Predictive Maintenance Program Research Articles

Operating load based real-time rolling grey forecasting for machine health prognosis in dynamic maintenance schedule

Machine health prognosis plays an important role in the dynamic maintenance decision-making. For complex manufacturing systems, it is necessary to schedule a predictive maintenance program and avoid production losses by predicting machine degradations. This paper proposes a novel prognostic method, a real-time rolling grey forecasting method, to provide efficient and accurate machine health prediction, while effects of influencing factors such as operating load are considered and analyzed. In this grey forecasting model, generating coefficient $$W$$ W values corresponding to variable operating loads are dynamically generated to overcome the shortage of a static $$W$$ W value. It improves the forecast accuracy of the frequency of failures. A series data about increasing machine health states of failure frequency is used as the in-sample test data. Results of the out-of-sample predictive data show that the application of the proposed method leads to a noticeable increase in forecast accuracy. This indicates the improved rolling grey forecasting model offers a potential to predict the failure frequency trend for supporting the dynamic maintenance schedule.

Temperature profile of progressive damaged overhead electrical conductors

The Brazilian transmission system is characterized by installations that average 20years of operation. Competitiveness of the energy sector, lack of resources for new investments and the aging of the system lead to the necessity of not only to reform but also to optimize it in order to face the increasing demand of the Brazilian energy market. The overhead electrical conductor is naturally the most important element on the transport of electrical energy and requires careful predictive and preventive maintenance programs. Therefore, it is of fundamental importance to predict the operational life of overhead electrical conductors using mathematical models so that their energy transport capacity can be optimized. However, it is necessary to validate such models by means of test programs so that their predictions can be trusted. One of the most important factors on the structural decay of overhead electrical conductors is the variation of the temperature profile in the event of the rupture of one or more of its Aluminum wires by fatigue or fretting. Therefore, models that include this temperature variation must be validated through test programs that can experimentally establish a mathematical relationship which considers effects such as contact resistance, material thermo-mechanical properties modification, annealing of the material and the presence of defects. The objective of this work is to evaluate the effect of progressive Aluminum wire rupture on the temperature profile of an ACSR (Aluminum Conductor Steel Reinforced) overhead electrical conductor, not only on the section of the damage but also along the length of the conductor. A test procedure was developed and performed to establish this effect. Results were compared to a mathematical model and showed that the temperature profile dependency of the increasing rupture of Aluminum wires is not linear and includes effects other than the cross section loss.

A multi-criteria model for auditing a Predictive Maintenance Programme

Auditing tools can play a key role in the continuous improvement of maintenance policies, in particular to enhance predictive maintenance (PM). This paper proposes a multi-criteria model for auditing a Predictive Maintenance Programme (PMP) developed and implemented in the General Hospital of Ciudad Real (GHCR) in Spain. The model has a two-level structure, with top level auditing areas specified by second level auditing criteria on which the performance of the PMP should be appraised. This structure resulted from the analysis and discussion of an internal questionnaire to the management, technical and consulting staff of GHCR. This also guided the association of a performance scale with each criterion, describing several reference levels of accomplishment. Using the MACBETH (Measuring Attractiveness by a Categorical Based Evaluation Technique) approach, a hierarchical additive value model was constructed, with criteria weights and value scales derived from staff judgments of comparison of different reference levels and profiles of performance. This model enables managers to measure the performance of the PMP and its added value for the hospital, not only against each audit criterion individually, but also on each area and in overall terms. Integrated in a management “tableau de bord”, the model outputs permit the identification of PMP deficiencies requiring urgent intervention and corrective measures for its continuous improvement.

Missile captive carry monitoring and helicopter identification using a capacitive microelectromechanical systems accelerometer

