Integrated predictive maintenance strategy for manufacturing systems by combining quality control and mission reliability analysis

Predictive maintenance (PdM) is an effective means to eliminate potential failures, ensure stable equipment operation and improve the mission reliability of manufacturing systems and the quality of products, which is the premise of intelligent manufacturing. Therefore, an integrated PdM strategy considering product quality level and mission reliability state is proposed regarding the intelligent manufacturing philosophy of ‘prediction and manufacturing’. First, the key process variables are identified and integrated into the evaluation of the equipment degradation state. Second, the quality deviation index is defined to describe the quality of the product quantitatively according to the co-effect of manufacturing system component reliability and product quality in the quality–reliability chain. Third, to achieve changeable production task demands, mission reliability is defined to characterise the equipment production states comprehensively. The optimal integrated PdM strategy, which combines quality control and mission reliability analysis, is obtained by minimising the total cost. Finally, a case study on decision-making with the integrated PdM strategy for a cylinder head manufacturing system is presented to validate the effectiveness of the proposed method. The final results shows that proposed method achieves approximately 26.02 and 20.54% cost improvement over periodic preventive maintenance and conventional condition-based maintenance respectively.     

A new approach to solving problems of multi‐state system reliability optimization

Usually engineers try to achieve the required reliability level with minimal cost. The problem of total investment cost minimization, subject to reliability constraints, is well known as the reliability optimization problem. When applied to multi‐state systems (MSS), the system has many performance levels, and reliability is considered as a measure of the ability of the system to meet the demand (required performance). In this case, the outage effect will be essentially different for units with different performance rate. Therefore, the performance of system components, as well as the demand, should be taken into account. In this paper, we present a technique for solving a family of MSS reliability optimization problems, such as structure optimization, optimal expansion, maintenance optimization and optimal multistage modernization. This technique combines a universal generating function (UGF) method used for fast reliability estimation of MSS and a genetic algorithm (GA) used as an optimization engine. The UGF method provides the ability to estimate relatively quickly different MSS reliability indices for series‐parallel and bridge structures. It can be applied to MSS with different physical nature of system performance measure. The GA is a robust, universal optimization tool that uses only estimates of solution quality to determine the direction of search. Copyright © 2001 John Wiley & Sons, Ltd.     

Developing a factory-wide intelligent predictive maintenance system based on Industry 4.0

Abstract

The main purpose of predictive maintenance (PdM) is to reduce unscheduled downtime and consequently improve productivity and reduce production cost. PdM has been featured as a key theme of Industry 4.0. However, the traditional PdM system was only designed for a single tool; as such, the resources allocation will become extremely complicated when hundreds of tools are working together in a factory. A manageable hierarchy and various health indexes are required for factory-wide equipment maintenance. To solve the problem mentioned above, this paper proposes a factory-wide intelligent predictive maintenance system by applying the so-called cyber-physical agent and advanced manufacturing cloud of Things to fulfill the requirements of Industry 4.0, the baseline predictive maintenance scheme to accomplish the PdM functions, and the newly proposed health index hierarchy to supervise factory-wide equipment maintenance.     

Predictive maintenance of complex system with multi-level reliability structure

Onboard sensors, which constantly monitor the states of a system and its components, have made the predictive maintenance (PdM) of a complex system possible. To date, system reliability has been extensively studied with the assumption that systems are either single-component systems or they have a deterministic reliability structure. However, in many realistic problems, there are complex multi-component systems with uncertainties in the system reliability structure. This paper presents a PdM scheme for complex systems by employing discrete time Markov chain models for modelling multiple degradation processes of components and a Bayesian network (BN) model for predicting system reliability. The proposed method can be considered as a special type of dynamic Bayesian network because the same BN is repeatedly used over time for evaluating system reliability and the inter-time–slice connection of the same node is monitored by a sensor. This PdM scheme is able to make probabilistic inference at any system level, so PdM can be scheduled accordingly.     

