A Knowledge-Intensive Decision Support System for Industrial Machines Maintenance

Corrective maintenance strategies are important for safeguarding optimum photovoltaic (PV) performance while also minimizing downtimes due to failures. In this work, a complete operation and maintenance (O&M) decision support system (DSS) was developed for corrective maintenance. The DSS operates entirely on field measurements and incorporates technical asset and financial management features. It was validated experimentally on a large-scale PV system installed in Greece and the results demonstrated the financial benefits of performing corrective actions in case of failures and reversible loss mechanisms. Reduced response and resolution times of corrective actions could improve the PV power production of the test PV plant by up to 2.41%. Even for 1% energy yield improvement by performing corrective actions, a DSS is recommended for large-scale PV plants (with a peak capacity of at least 250 kWp).

The high costs in maintaining today’s complex and sophisticated equipment make it necessary to enhance modern maintenance management systems. Conventional condition-based maintenance (CBM) reduces the uncertainty of maintenance according to the needs indicated by the equipment condition. The intelligent predictive decision support system (IPDSS) for condition-based maintenance (CBM) supplements the conventional CBM approach by adding the capability of intelligent condition-based fault diagnosis and the power of predicting the trend of equipment deterioration. An IPDSS model, based on the recurrent neural network (RNN) approach, was developed and tested and run for the critical equipment of a power plant. The results showed that the IPDSS model provided reliable fault diagnosis and strong predictive power for the trend of equipment deterioration. These valuable results could be used as input to an integrated maintenance management system to pre-plan and pre-schedule maintenance work, to reduce inventory costs for spare parts, to cut down unplanned forced outage and to minimise the risk of catastrophic failure.

Purpose This study aims to develop and validate a decision support system for diesel generator maintenance at KM. Bukit Siguntang through identifying critical parameters that affect maintenance needs, analyzing failure patterns and reliability levels of key components, and implementing a validated model to optimize maintenance strategies based on actual engine conditions. Methodology This study uses a mixed-method approach with a combination of quantitative and qualitative methods. The research design is exploratory sequential mixed-method, which begins with a qualitative stage to identify parameters and decision-making criteria, followed by a quantitative stage for model development and system validation. The collected data were analyzed using the Descriptive Statistical Analysis method, Reliability Centered Maintenance (RCM) Analysis. Findings The results showed a decrease in the number of unplanned failures by 57.1% and a reduction in downtime by 53.8% indicating a substantial increase in system reliability. This contributed to an increase in diesel generator availability from 94.2% to 97.3%, which is very important for ship operations. Originality This study successfully developed and validated a decision support system for diesel generator maintenance at KM. Bukit Siguntang by identifying 11 critical parameters that affect maintenance needs and analyzing failure patterns and reliability of critical components.

Besides pursuing the economic goals of low costs and high profits, companies are becoming more and more aware of the environmental and social impact of their actions. Companies striving for the integrated optimization of environmental and economic perspectives within their production processes, need to be supported by tools helping to understand the effects of the decision making process. In this context, this paper describes a Decision Support System (DSS) enabling the early identification of problems occurring on manufacturing lines thus suggesting related recovery actions, together with the potential repercussions of their adoption, at economic and environmental level. The decision making process beneath the DSS starts from the aggregation of production lines sensors data in Key Performance Indicators (KPI). The data are then processed by means of an Artificial Neural Networks (ANN) based knowledge system which enables to suggest preventive maintenance interventions. The proposed maintenance activities, elaborated throughout a scheduling engine, are integrated within the weekly production schedule, according to the selected optimization policy. Preliminary tests have been carried out in manufacturing plants of IKEA industries and Brembo.

The Federal Highway Administration's Office of Transportation Operations Road Weather Management Program began a project in FY 1999 to develop a prototype winter road maintenance decision support system (MDSS). The MDSS capabilities are based on feedback received by the FHWA in 2001 from maintenance managers at a number of state departments of transportation (DOTs) as part of an initiative to capture surface transportation weather decision support requirements. The MDSS project goal is to seed the implementation of advanced decision support services provided by the private sector for state DOTs. This has been achieved by developing core software capabilities that serve as a basis for these tailored products. After the 2001 user needs assessment was completed, the MDSS program was extended with the objective of developing and demonstrating a functional prototype MDSS. Field demonstrations of the prototype MDSS were conducted in Iowa between February and April 2003, and during the winter of 2004. The performance of the prototype MDSS was much improved during the second winter. The weather and road condition predictions were more accurate, and the treatment recommendations generated by the system were reasonable given the predicted conditions. Iowa garage supervisors actively considered the treatment guidance, and on occasion they successfully used the recommended treatments without modification. This paper describes the status of the MDSS project, results and lessons learned from the field demonstrations, and future development efforts.

