3D Railway Modelling for Extending the Remaining Useful Life of a Bogie

Condition-based maintenance(CBM) policies and predictive maintenance(PdM) policies are emerging maintenance policies. However, comparative studies on CBM/PdM policies and traditional CM/PM policies are critical for industrial applications of CBM/PdM policies, but are very limited. Based on the failure times and condition monitoring data of BGA packages of lead-free solder joints, the application flowchart of a PdM policy is demonstrated. In addition, a quantitative comparison among a CM policy, a PM policy, a CBM policy and the PdM policy is conducted. Moreover, the reason for the improvement of maintenance effectiveness of the CBM and PdM policies are investigated. The results show that the CBM policy and the PdM policy share more accurate and reliable predictions of product lifetimes when deciding the maintenance schedules, by fully utilizing their condition monitoring data. Consequently, the CBM policy and the PdM policy can better balance the risks(e.g., the maintenance cost, the cost of product failures) and improve the maintenance effectiveness.

Degradation prediction and rolling predictive maintenance policy for multi-sensor systems based on two-dimensional self-attention

New maintenance policies like condition monitoring and prognostics are developed to predict the remaining useful life (RUL) of components. However, decision making based on these predictions is still an underexplored area of maintenance management. Furthermore, maintenance relies on the availability of spare parts for replacement in order to reduce failure downtime and costs. Accurate predictions of component failure times can be used to improve both maintenance and inventory decisions. During the past decades, several joint maintenance and inventory optimization systems have been studied in literature. Compared to the separate optimization of both models, these publications reported a remarkable improvement on total cost due to joint optimization. However, the inclusion of RUL in joint maintenance and inventory models for multi-component systems has not been considered before. The objective of this chapter is to quantify the added value of predictive information (RUL) in joint maintenance and inventory decision making for multi-component systems considering different levels of inter-component dependence (i.e. economic, structural and stochastic). A dynamic predictive maintenance policy is developed, which optimizes both maintenance and inventory parameters while minimizing the long-term average maintenance and inventory cost per unit time.KeywordsPreventive MaintenanceMaintenance ActionInventory PolicySpare PartInventory CostThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A metric for assessing and optimizing data-driven prognostic algorithms for predictive maintenance

Deterioration modeling and remaining useful life (RUL) estimation of equipment are key enabling tasks for the implementation of a predictive maintenance (PM) policy, which plays nowadays an important role for maintaining engineering systems. Hidden Markov Models (HMM) have been used as an efficient tool for modeling the deterioration mechanisms as well as for estimating the RUL of monitored equipment. However, due to some assumptions not always justified in practice, the applications of HMM on real-life problems are still very limited. To tackle this issue and to relax some of these unrealistic assumptions, this paper proposes a multi-branch Hidden semi-Markov modeling (MB-HSMM) framework. The proposed deterioration model comprises several different branches, each one being itself an HSMM. The proposed model offers thus the capacity to 1) explicitly model the sojourn time in the different states and 2) take into account multiple co-existing and competing deterioration modes, even within a single component. A diagnosis and RUL prognosis methodology based on the MB-HSMM model is also proposed. Thanks to its multiple branches property, the MB-HSMM model makes it possible not only to assess the current health status of the component but also to detect the actual deterioration mechanism. Based on the diagnostic results, the component RUL can then be calculated. The performance of the proposed model and prognosis method is evaluated through a numerical study. A Fatigue Crack Growth (FCG) model based on the Paris-Erdogan law is used to simulate deterioration data of a bearing under different operation conditions. The results show that the proposed MB-HSMM gives a very promising performance in deterioration mo de detection as well as in the RUL estimation, especially in the case where these deterioration modes exhibit very different dynamics.

Electric motors are widely used in our society in applications like cars, household appliances, industrial equipment, etc. Costly failures can be avoided by establishing predictive maintenance (PdM) policies or mechanisms for the repair or replacement of the components in electric motors. One of key components in the motors are bearings, and it is critical to measure the key features of bearings to support maintenance decision. This paper proposes a data science approach with embedded statistical data mining and a machine learning algorithm to predict the remaining useful life (RUL) of the bearings in a motor. The vibration signals of the bearings are collected from the experimental platform, and fault detection devices are developed to extract the important features of bearings in time domain and frequency domain. Regression-based models are developed to predict the RUL, and weighted least squares regression (WLS) and feasible generalized least squares regression (FGLS) are used to address the heteroscedasticity problem in the vibration dataset. Support vector regression (SVR) is also applied for prediction benchmarking. Case studies show that the proposed data science approach handled large datasets with ease and predicted the RUL of the bearings with accuracy. The features extracted from time domain are more significant than those extracted from frequency domain, and they benefit engineering knowledge. According to the RUL results, the PdM policy is developed for component replacement at the right moment to avoid the catastrophic equipment failure.

