks

Bees are an important part of local ecosystems. Many companies have beehives set up on their company premises and looked after by beekeepers as an ecological measure. Remote digital monitoring can be a useful way of reducing the workload while ensuring the health and continued existence of the bee colony. The developed prototype and AI-based object recognition offers beekeepers the opportunity to monitor activity levels in the hive, detect intruders such as wasps or recognize a drone brood at an early stage, which occurs when the queen bee dies.

AI, image-recognition, Bees

IPH is developing an autonomously flying indoor drone in the AIMS 5.0 research project as one of 20 application examples for the industry of the future. The project is funded by the EU and involves 53 research and industry partners from twelve countries.

Drone, copter, data acquisition, digital twin, industry 5.0

An ageing society and the emergence of new diseases are generating rapid growth in the healthcare industry in many industrialized countries. The use of AI can lead to an increase in performance while at the same time reducing costs. This is why the use of AI in the medical technology is continuously increasing, driven by the numerous benefits it brings, including

• Diagnosis can be significantly optimized by incorporating extensive experiential knowledge into and retrieving it from AI systems. In this respect, AI enables us to analyze images, laboratory results and patient files can be analyzed and evaluated.
• Individualized treatment plans can be developed through the use of AI can be developed. These plans holistically take into account all aspects of the patient and thus help to significantly increase the effectiveness significantly increase the effectiveness of the therapy.
• Predictive analyses are made possible through the use of AI. AI can identify risk factors and predict complications.

AI, Unsupervised Learning, Diagnostics

Energy transition yes, but a wind turbine nearby? No! The expansion of wind energy is urgently needed, but resistance in the neighborhood and from nature conservation associations delays or stops many construction projects. Using artificial intelligence (AI), the interdisciplinary WindGISKI joint project aims to accelerate the expansion of wind energy. Eight companies, associations and research institutions are developing a geo-information system that will predict the prospects of success for wind energy construction projects.

artificial intelligence, AI, energy transition, wind energy, land evaluation, geoinformation system

Machine learning is already used in many areas of everyday life and offers far-reaching potential in production. At the same time, the efficient use of resources is becoming increasingly important due to the growing relevance of ESG. By implementing machine learning in production to increase resource efficiency, companies can become more effective and efficient while implementing ESG strategies. SMEs, in particular, face a major challenge when it comes to implementation. In addition to the high complexity of Machine Learning applications, there is often a lack of knowledge about suitable application possibilities as well as a lack of conviction about the benefits that can be derived from them. In the following article, applications of Machine Learning to increase resource efficiency along the internal supply chain as well as their potentials are discussed.

Machine Learning, production, resource efficiency

The use of machine learning has already become es-tablished and is applied in many areas of everyday life. Machine Learning is also becoming increasingly important in the field of production and logistics. However, the complex implementation poses major challenges, especially for small and medium-sized enterprises (SMEs). This leads to the fact that many SMEs refrain from using Machine Learning applications. For this reason, IPH – Institut für Integrierte Produktion and IPRI – International Performance Research Institute are working together on the research project „MLready“ to develop an implementation strategy that will enable SMEs to im-plement and use machine learning easily and efficiently.

machine learning, SMEs, production, ML implementation strategy

Although factory planning is widely recognized as a way to significantly enhance manufacturing productivity, the associated costs in terms of time and money can be prohibitive. In this paper, we present a solution to this challenge through the development of a Software-in-the-loop (SITL) framework that leverages an Unmanned Aircraft System (UAS) in an autonomous capacity. The framework incorporates simulated sensors, a UAS, and a virtual factory environment. Moreover, we propose a Deep Reinforcement Learning (DRL) agent that is capable of collision avoidance and exploration using the Dueling Double Deep Q-Network (3DQN) with prioritized experience replay.

Artificial Intelligence, reinforcement learning, Unmanned Aircraft Systems

Progressive digitalization and new technologies have had a major impact on the development of artificial intelligence (AI) in recent years. Particularly for companies in the skilled trades sector, the time factor is taking on an increasingly changing customer behavior, more complex and demanding tasks, and other challenges, the time factor is playing an increasingly decisive role.

artificial intelligence, craft, guideline

In order to use laser transmission welding (LTW) for additively manufactured parts such as prototypes, small series, or one-off products, an enhanced process knowledge is needed to overcome the difficulties in the part composition resulting from the additive manufacturing process itself. In comparison to an injection molding process for thermoplastic parts, the additive manufacturing process fused deposition modeling leads to an inhomogeneous structure with trapped air inside the volume.

