Time-based Maintenance Research Articles

Remote monitoring and alert system of HV transformer based on FMEA

This paper presents a technique to measure and collect maintenance data for remote monitor of high voltage transformer. The technique installs field instruments to measure winding temperature, cooling-oil temperature, inner pressure, electrical power, and so on. IoT2040 is applied for acquisition (DAQ), processing unit and smart gateway. It converts field data into information that enables for real time monitoring and preventive maintenance applications. This technique can transform time-based maintenance to condition-based maintenance. In addition, the proposed script functions are created based on failure modes and effects analysis (FMEA) to identify alarm and alert conditions. Consideration alarm-referenced parameters that are diagnostic, performance/efficiency analysis relate to operation or communication conditions also assign by script functions. The relevant data from IoT2040 can be transmitted to the local computer as well as a remote-mobile devices running the dashboard with Ubidots server. Ubidots server is responsible for HMI and delivering specific alarm and alert services to the user. Users can access for remote monitoring by smart phone, tablet, laptop, and PC. The experiment performs by simulation with 3 phase Oil immersed distribution transformer. Electrical specification is 50 Hz 250 kVA, 22 kV, 400/230 V. The results shown the assigned data, dashboard, and notices message that notices relate the FMEA scripts. The technique provides early warning detection of transformer statuses that make opportunity to take corrective action to prevent failure.

Generative Adversarial Network-based Missing Data Handling and Remaining Useful Life Estimation for Smart Train Control and Monitoring Systems

As railway is considered one of the most significant transports, sudden malfunction of train components or delayed maintenance may considerably disrupt societal activities. To prevent this issue, various railway maintenance frameworks, from “periodic time-based and distance-based traditional maintenance frameworks” to “monitoring/conditional-based maintenance systems,” have been proposed and developed. However, these maintenance frameworks depend on the current status and situations of trains and cars. To overcome these issues, several predictive frameworks have been proposed. This study proposes a new and effective remaining useful life (RUL) estimation framework using big data from a train control and monitoring system (TCMS). TCMS data is classified into two types: operation data and alarm data. Alarm or RUL information is extracted from the alarm data. Subsequently, a deep learning model achieves the mapping relationship between operation data and the extracted RUL. However, a number of TCMS data have missing values due to malfunction of embedded sensors and/or low life of monitoring modules. This issue is addressed in the proposed generative adversarial network (GAN) framework. Both deep neural network (DNN) models for a generator and a predictor estimate missing values and predict train fault, simultaneously. To prove the effectiveness of the proposed GAN-based predictive maintenance framework, TCMS data-based case studies and comparisons with other methods were carried out.

Preventive Maintenance Study on H-25 Gas Turbine

This study aims to determine the effect of the time-based maintenance method preventive maintenance, namely major inspection on the efficiency of H-25 gas turbine. The efficiency calculation method based on operating data from the gas turbine. The effect of major inspection can be seen from the compressor efficiency, turbine efficiency and fuel consumption. The results of calculations before the major inspection are 80% of compressor efficiency, 83% of turbine efficiency, and 0.751 kg/kWh of fuel consumption, while after the major inspection, compressor efficiency is 80%, turbine efficiency is 85% and fuel consumption is 0.740 kg/kWh.

Self-Assessment of Health Conditions of Electrical Assets and Grid Components: A Contribution to Smart Grids

Broadening the concept of smart grid to include bi-directional interactions between grid and asset electrical components as regards their health conditions would help optimizing maintenance and operation actions from asset/grid management side. However, as long as data processing from diagnostic tools requires long and costly expert time, there is no real chance that the knowledge and technology developed in the field of condition monitoring can become broadly available for grid smart management. This article presents algorithms able to automate the acquisition of health information from electrical asset components. Referring to partial discharges, which are associated with the most harmful insulation aging factor, an innovative technique able to reject noise and thus make automatic partial discharge recognition possible, is proposed and its validity assessed. The information from partial discharge measurement, and other diagnostic quantity monitored is translated into a simple and straightforward indication of component health. This assessment can be automatic, dynamic and continuously updating during operation, thus making feasible an effective time-based condition maintenance approach. The outcome of the proposed approach is to contribute keeping asset reliability at a specified level, minimizing disastrous outages and increasing the return of investment. This benefits also optimal electrical component operation and power flow.