A knowledge-based prototype for optimization of preventive maintenance scheduling

A methodology has been developed, and a prototype tool, the Maintenance Advisor, has been designed and implemented based on this methodology which would assist the scheduling and decision-making for performance of preventive maintenance activities in a plant, based on probabilistic judgedment and probabilistic inference rules. Using data on failure rates, repair times, repair costs and indirect economic costs (e.g. power replacement and accident risk), and within the imposed deterministic constrainst, the program develops an optimum (minimum expected cost) maintenance schedule for the various pieces of equipment described by the model.

The Maintenance Advisor is a frame-based object-oriented tool, programed in KEE and Lisp. Equipment and other objects are represented as complex units, containing a complete set of characteristics, data and functional capabilities. Functional relations between the units are described in terms of two relations: TYPE-OF and PART-OF. The hierarchies formed by these relations serve as the basis for probabilistic and other inferences.     

Optimal age replacement scheduling for a random work system with random lead time

System maintenance and spare parts are two closely related logistics activities since maintenance generates the demand for spare parts. Most studies on integrated models of preventive replacement and inventory of spare parts have focused on age replacement scheduling, while random replacement policy, which is sensible and necessary in practice, is rarely discussed and applied. The purpose of this paper is to present a generalised age replacement policy for a system which works at random time and considers random lead time for replacement delivery. To model an imperfect maintenance action, we consider that the system undergoes minimal repairs at minor failures and corrective replacements at catastrophic failures. Before catastrophic failures, the system is replaced preventively at age T or at the completion of a working time, whichever occurs first. The main objective is to determine an optimal schedule of age replacement that minimises the mean cost rate function of the system in a finite time horizon. The existence and uniqueness of optimal replacement policy are derived analytically and computed numerically. It can be seen that the proposed model is a generalisation of the previous works in maintenance theory.     

Short communication optimal replacement scheduling in multi‐state series–parallel systems

The paper generalizes a replacement schedule optimization problem to multi‐state systems, where the system and its components have a range of performance levels—from perfect functioning to complete failure. The multi‐state system reliability is defined as the ability to satisfy a demand which is represented as a required system performance level. The reliability of system elements is characterized by their lifetime distributions with hazard rates increasing in time and is specified as expected number of failures during different time intervals. The optimal number of element replacements during the study period is defined as that which provides the desired level of the system reliability by minimum sum of maintenance cost and cost of unsupplied demand caused by failures. To evaluate multi‐state system reliability, a universal generating function technique is applied. A genetic algorithm (GA) is used as an optimization technique. Examples of the optimal replacement schedule determination are demonstrated. Copyright © 2000 John Wiley & Sons, Ltd.     

Maintenance schedule optimisation for a railway power supply system

High reliability is the crucial requirement in railway operation and a power supply system is one of the key components of electrified railways. The cost-effectiveness of the maintenance works is also the concern of the railway operators while the time window on trackside maintenance is often limited. Maintenance scheduling is thus essential to uphold reliability and to reduce operation cost. It is however difficult to formulate the optimal schedule to meet both reliability and maintenance cost for a railway power supply system as a whole because of its functional complexity and demanding operation conditions. Maintenance scheduling models to achieve reliability and maintenance cost are proposed in this study. Optimisation algorithms are then developed to attain the solutions of the model. The applicability of the models and efficiency of the solution algorithms are demonstrated in an example. The proposed methods are vitally important for the railway engineers and operators to assure the service quality in the increasing demands of the modern electrified railways.     

Selective maintenance scheduling under stochastic maintenance quality with multiple maintenance actions

Many systems are required to perform a series of missions with finite breaks between any two consecutive missions. To improve the probability of system successfully completing the next mission, maintenance action is carried out on components during the breaks. In this work, a selective maintenance model with stochastic maintenance quality for multi-component systems is investigated. At each scheduled break, a set of maintenance actions with different degrees of impact are available for each component. The impact of a maintenance action is assumed to be random and follow an identified probability distribution. The corresponding maintenance cost and time are modelled based on the expected impact of the maintenance action. The objective of selective maintenance scheduling is to find the cost-optimal maintenance action for each component at every scheduled break subject to reliability and duration constraints. A simulated annealing algorithm is used to solve the complicated optimisation problem where both multiple maintenance actions and stochastic quality model are taken into account. Two illustrative numerical examples and a real case study have been solved to demonstrate the performance of the proposed approach. A comparison with deterministic maintenance shows the importance of considering the proposed stochastic quality in selective maintenance scheduling.     