In this paper, a neural network-based expert system is presented that provides the user with process knowledge in order to improve the weld seam quality of laser welded additively manufactured parts. Both additive manufacturing and LTW process are assisted by the expert system. First, the designed expert system supports the user in setting up the additive manufacturing process to increase the transmissivity. During welding, the additive manufacturing and LTW process parameters are used to predict the weld seam strength. To create the database for the expert system, specimens of transparent and black polylactide are additively manufactured. In order to change the transmissivity at an emission wavelength of 940?nm of the diode laser used, the manufacturing parameters for the transparent parts are varied. The transmissivity of the parts is measured with a spectroscope. The transparent samples are welded to the black samples with laser powers between 8 and 14?W in the overlap configuration and shear tensile tests are performed. In this work, the predictions of the transmissivity and the shear tensile force are demonstrated with an accuracy of more than 88.1% of the neural networks used for the expert system.

Additive manufacturing, laser transmission welding, neural networks, expert system

Laser transmission welding (LTW) is a known technique to join conventionally produced thermoplastic parts, e.g. injected molded parts. When using LTW for additively manufactured parts (usually prototypes, small series), this technique has to be evolved to overcome the difficulties in the part composition resulted in the additive manufacturing process itself.

In this paper, a method is presented to enhance the weld seam quality of laser welded additively manufactured parts assisted by a neural network-based expert system. To validate the expert system, specimens are additively manufactured from polylactide. The parameters of the additive manufacturing process, the transmissivity, and the LTW process parameters are used to predict the shear tensile force with the neural network. The transparent samples are welded to black absorbent samples in overlap configuration and shear tensile tests are performed. In this work, the prediction of the shear tensile force with an accuracy of 88.1 % of the neuronal network based expert system is demonstrated.

Additive manufacturing, laser transmission welding, neural networks, expert system

Factory planning can increase the productivity of manufacturing significantly, though the process is expensive when it comes to cost and time. In this paper, we propose an Unmanned Aerial Vehicle (UAV) framework that accelerates this process and decreases the costs. The framework consists of a UAV that is equipped with an IMU, a camera and a LiDAR sensor in order to navigate and explore unknown indoor environments. Thus, it is independent of GNSS and solely uses on-board sensors. The acquired data should enable a DRL agent to perform autonomous decision making, applying a reinforcement learning approach. We propose a simulation of this framework including several training and testing environments, that should be used for developing a DRL agent.

drone, UAS, deep reinforcement learning

Progress is urgently needed in the energy transition - but there are always acceptance problems and lawsuits with renewable energies. In the project "WindGISKI", a geoinformation system based on artificial intelligence is to be developed, which addresses these issues. In a preliminary project, influencing factors within the area of conflict between species, environmental and climate protection have already been identified. An interdisciplinary team from science and industry is now taking the next step with the development of artificial intelligence.

wind energy, area selection, artificial intelligence

Laser transmission welding (LTW) is a known technique to join conventionally produced high volume thermoplastic parts, e.g. injected molded parts for the automotive sector. For using LTW for additively manufactured parts (usually prototypes, small series, or one-off products), this technique has to be evolved to overcome the difficulties in the part composition resulted in the additive manufacturing process itself. In comparison to the injection molding process, the additive manufacturing process leads to an inhomogeneous structure with trapped air inside the volume. Therefore, a change in the transmissivity results due to the additive manufacturing process.

In this paper, a method is presented to enhance the weld seam quality of laser welded additively manufactured parts assisted by a neural network-based expert system. The designed expert system supports the user setting up the additive manufacturing process. With the results of a preliminary work, a neural network is trained to predict the transmissivity values of the transparent samples. To validate the expert system, specimen of transparent polylactide are additively manufactured with various manufacturing parameters in order to change the transmissivity. The transmissivity of the parts are measured with a spectroscope. The parameters of the additive manufacturing process are used to predict the transmissivity with the neural network and are compared to the measurements. The transparent samples are welded to black polylactide samples with different laser power in overlap configuration and shear tensile tests are performed. With these experiments, the prediction of additive manufacturing parameters with the expert system in order to use the parts for a LTW process is demonstrated.

