Prognostic Health Management Research Articles

Diagnosis Method of Lubrication Failure by Coolant Immersion for a CNC Lathe Spindle

As a result of the development of network technologies, diagnosis techniques that can collect machine states continuously and prognostic health management (PHM) are available in the factory. PHM technology is also beginning to be implemented in the machine tool field. However, few studies have described causality between feature values, including vibration and acoustic emission data, collected by machine and physical phenomena of failures under the actual use of machine tools. In the present paper, a PHM system of lubrication failure of bearings in CNC lathe spindles is developed. An acceleration sensor is used to collect machine states, and statistical feature parameters that characterize the lubrication failure are extracted from the obtained vibration data. Moreover, in order to clarify the cause-effect relation between the extracted feature parameters and physical phenomena of lubrication failure, several analyses using surface roughness measurement, residual stress measurement, and grease consistency measurement are conducted.

An Edge-Fog-Cloud Computing-Based Digital Twin Model for Prognostics Health Management of Process Manufacturing Systems

The prognostics health management (PHM) from the systematic view is critical to the healthy continuous operation of process manufacturing systems (PMS), with different kinds of dynamic interference events. This paper proposes a three leveled digital twin model for the systematic PHM of PMSs. The unit-leveled digital twin model of each basic device unit of PMSs is constructed based on edge computing, which can provide real-time monitoring and analysis of the device status. The station-leveled digital twin models in the PMSs are designed to optimize and control the process parameters, which are deployed for the manufacturing execution on the fog server. The shop-leveled digital twin maintenance model is designed for production planning, which gives production instructions from the private industrial cloud server. To cope with the dynamic disturbances of a PMS, a big data-driven framework is proposed to control the three-level digital twin models, which contains indicator prediction, influence evaluation, and decision-making. Finally, a case study with a real chemical fiber system is introduced to illustrate the effectiveness of the digital twin model with edge-fog-cloud computing for the systematic PHM of PMSs. The result demonstrates that the three-leveled digital twin model for the systematic PHM in PMSs works well in the system's respects.

A Parallel Hybrid Neural Network With Integration of Spatial and Temporal Features for Remaining Useful Life Prediction in Prognostics

Prediction of remaining useful life (RUL) is an indispensable part of prognostics health management (PHM) in complex systems. Considering the parallel integration of the spatial and temporal features implicated in measurement data, this article proposes a novel parallel hybrid neural network that consists of 1-D convolutional neural network (1-DCNN) and bidirectional gated recurrent unit (BiGRU) to predict RUL. Specifically, the spatial and temporal information from historical data is parallel extracted with the aid of 1-DCNN and BiGRU, respectively. On this basis, the trained network can be applied for RUL prediction in real time. The proposed parallel hybrid neural network is evaluated by two public datasets, in detail, an aircraft turbofan engine dataset and a milling dataset. Experimental results demonstrate that the proposed parallel hybrid network can effectively predict the RUL, which outperforms the existing literature.

Fault Detection of Aerospace Systems Based on Binary Grasshopper Optimization Algorithm

The entire flight movement procedure is managed by the aerospace system.Its ability to detect faults can help the aerospace prognostic health management system make decisions and carry out targeted maintenance, which is crucial for enhancing the safety and dependability of the air- craft systems. Aerospace systems are constantly subject to several failures due to the risks and difficulties of the space environment, including the deterioration of subsystem performance, sensor errors, connection loss, or equipment damage.The fault diagnosis method for aerospace systems based on binary grasshopper optimisation algorithm is proposed in this study using Deep Learning (DL) technique by taking use of the strong learning and intelligent recognition capacity.The suggested system offered a novel LSTM autoencoder architecture with supervised machine learning and deep learning techniques to carry out two distinct stages of fault diagnosis. The detection phase, employing the LSTM autoencoder with KNN, compacted the two phases. Then, the fault diagnosis phase, which is represented by the classification schema, is updated using a decision tree with KNN.The fault detection and diagnostics for LSTM in aircraft systems was completed successfully. The experimental findings proved the superiority and efficacy of the suggested strategy. The experimental findings proved the efficacy and superiority of the suggested strategy.

