Search

The identification of appropriate manufacturing process parameters typically relies on rule-based schemes, expertise, and domain knowledge of highly skilled workers. Usually, the parameter settings remain the same for each part in an individual production lot once an acceptable quality is reached. Each part, however, has slightly different properties and part-specific parameter settings have the opportunity to increase quality and reduce scrap. We propose a simple linear regression model to identify process parameters based on experimental data and extend that model with ideas from time series analysis to achieve highly-accurate, part-specific parameter settings in a real-world manufacturing use case. We show the usefulness of exploiting the (autocorrelated) structure of regression residuals to improve the predictive performance of regression models in manufacturing environments.

The goal of this paper is to test if data partitioning based on domain knowledge improves the performance of unsupervised anomaly detection algorithms for the detection of faulty internal combustion engines. We test three common anomaly detection algorithms to predict defective engines at the end of an assembly line, both with and without data partitioning. The algorithms are trained on high-dimensional vibration data. To evaluate and compare the detection performance of partitioned and unpartitioned approaches, we use a labeled collection of known anomalies. Using domain knowledge to partition the data improves the anomaly detection performance of all tested algorithms. A divide and conquer strategy based on data partitioning, thus, appears to be a viable anomaly detection approach in cases where abundant unlabeled data is available.

Technological change, based on digitalization, is happening fast and companies have to place emphasis on qualifying their employees and improve their infrastructure to be up to date. Learning Factories are adequate facilities for qualifying employees in a safe environment with proper guidance and infrastructure. However, there are three important questions in connection to handling the change in companies. The first is “How is the qualification and infrastructure status quo in a company?” The second is “Which readiness level should be achieved to handle the change appropriate?” The third is “What is the gap and how to close it in terms of qualification and infrastructure?” For answering the first question, an investigation in the company is necessary and a rating has to be conducted. Nevertheless, a standardized maturity model can help to answer this question. The maturity model also supports the answer to the second question. By using the reference table a target level can be defined. The answer to the third question is the delta between the status quo and the target level of the company’s readiness investigation. The gap between the status quo and target is usually indicated by infrastructure, process, organizational and qualification improvements. Furthermore, the gap and hence the necessary improvement is the basis for training in a learning factory. Derived from the gap, the learning factory can prepare a training curriculum and the needed infrastructure to train the staff with the utmost precision.

The Cross-Industry Standard Process for Data Mining (CRISP-DM) is a widely accepted framework in production and manufacturing. This data-driven knowledge discovery framework provides an orderly partition of the often complex data mining processes to ensure a practical implementation of data analytics and machine learning models. However, the practical application of robust industry-specific data-driven knowledge discovery models faces multiple data- and model development-related issues. These issues need to be carefully addressed by allowing a flexible, customized and industry-specific knowledge discovery framework. For this reason, extensions of CRISP-DM are needed. In this paper, we provide a detailed review of CRISP-DM and summarize extensions of this model into a novel framework we call Generalized Cross-Industry Standard Process for Data Science (GCRISP-DS). This framework is designed to allow dynamic interactions between different phases to adequately address data- and model-related issues for achieving robustness. Furthermore, it emphasizes also the need for a detailed business understanding and the interdependencies with the developed models and data quality for fulfilling higher business objectives. Overall, such a customizable GCRISP-DS framework provides an enhancement for model improvements and reusability by minimizing robustness-issues.

In this paper an analytical model to calculate service level, FGI and tardiness for a make-to-order (MTO) production system based on the production leadtime, utilisation and WIP is presented. The distribution of customer required leadtime is linked to the already available equations for an M/M/1 production system from queuing theory. Explicit equations for service level, FGI, FGI leadtime and tardiness are presented for an M/M/1 production system within an MTO environment. For a G/G/1 production system an approximation based extension is provided – discussing the influence of variation in the inter-arrival and processing time distribution in this framework. Moreover, the integration of a work ahead window (WAW) work release policy is discussed. Based on a numerical study, a high potential to decrease FGI (up to 97% FGI reduction) when applying such a WAW strategy is found and it is shown that the higher the targeted service level is, the higher the FGI reduction potential. The paper contributes to a bette...

Decisions regarding production planning and control strategy (PPCS) choices can be classified as strategic, whereas parametrization issues are of a tactical nature. However, readjustment is often skipped either as a result of a lack of planning expertise or because it would require extended planning. For this reason, robustness, which is defined as PPCS behaviour within dynamic environments, is investigated. To achieve a greater understanding of the sensitivity on parameter changes in a production system, PPCS stability is examined. An eM-Plant based simulation model is presented that discusses the service-level performance of material requirement planning (MRP), kanban, constant work in process (CONWIP) and drum–buffer–rope (DBR) in a flow-shop with attention to the work in process (WIP). Although the service-level performance of CONWIP exceeds that of the other systems, CONWIP struggles to maintain its advantage under dynamic conditions. The paper seeks to support industrial practitioneers both in their...

Because of the fact that some logistical objectives are controversial, a trade-off between short actual lead times, low inventories, high utilization, high service levels and low backorders is necessary. To make good decisions in the design and, in particular, the optimization of a production system or supply chain a deep understanding of the relationship between the logistical figures is essential. In this article relationships between these logistical figures are developed by an analytical approach for a time-continuous multi-item production model. Furthermore, the deviation of work in process is used to describe the fluctuation and disturbances of real systems.

For the design of a supply chain as well as for a production system, the relationship between utilization, range, lead time and work in progress is very important. Because of the cost of the available capacity, the utilization should be high, but on the other hand full utilization has a negative impact on the lead time and work in progress. In this paper, some relationships for a continuous production system are formulated and theoretically proven between average lead time, average range, average work in progress and average utilization for a multi-item system with a dynamic demand. The basic equation that is developed is the continuous and deterministic analogous relationship to the well-known Little Law based on queuing theory. The theoretically deduced and proven logistical curves are similar to the results of the funnel model based on empirical studies and simulation. One interesting result is that the variability of the inventory or of the production load causes a waste of capacity and therefore a re...

Correct standard times are needed for logistic operating curves, manufacturing planning and control systems and Advanced Planning Systems (APS) for scheduling, lot-sizing and sequencing. This paper presents a model for calculation of standard times based on the knowledge of the total busy time of a work center and the produced number of items in a fixed time period. The developed method requires little effort in comparison to other methods such as Work-Factor or time observation. It can regularly determine standard times using current confirmation data.

The purpose of this article is to develop a method for short and medium term capacity setting decisions for providing a market oriented level of available capacity for the investigated machine groups. An MTO (make to order) production system is considered. The basic concept is that the cumulative available capacity of the machine group has to be greater than or equal to the cumulative needed capacity influenced by the customer orders. The cumulative needed capacity is corrected with an operation characteristic which defines the slack of the production system, in order to include enough capacity for short term orders.

Companies have to focus on their customers to stay competitive in the future. Therefore, metrics are necessary to measure the performance of production plants. Based on the TPM approach a metric is introduced in this paper which includes the market. This is done by taking only the produced products into account which fulfill a customer order. Products produced on stock are excluded. As a result the new metric is suitable as a performance measurement in production plants because it supports on the one hand the management objective of optimizing quality rate, performance rate and availability of the equipment. And on the other hand the management has to adjust the loading time on the customer demand. A numerical example emphasis the major drawbacks of the classical TPM metrics and illustrates the advantages of the presented performance metric.