维修工程管理研究与发展综述

综述了近几十年来维修工程管理的研究与发展，如人工智能、故障诊断、机器状态监测技术(如振动分析、红外检测、热录像仪等)、预测和预防性维修(PPM)、全员生产维修(TPM)和主动性维修(PM)等，论述了综合应用机器实时状态监测与故障诊断、人工智能、计算机通讯技术以及先进的维修管理理念的集成质量控制与维修系统，最后提出一种目前世界领先的远程智能维修系统。内容包括：实践应用中的维修管理评估、智能和集成维修管理、状态监测维修中的智能预测决策支持系统(IPDSS)、设备状况衰退趋势预测——人工神经网络方法、IPDSS支持的维修管理、故障诊断中的人工智能应用、基于可靠性的预防性维修安排和远程智能维修系统。     

Optimizing preventive maintenance for mechanical components using genetic algorithms

This paper presents periodic preventive maintenance (PM) of a system with deteriorated components. Two activities, simple preventive maintenance and preventive replacement, are simultaneously considered to arrange the PM schedule of a system. A simple PM is to recover the degraded component to some level of the original condition according to an improvement factor which is determined by a quantitative assessment process. A preventive replacement is to restore the aged component by a new one. The degraded behavior of components is modeled by a dynamic reliability equation, and the effect of PM activities to reliability and failure rate of components is formulated based on age reduction model. While scheduling the PM policy, the PM components within a system are first identified. The maintenance cost and the extended life of the system under any activities-combination, which represents what kind of activities taken for these chosen components, are analyzed for evaluating the unit-cost life of the system. The optimal activities-combination at each PM stage is decided by using genetic algorithm in maximizing the system unit-cost life. Repeatedly, the PM scheduling is progressed to the next stage until the system's unit-cost life is less than its discarded life. Appropriately a mechatronic system is used as an example to demonstrate the proposed algorithm.     

Extended great deluge algorithm for the imperfect preventive maintenance optimization of multi-state systems

This paper deals with preventive maintenance optimization problem for multi-state systems (MSS). This problem was initially addressed and solved by Levitin and Lisnianski [Optimization of imperfect preventive maintenance for multi-state systems. Reliab Eng Syst Saf 2000;67:193–203]. It consists on finding an optimal sequence of maintenance actions which minimizes maintenance cost while providing the desired system reliability level. This paper proposes an approach which improves the results obtained by genetic algorithm (GENITOR) in Levitin and Lisnianski [Optimization of imperfect preventive maintenance for multi-state systems. Reliab Eng Syst Saf 2000;67:193–203]. The considered MSS have a range of performance levels and their reliability is defined to be the ability to meet a given demand. This reliability is evaluated by using the universal generating function technique. An optimization method based on the extended great deluge algorithm is proposed. This method has the advantage over other methods to be simple and requires less effort for its implementation. The developed algorithm is compared to than in Levitin and Lisnianski [Optimization of imperfect preventive maintenance for multi-state systems. Reliab Eng Syst Saf 2000;67:193–203] by using a reference example and two newly generated examples. This comparison shows that the extended great deluge gives the best solutions (i.e. those with minimal costs) for 8 instances among 10.     

