Search

With the trend of increasing sensors implementation in production systems and comprehensive networking, essential preconditions are becoming required to be established for the successful application of data-driven methods of equipment monitoring, process optimization, and other relevant automation tasks. As a protocol, these tasks should be performed by engineers. Engineers usually do not have enough experience with data mining or machine learning techniques and are often skeptical about the world of artificial intelligence (AI). Quality assurance of AI results and transparency throughout the IT chain are essential for the acceptance and low-risk dissemination of AI applications in production and automation technology. This article presents a conceptual method of the stepwise and level-wise control and improvement of data quality as one of the most important sources of AI failures. The appropriate process model (V-model for quality assurance) forms the basis for this. [ABSTRACT FROM AUTHOR]

With the trend of increasing sensors implementation in production systems and comprehensive networking, essential preconditions are becoming required to be established for the successful application of data-driven methods of equipment monitoring, process optimization, and other relevant automation tasks. As a protocol, these tasks should be performed by engineers. Engineers usually do not have enough experience with data mining or machine learning techniques and are often skeptical about the world of artificial intelligence (AI). Quality assurance of AI results and transparency throughout the IT chain are essential for the acceptance and low-risk dissemination of AI applications in production and automation technology. This article presents a conceptual method of the stepwise and level-wise control and improvement of data quality as one of the most important sources of AI failures. The appropriate process model (V-model for quality assurance) forms the basis for this.

The value of data analytics is fundamental in cyber-physical production systems for tasks like optimization and predictive maintenance. The de facto standard for conducting data analytics in industrial applications is the CRISP-DM methodology. However, CRISP-DM does not specify a data acquisition phase within production scenarios. With this chapter, we present DMME as an extension to the CRISP-DM methodology specifically tailored for engineering applications. It provides a communication and planning foundation for data analytics within the manufacturing domain, including the design and evaluation of the infrastructure for process-integrated data acquisition. In addition, the methodology includes functions of design of experiments capabilities to systematically and efficiently identify relevant interactions. The procedure of DMME methodology is presented in detail and an example project illustrates the workflow. This case study was part of a collaborative project with an industrial partner who wanted an application to detect marginal lubrication in linear guideways of a servo-driven axle based only on data from the drive controller. Decision trees detect the lubrication state, which are trained with experimental data. Several experiments, taking the lubrication state, velocity, and load on the slide into account, provide the training and test datasets. [ABSTRACT FROM AUTHOR]

Abstract The value of data analytics is fundamental in cyber-physical production systems for tasks like optimization and predictive maintenance. The de facto standard for conducting data analytics in industrial applications is the CRISP-DM methodology. However, CRISP-DM does not specify a data acquisition phase within production scenarios. With this work, we present DMME as an extension to the CRISP-DM methodology specifically tailored for engineering applications. It provides a communication and planning foundation for data analytics within the production domain. We show the feasibility of our methodology for engineering applications within a case study in the field of work piece detection. [ABSTRACT FROM AUTHOR]

The value of data analytics is fundamental in cyber-physical production systems for tasks like optimization and predictive maintenance. The de facto standard for conducting data analytics in industrial applications is the CRISP-DM methodology. However, CRISP-DM does not specify a data acquisition phase within production scenarios. With this chapter, we present DMME as an extension to the CRISP-DM methodology specifically tailored for engineering applications. It provides a communication and planning foundation for data analytics within the manufacturing domain, including the design and evaluation of the infrastructure for process-integrated data acquisition. In addition, the methodology includes functions of design of experiments capabilities to systematically and efficiently identify relevant interactions. The procedure of DMME methodology is presented in detail and an example project illustrates the workflow. This case study was part of a collaborative project with an industrial partner who wanted an application to detect marginal lubrication in linear guideways of a servo-driven axle based only on data from the drive controller. Decision trees detect the lubrication state, which are trained with experimental data. Several experiments, taking the lubrication state, velocity, and load on the slide into account, provide the training and test datasets.

This paper presents model-based methods and algorithms for describing and analyzing complex technological interactions in production process chains for the manufacturing of composite materials and components. The presented holistic approach includes the modeling of the process chain, the construction of suitable designs of experiments, the logging and the collection of experimental and production data, the data analysis, as well as the visualization of analysis results and the deduction of the room of maneuver for production settings. Supported by these methods, the development and the putting into operation of complex process chains will become much more efficient. [ABSTRACT FROM AUTHOR]

Increasing global demand for composites continues to be driven by the aerospace industry. However, expensive raw material and the complexity of manufacturing process increases the risk level in composite technology. Considering the complexities of composite manufacturing, our paper describes a data management application in composite manufacturing at an aerospace manufacturer. The scope of this manufacturing data management application is from the raw material issuance from warehouse to the painted final composite product. After a description of the application, we will discuss potential problems and possible solutions and improvements of the data management in composite manufacturing in the aerospace industry. [ABSTRACT FROM AUTHOR]

Abstract: The paper wants to illustrate a new approach for modelling and analysing innovative technological process chains aiming at the determination of cause-effect relations between material properties and manufacturing conditions concerning the required component quality. The intention is to assist the domain specific experts at their research and development of novel technologies. A supporting software tool is under development. Using the example of the process chain of the manufacturing of a hybrid yarn textile thermoplastic composite component the application of the approach and the test of the software tool was performed for the modelling of the process chain and for the analysing of a selected process step. Therefrom requirements were derived for the further development of the methods and the software tool. [Copyright &y& Elsevier]