Additive manufacturing, laser transmission welding, neural networks, expert system

Product complexity and variant diversity increase the effort for the development of production processes at SMEs. As part of the IGF research project "Self-learning multi-stage quality monitoring processes for (laser) material processing" (AiF No.: 20419N), an expert system was therefore developed for manufacturing companies in the field of laser material processing. The expert system supports users in process control and quality prediction of new products and product variants .

laser material processing, expert system, machine learning

Reducing the planning and development time for efficient staging sequences in closed die forging offers companies in the forging industry a high potential for responding to competitive to respond to competitive challenges and remain competitive.The digitization of development processes opens up innovative support options for companies.

forging sequence desing, forming technology, digitization, process development, CAD

To increase the economic efficiency in the production of geometrically complicated forgings, material efficiency is a determining factor. In this study, a method is being validated to automatically design a multi-staged forging sequence initially based on the CAD file of the forging. The method is intended to generate material-efficient forging sequences and reduce development time and dependence on reference processes in the design of forging sequences. Artificial neural networks are used to analyze the geometry of the forging and classify it into a shape class. Result of the analysis is information on component characteristics, such as bending and holes. From this, special operations such as a bending process in the forging sequence can be derived. A slicer algorithm is used to divide the CAD file of the forging into cutting planes and calculate the mass distribution around the center of gravity line of the forging. An algorithm approaches the mass distribution and cross-sectional contour step by step from the forging to the semi-finished product. Each intermediate form is exported as a CAD file. The algorithm takes less than 10 min to design a four-stage forging sequence. The designed forging sequences are checked by FE simulations. Quality criteria that are evaluated and investigated are form filling and folds. First FE simulations show that the automatically generated forging sequences allow the production of different forgings. In an iterative adaptation process, the results of the FE simulations are used to adjust the method to ensure material-efficient and process-reliable forging sequences.

Automatic process design, Forging, FEA, Resource efficiency, CAD

A method is presented that enables the complexity of a forging to be determined automatically on the basis of the CAD file of the forging. An automated evaluation of the forging complexity is necessary for a digitized and automated design of stage sequences in order to be able to determine important design parameters such as the flash ratio or the number of stages.

CAD, forming technology, algorithms

Unmanned aerial systems have changed the industry dramatically. The rapidly advancing technological development of so-called Unmanned Aircraft Systems (UAS) makes it necessary to address the design of future operational scenarios at an early stage.

UAS, Drones, Navigation

In order to automate the order control of tooth replacement products, an AI model was developed that enables classification into different product classes. The individual tooth replacement products are available in STL files. A mixed-data approach was used for the AI model. The STL file is converted to an image file and passed to a CNN and in parallel, information such as volume and surface dimensions were extracted from the STL file and passed to a ANN. The output from the ANN and the CNN is then combined to produce the final classification of the tooth replacement product.

Automated order control, AI, ANN, image processing, CAD

The machine learning based method for layout optimization of smallscale modular conveyor systems, which is developed within a research project at IPH – Institut für Integrierte Produktion Hannover gGmbH, provides SMEs a decision support, which enables them to execute complex layout planning independently. In addition, the machine learning method is intended to reduce the cost and time required for planning and to improve the quality of the solution compared to manual layout design.

Small-scale modular conveyors, conveyor systems, machine learning, artificial intelligence

To this day, the design of preforms for hot forging processes is still a manual trial and error process and therefore time consuming. Furthermore, its quality vastly depends on the engineer’s experience. At the same time, the preform is the most influencing stage for the final forging result. To overcome the dependency on the engineer’s experience and time-consuming optimization processes this paper presents and evaluates a preform optimization by an algorithm for cross wedge rolled preforms. This algorithm takes the mass distribution of the final part, the preform volume, the shape complexity, the appearance of folds in the final part and the occurring amount of flash into account. This forms a multi-criteria optimization problem resulting in large search spaces. Therefore, an evolutionary algorithm is introduced. The developed algorithm is tested with the help of a connecting rod to estimate the influence of the algorithm parameters. It is found that the developed algorithm is capable of creating a suitable preform for the given criteria in less than a minute. Furthermore, two of the five given algorithm parameters, the selection pressure und the population size, have significant influence on the optimization duration and quality.

preform optimization, genetic algorithm, cross wedge rolled, adaptive flash

A product-dependent, individual process development represents a main cost driver in laser material processing. Therefore, the expert system SmQL is being developed in an FQS-funded project, in which process knowledge can be stored in a formalized form and represented in rule form. This is intended to minimize times for setup processes and secure knowledge in the company in the long term.