Military missiles are exposed to many sources of mechanical vibration that can affect system reliability, safety, and mission effectiveness. The US Army Aviation and Missile Research Development and Engineering Center has been developing missile health monitoring systems to assess and improve reliability, reduce life cycle costs, and increase system readiness. One of the most significant exposures to vibration occurs when the missile is being carried by a helicopter or other aviation platform, which is a condition known as captive carry. Recording the duration of captive carry exposure during the missile’s service life can enable the implementation of predictive maintenance and resource management programs. Since the vibration imparted by each class of helicopter varies in frequency and amplitude, tracking the vibration exposure from each helicopter separately can help quantify the severity and harmonic content of the exposure. To help address these needs, the authors have developed a captive carry health monitor for the Hellfire II missile. The captive carry health monitor is an embedded usage monitoring device installed on the outer skin of the Hellfire II missile to record the cumulative hours the host missile has been in captive carry mode. To classify the vibration by class of helicopter, the captive carry health monitor analyzes the amplitude and frequency content of the vibration with the Goertzel algorithm to detect the presence of distinctive rotor harmonics. This article provides an overview of the captive carry health monitor, presents vibration data collected on missiles during captive carry, describes data analysis techniques used to monitor captive carry and identify the class of helicopter, and discusses the potential application of missile health and usage data for real-time reliability analysis. More broadly, this article illuminates the challenges of developing a structural health monitor to classify transportation modes in an unstructured environment.

Prioritization of maintenance tasks on industrial equipment for reliability

PurposeThis paper aims to prioritize preventive maintenance actions on process equipment by evaluating the risk associated with failure modes using predictive maintenance data instead of maintenance history alone.Design/methodology/approachIn process plants, maintenance task identification is based on the failure mode and effect analysis (FMEA). To eliminate or mitigate risk caused by failure modes, maintenance tasks need to be prioritized. Risk priority number (RPN) can be used to rank the risk. RPN is estimated invariably using maintenance history. However, maintenance history has deficiencies, like limited data, inconsistency etc. To overcome these deficiencies, the proposed approach uses the predictive maintenance data clubbed with expert domain knowledge. Unlike the traditional single step approach, RPN is estimated in two steps, i.e. Step 1 estimates the “Possibility of failure mode detection” and Step 2 estimates RPN using output of step 1. Fuzzy sets and approximate reasoning are used to handle the uncertainty/imprecision in data and subjectivity/vagueness of expert domain knowledge. Fuzzy inference system is developed using MATLAB® 6.5.FindingsThe proposed approach is applied to a large gearbox in an integrated steel plant. The gearbox is covered under a predictive maintenance program. RPN for each of the failure modes is estimated with the proposed approach and compared with the maintenance task schedule. The illustrative case study results show that the proposed approach helps in detection of failure modes more scientifically and prevents “Over maintenance” to ensure reliability.Originality/valueThis approach gives an opportunity to integrate the predictive maintenance data and subjective/qualitative domain expertise to evaluate the possibility of failure mode detection (POD) quantitatively, which is otherwise purely estimated using subjective judgments. The approach is generic and can be applied to a variety of process equipment to ensure reliability through prioritized maintenance scheduling.

Wireless sensors for predictive maintenance of rotating equipment in research reactors

In 2008–2009, the High Flux Isotope Reactor (HFIR) at the Oak Ridge National Laboratory (ORNL) tested the potential of predictive or condition-based maintenance techniques to reduce maintenance costs, minimize the risk of catastrophic failures, and maximize system availability by attaching wireless-based sensors to selected rotating equipment at HFIR. Rotating equipment is an ideal “test case” for the viability of integrated, online predictive maintenance strategies because motors, bearings, and shafts are ubiquitous in nuclear power plants and because the maintenance methods typically performed on rotating equipment today (such as portable or handheld vibration data collection equipment) are highly labor-intensive. The HFIR project achieved all five of its objectives: (1) to identify rotating machinery of the types used in research reactors and determine their operational characteristics, degradation mechanisms, and failure modes, (2) to establish a predictive maintenance program for rotating equipment in research reactors, (3) to identify wireless sensors that are suitable for predictive maintenance of rotating machinery and test them in a laboratory setting, (4) to establish the requirements and procedures to be followed when implementing wireless sensors for predictive maintenance in research reactors, and (5) to develop a conceptual design for a predictive maintenance system for research reactors based on wireless sensors. The project demonstrated that wireless sensors offer an effective method for monitoring key process conditions continuously and remotely, thereby enhancing the safety, reliability, and efficiency of the aging research reactor fleet.

Machine condition prognosis based on sequential Monte Carlo method

Machine condition prognosis is an important part of the decision-making in condition-based maintenance. By predicting the degradation of working conditions of machinery, it can organize a predictive maintenance program and prevent production loss. For complex systems, the trending data of the performance degradation is nonlinear over time known as a time series. This paper proposes a prognosis algorithm applied in a real dynamic system. Sequential Monte Carlo method, also known as a particle filter, can be used in nonlinear systems without any assumption of linearity. It is based on the sequential important sampling and resampling algorithm, which represents the posterior probability density function by a set of randomly drawn samples (called particles) and their associated weights. The prediction estimations are computed based on those samples and their weights. The real trending data of low methane compressors acquired from condition monitoring routines is employed for evaluating the proposed method. The results show that the proposed method offers a potential to predict the trending data in real systems of machine condition prognosis.