Reliability with finite buffer size for a multistate manufacturing system with parallel production lines

Abstract

This study examines system reliability for a manufacturing system with parallel production lines by creating a model of a multistate manufacturing system (MMS). System reliability is defined as the probability of demand satisfaction, which reflects the probability that the current capacity state of the MMS can successfully process a given demand. In particular, a buffer station with a finite size is taken into consideration to avoid blockage and starvation in the MMS. To the best of our knowledge, there is no existing research that considers a finite buffer size in a model of an MMS with parallel production lines. This study proceeds through the following phases. (i) In the model construction phase, the amount of input material, workload, and minimal capacity required by each workstation to satisfy a given demand level are studied by flow analysis; subsequently, a buffer usage matrix (BUM) is proposed to calculate buffer reliability. (ii) In the performance evaluation phase, system reliabilities with both infinite and finite buffer sizes are derived in terms of both minimal capacity vector and buffer reliability. (iii) In the case demonstration phase, two examples are utilized to illustrate the proposed method. Results of both examples show that the system reliability is overestimated with an infinite buffer size.     

Heated tool-butt welding of polyethylene-pipes — Welding parameters and testing technique

Pipes in semi-crystalline thermoplastics are frequently joined by heated tool butt welding. The quality of the connection is essential dependent upon the set process parameters, the pipe material and the surrounding conditions.

The paper first looks into the welding parameters of temperature, pressure, displacement and time. A matching displacement equation is set out, which links all the essential parameters of the matching phase. A model law for matching is derived from this and illustrated with an example. The pressureless heating phase is described by an equation for the temperature distribution in the part being joined. The thickness of the molten layer present after heating is calculated and tallies well with experimental results. A theoretically derived joining displacement equation is shown for the connection process. This allows the influence of temperature and pressure on joining displacement to be estimated.

The known short-time test methods are not suitable for optimising the welding parameters. Two test methods modified for testing weld seams are thus presented. These are the low temperature bending test and the tensile test on hole-notched weld specimens. Both methods show that above a minimum welding temperature the temperature has no essential influence on seam quality.     

Kronecker algebra for series–parallel multi-state systems reliability evaluation

Multi-state systems (MSS) are systems whose stochastic degradation process is characterised by several performance levels varying from nominal functioning to complete failure. MSS arise naturally in many application areas. MSS reliability evaluation and estimation has received much attention from researchers and a wide range of papers dealing with MSS have been published. In this paper, an approach based on Kronecker algebra combined with stochastic processes is proposed to evaluate the reliability of a series–parallel MSS. The main advantage of the proposed approach is that the mathematical expressions of the MSS reliability indices are derived from data of individual elementary components without generating the whole, possibly huge, MSS state space. Furthermore, the approach is well formalised and easy to implement thanks to Kronecker algebra operators. Examples are given to illustrate the proposed approach.     

Joint redundancy and maintenance optimization for multistate series–parallel systems

This paper formulates the joint redundancy and replacement schedule optimization problem generalized to multistate system, where the system and its components have a range of performance levels. Multistate system reliability is defined as the ability to maintain a specified performance level. The system elements are chosen from a list of available products on the market and the number of such elements is determined for each system component. Each element is characterized by its capacity, reliability and cost. The reliability of a system element is characterized by its lifetime distribution with the hazard rate, which increases with time. It is specified as the expected number of failures during different time intervals. The optimal system structure and the number of element replacements during the study period are defined as those which provide the desired level of system reliability with minimal sum of costs of capital investments, maintenance and unsupplied demand caused by failures. A universal generating function technique is applied to evaluate the multistate system reliability. A genetic algorithm is used as an optimization technique. Examples of determination of the optimal system structure and replacement schedule are provided.     

Improving Performance in HPC Centers by Modeling Users Through an Evolutionary Virtual Interface

An agent-based profiling approach is presented in this paper in the form of a virtual interface that models user behavior and satisfaction with the objective of improving the performance of high-performance computing (HPC) centers. The interface's function is to translate user requests and satisfaction criteria into what is really necessary, thus permitting the optimization of the HPC center's scheduling, taking into account the predicted user satisfaction together with the objectives of the management of the center in terms of resource usage and cost. The system is built using an evolutionary agent-based profiling architecture where agents are evolved in real time to adapt to the different users. These agents cooperate with the scheduling mechanism, providing resource usage estimations for the different tasks, as well as predicting the effect of possible strategies on user satisfaction. This paper focuses on the user behavior modeling component, although the global architecture is also presented. Some experiments are carried out where the proposed architecture interacts with a real job-management system (JMS) (Sun Grid Engine). They clearly show that modeling the user and taking user satisfaction into account helps to improve system performance.      