As the reliability, availability, maintainability, and safety of industrial equipment have become crucial in the context of intelligent manufacturing, there are increasing expectations and requirements for maintenance policies. Compared with traditional methods, data-driven Predictive Maintenance (PdM), a superior approach to equipment and system maintenance, has been paid considerable attention by scholars in this field due to its high applicability and accuracy with a highly reliable quantization basis provided by big data. However, current data-driven methods typically provide only point estimates of the state rather than quantification of uncertainty, impeding effective maintenance decision-making. In addition, few studies have conducted further research on maintenance decision-making based on state predictions to achieve the full functionality of PdM. A PdM policy is proposed in this work to obtain the continuous probability distribution of system states dynamically and make maintenance decisions. The policy utilizes the Long Short-Term Memory (LSTM) network and Kernel Density Estimation with a Single Globally-optimized Bandwidth (KDE-SGB) method to dynamic predicting of the continuous probability distribution of the Remaining Useful Life (RUL). A comprehensive optimization target is introduced to establish the maintenance decision-making approach acquiring recommended maintenance time. Finally, the proposed policy is validated through a bearing case study, indicating that it allows for obtaining the continuous probability distribution of RUL centralized over a range of ±10 sampling cycles. In comparison to the other two policies, it could reduce the maintenance costs by 24.49~70.02%, raise the availability by 0.46~1.90%, heighten the reliability by 0.00~27.50%, and promote more stable performance with various maintenance cost and duration. The policy has offered a new approach without priori hypotheses for RUL prediction and its uncertainty quantification and provided a reference for constructing a complete PdM policy integrating RUL prediction with maintenance decision-making.

Facility management (FM) accounts for more than two thirds of the total cost of the whole life cycle of a building. FM staff do have inadequate visualization and often have difficulty in querying information using 2D drawings and traditional facility management systems. Currently, building information modeling (BIM) is increasingly applied to FM in the operations and maintenance (O&M) stage. BIM represents the geometric and semantic information of building facilities in 3D object-based digital models and enables facility managers to manage building facilities better in the O&M stage. At the same time, the Internet of Things (IoT) technology can be used to acquire operational data of building facilities and real-time environmental data to support FM. However, few studies have used BIM and IoT technologies together for automated management and maintenance of building facilities. Around 65%~80% of the FM comes from facility maintenance management (FMM). However, there is a lack of efficient maintenance strategies and appropriate decision making approaches that can reduce FMM costs. Facility managers usually undertake reactive maintenance or preventive maintenance strategies in the O&M stage. However, reactive maintenance cannot prevent failures and preventive maintenance cannot predict the future condition of building components, which leads to maintenance actions being performed after failure has occurred and it cannot keep the functionality of a building consistent. This study aims to apply a predictive maintenance strategy with BIM and IoT technologies to overcome these limitations. In addition, there is an information interoperability problem among BIM, IoT and the FM system. Therefore, this study aims to leverage the BIM and IoT technologies to improve the efficiency of FMM and to address the information interoperability problem of integrating BIM, IoT and the FM system. In order to improve the efficiency of FMM, an FMM framework is proposed based on BIM and facility management systems (FMSs), which can provide automatic scheduling of maintenance work orders (MWOs) to enhance good decision making in FMM. In this framework, data are mapped between BIM and FMSs according to the developed Industry Foundation Classes (IFC) extension of maintenance tasks and MWO information in order to achieve data integration. Geometric and semantic information of the failure components is extracted from the BIM models in order to calculate the optimal maintenance path in the BIM environment. Moreover, the MWO schedule is automatically generated using a modified Dijkstra algorithm that considers four factors, namely, problem type, emergency level, distance among components, and location. In order to provide a better maintenance strategy for building facilities, a data-driven predictive maintenance framework based on BIM and IoT technologies for FMM has been developed. The framework consists of an information layer and an application layer. Data collection and data integration among the BIM models, FM system, and IoT system are undertaken in the information layer, while the application layer contains four modules to achieve predictive maintenance, namely: (1) condition monitoring and sensor data acquisition, (2) condition assessment module, (3) condition prediction module, and (4) maintenance planning module. In addition, machine learning algorithms, i.e. artificial neural network (ANN) and support vector machine (SVM), are used to predict the future condition of building components. For the information interoperability problem among BIM, IoT and FM system, an ontology-based methodology framework is proposed for data integration among the BIM, IoT and FM domains. The ontology-based approach is developed as a tool to facilitate knowledge management in BIM- and IoT-based FMM and improve the data integration process. First, three ontologies are developed for BIM, IoT, and FMM respectively according to the ontology development process and facility information requirement. Second, an ontology mapping method is designed to integrate the three developed ontologies based on mapping rules. Moreover, ontology reasoning rules are developed based on description logics to infer implicit facts from the integrated ontology and support quick information querying on FMM. The developed framework is validated through an illustrative example. This research provides an automatic work order scheduling approach in FMM and predictive maintenance strategy for building facilities, thereby enabling great saving in time and labor costs for facility staff. In addition, the proposed ontology-based methodology can address the information interoperability problem and integrate data from BIM, IoT and FM system for facility maintenance activities. In the future, the ontology-based methodology will be applied for the operation management of building facilities.