A framework to practical predictive maintenance modeling for multi-state systems

A simple practical framework for predictive maintenance (PdM)-based scheduling of multi-state systems (MSS) is developed. The maintenance schedules are derived from a system-perspective using the failure times of the overall system as estimated from its performance degradation trends. The system analyzed in this work is a flow transmission water pipe system. The various factors influencing PdM-based scheduling are identified and their impact on the system reliability and performance are quantitatively studied. The estimated times to replacement of the MSS may also be derived from the developed model. The results of the model simulation demonstrate the significant impact of maintenance quality and the criteria for the call for maintenance (user demand) on the system reliability and mean performance characteristics. A slight improvement in maintenance quality is found to postpone the system replacement time by manifold. The consistency in the quality of maintenance work with minimal variance is also identified as a very important factor that enhances the system's future operational and downtime event predictability. The studies also reveal that in order to reduce the frequency of maintenance actions, it is necessary to lower the minimum user demand from the system if possible, ensuring at the same time that the system still performs its intended function effectively. The model proposed can be utilized to implement a PdM program in the industry with a few modifications to suit the individual industrial systems’ needs.

Model for the Selection of Predictive Maintenance Techniques

A Predictive Maintenance Program can provide significant benefits to industrial plants in the areas of security, quality and availability. However, Predictive Maintenance Programs have lacked analysis in matters related to their set up, management and control. In this paper, a model is proposed in order to select the most suitable predictive technique to set up in an industrial plant. For this purpose, different alternatives are proposed depending on the technological level of the Predictive Maintenance Program. The condition monitoring techniques considered in the model are: vibration analysis and lubricant analysis; the integration of both techniques is also considered in the construction of alternatives. The proposed model can facilitate the decision making process for setting up Predictive Maintenance programs, and also help to avoid the failure of such programs. The model has been tested in a set of industrial plants with a Predictive Maintenance Program.

Model for the Selection of Predictive Maintenance Techniques

A Predictive Maintenance Program can provide significant benefits to industrial plants in the areas of security, quality and availability. However, Predictive Maintenance Programs have lacked analysis in matters related to their set up, management and control. In this paper, a model is proposed in order to select the most suitable predictive technique to set up in an industrial plant. For this purpose, different alternatives are proposed depending on the technological level of the Predictive Maintenance Program. The condition monitoring techniques considered in the model are: vibration analysis and lubricant analysis; the integration of both techniques is also considered in the construction of alternatives. The proposed model can facilitate the decision making process for setting up Predictive Maintenance programs, and also help to avoid the failure of such programs. The model has been tested in a set of industrial plants with a Predictive Maintenance Program.

Blades condition monitoring using shaft torsional vibration signals

PurposeThe purpose of this paper is to validate mathematically the feasibility of extracting the rotating blades vibration condition from the shaft torsional vibration measurement.Design/methodology/approachA mathematical model is developed and simulated for extracting rotating blades vibration signatures from the shaft torsional vibration signals. The model simulates n‐blades attached to a rigid disk at setting angles and the shaft drives the disk is flexible in torsion. The model is developed using the multi‐body dynamics approach in conjunction with the Lagrangian dynamics. A three‐blade rotor system example is simulated for blades free and forced vibration under stationary and rotating conditions. Frequency spectrums for the shaft torsional and blades bending vibration are represented and studied for analysis verification purposes.FindingsThe torsional vibration frequency spectrums showed blades free and forced vibration signatures. The blade setting angle is shown to reduce the sensitivity of torsional vibration signal to blades vibration signatures as it increases. The torsional vibration signals captured the variation in blades properties and produced broadband frequency components for mistuned system. The shaft torsional rigidity is shown to reduce the sensitivity of torsional vibration signal to blades vibration if increased to extremely high values (approaching rigid shaft). The rotor inertia is shown to have less effect on the torsional vibration signals sensitivity. The method of torsional vibration as a tool for rotating blades vibration measurement, based on the proposed mathematical model and its simulation, is feasible.Practical implicationsThere is a growing need for reliable predictive maintenance programs that in turn requires continuous development in methods for machinery health monitoring through vibration data collection and analysis. Turbo machinery and bladed assemblies like fans, marine propellers and wind turbine systems usually suffer from the problem of blades high vibration that is difficult to measure. The proposed new method for blades vibration measurement depends on the shaft torsional vibration signals and can be used also for verifying the signals from other types of bearings sensors for possible blades vibration condition monitoring.Originality/valueThis paper presents a unique mathematical model and simulation results for the rotating blades vibration monitoring. The developed model can be simulated for studying coupled blades vibration problems in the design stage as well as for condition monitoring in maintenance applications.

