SMART-PDM Showcased at IEEE IECON 2021

Barış Bulut of Enforma & Luis Lino Ferreira of ISEP co-chaired the session entitled “Predictive maintenance architectures and applications for industrial systems“.In the session there were 6 papers presented (see below). One of the papers was co-authored by SMART-PDM partners ISEP, VPS and Enforma, entitled “Predictive Maintenance of Home Appliances

S641 – SS Predictive Maintenance Architectures and Applications for Industrial Systems

Oct-16 2:00pm – 3:20pm Europe/Istanbul Time    2021-10-16 

Room H

Chairs: Luis Lino Ferreira, Barış Bulut


Paper ID: TF-024821
Title: Automated Pipe Inspection Based on Image Processing

Abstract: The gas that keeps us warm or water that we need for our survival are all transported to our crowded cities from rural areas via many underground pipelines. Generally, the inspection of these pipelines is performed visually using videos recorded by a camera mounted on a mobile system which moves inside the pipelines and controlled by an operator. The video recorded by this mobile system is later analysed by operators to find anomalies that may present at the interior of these pipelines. However, this method is human dependent and rather slow. This paper introduces a highly automated system that is capable of performing fast and high precision inspection of dents via creating 3D profiles using a special laser profiler mechanism and image processing algorithms. In the proposed system, a laser source is used to project a laser beam onto a canonical mirror to form a ring shape laser light on the pipe’s internal surface. Images of the laser ring profile are acquired with an omnidirectional camera; the circular shape of the laser ring profile disturbed when the laser passes through dents. A fast boundary following is developed to detect these changes in the profile by computing Euclidean distance between each measured point on the laser ring and the ideal centre of the profile. The locations and characteristics of dents are determined by means of odometry sensors and the proposed image processing techniques, respectively.

Paper ID: TF-005452
Title: Smart Machine Box with Early Failure Detection for Automatic Tool Changer Subsystem of CNC Machine Tool in the Production Line

Abstract: This research aims to propose an innovative smart system we developed for early failure detection of Automatic Tool Change (ATC) systems. Input data is the system’s tool magazine door open/close signals. Then, 41 indicators from 26 machines are obtained from statistics-based feature extraction methods. Under the guidance of predefined risk levels, nine high-ranking top level indicators are selected using correlation and regression analysis. In addition, some lightweight supervised learning algorithms are used to build and train the model to solve the classification problem of the system states, such as Normal, Caution, and Danger. The experimental results confirm that the high-ranking indicators can achieve the most prominent and stable performance under a series of tests. Under 10-fold cross-validation, the average accuracy is 89.43 %, which is 19~38 % higher than those of other feature groups. Among them, the Naive Bayes algorithm obtains the best accuracy of 94.2 %. This proves that the proposed smart system can effectively grasp the health status of the ATC systems.

Paper ID: TF-013773
Title: Autonomous CPSoS for Cognitive Large Manufacturing Industries

Abstract: The general aim of a cognitive Cyber Physical System of Systems (CPSoS) is to provide managed access to data in a smart fashion such that sensing and actuation capabilities are connected. Whilst there is significant funding and research devoted to this area, focus remains purely on creating bespoke systems. This paper presents a novel approach, based on a set of components to leverage Situational Awareness and Smart Actuation in large manufacturing industries with the focus on enabling predictive maintenance for asset and abnormal situation management. This paper presents a novel generic platform, named AtiCoS, that combines case-based and common-sense reasoning, as the enabling methodologies for enhancing CPSoS with cognitive capabilities.

Paper ID: TF-003425
Title: LSTM-based Anomaly Detection for Railway Vehicle Air-conditioning Unit using Monitoring Data

Abstract: Railway vehicles have a lot of equipment, and their faults possibly have significant impacts on the reliability and safety on railway operations. Some vehicles these days have Train Control and Monitoring System (TCMS), and constantly monitor and collect data of the equipment conditions during operations. In this paper, to utilize the monitoring data, we propose a method to continuously evaluate abnormalities of vehicle equipment using Neural Network with Long Short Term Memory (LSTM), which effectively and flexibly learn time series data. In the method, to implement anomaly detection, we introduce “anomaly score”, which is an indicator to express the degree of abnormality of vehicle equipment. In this paper, we show that the anomaly score increases as a fault of an air-conditioning unit progresses from 1.5 month before its fault become apparent. Consequently, the reliability of the railway operation can be improved by evaluating abnormalities of the vehicle air-conditioning unit or identifying signs of faults from monitoring data recorded with TCMS.

Paper ID: TF-023582
Title: Predictive Maintenance of home appliances: Focus on Washing Machines

Abstract: The remote maintenance of home appliances, like washing machines, air conditioning, and heating system is a complex problem, but with the help of the ongoing developments on Internet of Things, Data Analysis and Artificial Intelligence, the problem can now be tackled with success. This paper mostly focus in presenting the architecture developed within the aim of the SMART-PDM project for the acquisition of data on the operation of home appliances and then it also shows some preliminary results for washing machines, which give some hints on how to fine tune the system to achieve predictive maintenance and condition monitoring.

Paper ID: TF-022845
Title: Flexible Architecture for Data-Driven Predictive Maintenance with Support for Offline and Online Machine Learning Techniques

Abstract: Predictive maintenance requires the constant monitorization of equipment and the accumulation of data captured from sensors, industrial equipment, and existing management software. This data must be cleaned and processed before being used to train machine learning models that will generate different outputs of interest, such as fault prediction, fault detection, estimation of an equipment’s remaining useful life, among others. Considering these requirements and the different technologies needed to accommodate them, we present an architecture for predictive maintenance, based on existing standard architectures for Industry 4.0, that not only supports the implementation of all stages of predictive maintenance, but is flexible enough to be applied in distinct industrial scenarios. Moreover, the architecture is capable of accommodating both offline and online data pre-processing and machine learning techniques.