expert system, industry 4.0, laser materials processing

This paper presents a method for the automated classification of forged parts for classification into the Spies order of shapes by artificial neural networks. The aim is to develop a recognition program within the framework of automated forging sequence planning, which can directly identify a shape class from the CAD file of the forged part and characteristics of the forged part relevant for the design of the process.

forging, ANN,CAD

Driverless transport systems are a building block for more efficient production systems in intralogistics, but have weaknesses in human-machine interaction. In a complex research project, a voice-based assignment is being developed, among other things, which is intended to make human-machine interaction more intuitive and increase its acceptance.

automated guided vehicle, augmented reality, smart glasses, voice control

Material efficiency and the development time of a forging sequence are decisive criteria for increasing the economic efficiency in the production of complex forgings. SMEs can often only interpret forging sequences in a shortened form due to insufficient capacities and high competitive pressure. Therefore, a generally valid method is to be developed that automatically generates multi-stage, efficient forging sequences based on the mass distribution of any forged part.

automated process design, die forging, resource efficiency

Driverless transport systems (AGV-Systems) are an established and effective instrument for increasing the profitability of modern production plants and making intralogistical processes more efficient. In addition to a master control system and a communication system, driverless transport vehicles (AGVs) are among the main components of an AGV-System. In relation to manually controlled industrial trucks, automated AGVs are characterised by higher efficiency. The disadvantage of AGV-Systems is that they are not able to solve critical operating situations independently. In this case, extensive intervention by specialist personnel is required.
With the aim of overcoming these obstacles, the project "Mobile Human-Machine Interaction for commissioning and control of AGV-Systems (MobiMMI)" was developed. In this project, the human-machine interaction between an operator and an AGV is to be extended by the use of a speech and gesture-based system in order to make the intervention by the operator easier and more intuitive and thus significantly reduce the acquisition and operating costs of AGV-Systems.
Against the background of safety, ergonomics, user-friendliness and integrability, a mobile system will be developed for this purpose and equipped with various sensors for 3D detection of the environment, indoor positioning and multimodal communication. The recorded data is evaluated by means of computer vision and machine learning, enabling the operator to react quickly and easily to critical operating situations.

automated guided vehicle, human-machine-interface

Currently used methods for factory layout planning are limited in their evaluation methods. Factory evaluation is either qualitative or quantitative, but limited to a few objectives. These deficits were overcome by the development of a quantitative, multidimensional ad hoc factory evaluation method. On this basis, it is now possible to develop a method for factory layout planning that reduces the planning effort and significantly increases the quality of the solution.

facility layout planning, factory planning, operations research, mathematical modelling

In forging industry, the development of new bulk metal forming technologies still is determined by a separation between construction and simulation. The resulting iterations take a lot of time. In this paper, the data mining method neuronal network is used to predict the forming force of a finite element forging simulation of a flange.

simulation, AI, prognosis, forming force

In the forging industry, like in many other economic sectors, it is common to simulate forming processes before executing experimental trials. An iterative simulation process is more economic than trials only but still takes a lot of time. A simulation with realistic parameters takes many hours. For an economical production the idea of predicting some main results of the simulation by Data mining was developed. Within this paper, the use of four different Data mining methods for the prediction of certain characteristics of a simulated flange forging process are presented. The methods artificial neural network, support vector machine, linear regression and polynomial regression are used to predict forming forces and the lack of volume. Both are important parameters for a successful simulation of a forging process. Regarding both, forging forming forces and lack of volume after the simulation, it is revealed that an artificial neural network is the most suitable.

data mining, artificial neural network, linear and polynomial regression, support vector machine

Lot sizing is an important task of production planning and control: basis of lot sizes are order change costs and costs for storage. Models for lot sizing do not consider lot size dependent maintenance costs. However, for a forging company the tool wear is very important, because the tooling costs represent a major part in the production cost. In this article, the deter-ministic lot size model of Andler is extended with lot size dependent maintenance costs. For this purpose, the correlation between lot size and the tool wear is ?rst derived in order to develop a lot size dependent wear function. The linking of a lot size dependent wear function with maintenance costs results in a lot size dependent maintenance cost function, which can be integrated into existing lot size models with a customized total cost function. The validation of the extended lot size model consists of two parts. In the ?rst part, the functionality of the extended lot size model is validated. In the second part, a sensitivity analysis of the lot size is carried out with regard to lot size dependent costs and unit costs.

lot sizing, tool wear, forging industry, sensitivity analysis

Awkward bending, lifting heavy items, working overhead: Such movements may cause permanent health problems. As a preventive measure, researchers of IPH and IFA developed an ergonomics assessment tool for assembly workplaces: 3D cameras capture unhealthy movements automatically.

