Abstract.A structured procedure is presented to identify similar processes producing similar features on different products in small batch and job production processes. Similar processes are clustered together to achieve the minimum necessary amount of samples to monitor and control the respective production process using statistical process control (SPC). It is described how the procedure was successfully applied to a process in the manufacturing of boring/milling machines.Keywords: SPC / process control / small batches / reward / quality management Implications and influencesThe structured procedure described here is a first step towards the application of SPC using a process cluster approach. Future work will provide an algorithm that allows to automatically identify homogeneous clusters based on historical process data.

To detect root causes of non-conforming parts - parts outside the tolerance limits - in production processes a high level of expert knowledge is necessary. This results in high costs and a low flexibility in the choice of personnel to perform analyses. In modern production a vast amount of process data is available and machine learning algorithms exist which model processes empirically. Aim of this paper is to introduce a procedure for an automated root cause analysis based on machine learning algorithms to reduce the costs and the necessary expert knowledge. Therefore, a decision tree algorithm is chosen. A procedure for its application in an automated root cause analysis is presented and simulations to prove its applicability are conducted. In this paper influences affecting the success of detection are identified and simulated e.g. the necessary amount of data dependent on the amount of variables, the ratio between categories of non-conformities and OK parts as well as detectable root causes. The simulations are based on a regression model to determine the roughness of drilling holes. They prove the applicability of machine learning algorithms for an automated root cause analysis and indicate which influences have to be considered in real scenarios.

PurposeTo ensure product quality within a manufacturing process, inspection processes are indispensable. One task of inspection planning is the selection of inspection characteristics. For optimization of costs and benefits, key characteristics can be defined by which the product quality can be checked with sufficient accuracy. The manual selection of key characteristics requires substantial planning effort and becomes uneconomic if many product variants prevail. This paper, therefore, aims to show a method for the efficient determination of key characteristics.Design/methodology/approachThe authors present a novel Algorithm for the Selection of Key Characteristics (ASKC) based on an auto-encoder and a risk analysis. Given historical measurement data and tolerances, the algorithm clusters characteristics with redundant information and selects key characteristics based on a risk assessment. The authors compare ASKC with the algorithm Principal Feature Analysis (PFA) using artificial and historical measurement data.FindingsThe authors find that ASKC delivers superior results than PFA. Findings show that the algorithms enable the cost-efficient selection of key characteristics while maintaining the informative value of the inspection concerning the quality.Originality/valueThis paper fills an identified gap for simplified inspection planning with the method for the efficient selection of key features via ASKC.

In this study, we present and compare four grouping algorithms to combine samples from low volume production processes. This increases their sample sizes and enables the application of Statistical Process Control (SPC) to low volume production processes. To develop the grouping algorithms, we define different grouping criteria and a general grouping process. To identify which algorithm is optimal, we deduct following requirements on the algorithms from real production datasets: their ability to handle different amount of characteristics and sample sizes within each characteristic as well as being able to separate characteristics possessing distributions with different spreads and locations. To check the fulfillment of these requirements, we define two performance indices and conduct a full-factorial Design of Experiments. We achieve the performance indices for each algorithm by using simulations with artificial data incorporating the aforementioned requirements. One index rates the achieved group sizes and the other one the compactness within groups and the separation between groups. To validate the applicability of grouping algorithms within SPC, we apply real production data to the grouping algorithms and control charts. The result of this analysis shows that the grouping algorithm based on cluster analysis and splitting exceeds the other algorithms. In conclusion, the grouping algorithms enable the application of SPC to small sample sizes. This provides companies, which produce in low volumes, with new means of reducing scrap, generating process knowledge and increasing quality.

In der Kleinserienproduktion ist eine 100 %-Prüfung üblich. Eine kostengünstigere Stichprobenprüfung ist nicht anwendbar, da produzierte Lose nicht die nötige Datenanzahl aufweisen. Um sie zu erhöhen und die Stichprobenprüfung anwendbar zu machen, können ähnliche Produktmerkmale mit einem Gruppierungsalgorithmus zusammengefasst werden. Darauf aufbauend wird eine Methodik zur Erstellung eines adaptiven Prüfplans für Kleinserien vorgestellt, angewendet und der weitere Forschungsbedarf dargestellt.   In small series production, 100 % inspection is common practice. A more cost-effective sampling inspection is not applicable as batches produced do not provide the necessary amount of data. To increase the amount of data and allow for sampling inspection, similar product features can be grouped by a grouping algorithm. Thus, a methodology is presented for designing an adaptive sampling plan for small batch production while further research requirements are discussed.