An evaluation system of the setting up of predictive maintenance programmes

Predictive Maintenance can provide an increase in safety, quality and availability in industrial plants. However, the setting up of a Predictive Maintenance Programme is a strategic decision that until now has lacked analysis of questions related to its setting up, management and control. In this paper, an evaluation system is proposed that carries out the decision making in relation to the feasibility of the setting up. The evaluation system uses a combination of tools belonging to operational research such as: Analytic Hierarchy Process, decision rules and Bayesian tools. This system is a help tool available to the managers of Predictive Maintenance Programmes which can both increase the number of Predictive Maintenance Programmes set up and avoid the failure of these programmes. The Evaluation System has been tested in a petrochemical plant and in a food industry.

General Interpolated Fast Fourier Transform: A New Tool for Diagnosing Large Rotating Machinery

Vibration monitoring and diagnosis of rotating machinery is an important part of a predictive maintenance program to reduce operating and maintenance costs. In order to improve the efficiency and accuracy of diagnosis, the general interpolated fast Fourier transform (GIFFT) is introduced in this paper. In comparison to present interpolated fast Fourier transform, this new approach can deal with any type of window functions and possesses high accuracy and robust performance, especially coping with a small number of sampling points. Then, for the purpose of rotating machinery diagnosis, the harmonic vibration ellipse and orbit is reconstructed based on the GIFFT to extract the features of faults and remove the interference from environmental noise and some irrelevant components. This novel scheme is proving to be very effective and reliable in diagnosing several types of malfunctions in gas turbines and compressors and characterizing of the transient behavior of rotating machinery in the run-up stage.

A model to determine the cleanliness measurement interval in an automotive paint shop

Making a choice between different alternative solutions is a common management problem. Also in maintenance operations, a variety of different decision areas can be identified. In these decisions, different criteria, both tangible and intangible are relevant and must be considered at the same time. In order to be able to make rational and justifiable tactical decisions for these so‐called multi‐criteria decision problems, one needs a multi‐criteria decision making model (MCDM). In this paper the tactical choice of a predictive maintenance program for an automotive paint shop is elaborated. An MCDM approach is applied to tackle the problem considering different criteria, which often are conflicting.

Proposal of a Method for Implementing Infrared Scanning Inspection Programs in Merchant Vessels

This paper summarizes a proposal for implementing a predictive maintenance program based on infrared scanning inspection in merchant vessels. Current use of infrared inspection in merchant vessels is discussed, with an analysis of the problems and the benefits. Finally, a method for developing an inspection plan is proposed. The method consists of a selection of parameters, with consideration of infrared thermography and which general and specific criteria must be followed. Infrared thermal imaging is currently used for many engineering activities, mainly in industrial plants, in which predictive maintenance is widely used. However, this technique is being applied only in some types of merchant vessels, such as fast ferries and, in general, high-speed crafts. The main objective of the maintenance program proposed in this paper is prevention of loss by reducing the risks of fire and explosion. Twenty percent of the world ship losses in the last 25 years were caused by fire or explosions, the second most common cause of loss after bad weather. The proposed method consists of inspection and diagnostic tasks done on a systematic basis. The measurements of surface temperatures can detect hot spots and, subsequently, potential ignition sources. All the electrical power, distribution, and receptor devices; insulations; and any hot surface in the engine room, such as boiler casings and exhaust pipes, are included in the maintenance program. The second objective is related to the savings achieved by preventive maintenance reduction and the benefits of healthy facilities. Thermal scanning can detect small temperature differences between close points on a surface. This capability allows the detection of potential failures, such as cracks and lack of insulation in pipes and casings, thermal isolations, and small leaks of pressurized fluids such as steam, compressed air, and nonvisible fluids. The authors are currently working on a research project sponsored by the Spanish Maritime Authority within the scope of the development of new technologies focused on increasing maritime safety. One of the tasks of that project is the method of carrying out the inspection programs presented in this paper.