Time‐based replacement policies for a fault tolerant system subject to degradation and two types of shocks

AbstractA single component nonrepairable system suffering from both an internal stochastic degradation process and external random shocks is investigated in this paper. More specifically, the Wiener process with a positive drift coefficient is introduced to describe the gradual deterioration and the arrival number of external shocks is counted with a nonhomogeneous Poisson process (NHPP). Meanwhile, fault tolerant design is incorporated into the stochastically deterioration system so as to protect it from shock failures to some extent and is consummately addressed via a generalized m − δ shock model. From the actual engineering point of view, external shocks are typically classified into two distinct categories in this current research, that is, a minor shock (Type I shock) increasing the damage load on current degradation level and a traumatic shock (Type II shock) resulting in system catastrophic failure immediately. The closed‐form expression of system survival function is derived analytically and is viewed as the generalization of existing reliability function for systems subject to dependent and competing failure processes. Based on which, two time‐based maintenance (TBM) policies including an age replacement model and a block replacement model are scheduled, where the expected long‐run cost rate (ELRCR) in each model is, respectively, optimized to seek the optimal replacement interval. In the illustrative example part, a subsea blowout preventer (BOP) control system is arranged to validate the theoretical results numerically. To compare which policy is more profitable under different conditions, the relative gain on optimal maintenance cost rate of the two TBM policies is presented.

An integrated assessment of safety and efficiency of aircraft maintenance strategies using agent-based modelling and stochastic Petri nets

Aircraft maintenance is key for safe and efficient aircraft operations. While most studies propose cost-efficient maintenance strategies, the safety and efficiency of these strategies need to be quantified. This paper proposes a formal framework to assess the safety and efficiency of maintenance strategies by means of agent-based modelling, stochastically and dynamically coloured Petri nets, and Monte Carlo simulation. We model an end-to-end aircraft maintenance process, considering several maintenance stakeholders. We apply our framework for aircraft landing gear brakes, and use a Gamma process to model the degradation trends of the brakes. The numerical results show that applying data-driven strategies reduces the number of inspections by 36%, while maintaining the same level of safety as in the case of traditional time-based maintenance strategies. Furthermore, in order to discuss the possibility to substitute all inspections by sensor monitoring, an advanced data-driven strategy using prognostics is considered. Overall, our proposed framework is generic and can readily be applied to assess the safety and efficiency of the maintenance of other aircraft components and maintenance strategies.

Predictive model for the degradation state of a hydraulic system with dimensionality reduction

In recent years, the optimization in the use of resources has a key role in achieving a bigger marginality, reducing the operative costs. Due to the advances in the data science field, even the maintenance context is living important changes. The predictive maintenance and the condition-based maintenance can overcome the classic traditional maintenance methods, like the time-based maintenance or the corrective maintenance, with respect to the first intervention, reducing the costs for unscheduled maintenance, manpower, or loss of production and extending the useful life of the components. Based on these presuppositions, the paper proposes the development of a predictive model for the degradation state of the components of a complex hydraulic system, with some tests and some suggestions about the dimensionality reduction. The system has four known types of breakdown, with different degrees of severity; moreover, a fifth parameter represents whether the cycle has reached stable conditions or not.

Algorytm wsparcia strategii tbm w wielomaszynowych systemach wytwórczych

The execution of production processes in real manufacturing systems is associated with the occurrence of numerous disruptions, which predominantly revolve around technological machine failure. Therefore, various maintenance strategies are being developed, many of which tend to emphasise effective preventive measures, such as the Time-Based Maintenance (TBM) discussed in this paper. Specifically, this publication presents the time-based machine failure prediction algorithm for the multi-machine manufacturing environment. The Introduction section outlines the body of knowledge related to typical strategies applied in maintenance. The next part describes an approach to failure prediction that treats processing times as makespan and is followed by highlighting the key role of historical data in machine failure management, in the subsequent section. Finally, the proposed time-based machine failure prediction algorithm is presented and tested by means of a two-step verification, which confirms its effectiveness and further practical implementation

