Within the context of Industry 4.0, quality assessment procedures using data-driven techniques are becoming more critical due to the generation of massive amounts of production data. In this paper, we address the detection of abnormal screw tightening processes, which is a key industrial task. Since labeling is costly, requiring a manual effort, we focus on unsupervised detection approaches. In particular, we assume a computationally light low-dimensional problem formulation based on angle–torque pairs. Our work is focused on two unsupervised machine learning (ML) algorithms: isolation forest (IForest) and a deep learning autoencoder (AE). Several computational experiments were held by assuming distinct datasets and a realistic rolling window evaluation procedure. First, we compared the two ML algorithms with two other methods, a local outlier factor method and a supervised Random Forest, on older data related with two production days collected in November 2020. Since competitive results were obtained, during a second stage, we further compared the AE and IForest methods by adopting a more recent and larger dataset (from February to March 2021, totaling 26.9 million observations and related to three distinct assembled products). Both anomaly detection methods obtained an excellent quality class discrimination (higher than 90%) under a realistic rolling window with several training and testing updates. Turning to the computational effort, the AE is much lighter than the IForest for training (around 2.7 times faster) and inference (requiring 3.0 times less computation). This AE property is valuable within this industrial domain since it tends to generate big data. Finally, using the anomaly detection estimates, we developed an interactive visualization tool that provides explainable artificial intelligence (XAI) knowledge for the human operators, helping them to better identify the angle–torque regions associated with screw tightening failures.

In recent years, the Twin-Transition reference model has gained notoriety as one of the key options for decarbonizing the economy while adopting more sustainable models leveraged by the Industry 4.0 paradigm. In this regard, one of the most relevant challenges is the integration of data-driven approaches with sustainability assessment approaches, since overcoming this challenge will foster more agile sustainable development. Without disregarding the effort of academics and practitioners in the development of sustainability assessment approaches, the authors consider the need for holistic frameworks that also encourage continuous improvement in sustainable development. The main objective of this research is to propose a holistic framework that supports companies to assess sustainability performance effectively and more easily, supported by digital capabilities and data-driven concepts, while integrating improvement procedures and methodologies. To achieve this objective, the research is based on the analysis of published approaches, with special emphasis on the data-driven concepts supporting sustainability assessment and Lean Thinking methods. From these results, we identified and extracted the metrics, scopes, boundaries, and kinds of output for decision-making. A new holistic framework is described, and we have included a guide with the steps necessary for its adoption in a given company, thus helping to enhance sustainability while using data availability and data-analytics tools.