 
 
 A simulation-based real options analysis (ROA) approach is used to determine the optimum predictive maintenance opportunity for multiple wind turbines with remaining useful life (RUL) predictions in offshore wind farms managed under outcome-based contracts, i.e., power purchase agreements (PPAs). When an RUL is predicted for a subsystem in a single turbine using PHM, a predictive maintenance option is triggered that the decision-maker has the flexibility to decide if and when to exercise before the subsystem or turbine fails. The predictive maintenance value paths are simulated by considering the uncertainties in the RUL predictions and wind speeds (that govern the turbine’s revenue earning potential). By valuating a series of European options expiring on all possible predictive maintenance opportunities, a series of option values can be obtained, and the optimum predictive maintenance opportunity can be selected. The optimum predictive maintenance opportunity can also be determined using a stochastic discounted cash flow (DCF) approach that assumes the predictive maintenance will always be implemented on the selected opportunity. For a wind farm managed via a PPA with multiple turbines indicating RULs concurrently, the predictive maintenance value for each turbine depends on the operational state of the other turbines, the amount of energy delivered and to be delivered by the whole wind farm. A case study is presented in which the stochastic DCF and European ROA approaches are applied to a single turbine and to a wind farm managed via a PPA. The optimum predictive maintenance opportunities obtained from the two approaches are compared and it is demonstrated that the European ROA approach will suggest a more conservative opportunity for predictive maintenance with a higher expected option value than the expected net present value (NPV) from the stochastic DCF approach.
 
 

Railcar or Rolling stock that is referring to all vehicles moving on railway, is one of the most important component of the rail transport system. In-operation failures of the railcar results delays in transportation and therefore predicting the remaining useful life (RUL) and accordingly considering the preventive maintenance activities are essential. The RUL estimation is a key factor in predictive maintenance that has an influence on the maintenance scheduling, spare parts prediction and also the operational performance of the assets. This paper aims to model and analyze the RUL of railcars at LKAB, a Swedish Mining Company. To achieve this goal, first the failure behavior of the critical subsystems was analyzed and discussed. Then, with considering the effective operational factors (covariates), proportional hazard model (PHM) is applied to calculate the reliability functions. In this concept, RUL of the railcars can be obtained and discussed at the various initial survival times.

Remaining useful life prediction and predictive maintenance strategies for multi-state manufacturing systems considering functional dependence

Maintenance scheduling based on remaining useful life predictions for wind farms managed using power purchase agreements

Predictive maintenance (PdM) has seen significant advances through machine learning, yet its practical deployment remains challenged by data scarcity, system complexity, and uncertainty in cost-related decisions. The majority of current PdM strategies are concerned with enhancing Remaining Useful Life. Prediction accuracy of (RUL) in isolation and with maintenance scheduling as a problem (secondary or fixed). This study proposes a component based, decision oriented predictive maintenance (PdM) approach that links Remaining Useful Life (RUL) to optimization of maintenance. The two-stage framework proposed anticipates the component-specific RUL prediction where Long Short-Term Memory (LSTM) models was used to predict the Remaining Useful Life (RUL) of individual components. To address sparsity in failure data, Wasserstein Generative Adversarial Networks Gradient Penalty (WGAN-GP) were utilised to fill in run-to-failure sequences, stabilizing downstream modeling. In the second step, similar components in terms of Remaining Useful Life (RUL) degradation are clustered together by Density-Based Clustering Space (DBSCAN), which allows opportunistic maintenance. A decision on maintenance is then optimized cost-conscious grid search which works on fitted RUL distributions and a normalized. Not only based on point RUL estimates, but on a risk proxy. Empirical experimentation across multiple industrial components of a water bottling plant system indicates that the proposed approach continually reduces corrective failures and normalized maintenance costs as opposed to non-clustering approaches such as random choice and fixed choice of maintenance point. Sensitivity analysis also indicates that the optimal maintenance levels be consistent over a vast spectrum of cost assumptions, which emphasizes the resilience of the structure in economic uncertainty. Overall, this study contributes a robust and scalable maintenance literature that combines data augmentation, component based clustering, and risk aware optimization. This helps advance predictive maintenance practices into a more practical, cost aware decisions.

