Root Cause Analysis of a Printed Circuit Board (PCB) Failure in a Public Transport Communication System

A printed circuit board (PCB) is an essential element for practical circuit applications and its failure can inflict large financial costs and even safety concerns, especially if the PCB failure occurs prematurely and unexpectedly. Understanding the failure modes and even the failure mechanisms of a PCB failure are not sufficient to ensure the same failure will not occur again in subsequent operations with different batches of PCBs. The identification of the root cause is crucial to prevent the reoccurrence of the same failure. In this work, a step-by-step approach from customer returned and inventory reproduced boards to the root cause identification is described for an actual industry case where the failure is a PCB burn-out. The failure mechanism is found to be a conductive anodic filament (CAF) even though the PCB is CAF-resistant. The root cause is due to PCB de-penalization. A reliability verification to assure the effectiveness of the corrective action according to the identified root cause is shown to complete the case study. This work shows that a CAF-resistant PCB does not necessarily guarantee no CAF and PCB processes can render its CAF resistance ineffective.

Advancement in Data Engineering and Feature Processing Workflow by Using Deep Learning Techniques for the Automation of ESP Failure Root Cause Analyses

Today, Electrical Submersible Pump (ESP) failure analysis is a tedious, human-intensive, and time-consuming activity involving dismantle, inspection, and failure analysis (DIFA) for each failure. This paper presents a novel artificial intelligence workflow using an ensemble of machine learning (ML) algorithms coupled with natural language processing (NLP) and deep learning (DL). The algorithms outlined in this paper bring together structured and unstructured data across equipment, production, operations, and failure reports to automate root cause identification and analysis post breakdown. This process will result in reduced turnaround time (TAT) and human effort thus drastically improving process efficiency.

Bayesian network-based root cause analysis and fault pathway identification in complex industrial processes

Real-time root cause identification (RCI) of faults or abnormal events in industries gives plant personnel the opportunity to address the faults before they progress and lead to failure. RCI in industrial systems must deal with their complex behavior, variable interactions, corrective actions of control systems and variability in faulty behavior. Bayesian networks (BNs) is a data-driven graph-based method that utilizes multivariate sensor data generated during industrial operations for RCI. Bayesian networks, however, require data discretization if data contains both discrete and continuous variables. Traditional discretization techniques such as equal width (EW) or equal frequency (EF) discretization result in loss of dynamic information and often lead to erroneous RCI. To deal with this limitation, we propose the use of a dynamic discretization technique called Bayesian Blocks (BB) which adapts the bin sizes based on the properties of data itself. In this work, we compare the effectiveness of three discretization techniques, namely EW, EF and BB coupled with Bayesian Networks on generation of fault propagation (causal) maps and root cause identification in complex industrial systems. We demonstrate the performance of the three methods on the industrial benchmark Tennessee-Eastman (TE) process. For two complex faults in the TE process, the BB with BN method successfully diagnosed correct root causes of the faults, and reduced redundancy (up to 50%) and improved the propagation paths in causal maps compared to other two techniques.

Automated ESP Failure Root Cause Identification and Analyses Using Machine Learning and Natural Language Processing Technologies

Today, the Dismantle, Inspection, and Failure Analysis (DIFA) process for electrical submersible pump (ESP) failure analysis is a tedious, human-intensive, and time-consuming activity. The activity involves a set of data and various information formats from several activities in the ESP operation lifecycle. This paper proposes a novel artificial intelligence workflow to improve the efficiency of the DIFA process using an ensemble of machine learning (ML) algorithms. This ensemble of algorithms brings together structured/unstructured data across equipment, production, operations, and failure reports to automate root-cause identification and analysis post breakdown. As a result, the time and human effort required in the process has been reduced, and process efficiency has drastically improved.

