Condition-based Predictive Maintenance Research Articles

Condition-based Predictive Maintenance as an Efficient Strategy for Industrializing Additive Manufacturing Technology

Objective: Traditional manufacturing has several issues to determine a general maintenance strategy. Additive Manufacturing (AM) is a special type of fabrication, which possesses different issues, especially uncertainty failure cases. This forms a big obstacle to becoming an industrialized production strategy. The objective of this work is to provide the most suitable maintenance strategy in order to reduce the likelihood of failure that can help in industrializing the AM technology. Methods: Among the different maintenance strategies, Predictive Maintenance (PdM) became widely treated in academia and industry. According to the methods used for detecting the failure signs, it can be classified into two types: Condition-Based Predictive Maintenance (CBPdM) and Statistical-Based Predictive Maintenance (SBPdM). The use of the last type highly depends on available and accessible data. However, CBPdM depends on only periodic or continuous condition monitoring tools for detecting the failure signs. Results: The existence of various types of failure cases yields to a big difficulty to predict failures. In addition, because of insufficient data, SBPdM cannot be selected as a suitable maintenance strategy for additive manufacturing. According to the presented examples, the CBPdM can be considered here as the best maintenance strategy for AM. Conclusion: CBPdM strategy is the best compromise between cost and applicability where there is not enough data. This selected maintenance approach represents an efficient tool in industrializing AM technology.

A novel decision optimization for thermal power unit based on condition-based predictive maintenance and equilibrium optimizer

A novel maintenance decision method for thermal power unit is proposed in paper. The proposed method tackles the issues of inflexibility and high cost in current thermal power unit maintenance strategies. It takes into account both intelligent fault prediction results and the current unit condition to make predictive maintenance decisions. It constructs a unit state model and a power generation prediction model based on DCS data from the thermal power unit. Constraints such as unit constraints, unit failure constraints, and unit power generation constraints are utilized in the construction of the objective function. The objective function incorporates start-stop cost, maintenance cost and downtime loss, and the Equilibrium Optimizer is used to determine the optimal maintenance strategy. Operational data from a power plant is used to verify the superiority of the method in enhancing unit power generation efficiency and the economic benefits of the power plant. The results show that the proposed method can reduce the cost by 34.9 % in case of minor failures.

Monitoring the Wear Trends in Wind Turbines by Tracking Fourier Vibration Spectra and Density Based Support Vector Machines

To make wind power more competitive, it is necessary to reduce turbine downtime and reduce costs associated with wind turbine operation and maintenance (O&M). Incorporating machine learning in the development of condition-based predictive maintenance methodologies for wind turbines can enhance their efficiency and reliability. This paper presents a monitoring method that utilizes Density Based Support Vector Machines (DBSVM) and the evolutionary Fourier spectra of vibrations. This method allows for the smart monitoring of the function evolution of the turbine. A complex optimal function (FO) for 5-degree order has been developed that will be the boundary function of the DBSVM to be timely determined from the Fourier spectrum through the magnitude–frequency and place of the failure occurring in the wind turbine drivetrains. The trend of the failure was constructed with the maximal values of the optimal frequency function for both yesthe cases of the upwind and downwind parts of the gearbox.

Self-Supervised Health Index Curve Generation for Condition-Based Predictive Maintenance

Modern machine degradation trend evaluation relies on the unsupervised model-based estimation of a health index (HI) from asset measurement data. This minimizes the need for timely human evaluation and avoids assumptions on the degradation shape. However, the comparability of multiple HI curves over time generated by unsupervised methods suffers from a scaling mismatch (non-coherent HIs) caused by the slightly different asset initial conditions and distinct HI model training. In this paper, we propose a novel self-supervised approach to obtain HI curves without suffering from the scale mismatch. Our approach uses an unsupervised autoencoder based on a convolutional neural network (CNN) to detect initial faults and autonomously label measurement samples. The resulting self-labeled data is used to train a 1D-CNN health predictor, effectively eliminating the scaling mismatch problem. On the basis of a bearing test-to-failure experiment, we show that our self-supervised scheme offers a promising solution for the non-coherent HI problem. In addition, we observed that our method indicates the gradual wear affecting the bearing prior to the independent analysis of a human expert.

