Machine Learning-Based Prediction of Missing Components for Assembly – a Case Study at an Engineer-to-Order Manufacturer

Peter Burggraf,Fabian Steinberg,Johannes Wagner,Benjamin Heinbach

doi:10.1109/access.2021.3075620

Peter Burggraf, Fabian Steinberg + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3075620

Copy DOI

Abstract

For manufacturing companies, especially for machine and plant manufacturers, the assembly of products in time has an essential impact on meeting delivery dates. Often missing individual components lead to a delayed assembly start, hereinafter referred to as assembly start delayers . Identifying the assembly start delayers early in the production process can help to set countermeasures to meet the required delivery dates. In order to achieve this, we set up 24 prediction models on four different levels of detail utilizing different machine learning-algorithms – six prediction models on every level of detail – and applying a case-based research approach in order to identify the model with the highest model quality. The modeling approach on the four levels of detail is different. The models on the coarsest level of detail predict assembly start delayers utilizing a classification approach. The models on the three finer levels of detail predict assembly start delayers via a regression of different lead times and subsequent postprocessing operations to identify the assembly start delayers. After training of the 24 prediction models based on a real data set of a machine and plant manufacturer and evaluating their model quality, the classification model utilizing a Gradient Boosting classifier showed best results. Thus, performing a binary classification to identify assembly start delayers was the best modelling approach. With the achieved results, our study is a first approach to predict assembly start delayers and gives insights in the performance of different modeling approaches in the area of a production planning and control.

Highlights

Production companies are facing an ongoing change
The following research question is posed, considering the previous explanations: ‘‘How does the level of detail of the modelling affect the model quality to predict assembly start delayers?’’ Considering the argumentation of the authors in [30], we formulate the following working hypothesis: ‘‘The model quality for the prediction of assembly start delayers increases with a finer level of detail.’’
THE PREDICTION MODEL To answer the research question, 24 machine learning (ML)-models were created in total, which differ in their level of detail and the utilized ML-algorithm

Summary

Introduction

Production companies are facing an ongoing change. They are challenged to assert themselves in international markets and to differentiate their products from other products available on the market in in terms of functionality, quality and price. The logistics performance, such as high adherence to delivery dates or short delivery and lead times, is becoming a key competitive factor [1]–[3]. A typical example for this are machine and plant manufacturers, whose products often consist of a large number of customized components to enable a tailor-made solution for the respective customer [4], [5]. To ensure high adherence to delivery dates and short lead times, the punctual assembly of a product is a central factor, as the product can only be delivered to the. Under the assumption that all components required for assembly must be available at the start of assembly, the assembly process is subsequently delayed, if only one component is provided too late [8]

Objectives

Results

Conclusion