Maintenance Of Industrial Plants Research Articles

A Novel Approach to Defining Maintenance Significant Items: A Hydro Generator Case Study

The operation and maintenance of industrial plants constitute a major concern among managers, scientists, and engineers. To allow the prioritization of maintenance actions for improved continuous equipment operation, this paper presents a novel method focused on identifying the most critical components of a plant’s systems. In a complex engineering approach, this method uses tools and techniques borrowed from several fields of knowledge, including an innovative technique devised by the authors, as well as a multi-criteria decision method in the criticality determination process. To illustrate the method, a case study is presented considering a 150 MW Kaplan hydro generator from a hydroelectric power plant located in the north of Brazil. An uncertainty analysis is presented, considering variations in the scores of each criterion, to verify the robustness of the proposed method. The results show that the method responds in a solid and structured way, allowing decision making from qualitative and quantitative data and eliciting the opinion of experts on the factors that can affect the degradation of the performance of a system. In addition, the method’s robustness is confirmed since the uncertainty propagation related to the criteria scores is small for the items classified as most significant from its application.

Motion planning with dynamics awareness for long reach manipulation in aerial robotic systems with two arms

Human activities in maintenance of industrial plants pose elevated risks as well as significant costs due to the required shutdowns of the facility. An aerial robotic system with two arms for long reach manipulation in cluttered environments is presented to alleviate these constraints. The system consists of a multirotor with a long bar extension that incorporates a lightweight dual arm in the tip. This configuration allows aerial manipulation tasks even in hard-to-reach places. The objective of this work is the development of planning strategies to move the aerial robotic system with two arms for long reach manipulation in a safe and efficient way for both navigation and manipulation tasks. The motion planning problem is addressed considering jointly the aerial platform and the dual arm in order to achieve wider operating conditions. Since there exists a strong dynamical coupling between the multirotor and the dual arm, safety in obstacle avoidance will be assured by introducing dynamics awareness in the operation of the planner. On the other hand, the limited maneuverability of the system emphasizes the importance of energy and time efficiency in the generated trajectories. Accordingly, an adapted version of the optimal Rapidly-exploring Random Tree algorithm has been employed to guarantee their optimality. The resulting motion planning strategy has been evaluated through simulation in two realistic industrial scenarios, a riveting application and a chimney repairing task. To this end, the dynamics of the aerial robotic system with two arms for long reach manipulation has been properly modeled, and a distributed control scheme has been derived to complete the test bed. The satisfactory results of the simulations are presented as a first validation of the proposed approach.

Estratégia de manutenção baseada em funções de confiabilidade para uma bomba centrífuga petrolífera

O objetivo deste artigo foi definir a estratégia de manutenção mais adequada para uma bomba centrífuga (preventiva, preditiva, corretiva ou emergencial), com base em cálculos de confiabilidade. O método de pesquisa foi a modelagem quantitativa, aplicada em uma planta petrolífera. O estudo pode contribuir para o aprimoramento de um modelo estratégico para a gestão da manutenção industrial da planta. Foram levantados, no sistema de informações da empresa, registros de onze anos dos tempos entre falhas e dos tempos para reparo do equipamento. Estes tempos foram modelados por distribuições de probabilidade. A partir dos resultados obtidos, foram calculadas as funções Confiabilidade R(t) e Mantenabilidade M(t). Pela combinação de seus valores esperados (MTBF e MTTR), foi calculada a disponibilidade Av da bomba. Os valores para MTBF, MTTR e Av foram respectivamente 3.936 horas, 133 horas e 96,73%. O fator de forma mais provável da distribuição de Weibull que modelou o tempo até a falha foi de 0,69. Com isso, foi possível afirmar que a bomba está em fase de mortalidade infantil. Pelo referencial teórico da RCM, a estratégia de manutenção indicada é a corretiva. Esta estratégia visa eliminar os defeitos de projeto do equipamento, reforçar os itens que quebraram e remover as causas de origem das falhas.

Reinforcement Learning for Predictive Maintenance of Industrial Plants

Abstract The reinforcement learning is a well-known approach for solving optimization problems having limited information about plant dynamics. Its key element, named “critic” is aimed at prediction of future “punish/reward” signals received as a result of undertaken control actions. The main idea in the present work is to use such a “critic” element for prediction of approaching alarm situations based on limited measurement information from the industrial plant. In order to train the critic network in real time it is proposed to use a special kind of a fast trainable recurrent neural network, called Echo State Network (ESN). The approach proposed is demonstrated on an example for predictive maintenance of a mill fan in Maritsa East 2 Thermal Power Plant

Advanced model for maintenance management in a continuous improvement cycle: integration into the business strategy

This paper presents an advanced model for the integrated management for industrial plant maintenance and equivalent. The proposed model achieves to align the local maintenance objectives with the overall business objectives. Additionally, the model provides a real operational context and takes consideration of certain restrictions that may affect the efficiency and/or the effectiveness of the industrial maintenance management. First, the importance of a proper maintenance management and its consequences are discussed. Then, the model will describe in seven stages how to manage and optimize in a continuous way all the processes that deal with planning, programming and maintenance execution. This starts from a management process in the design stage or, from an already established management process. Moreover, the model includes fundamental aspects that fully integrate the directives of the business with maintenance activities. This article ends with conclusions and all references used during the research process prior to the drafting of this document.

A freeze in time

This article discusses the use of freeze plugs in the maintenance of industrial plants. In 2006, ASME published a standard PCC-2—Repair of Pressure Equipment and Piping—to guide plant personnel in the swift and safe execution of several lesser-known but very valuable repair techniques, regardless of their experience. One such repair technique that is well documented in PCC-2 is the use of freeze plugs, which prevent flow in pipes to allow for downstream maintenance activity. A freeze plug, unlike the hot tap, does not compromise the integrity of the pipe pressure boundary by welding or drilling. The freeze plug is created by installing a bolt-on jacket around the pipe through which liquid nitrogen (at –321°F) is circulated until the water in the line freezes. Employing a freeze plug can prove to be more efficient both in terms of cost and schedule than the other repair alternatives. The concept is simple but execution must be well planned.

Application of performance shaping factor (PSF) for work improvement in industrial plant maintenance tasks

Human behaviors are formed and evaluated by their performance shaping factor (PSF). In this study, I examined industrial plant maintenance tasks and considered the countermeasure for work improvement through PSF. The aim of this study is to propose an original PSF for maintenance tasks and to characterize the PSF by structural analysis. PSF had been utilized to evaluate human reliability. But in this study, the above characterization was investigated not only from the standpoint of human reliability but also from the viewpoint of work efficiency and workload. Lastly, some indications for work improvement of plant maintenance tasks were suggested based on the character of the PSF. Relevance to industry This study has relevance to industry with respect to the aim of work improvement in industrial plant maintenance tasks. To achieve this aim, maintenance tasks were examined in terms of human performance shaping factor. Through a series of investigations, several indications of countermeasures for work improvement were proposed.

Delay Time Models of Industrial Inspection Maintenance Problems

The technique of delay time analysis is here extended to problems of industrial plant maintenance. A basic model of inspection maintenance is presented, along with models of some of the variations which have been observed in practice. Numerical examples indicate both the nature and sensitivity of the output from the models.