Mayank Kumar Pandey

Designing an integrated multi-echelon agile supply chain network: a hybrid taguchi-particle swarm optimization approach

The present paper attempts to explore the integration of production, distribution and logistics activities at the strategic decision making level where, the objective is to design a multi-echelon supply chain network considering agility as a key design criterion. The design network conceived here addresses a class of five echelons of supply chains including suppliers, plants, distribution centers, cross-docks and customer zones. The problem has been mathematically formulated as a multi-objective optimization model that aims to minimize the cost (fixed and variable) and maximizes the plant flexibility and volume flexibility. The notion of cross-dock has been introduced as an intermediate level between distribution centers and customer zones to increase the profitability of manufacturing and service industries. In order to solve the underlying problem, a novel algorithm entitled hybrid taguchi-particle swarm optimization (HTPSO) has been proposed that incorporates the characteristics of statistical design of experiments and random search techniques. The main idea is to integrate the fundamentals of taguchi method i.e. orthogonal array and signal to noise ratio (SNR) in the PSO meta-heuristic to minimize the effect of the causes of variations. The proposed model has been authenticated by undertaking problem instances of varying size. Extensive computational experiments are conducted to validate the same and also the efficacy of the proposed HTPSO algorithm. The results obtained reveal that proposed solution methodology is an effective approach to solve the underlying problem.

Selective maintenance for binary systems under imperfect repair

In many industrial environments like manufacturing systems, military equipments, power generation systems, etc., system maintenance is performed between successive missions. Different maintenance options (do nothing, minimal repair, preventive maintenance options or system overhaul, etc.) are possible for components in the system. However, it may not be feasible to do all possible maintenance actions during the maintenance break. Hence, optimal maintenance decision is required such that available resources are optimally used to maximize the next mission reliability. In this paper, a mathematical model is used to help in decision making for selective maintenance under imperfect repair. The level of maintenance actions determines the improvement in the component health. A model is formulated to relate the amount of resources used for maintenance to the level of imperfect repair. Further, a characteristic constant is used which determines the component response to resource consumed by a maintenance task. Selective maintenance model is formulated and illustrative examples are used to demonstrate the applicability and advantages of the proposed method. The results show that introduction of imperfect repair facilitates better allocation of maintenance resources.

Selective maintenance for multi-state series–parallel systems under economic dependence

Abstract This paper presents a study on selective maintenance for multi-state series–parallel systems with economically dependent components. In the selective maintenance problem, the maintenance manager has to decide which components should receive maintenance activities within a finite break between missions. All the system reliabilities in the next operating mission, the available budget and the maintenance time for each component from its current state to a higher state are taken into account in the optimization models. In addition, the components in series–parallel systems are considered to be economically dependent. Time and cost savings will be achieved when several components are simultaneously repaired in a selective maintenance strategy. As the number of repaired components increases, the saved time and cost will also increase due to the share of setting up between components and another additional reduction amount resulting from the repair of multiple identical components. Different optimization models are derived to find the best maintenance strategy for multi-state series–parallel systems. A genetic algorithm is used to solve the optimization models. The decision makers may select different components to be repaired to different working states based on the maintenance objective, resource availabilities and how dependent the repair time and cost of each component are.

Selective maintenance modeling for a multistate system with multistate components under imperfect maintenance

In many industrial environments, maintenance is performed during successive mission breaks. In these conditions, it may not be feasible to perform all possible maintenance actions due to limited maintenance resources such as time, budget, repairman availability, etc. A subset of maintenance actions is then performed on selected components such that the system is able to meet the next mission requirement. Such a maintenance policy is called selective maintenance. In this article, a selective maintenance strategy is developed for a MultiState System (MSS). The system can have several finite levels of performance in an MSS. Previous studies on selective maintenance have solely focused on MSSs with binary components. However, components in an MSS may be in more than two possible states. Hence, a series-parallel MSS that consists of multistate components is considered in this article. Imperfect maintenance of a component is considered to be a maintenance option, along with the replacement and the do-nothing options. Maintenance resources need to be allocated such that maximum system reliability during the next mission is ensured. A universal generating function is used to determine system reliability. An illustrative example is presented that depicts the advantages of utilizing imperfect maintenance/repair options.

Simultaneous optimization of parts and operations sequences in SSMS: a chaos embedded Taguchi particle swarm optimization approach

Simultaneous optimization of interrelated manufacturing processes viz. part sequencing and operation sequencing is required for the efficient allocation of production resources. Present paper addresses this problem with an integrated approach for Single Stage Multifunctional Machining System (SSMS), and identifies the best part sequence available in the part-mix. A mathematical model has been formulated to minimize the broad objectives of set-up cost and time simultaneously. The proposed approach has more realistic attributes as fixture related intricacies are also taken into account for model formulation. It has been solved by a new variant of particle swarm optimization (PSO) algorithm and named as Chaos embedded Taguchi particle swarm optimization (CE-TPSO) that draws its traits from chaotic systems, statistical design of experiments and time varying acceleration coefficients (TVAC). A simulated case study has been adopted from the literature and effectiveness of the proposed algorithm is proved. The results obtained with different variants of its own are compared along with the basic PSO and Genetic Algorithm (GA) to reveal the superiority of the proposed algorithm.

