RI2AP: Robust and Interpretable 2D Anomaly Prediction in Assembly Pipelines.

Predicting anomalies in manufacturing assembly lines is crucial for reducing time and labor costs and improving processes. For instance, in rocket assembly, premature part failures can lead to significant financial losses and labor inefficiencies. With the abundance of sensor data in the Industry 4.0 era, machine learning (ML) offers potential for early anomaly detection. However, current ML methods for anomaly prediction have limitations, with F1 measure scores of only 50% and 66% for prediction and detection, respectively. This is due to challenges like the rarity of anomalous events, scarcity of high-fidelity simulation data (actual data are expensive), and the complex relationships between anomalies not easily captured using traditional ML approaches. Specifically, these challenges relate to two dimensions of anomaly prediction: predicting when anomalies will occur and understanding the dependencies between them. This paper introduces a new method called Robust and Interpretable 2D Anomaly Prediction (RI2AP) designed to address both dimensions effectively. RI2AP is demonstrated on a rocket assembly simulation, showing up to a 30-point improvement in F1 measure compared to current ML methods. This highlights its potential to enhance automated anomaly prediction in manufacturing. Additionally, RI2AP includes a novel interpretation mechanism inspired by a causal-influence framework, providing domain experts with valuable insights into sensor readings and their impact on predictions. Finally, the RI2AP model was deployed in a real manufacturing setting for assembling rocket parts. Results and insights from this deployment demonstrate the promise of RI2AP for anomaly prediction in manufacturing assembly pipelines.

A Primer on the Factories of the Future.

In a dynamic and rapidly changing world, customers' often conflicting demands have continued to evolve, outstripping the ability of the traditional factory to address modern-day production challenges. To fix these challenges, several manufacturing paradigms have been proposed. Some of these have monikers such as the smart factory, intelligent factory, digital factory, and cloud-based factory. Due to a lack of consensus on general nomenclature, the term Factory of the Future (or Future Factory) has been used in this paper as a collective euphemism for these paradigms. The Factory of the Future constitutes a creative convergence of multiple technologies, techniques, and capabilities that represent a significant change in current production capabilities, models, and practices. Using the semi-narrative research methodology in concert with the snowballing approach, the authors reviewed the open literature to understand the organizing principles behind the most common smart manufacturing paradigms with a view to developing a creative reference that articulates their shared characteristics and features under a collective lingua franca, viz., Factory of the Future. Serving as a review article and a reference monograph, the paper details the meanings, characteristics, technological framework, and applications of the modern factory and its various connotations. Amongst other objectives, it characterizes the next-generation factory and provides an overview of reference architectures/models that guide their structured development and deployment. Three advanced communication technologies capable of advancing the goals of the Factory of the Future and rapidly scaling advancements in the field are discussed. It was established that next-generation factories would be data rich environments. The realization of their ultimate value would depend on the ability of stakeholders to develop the appropriate infrastructure to extract, store, and process data to support decision making and process optimization.

Towards Semantic Integration of Machine Vision Systems to Aid Manufacturing Event Understanding.

A manufacturing paradigm shift from conventional control pyramids to decentralized, service-oriented, and cyber-physical systems (CPSs) is taking place in today's 4th industrial revolution. Generally accepted roles and implementation recipes of cyber systems are expected to be standardized in the future of manufacturing industry. The authors intend to develop a novel CPS-enabled control architecture that accommodates: (1) intelligent information systems involving domain knowledge, empirical model, and simulation; (2) fast and secured industrial communication networks; (3) cognitive automation by rapid signal analytics and machine learning (ML) based feature extraction; (4) interoperability between machine and human. Semantic integration of process indicators is fundamental to the success of such implementation. This work proposes an automated semantic integration of data-intensive process signals that is deployable to industrial signal-based control loops. The proposed system rapidly infers manufacturing events from image-based data feeds, and hence triggers process control signals. Two image inference approaches are implemented: cloud-based ML model query and edge-end object shape detection. Depending on use cases and task requirements, these two approaches can be designated with different event detection tasks to provide a comprehensive system self-awareness. Coupled with conventional industrial sensor signals, machine vision system can rapidly understand manufacturing scenes, and feed extracted semantic information to a manufacturing ontology developed by either expert or ML-enabled cyber systems. Moreover, extracted signals are interpreted by Programmable Logical Controllers (PLCs) and field devices for cognitive automation towards fully autonomous industrial systems.