Multi Agent System for Machine Learning Under Uncertainty in Cyber Physical Manufacturing System

Abstract

Recent advancements in predictive machine learning has led to its application in various use cases in manufacturing. Most research focused on maximising predictive accuracy without addressing the uncertainty associated with it. While accuracy is important, focusing primarily on it poses an overfitting danger, exposing manufacturers to risk, ultimately hindering the adoption of these techniques. In this paper, we determine the sources of uncertainty in machine learning and establish the success criteria of a machine learning system to function well under uncertainty in a cyber-physical manufacturing system (CPMS) scenario. Then, we propose a multi-agent system architecture which leverages probabilistic machine learning as a means of achieving such criteria. We propose possible scenarios for which our proposed architecture is useful and discuss future work. Experimentally, we implement Bayesian Neural Networks for multi-tasks classification on a public dataset for the real-time condition monitoring of a hydraulic system and demonstrate the usefulness of the system by evaluating the probability of a prediction being accurate given its uncertainty. We deploy these models using our proposed agent-based framework and integrate web visualisation to demonstrate its real-time feasibility.

Toward Smart Traceability for Digital Sensors and the Industrial Internet of Things

“…For instance, an interpolating agent only needs to be present in the chain if some later step requires equidistant data. An agent framework that is designed with metrological use cases in mind is the Python package agentMET4FOF 0.4.1 [13]. The following example is implemented using this framework.…”

Metrological Challenges in Collaborative Sensing: Applicability of Digital Calibration Certificates

“…Yong et al have presented a demonstrator system for using the sensor agents to improve the handling of uncertainty in predictive ML in a cyber-physical manufacturing system (CPMS) [ 35 ]. ML has become more and more popular in optimizing operations and processes in manufacturing and quality control as it can effectively be used, for example, in predictive maintenance.…”

“…The idea behind IIoT is that it enables an increased level of automation and better overall understanding of processes, leading to improved efficiency and thus profitability. In smart factories and manufacturing, sensor networks are used to provide data for ML applications, cyber-physical systems, and digital twins, for example, for managing manufacturing processes or supply chains [ 2 , 35 , 55 , 56 ]. Such applications provide frameworks for predictive analysis for maintenance, prognostics, and decision-making.…”

Secure and communications‐efficient collaborative prognosis

“…The digital twins and the social platform are implemented for experiments discussed here and are therefore briefly described in the following paragraphs. A detailed description of the overall architecture and industrial multi‐agent systems, in general, can be found in [8, 16, 34, 35], respectively. The notion of agents’ in this paper refers to a collection of computational entities, that cooperate or compete to achieve a certain objective [36].…”