Current Status and Applications for Hydraulic Pump Fault Diagnosis: A Review

To implement Prognostics Health Management (PHM) for hydraulic pumps, it is very important to study the faults of hydraulic pumps to ensure the stability and reliability of the whole life cycle. The research on fault diagnosis has been very active, but there is a lack of systematic analysis and summary of the developed methods. To make up for this gap, this paper systematically summarizes the relevant methods from the two aspects of fault diagnosis and health management. In addition, in order to further facilitate researchers and practitioners, statistical and comparative analysis of the reviewed methods is carried out, and a future development direction is prospected.

Prognostic Health Management of Pumps Using Artificial Intelligence in the Oil and Gas Sector: A Review

A system’s operational life cycle now includes an integrated health management and diagnostic strategy due to improvements in the current technology. It is evident that the life cycle may be used to identify abnormalities, analyze failures, and forecast future conditions based on current data. Data models can be trained using machine learning and statistical ideas, employing condition data and on-site feedback. Once data models are trained, the data-processing logic can be integrated into onboard controllers, allowing for real-time health evaluation and analysis. Interestingly, the oil and gas industries may encounter numerous obstacles and hurdles as a result of the integration, highlighting the need for creative solutions to the perplexing problem. The potential benefits in terms of challenges involving feature extraction and data classification, machine learning has received significant research attention recently. The application and utility in pump system health management should be investigated to explore the extend it can be used to increase overall system resilience or identify potential financial advantages for maintenance, repair, and overhaul activities. This is seen as an evolving research area, with a variety of application domains. This article present a critical analysis of machine learning’s most current advances in the field of artificial intelligence-based system health management, specifically in terms of pump applications in the oil and gas industries. To further understand its potential, various algorithms and related theories are examined. Based on the examined studies, machine learning shows potential for prognostics and defect diagnosis. There are, few drawbacks that is seen to be preventing its widespread adoption which prompt for further improvement. The article discussed possible solutions to the identified drawbacks and future opportunities presented. This study further elaborates on the commonly available commercial machine learning (ML) tools used for pump fault prognostics and diagnostics with an emphasis on the type of data utilized. Findings from the literature review shows that the neural network (NN) is the most prevalent algorithm employed in studies, followed by the Bayesian network (BN), support vector machine (SVM), and hybrid models. While the need for selecting appropriate training algorithms is seen to be significant. Interestingly, no specific method or algorithm exists for a given problem instead the solution relies on the type of data and the algorithm’s or method’s aptitude for resolving the provided errors. Among the various research studies on pump fault diagnosis and prognosis, the most frequently discussed problem is a bearing fault, with a percentage of 46%, followed by cavitation. The studies rank seal damage as the third most prevalent flaw. Leakage and obstruction are the least studied defects in research. The main data types used in machine learning techniques for diagnosing pump faults are vibration and flow, which might not be sufficient to identify the condition of pumps and their characteristics. The various datasets have been derived from expert opinion, real-world observations, laboratory tests, and computer simulations. Field data have frequently been used to create experimental datasets and simulated data. In comparison to the algorithmic approach, the data approach has not received significant research attention.

An Ontology for Prognostic Health Management in Spacecraft Avionics

Prognostic Health Management (PHM) is the disciplined application of measurement, monitoring, and support strategies to protect structural, electrical, or data entities precluding the failure of measured systems in all phases of operation. Model-Based Systems Engineering (MBSE) can be used to formalize system structure, operations, behavior, and requirements using an Architecture Framework (AF), Process Framework (PF), modeling language, and ontology; whereas the AF, PF, and modeling language may be specific to the program or mission employing MBSE, ontologies may be developed specific to a given domain. The PHM domain considers failure modes, effects, and criticality, and ontological system analysis in this domain can inform system structure, operations, behavior, or requirements. A reference ontology for the PHM domain in spacecraft avionics is presented here including aspects of existing ontologies such as the Basic Formal Ontology (BFO), a Top-Level Ontology (TLO) newly recognized by the International Organization for Standardization (ISO), the Information Artifact Ontology (IAO), and the Space Object Ontology (SOO). A distinction is made between a full PHM domain ontology, which would include many mechanical or electrical systems with myriad purposes, and a PHM domain ontology specific to spacecraft avionics. Present ontological development originated using the parlance and format of BFO and IAO in Stanford University’s Protégé software but diverged to include International Union of Pure and Applied Chemistry (IUPAC) terminology and classifications. When interacting with this ontology, engineers seeking to characterize system-specific failure modes, effects, and criticality can query the ontology with their hardware or software entities to obtain failure information specific to the operation of their system in a given operational environment. While this domain ontology is robust, the authors do not claim it to be complete or validated for all spacecraft avionics. It should be considered version one of a useful PHM tool with continual updates occurring after peer review and feedback.

