A New Particle Swarm Optimization Algorithm for Outlier Detection: Industrial Data Clustering in Wire Arc Additive Manufacturing

Abstract

In this paper, a novel outlier detection method is proposed for industrial data analysis based on the fuzzy C-means (FCM) algorithm. An adaptive switching randomly perturbed particle swarm optimization algorithm (ASRPPSO) is put forward to optimize the initial cluster centroids of the FCM algorithm. The superiority of the proposed ASRPPSO is demonstrated over five existing PSO algorithms on a series of benchmark functions. To illustrate its application potential, the proposed ASRPPSO-based FCM algorithm is exploited in the outlier detection problem for analyzing the real-world industrial data collected from a wire arc additive manufacturing pilot line in Sweden. Experimental results demonstrate that the proposed ASRPPSO-based FCM algorithm outperforms the standard FCM algorithm in detecting outliers of real-world industrial data. Note to Practitioners-Electric arc (which is governed by the current and arc voltage) plays a significant role in monitoring the operating status of the wire arc additive manufacturing (WAAM) process. The nominal periodic current and voltage may occasionally change abruptly due to anomalies (such as arc instability, unstable metal transfer, geometrical deviations, and surface contaminations), which would affect the quality of the fabricated component. This paper focuses on detecting possible anomalies by analyzing the current and voltage during the WAAM process. A novel clustering-based outlier detection method is proposed for anomaly detection where abnormal and normal instances are categorized into two separate clusters.A new particle swarm optimization algorithm is put forward to optimize the initial cluster centroid so as to improve the detection accuracy. The proposed outlier detection method is applied to real-world data collected from a WAAM pilot line for detecting abnormal instances. Experimental results demonstrate the effectiveness of the proposed outlier detection method. The proposed outlier detection method can be applied to other industrial applications including electrical engineering, mechanical engineering and medical engineering. In the future, we aim to develop an online outlier detection system based on the proposed

A Dynamic Linear Bias Incorporation Scheme for Nonnegative Latent Factor Analysis

“…(1) The proposed DNLFA's d1 and d2 are set at 20 and 5, respectively. Considering compared model, their LF dimension is set at 20 uniformly; (2) For each model on each data set, the results generated from 10 different random initial values are recorded to calculate the average RMSE and convergence time for eliminating the effect of initial assumptions [13,[41][42][43][44][45]. (3) The training process of the test model is terminated when: 1) the iteration count reaches a preset threshold, which is 1000; 2)…”

Modeling and Causality Analysis of Human Sensorimotor Control System Based on NVAR Method

“…When the degree of system nonlinearity is high, the complexity of the VAR model may become quite substantial. This requires more regression terms and parameters to describe the system's dynamics [16], resulting in model overfitting and increased computational complexity [17].…”

Relaxed Symmetric Non-negative Latent Factor Analysis for Large-scale Undirected Weighted Networks

“…Note that it is crucial to find optimal the model's hyper-parameters for achieving its good performance [14,32,41]. According to previous studies [50], we adopt one kind of BO method, i.e., the commonly-adopted tree-structured of parzen estimators (TPE) algorithm for implementing adaptation of PSNL's hyper-parameters, i.e., λ, γ, μ and η.…”