Using Bayesian networks to improve fault diagnosis during manufacturing tests of mobile telephone infrastructure

Abstract

Intense competition and the requirement to continually drive down costs within a mature mobile telephone infrastructure market calls for new and innovative solutions to process improvement. One particular challenge is to improve the quality and reliability of the diagnostic process for systems testing of Global System for Mobile Communications and Universal Mobile Telecommunications System products. In this paper, we concentrate on a particularly important equipment type-the Base Transceiver Station (BTS). The BTS manages the radio channels and transfers signalling information to and from mobile stations (ie mobile phones). Most of the diagnostic processes are manually operated and rely heavily on individual operators and technicians' knowledge for their performance. Hence, there is a high cost associated with troubleshooting in terms of time and manpower. In this paper, we employ Bayesian networks (BNs) to model the domain knowledge that comprises the operations of the System Under Test, Automated Test Equipment (ATE), and the diagnostic skill of experienced engineers, in an attempt to enhance the efficiency and reliability of the diagnostic process. The proposed automated diagnostic tool (known as Wisdom) consists of several modules. An intelligent user interface provides possible solutions to test operators/technicians, captures their responses, and activates the automated test program. Server and client software architecture is used to integrate Wisdom with the ATE seamlessly and to maintain Wisdom as an independent module. A local area network provides the infrastructure for managing and deploying the multimedia information in real time. We describe how a diagnostic model can be developed and implemented using a BN approach. We also describe how the resulting process of diagnosis following failure, advice generation, and subsequent actions by the operator are handled interactively by the prototype system. The results from an initial survey are presented, indicating sizeable reductions in fault correction times for many fault types.

Using Bayesian Networks to forecast spares demand from equipment failures in a changing service logistics context

“…These provide a powerful and flexible approach to reasoning under uncertainty. There have been a number of studies investigating the use of BNs in related fields including reliability (Langseth and Portinale 2007),maintenance (Weber, Jouffe, and Munteanu 2004;Weber and Jouffe 2006), system testing in manufacturing (Chan and McNaught 2008) and supplier selection (Hosseini and Barker 2016). However, we have not found any application to the kind of logistical support problems outlined here.…”

IDARTS – Towards intelligent data analysis and real-time supervision for industry 4.0

“…In [19], the authors survey several articles pertaining to the applications of PMS and propose to group them into four main application fields, namely system control [20], quality control [21], fault diagnosis [22], and predictive maintenance [23]. Other recent examples include an architecture for predictive maintenance as a service based on the cloud computing paradigm [24], the prediction of power consumption levels in machining processes through big data analytics [25] and a distributed multi-agent oriented framework for failure prediction from real-time sensor data [26].…”

Towards a domain-specific framework for predictive analytics in manufacturing

“…Predictive techniques have been used for fault diagnosis in manufacturing applications. In [17], the authors present a system called Wisdom. This system has been developed to enhance fault diagnosis on a Base Transceiver Station (BTS), an equipment used in a Motorola factory.…”