An AI-Layered with Multi-Agent Systems Architecture for Prognostics Health Management of Smart Transformers: A Novel Approach for Smart Grid-Ready Energy Management Systems

After the massive integration of distributed energy resources, energy storage systems and the charging stations of electric vehicles, it has become very difficult to implement an efficient grid energy management system regarding the unmanageable behavior of the power flow within the grid, which can cause many critical problems in different grid stages, typically in the substations, such as failures, blackouts, and power transformer explosions. However, the current digital transition toward Energy 4.0 in Smart Grids allows the integration of smart solutions to substations by integrating smart sensors and implementing new control and monitoring techniques. This paper is proposing a hybrid artificial intelligence multilayer for power transformers, integrating different diagnostic algorithms, Health Index, and life-loss estimation approaches. After gathering different datasets, this paper presents an exhaustive algorithm comparative study to select the best fit models. This developed architecture for prognostic (PHM) health management is a hybrid interaction between evolutionary support vector machine, random forest, k-nearest neighbor, and linear regression-based models connected to an online monitoring system of the power transformer; these interactions are calculating the important key performance indicators which are related to alarms and a smart energy management system that gives decisions on the load management, the power factor control, and the maintenance schedule planning.

Clustering Federated Learning for Bearing Fault Diagnosis in Aerospace Applications with a Self-Attention Mechanism

Bearings, as the key mechanical components of rotary machinery, are widely used in modern aerospace equipment, such as helicopters and aero-engines. Intelligent fault diagnosis, as the main function of prognostic health management systems, plays a critical role in maintaining equipment safety in aerospace applications. Recently, data-driven intelligent diagnosis approaches have achieved great success due to the availability of large-scale, high-quality, and complete labeled data. However, in a real application, labeled data is often scarce because it requires manual labeling, which is time-consuming and labor-intensive. Meanwhile, health monitoring data are usually scattered in different regions or equipment in the form of data islands. Traditional fault diagnosis techniques fail to gather enough data for model training due to data security, economic conflict, relative laws, and other reasons. Therefore, it is a challenge to effectively combine the data advantages of different equipment to develop an intelligent diagnosis model with better performance. To address this issue, a novel clustering federated learning (CFL) method with a self-attention mechanism is proposed for bearing fault diagnosis. Firstly, a deep neural network with a self-attention mechanism is developed in a convolutional pipe for feature extraction, which can capture local and global information from raw input. Then, the CFL is further constructed to gather the data from different equipment with similar data distribution in an unsupervised manner. Finally, the CFL-based diagnosis model can be well trained by fully utilizing the distributed data, while ensuring data privacy safety. Experiments are carried out with three different bearing datasets in aerospace applications. The effectiveness and the superiority of the proposed method have been validated compared with other popular fault diagnosis schemes.

Prognostic health management of the robotic strain wave gear reducer based on variable speed of operation: a data-driven via deep learning approach

ABSTRACT The robotic reducer is prone to failure because of its unique characteristics. Data from vibration and acoustic emission sensors have been used for the prognostics of the reducer. However, various issues are associated with such traditional techniques. Hence, our research group proposes a novel approach to utilize the embedded setup of the electrical current to detect the mechanical fault of the robotic reducer in the actual industrial robot. Previously, a comprehensive approach of feature engineering was proposed to classify the mechanical fault for the robotic reducer. However, handcraft-based feature extraction is quite a tedious task, and computationally expensive. These features require a well-designed feature extractor, and the features need to be manually optimized before feeding into classifiers. In addition, the handcrafted features are problem-specific, and are complicated to generalize. To resolve these challenges, deep features are extracted to classify the fault and generalize for two different motion profiles under different working conditions. In the proposed research work, the fault characteristic is generalized for variable speed of operations considering various kinds of scenarios. In this research work, the generalization capability of the proposed approach is comprehensively evaluated. For that purpose, the data under different working conditions such as of lower speeds, higher speeds, and speed sequestration are used as unseen data to validate the model. The authenticity of the presented approach can be supported by the performance evaluation for fault classification of the different motion profiles and speed of operations.