3D camera system, ergonomics assessment, assembly

The preform design of forging processes mainly influences the economics of a multistage forging process and is very time consuming. This thesis presents an automated approach for preform design, aiming to reduce the development effort for multistage forging processes. Therefore analytical equations are derived to describe the quality of preforms. The equations take into account all main quality (formfilling, folds) and economic parameters (amount of flash, forming force, manufacturing expenses) for preforms.

To solve the multicriteria optimization problem an evolutionary algorithm is used. The results show that it is possible to obtain a suitable preform by using the algorithm in less than 60 seconds. Furthermore a method to reduce the amount of flash for cross wedge rolled preforms is developed in this thesis. Based on an equation describing the minimum required amount of flash in each area of the final part an optimized mass pre-distribution is achieved. Compared to conventional preforms a flash reduction of 66 % is reached.

bulk forming, evolutionary algorithm, preform optimization, flash reduction

The generation of bulk metal forming processes needs a lot of time. Researchers construct and simulate many days until a forming sequence without defects is found. At IPH a algorithm is supposed to predict a simulation result within one minute based on the constructions made. The basis for the prediction are many simulations, which were set up, executed and analysed automatically. This article decribes one possible way of doing so.

KImulation, simulation, automation

Work-related illnesses and their results may pose a threat to businesses' productivity. This may as well affect businesses' competitiveness for the worse. A workplace designed by methods of ergonomic workplace-design may counter some of the caused issues. But companies often lack knowledge or fear required financial resources to restructure workplaces. With this article technical requirements to an automated ergonomics assesment system are described.

ergonomics, evaluation, optimization, workplace design

Researchers at the Institut für Integrierte Produktion Hannover (IPH) have developed a software programme for an objective evaluation of factory layouts. With this tool, you can select your optimum layout numerically instead of following your gut instincts.

factory planning, layout evaluation, optimization procedures

In complaint management, 8D reports are used to document the analysis and elimination of errors. However, the quality of these reports is often insufficient and leads to longer processing times and the repetition of errors. The newly developed evaluation system QuSys enables an automated check of 8D reports.

complaints, quality, evaluation system, errors, 8D reports

Regarding the handling of complaints by customers, 8D reports are used for analysis and correction of errors that occur in the production process. However, the quality of these reports is often inadequate and leads to longer processing time and errors. Due to time and capacity restrictions in most cases, 8D reports undergo inadequate internal quality testing. Consequently, the aim of optimizing internal processing fails and poor 8D reports with insufficient solutions are sent to the customer. In this paper, we describe problems with faulty 8D reports in detail, and then present a system that automates quality checking of 8D reports based on these facts. This paper focusses on the basic structure of the developed system and how it improves the quality level of 8D reports within the complaint handling process.

complaint, quality management, 8D method, 8D report

Evaluation of factory layouts can currently be carried out by experts or by means of simulation models. The review by an expert can be carried out quickly and with little effort, but the assessment is only qualitative and subjective in nature. A quantitative, objective evaluation is possible by simulation models. However, these are more expensive and time-consuming than the expert review. For small and medium enterprises (SMEs) simulation models are often too great a financial or capacitive load. To fill this gap, a research project enables a low-maintenance quantitative and therefore objective evaluation of factory layouts. The basis for this are the appropriate modeling of the factory layout and the calculation rules, which will be presented by two examples..

factory evaluation, factory planning, layout review

In multistage hot forging processes, the preform shape is the parameter mainly influencing the final forging result. Nevertheless, the design of multistage hot forging processes is still a trial and error process and therefore time-consuming. The quality of developed forging sequences strongly depends on the engineer's experience. To overcome these obstacles, this paper presents an algorithm for solving the multi-objective optimization problem when designing preforms. Cross wedge rolled (CWR) preforms were chosen as subject of investigation. An evolutionary algorithm is introduced to optimize the preform shape taking into account the mass distribution of the final part, the preform volume and the shape complexity. The developed algorithm is tested using a connecting rod as a demonstration part. Based on finite element analysis, the implemented fitness function is evaluated, and thus the progressive optimization can be traced.