In North America, many utility‐scale turbines are approaching, or are beyond the half‐way point of their originally anticipated lifespan. Accurate estimation of the times to failure of major turbine components can provide wind farm owners insight into how to optimise the life and value of their farm assets. In this study, data records from a wind farm have been used to estimate the reliability of wind turbine (WT) generators. For this study, non‐parametric life data analysis, Weibull Standard Folio life data analysis, and ALTA Standard Folio life data analysis have been used to predict the reliability of the generators. The naive prediction interval procedure also has been used here to provide an approximate range for the remaining life of each generator. This study provides some insight into how reliable a subset of WT generators is and the lifetime distribution of individual generators. These outcomes may be leveraged further by the research community for companion applications like prognostic maintenance and investment decision support systems. This study also begins to investigate how electrical loads may influence turbine generator reliability. The work also illustrates a valuable example of how to estimate component remaining useful life based on truncated/limited data records.

Web-based GIS spatial decision support system for infrastructural maintenance of roads and irrigation facilities in Central and East Sumba

The prediction of the permanent deformation and respective accuracy in the subgrade is one of the main concerns of the Railway Infrastructure managers to reduce the maintenance costs and operations. This paper purposes a new methodology regarding the prediction of the permanent deformation based on a parametric study performed using a hybrid methodology that includes the short and long-term performance. In this parametric study, the dynamic mechanism was considered as well as several important factors with impact on the stress levels and permanent deformations: wavelength of the unevenness profile, type of railway structure, train speed, mechanical properties of the subgrade and the geometric position of the analysis in the track development direction. This extensive parametric study allowed building a robust database used to predict the permanent deformation induced by the passage of the train. This database feeds a neural network model whose performance was evaluated based on different metrics: Mean Absolute error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), standard deviation, and regression coefficient (R). Moreover, to show the ability of the model, it will be tested and validated based on published experimental results from a physical modelling of ballasted and ballastless tracks. Its results show that the developed model is rapid and efficient to predict accurately the permanent deformation induced by the passage of the train. It can have the potential to be further implemented in a computational decision support system for railway track maintenance and renewal management, instead of conventional corrective maintenance and renewal.KeywordsNeural networkPermanent deformationPredictionInfrastructureLife-cycle management

Validation of Diagnostic Models Using Graphical Belief Networks

Road traffic forecasting — A hybrid approach combining Artificial Neural Network with Singular Spectrum Analysis

On the design of group decision support systems

Distributed decision support and organizational connectivity: A case study

To solve the problem of maintenance deficiency and surplus emerges in the ship schedule maintenance mode, we developed intelligent condition-based maintenance decision support system. We adopted a multi-parameters synthetic condition assessment model based on fuzzy theory and set up a fault diagnosis model in terms of reasoning machine based on expert knowledge. Then the results from the above models may help the managers to make a maintenance decision. All of these operations were completed with the assistance of the data base. The software was programmed with C++ Builder as the basic tool. As a general platform, the system has integrated functions of condition assessment, fault diagnosis and maintenance decision. On the basis of the support system, we can inspect and maintain the ship or part of that effectively and economically.

This paper presents the design and development of a Web-based decision support system for site quality evaluation of plantation (SSQEP).SSQEP is an operational automatic evaluation tool that helps farmers in estimating site quality and predicting the growth performance of trees.The SSQEP consists of three subsystems: (i) site quality evaluation for forest land subsystem; (ii) site quality evaluation for non-forest land subsystem; and (iii) stand growth and yield prediction subsystem.Expert system principle was adopted in the site quality evaluation for non-forest land.An automatic knowledge acquisition module provides a user-friendly interface to domain experts for entering and storing domain-specific knowledge.The knowledge base was used to store and manage the knowledge of domain experts, which is presented as rules and facts.Inference engine was designed and implemented to use forward reasoning mechanism to search the site quality evaluation knowledge.Furthermore, two site quality evaluation methods for forest land (i.e., site index and growth model methods) were designed in the SSQEP.After evaluating site quality, the stand growth and yield were predicted by a graph.

It is generally accepted that adaptive design methods and flexible constructs facilitate the design and implementation of decision support systems. Flexible constructs in the form of decision support system generators have been proposed for the timely construction of specific decision support systems. Effective communication, however, underlies the success of applying adaptive design methods and creating and modifying decision support system generators. Accordingly, we propose to investigate communication as a mode of action that allows the participants to structure and to exert control over the design environment. A descriptive model is presented that describes how different modes of communicative action are used to enhance the prospects of success when building decision support systems.