1,720,967 research outputs found
Maintenance optimization in industry 4.0
Full text linkThis work reviews maintenance optimization from different and complementary points of view. Specifically, we systematically analyze the knowledge, information and data that can be exploited for maintenance optimization within the Industry 4.0 paradigm. Then, the possible objectives of the optimization are critically discussed, together with the maintenance features to be optimized, such as maintenance periods and degradation thresholds. The main challenges and trends of maintenance optimization are, then, highlighted and the need is identified for methods that do not require a-priori selection of a predefined maintenance strategy, are able to deal with large amounts of heterogeneous data collected from different sources, can properly treat all the uncertainties affecting the behavior of the systems and the environment, and can jointly consider multiple optimization objectives, including the emerging ones related to sustainability and resilience
Optimization of the Operation and Maintenance of renewable energy systems by Deep Reinforcement Learning
Full text linkEquipment of renewable energy systems are being supported by Prognostics & Health Management (PHM) capabilities to estimate their current health state and predict their Remaining Useful Life (RUL). The PHM health state estimates and RUL predictions can be used for the optimization of the systems Operation and Maintenance (O&M). This is an ambitious and challenging task, which requires to consider many factors, including the availability of maintenance crews, the variability of energy demand and production, the influence of the operating conditions on equipment performance and degradation and the long time horizons of renewable energy systems usage. We develop a novel formulation of the O&M optimization as a sequential decision problem and we resort to Deep Reinforcement Learning (DRL) to solve it. The proposed solution approach combines proximal policy optimization, imitation learning, for pre-training the learning agent, and a model of the environment which describes the renewable energy system behavior. The solution approach is tested by its application to a wind farm O&M problem. The optimal solution found is shown to outperform those provided by other DRL algorithms. Also, the approach does not require to select a-priori a maintenance strategy, but, rather, it discovers the best performing policy by itself
An unsupervised method for the reconstruction of maintenance intervention times
No full textThis paper presents a method for identifying when maintenance interventions have been performed on industrial components. The knowledge of the maintenance intervention times is essential in many situations, such as accident analysis, maintenance planning and development of prognostics and health management models. The proposed method is based on the application of a spectral clustering algorithm to raw data signals collected during the component life. A novel measure of similarity, based on Pearson's correlation coefficient, is used to build the similarity graph. The method is shown able to correctly identify the maintenance intervention times of nuclear power plants steam generators and cutting machines used in the packaging industry
Deep reinforcement learning for optimizing operation and maintenance of energy systems equipped with phm capabilities
Full text linkThe Life Cycle Cost (LCC) of energy systems including Renewable Energy Sources (RES) strongly depends on the Operation and Maintenance (O&M) costs. Nowadays, many components of these energy systems are equipped with Prognostics & Health Management (PHM) capabilities, for estimating their current and future health states. This information is intended to be used for the optimization of O&M. It is an ambitious and challenging objective as the uncertain information brought by PHM must be combined with other factors influencing O&M, such as the limited availability of maintenance crews, the variability of energy demand and production, the long-time horizons of energy systems. In this work, we formalize the O&M optimization of RES-based energy systems equipped with PHM as a sequential decision problem over a long-time horizon and we solve it by Deep Reinforcement Learning (DRL). The proposed methodology is applied to a small wind farm. Strengths and weaknesses are analyzed by means of a comparison with state-of-the-art O&M policies
Gaussian Fields for Predicting Drift of Oil and Gas Pipes
No full textIn the oil and gas industry, empirical models are used to estimate the drift of pipes. These models encode pipe geometrical features, measured along the pipe length. If the estimated drift does not meet the operability requirements, then the pipe is rejected. This improves the quality of the purchased pipes, but strongly affects their production costs. We rely on the Gaussian fields theoretical framework to address two issues: the a priori estimation of the probability of pipes rejection and the a posteriori estimation of the drift conformance probability, given the actual measured parameters. These are fundamental pieces of information for purchasing decisions. A case study is considered to show the application of the theoretical framework. The proposed methodology is applied to real pipe measurement data, which have been opportunely rescaled to avoid the disclosure of relevant information