preforming optimization, hot forging, evolutionary algorithms, cross wedge rolling

The future belongs to forging preforms that are designed automatically: IPH is presently working on a software programme based on evolutionary algorithms, allowing companies to save valuable development time and improve the efficiency of forging processes.

forming technology, forging, preform, evolutionary algorithms

The generation of bulk metal forming processes needs a lot of time. Researchers construct and simulate many days until a forming sequence without defects is found. At IPH a algorithm is supposed to predict a simulation result within one minute based on the constructions made.

Artificial intelligence, FEA

A factory planning is currently being assessed either at low cost and qualitatively by experts or quantitatively by a simulation model. A review by simulation model is both more costly and time-consuming and a big burden for small and medium enterprises. This article describes the procedure of a research project and the selection of evaluation fields that will in future allow a low-maintenance and at the same time quantitative factory evaluation.

factory planning, quantitative factory evaluation, simulation model

8D-reports are used to analyze and eliminate errors. Often the quality of 8D-reports is poor and leads to long processing times and problems in sustainable trouble shooting. An automated evaluation system helps to identify quality problems. It prevents companies from sending poor 8D-reports to their customers.

quality management, complaint handling, 8D-report, quality evaluation, evaluation method

The companies in the tool making industry are exposed to a high intensity of competition. To get customer orders, they have to prepare reliable quotes in a short time. The available rudimental and partially incomplete information about the tool is of limited suitability for a reliable estimation of manufacturing costs. This thesis aims to support the tool making companies with tender preparation through a method of feature-based estimation of manufacturing costs. Essential basis forms a digital representation of the tool, which is generated by an automated CAD model building using technical guidelines. The method is implemented in the form of an expert system. The cost estimation is done, firstly, by determining the costs for machining by an analytical method based on the CAD model. Second, the costs for manufacturing processes are determined by means of a data mining based method by features derived from the CAD model and serve as inputs for prediction models. Using practical examples, the application of the expert system is described in practice and the method is evaluated. Thereby the practical applicability and limitations of the method are shown.

tool making, tool shop, quotation costing, data mining, expert system

In this presentation the research project "Quality system for the evaluation of 8D report contents (QuSys)" was introduced. The objectives of the research project are the effective organization of complaint management and the internal fault management due to an automated quality evaluation of 8D reports. The evaluation allows to take well-directed measures and prevents that faulty 8D reports are sent to the customer.

claims management, reports, quality evaluation

More and more people want to live in the cities. Space is getting scarce – not only living space but space for offices, streets, parking, railways and stations. Will urban infrastructure still be sufficient in the future? And how can we use urban space as efficiently as possible?

material flow simulation, traffic

The complaint handling suffers from defective 8D-reports. Hence the costumer supplier relationship is also affected. A system for the formal and substantive evaluation of 8D-reports will be developed in a research project. The aim is to improve the complaint processing due to high quality 8D-reports.

8d-method, 8d-report, claims management, complaint, quality management

Will the freight depot still be large enough in ten years – or is it necessary to built new rails? An austrian company wanted an answer to this question – and IPH was able to help with a detailed material flow simulation.

material flow simulation, railway traffic

The systematic analysis of life cycle data provides the potential to identify weaknesses of current products and starting points for product innovations. This paper presents a tool for an automated analysis of life-cycle data and describes the necessary steps of a data analysis. In particular, the merging of data from different systems, the pre-processing of raw data, the data analysis and interpretation are explained. In this context, the pre-processing of free text is described. Moreover, two models for an automated analysis of life cycle data are introduced. Finally, the implementation of this concept into a software tool is described.

software tool, lifecycle, data analysis, data mining, knowledge deployment

An analysis of lifecycle data offers the potential to identify product weaknesses and starting points for product innovations. The paper describes a concept to analyze lifecycle data and declares which partial steps are necessary to collect, preprocess and analyze the data.