A condition-based maintenance policy for stochastically deteriorating systems

We focus on the analytical modeling of a condition-based inspection/replacement policy for a stochastically and continuously deteriorating single-unit system. We consider both the replacement threshold and the inspection schedule as decision variables for this maintenance problem and we propose to implement the maintenance policy using a multi-level control-limit rule.In order to assess the performance of the proposed maintenance policy and to minimize the long run expected maintenance cost per unit time, a mathematical model for the maintained system cost is derived, supported by the existence of a stationary law for the maintained system state.Numerical experiments illustrate the performance of the proposed policy and confirm that the maintenance cost rate on an infinite horizon can be minimized by a joint optimization of the maintenance structure thresholds, or equivalently by a joint optimization of a system replacement threshold and the aperiodic inspection schedule.     

A Decision Support System for Managing the Transportation Needs of a Large Corporation

This paper deals with the development of an on-line computerized system for planning, scheduling, and monitoring the internal and external transportation needs of a large corporation. In a corporation of that magnitude, the internal transportation of materials, components, subassemblies, final products, machines, tools, and people, is a complex operation that constitutes a significant portion of its total expenses. The corporation developed, over time, an internal organization with its own fleet of vehicles for satisfying its transportation needs. Excess demand was covered by leased vehicles.

A computer system was developed for: accumulating and forecasting user demand for trips; scheduling trip requests to depots and vehicles; serially combining trip requests; shifting excess demand to leased vehicles; deciding on locations from which vehicles should be leased; balancing the load among transportation units; and performing the follow-up, billing, and control on the actual operations.

The system accumulates user demand and actual performance data which is later used for statistical analysis and for driving models which support decisions such as fleet sizing, depot location, leasing contract negotiations, pricing policies, manpower planning and monitoring, and vehicle maintenance policies.

The paper describes: the computerized system, the reasons for its development; the basic processes which are part of the system; the heuristics and algorithms used by the system; an efficient method for mapping and computing interlocation distances; an overview of the Data Base Management System, which supports the system; and important aspects of the computer implementation. The system had a major impact on the corporation, generating significant short and long term benefits, and having a direct influence on the development of other systems by the data processing organization. These are discussed and presented with a summary of the major observations and lessons learned from the project.     

Deterministic and stochastic approach for safety and reliability optimization of captive power plant maintenance scheduling using GA/SA-based hybrid techniques: A comparison of results

This paper presents a comparison of results for optimization of captive power plant maintenance scheduling using genetic algorithm (GA) as well as hybrid GA/simulated annealing (SA) techniques. As utilities catered by captive power plants are very sensitive to power failure, therefore both deterministic and stochastic reliability objective functions have been considered to incorporate statutory safety regulations for maintenance of boilers, turbines and generators. The significant contribution of this paper is to incorporate stochastic feature of generating units and that of load using levelized risk method. Another significant contribution of this paper is to evaluate confidence interval for loss of load probability (LOLP) because some variations from optimum schedule are anticipated while executing maintenance schedules due to different real-life unforeseen exigencies. Such exigencies are incorporated in terms of near-optimum schedules obtained from hybrid GA/SA technique during the final stages of convergence. Case studies corroborate that same optimum schedules are obtained using GA and hybrid GA/SA for respective deterministic and stochastic formulations. The comparison of results in terms of interval of confidence for LOLP indicates that levelized risk method adequately incorporates the stochastic nature of power system as compared with levelized reserve method. Also the interval of confidence for LOLP denotes the possible risk in a quantified manner and it is of immense use from perspective of captive power plants intended for quality power.