The control of the setting up of a predictive maintenance programme using a system of indicators

Predictive maintenance is one of the maintenance policies which is revolutionising the industry, due to the increase in security, quality and availability which is on offer to an industrial plant. However, the implantation of a predictive maintenance programme (PMP) is a strategic decision, and to date the analysis and study of questions relative to its setting up, management and supervision have not been carried out sufficiently. This paper proposes a system composed of indicators to control the setting up of PMPs which should facilitate the early detection of anomalies which can appear during setting up, thus avoiding the failure of these programmes. The system developed can be considered a predictive control of the PMP.

Selection of diagnostic techniques and instrumentation in a predictive maintenance program. A case study

Predictive maintenance programs (PMPs) can provide significant advantages in relation to quality, safety, availability and cost reduction in industrial plants. Nevertheless, during implementation, different decision making processes are involved, such as the selection of the most suitable diagnostic techniques. A wrong decision can lead to the failure of the setting up of the predictive maintenance program and its elimination, with the consequent economic losses, as the setting up of these programs is a strategic decision. In this article, a model is proposed that carries out the decision making in relation to the selection of the diagnostic techniques and instrumentation in the predictive maintenance programs. The model uses a combination of tools belonging to operational research such as: analytic hierarchy process (AHP) and factor analysis (FA). The model has been tested in screw compressors when lubricant and vibration analyses are integrated.

Condition monitoring and lifetime estimation of a CO2 laser

Lasers are being successfully applied to a variety of manufacturing processes, including cutting, welding, cladding, and free forming. Part of their success is due to the high quality beam that is directly related to the condition of components involved in the lasing process. However, maintaining the requisite beam quality requires frequent and time-consuming intervention by maintenance operators, specifically, for dismounting, inspection, servicing, and reassembly. Preventive maintenance, targeting reduction of machine downtime by prevention of faults, is the de facto maintenance program for lasers in industry. In this work, condition monitoring and lifetime estimation have been proposed to enable predictive maintenance programs for CO2 lasers. Specifically, the cooling system of a CO2 laser is monitored to infer its health condition, which is then used to statistically predict its lifetime. A Weibull distribution has been used to model the hazard function that depends on the operating parameters and the condition of the machine. The monitoring and estimation strategy has been verified using simulation. Results of tests conducted at Applied Research Laboratory (ARL) at the Pennsylvania State University to exemplify the proposed approach are also presented.

Dynamic discriminant analysis for predictive maintenance of electrical components subjected to stochastic wear

An optimal maintenance program for electrical power system components should be based on their reliability. Since, for components characterized by high reliability and cost such as HV circuit breakers, available statistical data are in limited number, a physical model for their ageing is opportune. In the paper a Predictive Maintenance Program (PMP), for determining when a HV circuit‐breaker should be rebuilt, is formalized; it is based upon an adequate stochastic model of electrical wear associated with breaking operations due to system faults. In the model, both fault times and amplitudes are described by means of random variables, in order to deduce a reliability function used as input data for a Bayesian discriminant analysis which dynamically estimates, also in the presence of observation errors, the state of the component, determining the optimal times to perform a maintenance action.

Infrastructure Manager Software Provides Comprehensive, Multidiscipline Plant Assessments

This article discusses an electronic manual, produced by the American Water Works Association Research Foundation (AwwaRF), called “The Water Treatment Plant Infrastructure Assessment Manager” (AwwaRF project 460). The CD‐ROM and user's manual offers a multidisciplinary approach for assessing the condition and functionality of a treatment plant's infrastructure, including its subsystems and components. The manual's state‐of‐the‐art assessment techniques, coupled with user‐friendly software that records and represents the data, allow managers to efficiently conduct meaningful and standardized field assessments that can then be used by staff at all levels of an organization. The infrastructure manager software can be customized to reflect the specifics of an individual plant, and users can input more detailed information to generate more detailed reports. The infrastructure manager software allows utilities to reduce the amount of maintenance that is performed as a reaction to deteriorating conditions. Instead, they can initiate predictive maintenance and rehabilitation programs that are less costly but still produce safe, dependable drinking water.