An integrated fuzzy-AHP and TOPSIS approach for maintenance policy selection

PurposeThe purpose of this paper is to select the best maintenance policy for different types of equipment of a manufacturer integrating the fuzzy analytic hierarchy process (FAHP) and the technique for order of preference by similarity to ideal solution (TOPSIS) models.Design/methodology/approachThe decision hierarchy of this research includes three levels. The first level aims to choose the best maintenance policy for different types of equipment of an acid manufacturer. These equipment pieces include molten sulfur ponds, boiler, absorption tower, cooling towers, converter, heat exchanger and sulfur fuel furnace. The second level includes decision criteria of added-value, risk level and the cost. Lastly, the third level comprises time-based maintenance (TBM), corrective maintenance (CM), shutdown maintenance and condition-based maintenance (CBM) as four maintenance policies.FindingsThe best maintenance policy for different types of equipment of a manufacturer is the main finding of this research. Based on the obtained results, CBM policy is suggested for absorption tower, boiler, cooling tower and molten sulfur ponds, TBM policy is suggested for converters and heat exchanger and CM policy is suggested for a sulfur fuel furnace.Originality/valueThis research develops a novel model by integrating FAHP and an interval TOPSIS with concurrent consideration of added-value, risk level and cost to select the best maintenance policy. According to the highlights of the previous studies conducted on maintenance policy selection and related tools and techniques, an operative integrated approach to combine risk, added-value and cost with integrated fuzzy models is not developed yet. The majority of the previous studies have considered classic fuzzy approaches such as FAHP, FANP, Fuzzy TOPSIS, etc., which are not completely capable to reflect the decision makers’ viewpoints.

Preventive Maintenance Subject to Equipment Unavailability

Preventive maintenance has received considerable attention in industries and the literature. Conventional preventive maintenance models often assume that equipment is always available for maintenance activities. However, in many mission-critical industries, equipment may not be available for scheduled maintenance due to busy operational schedules. Forced shutdown of the equipment may incur extra costs that cannot be offset by the benefits from preventively maintaining the equipment. In this paper, we propose innovative preventive maintenance policies to address the challenges caused by equipment unavailability. Maintenance models with possible rescheduling are developed for both time-based and condition-based maintenance policies, and the objective is to minimize the long-run cost rate of all maintenance activities. The proposed policies, with consideration of equipment unavailability for prescheduled PM, are compared with the policies that ignore this unavailability. Numerical examples are provided to illustrate the proposed policies.

Probabilistic investigations into the value of information: A comparison of condition-based and time-based maintenance strategies

Optimal maintenance of marine structures is challenging due to numerous fatigue-prone components, serious failure consequences, high maintenance costs, harsh sea environments, difficult access, and uncertainties in fatigue loading, resistance, and inspection and maintenance activities. Time-based maintenance (TBM) is convenient to implement. However, condition-based maintenance (CBM) is proved to be more cost-effective. This paper assesses the value of information (VoI) by inspections in CBM, compared to TBM, and investigates the conditions for CBM to outperform TBM in terms of fatigue reliability. A probabilistic maintenance optimization method and a life cycle cost analysis framework are established to derive optimal CBM and TBM strategies with the objective of maximizing lifetime reliability and evaluating their life cycle costs. The advantages of CBM, in comparison to TBM, and the VoI depends strongly on the inspection time. The CBM can achieve higher reliability with fewer maintenance costs than the TBM. An illustrative example is provided using the established probabilistic method and framework to support optimal maintenance planning. This example serves as a basis to explain the benefits of CBM to lifetime fatigue reliability and cost reduction, the conditions when CBM is more beneficial than TBM, the conditions for beneficial, ineffective and unbeneficial repair, and the VoI by inspections.

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.

Optimization of on-condition thresholds for a system of degrading components with competing dependent failure processes

An optimization model has been formulated and solved to determine on-condition failure thresholds and inspection intervals for multi-component systems with each component experiencing multiple failure processes due to simultaneous exposure to degradation and shock loads. In this new model, we consider on-condition maintenance optimization for systems of degrading components, which offers cost benefits over time-based preventive maintenance or replace-on-failure policies. For systems of degrading components, this can be a particularly difficult problem because of the dependent degradation and dependent failure times. In previous research, preventive maintenance and periodic inspection models have been considered; however, for systems whose costs due to failure are high, it is prudent to avoid the event of failure, i.e., the components or system should be repaired or replaced the before the failure happens. The determination of optimal on-condition thresholds for all components is effective to avoid failure and to minimize cost. Low on-condition thresholds can be inefficient because they waste component's life, and high on-condition thresholds are risky because the components are prone to costly failure. In this paper, we formulated and solved a new optimization model to determine optimal on-condition thresholds and inspection intervals. In our model, when the system is inspected, all components are inspected at that time. An inspection interval may be optimal for one component, but might be undesirable for another component, so the optimization requires a compromise. The on-condition maintenance optimization model is demonstrated on several examples.