Maintenance Scheduling Algorithm for Transformers in Tanzania Electrical Secondary Distribution Networks

The drive by the government of Tanzania to electrify every village has resulted into expansion of the electrical secondary distribution networks (ESDNs). Therefore, maintenance management is of the highest priority for the smooth operation of the ESDNs to reduce unscheduled downtime and unexpected mechanical failures. Studies show that condition-based predictive maintenance (CBPdM) method allows the utility company to monitor, analyze and process the information obtained from ESDNs transformers. Thus, this study adopts the CBPdM method to develop a maintenance scheduling algorithm that can predict the transformer state, forecast maintenance time based on transformer load profile and schedule its maintenance using a knowledge-based system (KBS). Applying the challenge driven education approach, the requirements for developing an algorithm were established through an extensive literature survey and engagement of the key stakeholders from the Tanzania utility company. Our study uses the Dissolved Gas Analysis tool to collect the transformer parameters used in algorithm design. The parameter analysis was performed using Statistical Package for Social Sciences software. Results show that the designed KBS algorithm minimizes human-related maintenance errors and lowers labour costs as the system makes all the maintenance decisions. Specifically, the proposed maintenance scheduling algorithm reduces downtime maintenance costs by 1.45 times relative to the classical inspection-based maintenance model while significantly saving the maintenance costs.
 Keywords: Electrical power network, Forecasted load consumption, Knowledge-Based System, Maintenance Scheduling, Predictive Maintenance, Secondary Distribution

CONDITION BASED PREDICTIVE MAINTENANCE ON SHIP’S MAJOR EQUIPMENT USING AI

This project mainly aims at diagnostics and prognostics approach for Main Engine fitted onboard Ship. Keeping in mind the complexity of equipment’s fitted in ship and the frequency of defect, there is always a demands for prognostic maintenance approach rather than TBM (Time based Maintenance). Under these circumstances, the CbPM(Condition based predictive maintenance) helps in predicting the fault of a running machine and signals to perform maintenance on it only when required, thereby impacting operational readiness and logistic stability. Condition-based maintenance (CBM) is a program that banks upon three factor- data processing, maintenance decision making and data acquisition. The paper mainly focuses on implementing CBM on a mechanical system with emphasis on technology, algorithm and model for data processing. This project focuses on implementing CBM on machines rather than TBM by knowing the past defect history; maintenance schedule, periodic routine and then applying AI tool on the same for predicting the machines future condition. This will thereby help in improving the overall life of the equipment. An instance on the use of various classification algorithms is taken into picture and compared their accuracy based on the F1 score in this paper. Keywords -Diagnostic, Prognostics, Condition-based predictive maintenance (CbPM), Main Engine, PPM (Planned preventive Maintenance)

Collaborative production and predictive maintenance scheduling for flexible flow shop with stochastic interruptions and monitoring data

Flexible flow shop problem (FFSP) has been extensively researched in recent years. However, machine deterioration and stochastic production interruptions noticeably affect the regular job process in practice, incurring great cost. It is significant to incorporate the condition-based predictive maintenance scheduling and the production modification for interruptions with traditional FFSP. Nevertheless, this issue is rarely investigated in the existing FFSP studies. To solve the FFSP with maintenance and stochastic interruptions (FFSP-MSI), this paper proposes a collaborative optimization policy of production and maintenance (COPPM) by considering stochastic interruptions and monitoring data utilization for total cost reduction. For maintenance scheduling, a real-time prognosis updating method is leveraged based on monitoring data to capture the individual machine degradations. Assisted by the prognosis output, the optimal maintenance intervals are dynamically derived through a cost rate model. For production optimization, a variable neighborhood search (VNS) algorithm is presented to obtain the nearly- optimal initial production plan and the production modification for stochastic interruptions caused by machine failures and random jobs. This proposed COPPM comprehensively determines the cost-effective maintenance cycle, job order and machine selection for each job. Computational experiments of the wind turbine blade process are presented to certify the economic effectiveness of COPPM. Compared with the traditional production and maintenance scheduling method, the COPPM achieves 13.68 % total cost reduction in average under various problem scales.

A predictive multi-objective condition-based maintenance (CBM) policy considering ecological factors

PurposeThe purpose of this paper is to propose an improved multi-objective optimization model for the condition-based maintenance (CBM) of single-component systems which considers periodic imperfect maintenance and ecological factors.Design/methodology/approachBased on the application of non-periodic preventive CBM, two recursion models are built for the system: hazard rate and the environmental degradation factor. This paper also established an optimal multi-objective model with a normalization process. The multiple-attribute value theory is used to obtain the optimal preventive maintenance (PM) interval. The simulation and sensitivity analyses are applied to obtain further rules.FindingsAn increase in the number of the occurrences could shorten the duration of a maintenance cycle. The maintenance techniques and maintenance efficiency could be improved by increasing system availability, reducing cost rate and improving degraded condition.Practical implicationsIn reality, a variety of environmental situations may occur subsequent to the operations of an advanced manufacturing system. This model could be applied in real cases to help the manufacturers better discover the optimal maintenance cycle with minimized cost and degraded condition of the environment, helping the corporations better fulfill their CSR as well.Originality/valuePrevious research on single-component condition-based predictive maintenance usually focused on the maintenance costs and availability of a system, while ignoring the possible pollution from system operations. This paper proposed a modified multi-objective optimization model considering environment influence which could more comprehensively analyze the factors affecting PM interval.