Sensor-Based Prognostic Health Management of Advanced Driver Assistance System for Autonomous Vehicles: A Recent Survey

Recently, the advanced driver assistance system (ADAS) of autonomous vehicles (AVs) has offered substantial benefits to drivers. Improvement of passenger safety is one of the key factors for evolving AVs. An automated system provided by the ADAS in autonomous vehicles is a salient feature for passenger safety in modern vehicles. With an increasing number of electronic control units and a combination of multiple sensors, there are now sufficient computing aptitudes in the car to support ADAS deployment. An ADAS is composed of various sensors: radio detection and ranging (RADAR), cameras, ultrasonic sensors, and LiDAR. However, continual use of multiple sensors and actuators of the ADAS can lead to failure of AV sensors. Thus, prognostic health management (PHM) of ADAS is important for smooth and continuous operation of AVs. The PHM of AVs has recently been introduced and is still progressing. There is a lack of surveys available related to sensor-based PHM of AVs in the literature. Therefore, the objective of the current study was to identify sensor-based PHM, emphasizing different fault identification and isolation (FDI) techniques with challenges and gaps existing in this field.

Anomaly Detection of Servomotors Subject to Highly Accelerated Limit Testing

Companies utilize highly accelerated limit testing (HALT) to ensure efficient product development by accelerating loading conditions in the qualification process. The aim of qualitative accelerated testing such as HALT is to properly identify early behavioral anomalies. To this end, this study utilizes machine learning techniques for detecting anomalies in servomotors in electronic products subjected to HALT. A case study was conducted using a programmable robot kit with 12 servomotors. HALT comprises five types of stress: thermal conditioning (cold and heat), rapid thermal change, vibration, and combined stresses. The anomalous behavior of a servomotor can be identified using a k-nearest neighbor algorithm and verified by inspection using the loading conditions and electrical responses. In addition, anomalous behaviors among servomotors and a control board are assessed using a Gaussian graph model approach. Changes in the Gaussian graph are assessed as anomaly scores using Kullback–Leibler divergence. The anomaly score increased earlier than the operating limit defined by inspection, i.e., the deviation from the initial position of the shaft. The machine learning algorithm successfully identified the failure precursor of the unit. The proposed approach of HALT with the machine learning algorithm supports prognostic health management of servomotors.

Predictive Maintenance with PCA Approach for Multi Automated Railroad Crossing System (ARCS) in The Framework of Prognostic and Health Management (PHM) Planning

The existence of level crossings between railroads and road vehicles that do not have gates in areas far from crowds, such conditions require gates that are made automatically to avoid accidents. The Automated Railroad Crossing System (ARCS) is an automatically activated railroad crossing gate where train arrival information is obtained through sensors. For one level crossing, there are several electronic devices installed in the automatic railroad crossing system. It is planned that the automatic railroad crossing system will be installed at several level crossings. The problem is how to estimate the time to perform automatic railroad crossing maintenance at several different locations, For this reason, it is necessary to know the estimated remaining useful life (Remaining Useful Life) of the subsystems. The purpose of this research is to find the estimated remaining useful time (RUL) of the subsystem in the automatic railroad crossing system in order to estimate the time to perform maintenance. The process that is carried out to obtain the remaining useful time is through the Prognostic Health Management System development plan, while the analysis of the estimated remaining useful time is carried out using Principle Component Analysis (PCA), the results of this simulation show promising results to determine the estimated value of the remaining useful time. If it can be known the estimated remaining time of the benefit, it is hoped that the maintenance plan for each automatic railroad crossing system can be carried out more efficiently.