Managing engineering systems with large state and action spaces through deep reinforcement learning

Decision-making for engineering systems management can be efficiently formulated using Markov Decision Processes (MDPs) or Partially Observable MDPs (POMDPs). Typical MDP/POMDP solution procedures utilize offline knowledge about the environment and provide detailed policies for relatively small systems with tractable state and action spaces. However, in large multi-component systems the dimensions of these spaces easily explode, as system states and actions scale exponentially with the number of components, whereas environment dynamics are difficult to be described explicitly for the entire system and may, often, only be accessible through computationally expensive numerical simulators. In this work, to address these issues, an integrated Deep Reinforcement Learning (DRL) framework is introduced. The Deep Centralized Multi-agent Actor Critic (DCMAC) is developed, an off-policy actor-critic DRL algorithm that directly probes the state/belief space of the underlying MDP/POMDP, providing efficient life-cycle policies for large multi-component systems operating in high-dimensional spaces. Apart from deep network approximators parametrizing complex functions with vast state spaces, DCMAC also adopts a factorized representation of the system actions, thus being able to designate individualized component- and subsystem-level decisions, while maintaining a centralized value function for the entire system. DCMAC compares well against Deep Q-Network and exact solutions, where applicable, and outperforms optimized baseline policies that incorporate time-based, condition-based, and periodic inspection and maintenance considerations.

Nuclear Power Plant Maintenance Optimisation: Models, Methods & Strategies

Maintenance activities are very important for the complex and high-risk installations, especially for Nuclear Power Plant. Good maintenance will be able to minimise loss of production, reducing the cost of the electricity generation, and/or reducing the risk. However, there are many issues to make a good maintenance program, such as regarding limitation of reliability data, the complexity of the system, (in)dependency failure mechanism, unpredictable spare parts supply chain, accessibility for maintenance and repair, environmental limitation, human resources, management, regulation, etc. Many studies have been done by researchers and engineers from various sectors to optimising maintenance activities. We have studied several kinds of available literatures, especially that can be used for the nuclear industry. By using proposed maintenance framework, we would like to describe Nuclear Power Plant maintenance optimisation studies that have been done systematically. We also did a critical review and gap identification between scholar studies and real applications and then classified them to provide more easy understanding information that can be used as an information for the future development. Based on our study, there is a wide gap between academic study and implementation. Although many models, methods, and strategies have been proposed, most of the NPPs in the world are using traditional approach by following time-based and breakdown maintenance strategies. There are such kinds of factors, such as because of the regulatory framework barrier, weak relationships between stakeholders and regarding data availability. Future studies to explore those problems are needed.

Internet of Things enabling condition-based maintenance in elevators service

PurposeThe purpose of this paper is to demonstrate how Internet of Things (IoT) technology can enable highly distributed elevator equipment servicing by using remote-monitoring technology to facilitate a shift from traditional corrective maintenance (CM) and time-based maintenance (TBM) to more predictive, condition-based maintenance (CBM) in order to achieve various benefits.Design/methodology/approachLiterature review indicates that CBM has advantages over conventional CM and TBM from a theoretical perspective, but it depends on continuous monitoring enhancement via advanced IoT technology. An in-depth case study was carried out to provide practical evidence that IoT enables elevator firms to achieve CBM.FindingsFrom a theoretical perspective, the CBM of elevators makes business sense. The challenges lie in data collection, data analysis and decision making in real-world business contexts. The main findings of this study suggest that CBM can be commercialized via IoT in the case of elevators and would improve the safety and reliability of equipment. It would, thus, make sense from technological, process and economic perspectives.Practical implicationsOur longitudinal real-world case study demonstrates a practical way of making the CBM of elevators widespread. Integrating IoT and other advanced technology would improve the safety and reliability of elevator equipment, prolong its useful life, minimize inconvenience and business interruptions due to equipment downtime and reduce or eliminate major repairs, thus greatly reducing maintenance costs.Originality/valueThe main contribution of this paper lies in the empirical demonstration of the benefits and challenges of CBM via IoT relative to conventional CM and TBM in the case of elevators. The authors believe that this study is timely and will be valuable to firms working on similar research or commercialization strategies.