Health Index Analysis of Transmission System Components

Optimizing maintenance strategies for power transmission components is crucial to prevent failure in the system while maintaining and enhancing the overall economic efficiency. Condition-based maintenance can fulfill this and in the present paper health index-based efficient condition assessment is applied as an essential input to this type of maintenance. A method for the calculation of the health index of primary transmission system components is presented and discussed. Condition-based assessment is utilized for developing a calculation method for evaluating the health index at different levels in the system. The health index of each component is calculated by using the Weighting and Scoring Method. Several factors affecting the condition of different equipment are considered in the algorithm including environmental effects, mechanical stress, and accessibility issues. The special focus is on assigning a numeric value to the health of individual sub-components of the equipment to plan the condition-based predictive maintenance of power system components. The data indicate that in contrast to considering the health index of the entire system, making decisions considering the individual componet health indices can result in a more reliable operation.

Replacement and imperfect repair of deteriorating system: Study of a CBM policy and impact of repair efficiency

This paper studies a condition-based predictive maintenance policy in the presence of imperfect repairs for deteriorating systems. The effect of imperfect repairs is assumed to be random in the sense that a maintenance action reduces the systems degradation level by a random proportion. The associated distribution allows characterizing the repair efficiency. As an example, the beta distribution is considered. It allows defining a wide range of repair efficiencies. A maintenance policy with an aperiodic and predictive inspection planning is considered and a new decision criterion is introduced to evaluate the extent to which a repair would be beneficial. The aim is to find a proper balance between repair and replacement for preventive action which leads to optimal maintenance cost. With this consideration, the cost model is developed from regenerative and semi-regenerative properties. The expected cost is evaluated and the optimal policy is reached as a function of repair efficiency. Finally, a numerical study is drawn up to demonstrate the implementation and highlight the potential benefits of the proposed methods. A sensitivity analysis on critical parameters is also performed.

Smart Mechanical Systems for Manufacturing in the Era of Industry 4.0: Condition-Based Predictive Maintenance and Dynamic System Modification for Small and Medium-Sized Enterprises

We are in the era of the fourth industrial revolution. Which highlights adaptability, monitoring, digitisation and efficiency in manufacturing as a result of the design of new smart mechanical systems. A central role in Industry 4.0 is played by maintenance and, within this framework, we define and review condition-based predictive maintenance. Thereafter, we propose a new class of smart mechanical systems that self-optimise utilising both condition-based maintenance and dynamic system modification. Akin to smart structures, smart mechanical systems will recognise and predict faults or malfunctions and, subsequently, self-optimise to restore desirable system behaviour. Potential benefits include increased reliability and efficiency while reducing cost without the requirement of highly skilled technicians. Thus, small and medium-sized enterprises are a specific target of such technology due to their increasing level of automatisation within Industry 4.0.

Economic Analysis of a Massively Populated Internet of Things System: An Agent-Based Simulation Approach

With 212 locations serving a geographical area three times the size of the state of Texas, our international client has been experiencing unexpected failures in his portfolio of thousands of refrigeration units, resulting in an associated loss of $1.4 million. These losses have been attributed to lapses in food quality caused by improper refrigeration, and the adopted reactive maintenance strategy of the refrigeration units. To assist our client in complying with the cold-chain regulations of food safety and mitigate such losses, the agent-based simulation was used to model and assess the viability of two distinct massively populated Internet of Things (IoT) alternatives. The first (alternative A) involves monitoring the availability of each of the refrigeration units and signaling for the initiation of repair processes and food removal from failed units when the cooling temperature differs from a specified threshold and a more sophisticated and expensive alternative B that involves the adoption of the added capability of a condition-based predictive maintenance strategy to reduce unplanned downtime and mitigate or eliminate the causes of failure. Using historical data, a simulation of the current operations was first modeled, validated, and then augmented with capabilities to address the operational characteristics of the proposed IoT implementations. Results of financial analysis results including the probabilistic risk analyses, that account for the variations and the probability distributions of the assumption parameters, showed alternative A to be superior, with a mean net present value (NPV) of $416,703, and a modified IRR of about 18.77% exceeding the project cost of capital of 12.80% with complete certainty. The client was also advised that a 30% reduction in the acquisition cost would make investment B as viable as investment A.

