Deep learning‐based clustering of processes and their visual exploration: An industry 4.0 use case for small, medium‐sized enterprises

Abstract

This paper proposes a multi‐stage approach consisting of deep learning‐based image classification, process trace clustering, and visual/statistical knowledge discovery of process data. The proposed decision augmentation solution aims to facilitate the production planners in estimating the process‐specific production parameters such as activity duration, idle time, or machine utilization. This study focuses on ‘one‐of‐a‐kind production’ (OKP). Planning in OKP is especially challenging due to the increasing individualization of customer requirements. Furthermore, the uniqueness of products adds complexity to data and information structuring. To tackle this issue, we first train deep convolutional neural networks (CNN) with image data of production parts obtained from computer‐aided design (CAD) systems to extract meaningful features. After cross‐validation, uncertainty, and robustness assessment of the adopted deep learning approach, we use the data representation from the penultimate layer as input for clustering production parts. The goodness of clustering results is evaluated using a series of internal clustering validation indices. Finally, process event log data provided by manufacturing execution systems (MES) is mapped to each production part, allowing us to conduct statistical and visual knowledge discovery of process parameters for each cluster. The relevance of our proposed approach has been validated by studying a real‐world use case in a small, medium‐sized enterprise (SME) operating in the fixture and jig manufacturing industry.

Trace Encoding in Process Mining: a survey and benchmarking

“…First, we generated synthetic logs using the PLG2 tool [57]. Subsequently, the encoding of the generated logs was performed using open-source libraries in Python as described in Table 1, which include Sklearn 7 , Karate Club 8 , PM4PY 9 , NLTK 10 , Gensim 11 , GloVe 12 , and the position profile implementation on github 13 . We organize each method according to the proposed taxonomy and provide the respective references for original papers and online implementations.…”

“…As an attempt of capturing additional complexity, graph neural networks have been recently studied in the literature [12]. Convolutional neural networks have also been used for feature extraction [13]. Image-like data engineering methods have been introduced by [14,15,12].…”

“…https://github.com/gbrltv/business_process_encoding 7 https://github.com/scikit-learn/scikit-learn 8 https://github.com/benedekrozemberczki/karateclub 9 https://github.com/pm4py/pm4py-core 10 https://github.com/nltk/nltk 11 https://github.com/RaRe-Technologies/gensim 12 https://github.com/maciejkula/glove-python13 https://github.com/gbrltv/meta_trace_clustering/blob/main/clustering.py#L64…”

Recent trends and advances in machine learning challenges and applications for industry 4.0

“…Mehdiyev et al (2022) delve into deep learning‐based clustering. Authors spotlight Industry 4.0's visual exploration for SMEs, emphasising unique production.…”

“…The model aims to provide accurate and real-time KPI estimation, which is crucial for operational optimisation. Additionally, it also compares the proposed method with existing state-of-the-art techniques using real industrial data to demonstrate its effectiveness Mehdiyev et al (2022). delve into deep learning-based clustering.…”