Contribution to the Design and Implementation of a Reflexive Cyber-Physical System: Application to Air Quality Prediction in the Vallees des Gaves

This thesis aims to set up a scientific approach to monitor and take preventive actions on the air quality for the actors of a territory not covered by conventional measuring stations. Thus, a Cyber-Physical System (CPS) approach combined with Prognostics Health Management (PHM) methodologies is chosen to move toward a self-monitoring and self-reconfiguration system. To collect data in an inexpensive manner, measurement stations with low-cost sensors (LCS) are developed. LCS have drawbacks and the first part of this thesis is the use of redundancy and a proposed algorithm to increase their hardware and data reliability. A first station is deployed as proof of concept and the region is already receiving real-time data. The next phase is to build forecasting models to help authorities make decisions.

Online Flow Estimation for Condition Monitoring of Pumps in Aircraft Hydraulics

Hydraulic systems in conventional civil aviation are currently monitored in a very rudimentary way. Normally, measured values are compared with a fixed threshold. If these measured values are outside the predefined limits, the entire hydraulic system is usually shut down. To overcome this deficit, a study regarding a novel prognostic health management method for aircraft hydraulic pumps, which allows a statement about the pump condition, is presented in this paper. The method is based on measuring differential pressure and temperature at a suitable resistance. In the first part of the study, the overall concept for monitoring the motor pump unit is analyzed. This is followed by a discussion of possible measurement methods and suitable resistors to determine the condition of the pump. In the second part of the study, the implementation for online monitoring of the pump is discussed. After a suitable approximation is found, the quality of the proposed method is evaluated with real hydraulic power generation and consumers.

An unsupervised approach for health index building and for similarity-based remaining useful life estimation

Predictive maintenance techniques attempt to trigger a maintenance intervention at the right moment by estimating the life expectation. Predictive maintenance is increasingly implemented by automated approaches able to perform diagnostics and prognostics. The main part of recent research in these approaches is focused in machine learning structures whose reasoning is implicit and cannot be easily explained. This poses a problem for their implementation in highly constrained area such as aeronautics. To overcome this constraint, explicit reasoning approaches such as the Similarity-Based Model (SBM) can be implemented. The SBM has been widely used for fault diagnostics and the remaining useful life (RUL) estimation, but the development of SBM includes tasks that often rely on high skilled experts. For instance, data reduction techniques required for SBM are often performed by experts judgment whose outcomes are not always consistent. The produced features from these techniques are used to build the Health Index that can be used to create the degradation trends that serve as a reference for the SBM. To overcome these difficulties, an automatic and unsupervised approach based on the Kernel Principal Component Analysis is proposed to enhance the Health Index creation. It preserves as much of the sensor information as possible improving the similarity-based RUL estimation. Additionally, when estimating the RUL of a system, the most similar degradation trends stored in the SBM library are used to compute individual RULs, the final RUL is obtained by a fusion rule technique that combines all these individual RULs into a consolidated value. For the fusion rule techniques, a self-adaptive method that does not rely on human expertize is proposed. This fusion rule can benefit of the accumulated knowledge over the SBM operation. This unsupervised approach to develop a SBM is validated with promising results against an equivalent and supervised algorithm that came out best in the 2008 prognostic health management challenge.

A Semantic Ontology-Based Approach to Support Model-Based Systems Engineering Design for an Aircraft Prognostic Health Management System

The Prognostic and Health Management (PHM) system of an aircraft has complex structures and diverse functions. It is highly coupled with other systems, such as the avionics system and flight management system. The Model-based Systems Engineering (MBSE) method is effective to support the design and verification of the aircraft PHM system. As a powerful semantic web construction method, ontology has been widely used to express design information, such as the concepts and the relationships between them. However, traditional graphical MBSE models have a natural weakness in transforming into ontology. In this paper, a semantic MBSE method is proposed to support the transform of the ontology model. Firstly, according to the design characteristics of the aircraft PHM system, a meta-model library of the aircraft PHM system is developed to support the design and evaluation. An MBSE modeling method based on requirement analysis, function analysis, logical architecture design, and physic architecture design is applied in the PHM design process. Secondly, the semantic system modeling language KARMA based on “graph, object, property, point, relationship, role, and extension” (GOPPRRE) is used to transfer the graphical MBSE model to the semantic MBSE model, which can be easily transformed to an ontology model. Finally, an ontology based on semantic modeling is developed to describe the MBSE entities and to support MBSE design. In this paper, a case study of an aircraft fuel PHM system is carried out to validate the proposed method. Based on the developed meta-model library, a complete MBSE design process for the aircraft PHM system is realized. And then an ontology model supporting PHM system design is generated from the semantic MBSE model. The MBSE ontology provides a shareable capability to help designers communicate effectively. Quantitative analysis based on ontology is also provided to verify the complexity and scale of the MBSE design process. Moreover, logical reasoning ability can also be provided to support the early requirement traceability for MBSE design. In general, the case study results show the feasibility and effectiveness of the proposed method for the aircraft PHM system design.