Real-time fault diagnosis of HEMM using Bayesian Network: A case study on drag system of dragline

Undetected faults in heavy earth moving machinery (HEMM) are associated with unwanted failures. Dragline is an HEMM used in coal mining for removal of overburden and dumping it into de-coaled area. Failure of dragline contributed to total downtime of 4955 h in 28-month (2014–16) period and 50% of these downtimes were contributed by its drag system alone. The symptoms those exceeded threshold limit in the drag system during this period was 438, which led to 185 faults and subsequently 16 failures. Therefore, an attempt has been made for real-time fault diagnosis of drag system to analyse the faults by establishing causal relationships between cause, symptom and fault using Bayesian Network (BN). The new set of observed evidences (e.g., symptoms) obtained through built-in sensors or visual inspection during working of dragline can be updated in the BN model. Thereafter fault inference is used to identify the fault, and categorise the degraded and catastrophic faults. Simultaneously the change in probability values of the causes are recorded for the given symptoms. The conflict between the set of observed evidences was detected, and the correctness of the model was validated through conflict analysis. Appropriate condition-based predictive maintenance action can be undertaken by the maintenance engineer for eliminating these faults.

The application of machine learning for the prognostics and health management of control element drive system

Digital twin technology can provide significant value for the prognostics and health management (PHM) of critical plant components by improving insight into system design and operating conditions. Digital twinning of systems can be utilized for anomaly detection, diagnosis and the estimation of the system's remaining useful life in order to optimize operations and maintenance processes in a nuclear plant. In this regard, a conceptual framework for the application of digital twin technology for the prognosis of Control Element Drive Mechanism (CEDM), and a data-driven approach to anomaly detection using coil current profile are presented in this study. Health management of plant components can capitalize on the data and signals that are already recorded as part of the monitored parameters of the plant's instrumentation and control systems. This work is focused on the development of machine learning algorithm and workflow for the analysis of the CEDM using the recorded coil current data. The workflow involves features extraction from the coil-current profile and consequently performing both clustering and classification algorithms. This approach provides an opportunity for health monitoring in support of condition-based predictive maintenance optimization and in the development of the CEDM digital twin model for improved plant safety and availability.

A Case Study for Problem-based Learning Education in Fault Diagnosis Assessment

The use of Condition-based Predictive Maintenance (CBPdM) has grown significantly due to the Industry 4.0 movement and to the advancements in data acquisition, gathering, storing and analytics. In modern maintenance engineering education, there is the need to include CBPdM alongside with traditional maintenance approaches. Within this paper, a case study is proposed for education in Fault Diagnosis Assessment (FDA) using the Problem-based Learning (PBL) approach. Following a PBL approach, the proposed case study consists of a ‘close-to-real-life’ problem and allows the implementation of most of the steps of FDA, and the assessment of the answer through objective metrics. We hope that this work may impulse the production of more educational case studies within the topic of CBPdM.

Nondestructive Evaluation of Coatings Delamination Using Microwave Time Domain Reflectometry Technique

Ceramic based coatings such as Thermal Barrier Coatings (TBCs) are widely deposited onto gas turbine engine components to protect their metal substrate against high temperature. However, improper adhesive application, thermal stress and moisture penetration through the insulation materials can cause defects such as delamination to grow between the insulation and the metal surface. Such defects could lead to catastrophic failure if not immediately detected and repaired. Hence, it is imperative to non-destructively inspect these interfaces for delamination to avoid such an event. In this paper, a novel microwave non-destructive testing technique for ceramic-based coatings is proposed. This technique is based on scanning the surface of the coating with an open-ended rectangular waveguide and analyzing the reflections in the time domain. The proposed time-domain technique appears to reveal more about the depth of any existing delamination than any other microwave non-destructive testing (NDT) technique. Here, a ceramic sample with machined delamination is scanned using rectangular waveguides operating from 26.5 to 40 GHz. After applying Fourier analysis to the frequency domain waveguide reflections, time-domain results showed the delamination with significantly better depth resolution compared to frequency domain analysis. The results reported in this paper prove the advantages of the time-domain technique to forecast the relative delamination depth, which is important for many industrial applications. The depth information of delamination can be used in a condition-based predictive maintenance schedule to plan the inspection intervals efficiently, minimize the unnecessary replacements and provide practical guidance for future design.