The remaining useful life (RUL) prediction and predictive maintenance (PdM) fusion framework for high-power IGBT modules ensures timely maintenance decision-making, enhancing their operational reliability. However, existing frameworks suffer from low-robustness uncertainty management and insufficient consideration of both reliability information and random failure mode, causing RUL prediction and PdM decision deviations while limiting method applicability. Thus, an improved framework is proposed. The framework employs weighted multi-model (WMM)-enhanced particle filter (PF) to predict performance degradation parameters (PDPs). WMM provides more reliable observations for PF across device lifespans, robustly mitigating the variance accumulation and thereby reducing RUL prediction uncertainty. Based on PDP predictions, the RUL distribution and the reliability function characterizing fatigue failure are derived. By integrating the reliability function with random failure information, the reliable RUL considering both failure modes is acquired, extending the RUL prediction process to safety-critical scenarios. Furthermore, the framework employs deep reinforcement learning (DRL) to obtain optimal PdM strategies. The reward function considers not only conventional maintenance cost and availability terms but also reliability predictions, enabling the PdM strategy adapt to scenarios with different reliability requirements. Finally, the effectiveness and superiority of the proposed framework were validated using full-lifecycle thermal resistance degradation data from 6500V/750A IGBT modules.

Ubiquitous sensors and networks are critical elements that seamlessly integrate into our daily lives and enable diverse commercial and engineering applications, including the Internet-of-Things (IoT). By extension, the Industrial IoT (IIoT) entails continuously monitoring revenue-generating assets, such as wafer dicing, robotic pick and place, and industrial washing machines, for anomalous patterns and minimizing unplanned breakdowns of critical machines via predictive maintenance (PdM). However, PdM must grow beyond equipment maintenance to achieve prescriptive maintenance, and we identified several research gaps, which we highlight and address in the following paragraphs. In the first study, we consider that unplanned breakdown of critical equipment interrupts production throughput in IIoT, and data-driven PdM becomes increasingly important for companies seeking a competitive business advantage. Manufacturers must manually allocate competent manpower resources in the event of machine failure. Furthermore, human errors have a negative rippling impact on both overall equipment downtime and production schedules. To address these issues, we formulate the complex resource management of humans and machines as a resource optimization problem. We developed a maintenance repair simulator (MRS) game and conducted real-world experiments to support our findings. These results are contrasted against our proposed deep reinforcement learning (DRL) method to evaluate the efficacy of AI-based complex resource management for PdM applications. In addition, DRL improves its accuracy with more training data, self-learns an optimal maintenance strategy, and incorporates human feedback as part of its learning strategy. Notably, this study analyzes one machine for maintenance to limit the research scope of and validate our hypothesis. In the second study, preliminary examination of existing literature reveals that existing IIoT-based PdM frameworks do not consider complex real-time production states, machine health, and maintenance manpower resources. For this reason, we propose a generic PdM optimization framework to help maintenance teams prioritize and resolve maintenance task conflicts. Specifically, the PdM framework jointly optimizes edge-based machine network uptime and manpower allocation in a stochastic IIoT-enabled manufacturing environment utilizing model-free Deep Reinforcement Learning (DRL) methods. Since DRL requires a significant amount of training data, we propose and demonstrate the use of Transfer Learning (TL) method to help DRL learn more efficiently by incorporating expert demonstrations, termed TL with demonstrations (TLD). TLD reduces training wall-time by 58% compared to baseline methods, and we undertake numerous experiments to illustrate the performance, robustness, and scalability of TLD. PdM research focuses on improving RUL prediction accuracy via end-to-end models (i.e., raw sensor to RUL prediction) to increase factory productivity. Since machine remaining useful life (RUL)(i.e., ground truth information) is often unavailable, an RUL prediction model's success is not readily transferable to similar applications. Besides, DL-based RUL models require considerable training data, including rare failure data, and critical monitoring of model performance drift is not actively researched. To address these concerns, we first present an attentive multi-branch feature network (AMBFNet) model to improve RUL prediction performance and benchmark AMBFNet against comparable work on real-world datasets. Secondly, we present an incremental learning-based approach for monitoring field-deployed edge-based RUL model performance drift. Notably, the AMBFNet model surpasses state-of-the-art RUL prediction models in terms of prediction error, and we are the first to report incremental learning results for a popular PdM dataset. In summary, this thesis encloses several critical contributions to the corpus of knowledge in the PdM research topic. Specifically, we propose transforming PdM into a holistic maintenance strategy via AI-based methods, such as DRL. In this regard, DRL is used to learn data-driven decision-making strategies and provide actionable recommendations to augment human decision-makers, thereby termed ``augmented intelligence". Furthermore, we consider hybrid deep learning methods to improve RUL prediction performance and batch-based incremental learning to mitigate model drift. Finally, unifying the proposed contributions creates a generic PdM framework for data analysis in IIoT to jointly manage resources (i.e., humans and machines) and achieve good RUL prediction performance via AI-based methods.