software tool, lifecycle, data analysis, data mining, knowledge deployment

Automated guided vehicle systems (AGVS) basically consist of a control station, a communication system and automated guided vehicles (AGV). Control of the AGVS has the task to carry out a transport order once it is issued by a higher level system. The transport order is implemented by the AGVS-control in an actual movement of the AGV. The number of AGV varies between a few up to 100 AGV. Due to the high number of AGV the likelihood of distraction in the route network increases. Todays central AGVS controls take into account the dynamic and evolving traffic situations inadequately and are insufficiently robust and flexible in terms of changes and disturbances .

agv, decentralzied control, automated guided vehicles

Through the use of cooling systems in injection molding, the reduction of cycle time and increasing the quality of molded parts is desired. New manufacturing processes such as selective laser melting enable the layered structure of cooling systems and allow the free design of cooling systems which is close to the part geometry. With these form-fitting cooling systems, for example, the tempering cycle times can be reduced further. However, the degree of freedom in the design of cooling circuits increases with the new production method, which makes the manual design difficult and extends the simulation times. Automated design methods of conformal cooling systems based on geometric and process parameters are currently not available. An innovative software helps by constructing close-contoured channels and reducing the cycle time with minimized engineering effort.

injection molding, conformal cooling systems, design, nature-inspired algorithms

Economic growth in Germany and Europe secures jobs and prosperity. However, the impacts on our environment are often negative. Because more goods are produced and the consumption increases, traffic and thus the greenhouse gas emissions rise. In order to keep these emissions as low as possible, the stated goal is to shift transport from road to rail. Thats why many terminal stations are preparing for rising turnover figures. However, the problem of maximizing throughput capacities is unsolved. To answer this question, the IPH has developed an innovative, event-discrete model used in a material flow simulation based on the software Plant Simulation.

connection station, simulation model, material flow simulation

The overall objective of the project was to develop a method for the automated CAD modeling and costing of progressive dies. The method should firstly enable the automated creation of a CAD model of the tool based on a strip layout. The tools should be modularized and the interactions of the modules to the tool design are described in rules. The rules should then enable the automated CAD modeling. Secondly, a link of CAD models with automated costing and monitoring should be done. Basis of the costing and monitoring were the CAD models of the tool and the established standard processes in the tool production.

artificial intelligence, tool and die industry, determination of manufacturing costs, CAD-automation

A breakdown of a wind turbine entails high costs. The more reliable the prognosis of the condition of every single component is carried out, the better the maintenance can be planned. For example the maintenance could run in a time with low wind yield. Furthermore, impending breakdowns can be detected and avoided. Within the project “SteigProg” data-mining algorithms were analyzed for their ability to condition prognosis in wind turbines. An improved condition prognosis contributes a more efficient operation of wind turbines. Measurable savings result by minimizing downtimes, improved planning and shortening of maintenance operations.

condition prognosis, wind turbines

Innovative developments often result from the knowledge generated in the lifecycle of existing products. Following this approach in a current research project engineers of IPH develop methods and tools for the acquisition and utilization of knowledge from the entire product lifecycle.

product lifecycle, knowledge management

A central control of automated guided vehicle systems (AGVS) doesn’t longer satisfy the require-ments of a versatile production. With procedures from the field of artificial intelligence a control can be decentralized and made more flexible. In this way the tasks of the central control can be distributed to different entities in the system. Thus the complexity of the tasks is reduced. The present article deals with the decentralization of the AGVS control and focuses on the order allocation, route finding and conflict resolution.

agv, decentralzied control, automated guided vehicles

With automated guided vehicle systems (AGVs) a trend toward intelligent, distributed systems is emerging . Here, the so-called agent technology, originally from the field of artificial intelligence play an important role. Agents are autonomous entities that make the basis of predetermined rules independent decisions. Tasks in a AGV system such as the award of transport orders or the pathfinding, can be realized by certain patterns of behavior of the agents. Together with the IPH - Institute of Integrated Production Hannover scientists of the OFFIS develop an overall concept for the decentralized self-regulation of AGV systems.

agv, decentralzied control, automated guided vehicles

To meet the growing demand for energy, further developments are necessary in the field of renewable energies. In two research projects, engineers of IPH - Institut für Integrierte Produktion Hannover have investigated how to increase the efficiency of wind turbines.