Applications of Machine Learning in Aircraft Maintenance

Aircraft maintenance is an expansive multidisciplinary field which entails robust design and optimization of extensive maintenance operations and procedures; encompassing the fault identification, detection and rectification, and overhauling, repair or modification of aircraft systems, subsystems, and components, as well as the scheduling for various maintenance operations, in compliance with the aviation standards; in order to predict, pre-empt and prevent failures and thus ensure the continual reliability of aircraft. Advances in Big Data Analytics (BDA) and artificial intelligence techniques have revolutionized predictive maintenance operations. Predictive maintenance is making big strides in the aerospace sector accompanied by a variety of prognostic health management options. Artificial intelligence algorithms have recently been extensively applied to optimize aircraft maintenance systems and operations. Several researchers have proposed, analysed, and investigated the applications of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) based data analytics for predictive maintenance of aircraft systems, subsystems, and components. This paper provides a comprehensive review of the ML techniques like Multilayer Perceptron (MLP), Logic Regression (LR), Random Forest (RF), Artificial Neural Network (ANN), Support Vector Regression (SVR), Linear Regression (LR), and other common ML techniques for their present implementation and potential future applications in aircraft maintenance.

Prognostic health management of repairable ship systems through different autonomy degree; From current condition to fully autonomous ship

Maritime characteristics make the progress of automatic operations in ships slow, especially compared to other means of transportation. This caused a great progressive deal of attention for Autonomy Degree (AD) of ships by research centers where the aims are to create a well-structured roadmap through the phased functional maturation approach to autonomous operation. Application of Maritime Autonomous Surface Ship (MASS) requires industries and authorities to think about the trustworthiness of autonomous operation regardless of crew availability on board the ship. Accordingly, this paper aims to prognose the health state of the conventional ships, assuming that it gets through higher ADs. To this end, a comprehensive and structured Hierarchal Bayesian Inference (HBI)-based reliability framework using a machine learning application is proposed. A machinery plant operated in a merchant ship is selected as a case study to indicate the advantages of the developed methodology. Correspondingly, the given main engine in this study can operate for 3, 17, and 47 weeks without human intervention if the ship approaches the autonomy degree of four, three, and two, respectively. Given the deterioration ratio defined in this study, the acceptable transitions from different ADs are specified. The aggregated framework of this study can aid the researchers in gaining online knowledge on safe operational time and Remaining Useful Lifetime (RUL) of the conventional ship while the system is being left unattended with different degrees of autonomy.

Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism

Prediction of remaining useful life (RUL) is of vital significance in the prognostics health management (PHM) tasks. To deal with the reverse time series and to reflect the difference in RUL prediction results at different time instances, this paper proposes a novel bidirectional gated recurrent unit with temporal self-attention mechanism (BiGRU-TSAM) to predict RUL. Specifically, a novel approach is proposed where each of the considered time instance is assigned a self-learned weight according to the degree of significance. Furthermore, the parameter update process of the TSAM is obtained with solid theoretical foundation, and as a sign of interpretability, it is shown that the assigned weights can remain consistency over several independent training processes. On this basis, the BiGRU-TSAM is applied to predict RUL online. An aircraft turbofan engine dataset and a milling dataset are applied to verify the proposed RUL prediction approach. The experimental results show the superiority of the proposed approach over the existing ones based on machine learning and deep learning.