A Vibration Signal-Based Method for Fault Identification and Classification in Hydraulic Axial Piston Pumps

In recent years, the interest of industry towards condition-based maintenance, substituting traditional time-based maintenance, is growing. Indeed, condition-based maintenance can increase the system uptime with a consequent economic advantage. In this paper, a solution to detect the health state of a variable displacement axial-piston pump based on vibration signals is proposed. The pump was tested on the test bench in different operating points, both in healthy and faulty conditions, the latter obtained by assembling damaged components in the pump. The vibration signals were acquired and exploited to extract features for fault identification. After the extraction, the obtained features were reduced to decrease the computational effort and used to train different types of classifiers. The classification algorithm that presents the greater accuracy with reduced features was identified. The analysis has also showed that using the time sampling raw signal, a satisfying accuracy could be obtained, which will permit onboard implementation. Results have shown the capability of the algorithm to identify which fault occurred in the system (fault identification) for each working condition. In future works, the classification algorithm will be implemented onboard to validate its effectiveness for the online identification of the typical incipient faults in axial-piston pumps.

A Review in Fault Diagnosis and Health Assessment for Railway Traction Drives

During the last decade, due to the increasing importance of reliability and availability, railway industry is making greater use of fault diagnosis approaches for early fault detection, as well as Condition-based maintenance frameworks. Due to the influence of traction drive in the railway system availability, several research works have been focused on Fault Diagnosis for Railway traction drives. Fault diagnosis approaches have been applied to electric machines, sensors and power electronics. Furthermore, Condition-based maintenance framework seems to reduce corrective and Time-based maintenance works in Railway Systems. However, there is not any publication that summarizes all the research works carried out in Fault diagnosis and Condition-based Maintenance frameworks for Railway Traction Drives. Thus, this review presents the development of Health Assessment and Fault Diagnosis in Railway Traction Drives during the last decade.

Improvement of plant reliability based on combining of prediction and inspection of crack growth due to intergranular stress corrosion cracking

Abstract Improvement of plant reliability based on reliability-centred maintenance (RCM) is going to be implemented in nuclear power plants. RCM is supported by three types of maintenances: risk-based maintenance (RBM); time-based maintenance; and condition-based maintenance. RBM is supported by suitable combinations of prediction, inspection and maintenance (repair of elemental defects in their propagation stage). The combination of prediction and inspection is one of the key issues to promote RBM. Early prediction of IGSCC occurrence and its propagation should be confirmed throughout entire plant systems which should be accomplished by inspections at the target locations followed by timely applications of suitable countermeasures such as water chemistry improvements. At the same time, transparency and traceability as well as accuracy are strongly required for the prediction. A set of empirical formulas for evaluation of electrochemical corrosion potential (ECP) and crack growth rate due to IGSCC was applied for evaluation of IGSCC risk as well as IGSCC occurrence and propagation. The details of IGSCC formulas have been reported by various researchers along with the expected accuracy of prediction to prepare for ensuring their transparency and traceability. Based on prediction results, primary points for inspections will be determined. Unfortunately, it is still difficult to evaluate some key parameters in the plants, e.g., residual stress. From the inspections, accumulated data will be applied to confirm the accuracy of the IGSCC formulas and their computer codes, to tune some uncertainties of the key data for prediction, and then, to increase their accuracy. The synergetic effects of prediction and inspection on application of effective and suitable countermeasures are expected. In this paper, the procedures for the combination of prediction and inspection have been introduced.

Selective maintenance optimisation considering random common cause failures and imperfect maintenance

This article addresses a selective maintenance optimisation problem for systems subject to random common cause failures. A system is likely to suffer from several random common cause failures during a given mission. Random common cause events, which occur with a specific probability distribution, may result in the simultaneous failures of multiple elements. Because time is one of the most crucial maintenance resources, a time-based imperfect maintenance model is proposed to quantify the maintenance efficiency of each candidate maintenance action. To meet the demands of the next mission, a selective maintenance model is proposed to optimally identify a subset of maintenance activities to be performed on certain elements of a system. A genetic algorithm and Monte Carlo simulation method is presented to solve the proposed selective maintenance optimisation problem. Illustrative examples combined with detailed discussions are presented to demonstrate the effectiveness of the proposed model. The results show that the proposal of time-based imperfect maintenance model can yield better maintenance results, while ignoring random common cause failures in selective maintenance optimisation may produce biased maintenance decisions and system reliability.