xxl products, large-scale products, wind turbines, data mining

A smart option to increase the energy yield of wind turbine generators is to increase its height. There is an exponential increase of the usable wind energy at enlarging the tower’s height, but also an exponential increase of the tower’s weight. The application of lightweight design concepts in the production of wind turbine tower sections may lead to weight reduction while keeping the tower’s stiffness at an equal level. Here the results of a study for lightweight concepts and their implementation on towers and a guiding systematic approach are being presented. The investigated design solutions proved successfully in bionic, aerospace and automotive applications. FEA simulations were used to compare the different structures and to estimate their feasibility. The investigation’s main result is a lightweight structure which provides weight reductions up to 20 %, by using lower wall thicknesses.

forging, genetic algorithm, preforming optimization

The trend for automated guided vehicles (AGV) is heading from a central control to decentralization. The term of agents is becoming more important in this context. Here, software agents are used that are not related to secret service or insurances. Software agents are autonomous units that independently decide on their own, with the use of predefined rules. Thus, a decentralized control is built. Current decentralized solutions are not continuously decentralized. Vehicles share a common topology or are controlled by a central station. Together with the "OFFIS - Institut für Informatik" researchers from the IPH develop an overall concept for a decentralized self-regulated AGV.

agv, decentralzied control, automated guided vehicles

Economic efficiency and quality are both deciding competitive factors for companies with a production of industrial goods. To produce and deliver parts of a steady high-quality and simultaneously at low costs is a big challenge. An example is the industrial sector of injection moulding. A new software provides help by constructing canals closer to the surface. Therefore the quality of the parts increases and the cycle time decreases. Beyond this the effort for the constructor is optimized.

injection moulding, temperature mangement, software deveopment

The quality of molded products and production cycle times are influenced by mold temperature control systems. Today experienced technical designers are developing form-fitting temperature control systems manually. Afterwards they analyzes the systems in iterative and experimental simulations. Here, a method for automatic design of mold temperature control systems is presented. The method uses nature-inspired algorithms, which improve the economical benefit of the construction process and the injection molding process.

injection molding, conformal cooling systems, design, nature-inspired algorithms

Still profitability and quality are decisive competitive factors in production business. Therefore injection molding faces the challenge to produce valuable parts with constant quality at a lower cost. An innovative software helps by constructing close-contoured channels and reducing the cycle time with minimized engineering effort.

profitability and quality, injection molding, close-contoured construction of cooling channels

Still profitability and quality are decisive competitive factors in production business. Therefore injection molding faces the challenge to produce valuable parts with constant quality at a lower cost. An innovative software for automatic and close-contoured construction of cooling channels supports that by use of artificial intelligence developed by the IPH – Institute for integrated Production Hannover gGmbH together with several companies.

profitability and quality, injection molding, close-contoured construction of cooling channels

The aim is the development of a function-based method to support the planning of offerings in injection molding. It is assumed that tools and shapes are unique items, but the tools’ functions are recurrent. Possible post-calculations are captured and can be used better for the calculation of offerings via the function-based calculation. Methods of similarity search assist in prediction and precise determination of manufacturing expense of a tool. In order of the validation of the concept by real data the software-demonstrator is linked to existent post-calculation tools and transferred conceptually to further unique products.

function-based method, tender preparation, injection molding

The lecture introduced IPH – Institut für Integrierte Produktion Hannover gGmbH with its three fields of activity: forming technology, logistics and automation technology. Furthermore, research and consulting projects were discussed. In addition, forecasting methods regarding the life-cycle costs of tools and moulds were presented as a major focus of current research.

research and development, life-cycle costs, tool and mould making

During the utilization phase, sheet fabricating tools cause up to 70% of their own life cycle costs. In general, they may now be procured only on the basis of their purchase price. IPH - Institute of Integrated Production Hannover gGmbH has developed a method which can predict and consider the life cycle costs based on knowledge of these tools during the planning process.

calculation, life cycle costs, tool manufacturing

As a result of increasing globalization in procurement an increased competition exists for production companies. In the field of sheet metal forming companies will therefore be required to produce proper quality products with short delivery times at high punctuality at lowest possible production costs.

sheet metal forming, experience recovery, equipment effectiveness

Function based structures for cost estimating. The complexity and the unique character of tool and mould constructions are the reasons why the calculation during the offer phase of the moulds and tools are using customer requirements and insufficient product information as a basis. For this purpose an increasing number of commercial software packages are used. Nevertheless, the support for the calculation is still inadequate. The IPH develops a method which allows a precise, transparent and with little effort achievable estimation for an offer on the basis of tool functions and the knowledge about already produced tools in a company.

function-based method, tender preparation, injection molding

function-based method, tender preparation, injection molding