Incorporating dynamism in traditional machine loading problem: an AI-based optimisation approach

Machine breakdowns have been recognised in flexible manufacturing systems (FMS) as the most undesirable characteristic adversely affecting the overall efficiency. In order to ameliorate product quality and productivity of FMS, it is necessary to analyse, as well as to minimise the effect of breakdowns on the objective measures of various decision problems. This paper addresses the machine loading problem of FMS with a view to maximise the throughput and minimise the system unbalance and makespan. Moreover, insufficient work has been done in the domain of machine loading problem that considers effect of breakdowns. This motivation resulted in a potential model in this paper that minimises the effect of breakdowns so that profitability can be augmented. The present work employs an on-line machine monitoring scheme and an off-line machine monitoring scheme in conjunction with reloading of part types to cope with the breakdowns. The proposed model bears similarity with the dynamic environment of FMS, hence, termed as the dynamic machine loading problem. Furthermore, to examine the effectiveness of the proposed model, results for throughput, system unbalance and makespan on different dataset from previous literature has been investigated with application of intelligence techniques such as genetic algorithms (GA), simulated annealing (SA) and artificial immune systems (AIS). The results incurred under breakdowns validate the robustness of the developed model for dynamic ambient of FMS.

Selective maintenance scheduling over a finite planning horizon

A preventive maintenance scheduling model is proposed in this article. The proposed model includes finite planning horizon and limited available resources to perform maintenance scheduling. A subset of maintenance actions, that is, selective maintenance is needed during maintenance breaks due to limited resources such as time, cost, and repairman availability. Maintenance can not only improve the effective age of a component but also may alter the hazard rate. Therefore, a hybrid imperfect maintenance model is used in this article that considers the combined effect of age reduction and hazard adjustment on a component. For a multi-component system, selective maintenance is performed at periodic intervals. In addition to maintenance and failure costs, we have included the maintenance break duration and the shutdown cost in the proposed scheduling model. A periodic maintenance scheduling problem is solved in this article for a series–parallel system. The optimal number of periodic maintenance breaks in a finite planning horizon is determined. Also, maintenance actions required during each of the maintenance breaks are determined. The number of periodic maintenance breaks and maintenance actions during these breaks is selected in a way that the total maintenance, failure, and shutdown cost are minimum. An evolutionary algorithm is used to solve the problem.

Selective maintenance for binary systems using age-based imperfect repair model

In many applications, the break between successive missions provides an opportunity to perform maintenance under limited resources. Such maintenance policy is called selective maintenance. Traditionally, it was assumed that a component after repair may be as good as new or as bad as old. However, maintenance can bring a component in between these two extreme cases as well. This maintenance policy is called imperfect repair. Selective maintenance optimization under imperfect repair is studied in this paper. Age reduction model is used to represent imperfect repair for selective maintenance. It is suggested in [1] that age reduction factor depends on the maintenance cost, and a constant is used to reflect whether a component is relatively young or old. In this paper, a formulation is used for this characteristic constant which depends on the effective age of the component. It is shown that the formulation helps in establishing a relationship between age reduction factor, cost of maintenance, and effective age of the component. Also, advantage of selective maintenance with imperfect repair is shown and results are compared with the case when only minimal repair and replacement are considered as repair options.

EMPSO-based optimization for inter-temporal multi-product revenue management under salvage consideration

The retail market is governed by customer behavior, demand pattern and inventory replenishment policies. It is also observed that any decision would prove to be full of errors, and objective of enhancing the market share could not be achieved, without inclusion of these factors and policies. While an extensive set of literature exists on single and multi-product dynamic pricing, the issue of liquidation of leftover inventory has so far received scant attention from the researchers of Operations Management community. The current work primarily tries to bridge this research gap by addressing dual objectives of revenue maximization and reduction of salvaging losses. In this paper an inter-temporal dynamic pricing model for multiple products is developed under a market setup with price-sensitive demand. Ideas proposed by [1] and [2] have been taken into account for constructing a revenue structure. The formulated objective function is found to be tractable for deriving prices and procurement quantities of large product portfolios. A multi-objective problem has been devised to handle the optimization of normal and clearance revenue by satisfying several pragmatic constraints. Subsequently, an effective algorithm deriving its traits from Particle Swarm Optimization has been proposed to address this problem. An illustrative example from retail apparel industry has been simulated and solved by the afore-mentioned approach. To validate the model statistical analysis has been carried out and the managerial insights portrayed to reveal the practical complexities involved.

Selective preventive maintenance scheduling under imperfect repair

The demand for a system is sometimes available only for a finite time horizon. It thus becomes necessary to schedule maintenance activities during a given planning horizon such that the desired system performance is maintained and the available resources are optimally allocated. In this paper, a mathematical model is proposed for periodically planning preventive maintenance activities for a system comprising multiple components. Due to resource limitations, it may not be possible to perform all desired maintenance options; hence, a selective maintenance approach is used to find the components to be maintained and maintenance actions to be performed on the selected components. An imperfect maintenance based hybrid model is considered here which includes age reduction as well as hazard adjustment after maintenance. Due to the high dimension of the solution domain, evolutionary approach is used to solve the problem. The optimal number of intervals is found under reliability and maintenance time constraints. During each maintenance break, the optimal maintenance option is selected for each component such that the overall cost of maintenance and possible failures for the entire planning horizon is minimized. It is also found that considering one interval at a time will incur higher cost.