Root cause identification approach using decomposition of QFD and extended RPN for product manufacturing reliability degradation

Reliability is reflected in product during manufacturing. However, due to uncontrollable factors during production, product reliability may degrade substantially after manufacturing. Thus, root cause analysis is important in identifying vulnerable parameters to prevent the product reliability degradation in manufacturing. Therefore, a novel root cause identification approach based on quality function deployment (QFD) and extended risk priority number (RPN) is proposed to prevent the degradation of product manufacturing reliability. First, the connotation of product manufacturing reliability and its degradation mechanism are expounded. Second, the associated tree of the root cause of product manufacturing reliability degradation is established using the waterfall decomposition of QFD. Third, the classic RPN is extended to focus on importance to reliability characteristics, probability, and un-detectability. Furthermore, fuzzy linguistic is adopted and the integrated RPN is calculated to determine the risk of root causes. Therefore, a risk-oriented root cause identification technique of product manufacturing reliability degradation is proposed using RPN. Finally, a root cause identification of an engine component is presented to verify the effectiveness of this method. Results show that the proposed approach can identify the root cause objectively and provide reference for reliability control during production.

Defect patterns study of pick-and-place machine using automated optical inspection data

Purpose This paper aims to study the component pick-and-place (P&P) defect patterns for different root causes based on automated optical inspection data and develop a root cause identification model using machine learning. Design/methodology/approach This study conducts experiments to simulate the P&P machine errors including nozzle size and nozzle pick-up position. The component placement qualities with different errors are inspected. This study uses various machine learning methods to develop a root cause identification model based on the inspection result. Findings The experimental results revealed that the wrong nozzle size could increase the mean and the standard deviation of component placement offset and the probability of component drop during the transfer process. Moreover, nozzle pick-up position can affect the rotated component placement offset. These root causes of defects can be traced back using machine learning methods. Practical implications This study provides operators in surface mount technology assembly lines to understand the P&P machine error symptoms. The developed model can trace back the root causes of defects automatically in real line production. Originality/value The findings are expected to lead the regular preventive maintenance to data-driven predictive and reactive maintenance.

A Hierarchical Approach to Improve the Interpretability of Causality Maps for Plant-Wide Fault Identification

Modern mineral processing plants utilise fault detection and diagnosis to minimise time spent under faulty conditions. However, a fault originating in one plant section (PS) can propagate throughout the entire plant, obscuring its root cause. Causality analysis identifies the cause–effect relationships between process variables and presents them in a causality map to inform root cause identification. This paper presents a novel hierarchical approach for plant-wide causality analysis that decreases the number of nodes in a causality map, improving interpretability and enabling causality analysis as a tool for plant-wide fault diagnosis. Two causality maps are constructed in subsequent stages: first, a dimensionally reduced, plant-wide causality map used to localise the fault to a PS; second, a causality map of the identified PS used to identify the root cause. The hierarchical approach accurately identified the true root cause in a well-understood case study; its plant-wide map consisted of only three nodes compared to 15 nodes in the standard causality map and its transitive reduction. The plant-wide map required less fault-state data, time series in the order of hours or days instead of weeks or months, further motivating its application in rapid root cause analysis.

A Bibliometric Analysis of Product-Service Systems’ Design Methodologies: Potential Root-Cause Identification of PSS’ Failures

Product-service system (PSS) innovation is acknowledged as a promising way to achieve sustainability through better exploitation of given resources. Nevertheless, PSS implementation is also described as increasing failure risk for companies. Despite that authors have identified paradoxical situations as a source of failure while implementing PSS, few researches have focused on understanding the origin of these paradoxes. In this review, we aim at understanding how methodologies cope with the challenges of designing PSS throughout the complete company perimeter as well as how to manage interactions within this perimeter to avoid potential paradoxes and thus failure. To do so, we will rely on the business model innovation literature and, more specifically, the business model canvas to define and discretize the company perimeter. As for the interactions and their imbrication regarding paradoxes appearance, we will refer to Putnam et al. theory to gain deeper understanding of paradoxes-appearance mechanism. Our bibliometric strategy brought us to analyze 14 international articles via our graph, enabling us to highlight that some poles’ interactions during design are partly unaddressed, resulting potentially in the creation of tension sources and therefore potential paradoxes and ultimately implementation failure. Considering this, future research works could focus on defining all significant interactions to consider while designing a PSS as well as the typology of answers to engage while facing tensions. In that respect, these works could provide actionable solutions to lower PSS implementation-failure risk, thus benefiting those who wish to achieve better sustainability through PSS.