Advantages of using statistical models for detecting faulty components in railway bogies against using simple criteria as defined in standards

In general, railway vehicles are maintained preventively within certain time periods. Condition-based predictive maintenance strategies offer great economic potential because components can be used much longer and are not exchanged when they are still healthy. Some modern trains are equipped with many sensors on the bogie in order to perform diagnostics and prognostics of components. Within a railway bogie the yaw damper plays an important role because it helps to ensure a stable run of the bogie. Standards define an instability criterion for running safety based on domain knowledge. We analyse the sensitivity of the criterion on a faulty yaw damper. On the other hand, data-driven algorithms gain significance in diagnostics, which as the saying goes can obtain a much better performance. In this work, we compare the instability criterion against the prediction of a statistical model trained on real measured data. We investigate the detection of a yaw damper with reduced functionality. We also analyse the influence of operational conditions such as equivalent conicity and speed. Results show that data-driven classifiers are much more sensitive for faulty states and the prediction of a reduced functionality is possible. Even a faulty yaw damper with low equivalent conicity can be detected.

A generalized three-type lifetime probabilistic models-based hybrid maintenance policy with a practical switcher for time-based preventive maintenance and condition-based maintenance

This paper proposes a generalized hybrid maintenance policy for maintenance scheduling with the help of both time-based maintenance and condition-based maintenance techniques, in which three-type product lifetime probabilistic models are utilized. A dispersion of lifetime estimates-based switcher is proposed to recommend the choice of time-based maintenance or condition-based predictive maintenance schedules in a real-time manner. Within the condition-based predictive maintenance policy, which is a part of the hybrid maintenance policy, a novel weighted average of the maintenance schedules is proposed to recommend maintenance acts, which are estimated based on two types of product lifetime probabilistic models namely type-II and type-III lifetime probabilistic models. The hybrid maintenance policy includes the classical time-based maintenance policy, the traditional condition-based predictive maintenance policy, and the proposed condition-based predictive maintenance policy as special cases. An extensive numerical investigation for the stochastic linear degradation model verifies the effectiveness of the proposed hybrid maintenance policy, highlighting the existence of a special space among time-based maintenance and condition-based predictive maintenance polices, which provides even better maintenance performance than a solely condition-based predictive maintenance policy.

Prognostic condition monitoring for wind turbine drivetrains via generator current analysis

Maintenance costs account for a significant portion of the total cost of electricity generated by wind turbines. Currently in the wind power industry, maintenance is mainly performed on regular schedules or when significant damage occurs in a wind turbine making it inoperable, instead of being determined by the actual condition of the wind turbine. Among the total maintenance costs, approximately 25%~35% is related to regularly scheduled preventive maintenance and 65%~75% to unscheduled corrective maintenance. To reduce the failure rate and level and maintenance costs and improve the availability, reliability, safety, and lifespans of wind turbines, it is desirable to perform condition-based predictive maintenance for wind turbines, which will require a high-fidelity online prognostic condition monitoring system(CMS) for fault diagnosis and prognosis and remaining useful life(RUL) prediction of wind turbines. Most of the existing wind turbine CMSs are based on vibration monitoring and have no or limited capability in fault prognosis and RUL prediction. Compared to vibration monitoring, the prognostic condition monitoring techniques based on generator current signal analysis proposed recently have significant advantages in terms of cost, hardware complexity, implementation, and reliability. This paper discusses the principles and challenges of using generator current signals for prognostic condition monitoring of wind turbine drivetrains and presents an overview of recent advancements in this area.

Data-driven condition now- and forecasting of railway switches for

This contribution presents a data-based model that exploitsthe power consumed by point engines during bladesmovement of railway switches to detect relevant anomaliesin switch behavior. The model incorporates local airtemperature at the time of the measurement to account forthe significant influence of the environmental conditions onnormal switch behavior. Anomaly detection by the model isvalidated against alerts triggered by the state-of-the-artmonitoring system POSS®, which is based on switchspecific and manually selected reference curves. The databased model leads to less in number and more reliable alertsin comparison to the current version of POSS®. Especiallyfalse alerts caused by temperature effects are significantlyreduced. Furthermore, the high sensitivity of the modelproves to be capable of detecting emerging switch failures atan early stage of development. The detection capabilities ofswitch condition (nowcast) and identification of emergingfailures at an early stage (required for failure forecast)proves that the model is useful for traffic interferenceprevention, condition-based predictive maintenance andswitch health enhancement.