This study addresses a significant gap in the field of time series regression modeling by highlighting the central role of data augmentation in improving model accuracy. The primary objective is to present a detailed methodology for systematic sampling of training datasets through data augmentation to improve the accuracy of time series regression models. Therefore, different augmentation techniques are compared to evaluate their impact on model accuracy across different datasets and model architectures. In addition, this research highlights the need for a standardized approach to creating training datasets using multiple augmentation methods. The lack of a clear framework hinders the easy integration of data augmentation into time series regression pipelines. Our systematic methodology promotes model accuracy while providing a robust foundation for practitioners to seamlessly integrate data augmentation into their modeling practices. The effectiveness of our approach is demonstrated using process data from two milling machines. Experiments show that the optimized training dataset improves the generalization ability of machine learning models in 86.67% of the evaluated scenarios. However, the prediction accuracy of models trained on a sufficient dataset remains largely unaffected. Based on these results, sophisticated sampling strategies such as Quadratic Weighting of multiple augmentation approaches may be beneficial.

This study addresses the challenge of the optimization of milling in industrial production, focusing on developing and applying a novel framework for optimising manufacturing processes. Recognising a gap in current methods, the research primarily targets the underutilisation of advanced data analysis and machine learning techniques in industrial settings. The proposed framework integrates these technologies to refine machining parameters more effectively than conventional approaches. The research method involved the development of the framework for the realisation and analysis of measurement data from milling machines, focusing on six machine parts and employing a machine learning system for optimization and evaluation. The developed and realised framework in the form of a software demonstrator showed its applicability in different experiments. This research enables easy deployment of data-driven techniques for sustainable industrial practices, highlighting the potential of this framework for transforming manufacturing processes.

The prediction of energy-related time series for computer numerical control (CNC) machine tool axes is an essential enabler for the shift towards autonomous and intelligent production. In particular, a precise prediction of energy consumption is needed to determine the environmental impact of a product and the optimization of its production. For this purpose, a novel approach for predicting high-frequency time series of numerically controlled axes based on the program code to be executed is presented. The method involves simulative preprocessing of the input NC code to determine each axis’s acceleration, velocity, and process force. Combined with the material removal rate, these variables are input for a machine learning (ML) model that delivers axis-specific high-frequency time series predictions. Compared to common approaches, it is thus possible to make predictions for the variable energy consumption of machine tools for any tool path or target resolution in the time domain. Experiments show that this approach achieves a high precision when a robust learning data basis is available. For the X-, Y-, and Z-axis, errors of 0.2%, −1.09%, and 0.09% for aircut and of 0.15%, −3.55%, and 0.08% for material removal can be achieved. The potentials for further improvement are identified systematically.

Digital twins are a means to better understand, engineer, and use cyber-physical systems. In manufacturing, digital twins can optimize production, prevent failures, and save resources. To consolidate the different approaches to digital twins in manufacturing, ISO 23247 defines the essential functional elements of a digital twin. We present a model-driven digital twin exemplar that realizes part of this standard to analyze milling processes. Our digital twin reference architecture includes a digital twin service component that manages and connects different services to adapt the manufacturing process according to a given objective. Two digital twin services, for the adaptation of component and tool conditions and for geometric error adaptation, illustrate the potential of this reference architecture. The digital twin connects to an industrial milling machine via domain-specific languages. This exemplar uses models at design time and at runtime to separate the concerns of software engineers and domain experts and leverages these models to understand and optimize the use of industrial machine tools.

In recent years, Industrial Internet of Things (IIoT) respectively Industry 4.0 have become increasingly established and thus a widespread technology among companies. By means of data acquisition, processes can not only be made more sustainable and resource-efficient but through emerging technologies like fault detection or predictive maintenance, a higher Overall Equipment Effectiveness (OEE) can be achieved. As a result, the availability of the machine tools remains high and process chains will not be disturbed. However, many companies still operate in brownfield production sites with legacy machines and therefore with limited opportunities for machine data access and use in an economically viable manner. As a result, many advantages that would increase the OEE of machine tools cannot be used. To present a solution for retrofitting brownfield machines, a low-effort system was developed that extracts machine control signals from different machine data sources and automatically identifies them using a multi-stage algorithm. This algorithm consists of analytical rule bases built using expert knowledge and a machine learning model for classification. The best performing models were selected as machine learning models, which are a Residual Network, a Fully Convolutional Network, a Long-Short-Term Memory, and a Random Forest. With different datasets from two machine tools, the overall model was tested and was able to correctly identify the signals present with an accuracy of 86.92 % to 98.93 % on average. Using this approach, the identified signals are assigned to an information model linking them to the respective machine tool axes. As a result, brownfield machines are also made accessible for modern technologies such as predictive maintenance or a reduction in rejects as a result of error detection.

In today’s manufacturing landscape, Digital Twins play a pivotal role in optimising processes and deriving actionable insights that extend beyond on-site calculations. These dynamic representations of systems demand real-time data on the actual state of machinery, rather than static images depicting idealized configurations. This paper presents a novel approach for monitoring tool and component wear in CNC milling machines by segmenting and classifying individual machining cycles. The method assumes recurring sequences, even with a batch size of 1, and considers a progressive increase in tool wear between cycles. The algorithms effectively segment and classify cycles based on path length, spindle speed and cycle duration. The tool condition index for each cycle is determined by considering all axis signals, with upper and lower thresholds established for quantifying tool conditions. The same approach is adapted to predict component wear progression in machine tools, ensuring robust condition determination. A percentage-based component state description is achieved by comparing it to the corresponding Tool Condition Codes (TCC) range. This method provides a four-class estimation of the component state. The approach has demonstrated robustness in various validation cases.