Optimal Prescriptive Maintenance of Nuclear Power Plants by Deep Reinforcement Learning
No full textThe Operation & Maintenance (O&M) of complex energy systems, such as Nuclear Power Plants (NPPs), is driven by productivity and safety goals, but it is also challenged by the need of flexibility of production to respond to uncertain demand in an economically sustainable manner. Most O&M strategies for NPPs do not directly address the flexible requirement. In this paper, we develop a Deep Reinforcement Learning (DRL)-based prescriptive maintenance approach to search for the best O&M strategy, considering the actual system health conditions (e.g., the Remaining Useful Life (RUL), and satisfying the need of flexible operation to accommodate load-following while keeping reliability and profitability high. The approach integrates Proximal Policy Optimization (PPO) and Imitation Learning (IL) for training the RL agent of prescriptive maintenance. The Advanced Lead-cooled Fast Reactor European Demonstrator (ALFRED) is considered to show the applicability of the approach proposed
Deep reinforcement learning based on proximal policy optimization for the maintenance of a wind farm with multiple crews
Full text linkThe life cycle of wind turbines depends on the operation and maintenance policies adopted. With the critical components of wind turbines being equipped with condition monitoring and Prognostics and Health Management (PHM) capabilities, it is feasible to significantly optimize operation and maintenance (O&M) by combining the (uncertain) information provided by PHM with the other factors influencing O&M activities, including the limited availability of maintenance crews, the variability of energy demand and corresponding production requests, and the long-time horizons of energy systems operation. In this work, we consider the operation and maintenance optimization of wind turbines in wind farms woth multiple crews. A new formulation of the problem as a sequential decision problem over a long-time horizon is proposed and solved by deep reinforcement learning based on proximal policy optimization. The proposed method is applied to a wind farm of 50 turbines, considering the availability of multiple maintenance crews. The optimal O&M policy found outperforms other state-of-the-art strategies, regardless of the number of available maintenance crews
Optimal operation and maintenance of energy storage systems in grid-connected microgrids by deep reinforcement learning
No full textThe operation of microgrids, i.e., energy systems composed of distributed energy generation, local loads and energy storage capacity, is challenged by the variability of intermittent energy sources and demands, the stochastic occurrence of unexpected outages of the conventional grid and the degradation of the Energy Storage System (ESS), which is strongly influenced by its operating conditions. To effectively address these challenges, a novel method for combined operation and maintenance management of ESS has been developed. Unlike the currently available solutions, which typically address the one-day-ahead scheduling problem, the present work considers, for the first time, the realistic case of a microgrid in which the ESS degrades and unexpected outages of the conventional grid can occur along the long-time horizons of the entire microgrid lifetimes. The proposed method, which is based on deep reinforcement learning, is tested on a simulated grid-connected microgrid of a residential building equipped with photovoltaic modules and an ESS. The method outperforms other state-of-the-art approaches based on heuristics and metaheuristics by increasing the profit by 15% and reducing the average number of ESS replacements during its lifetime. Therefore, it can be concluded that the proposed DRL-based framework allows achieving prescriptive maintenance since the suggested actions are optimal from the point of view of effectively maximizing the profit and minimizing the maintenance interventions over the entire lifetime of the microgrid
A novel degradation state indicator for steam generators of nuclear power plants
Full text linkWe develop a degradation indicator for nuclear power plants steam generators, based on the use of signal measurements collected by sensors during plant operational transients between two successive maintenance interventions. Given the unavailability of information about the real degradation state during operation, an unsupervised approach is adopted. It consists in the extraction of several features from raw signals and in the selection of those features which best describe the degradation state evolution within a multi-objective optimization framework. The two considered objectives are the monotonicity and trendability of the features
- …
