Adaptive time dynamic model for production volume prediction

Data from a continuously operating high volume lathe was collected over a period of a number of months. This machine would periodically fail and unplanned maintenance was often necessary. Failures were due to a myriad of causes. At the beginning of each month, management was required to estimate production output for the month. This paper shows how this goal might be facilitated via a sequence of Bayesian models analysing previous data. The validity of the procedure is justified by an empirical study.     

Managing production of high-tech products with high production quality variability

We consider production systems in technology industries where output quality of a single production run has a large variance. Firms operating such systems classify products into different quality bins and sell units in one bin at the same tagged quality level and the same price. Consumers have heterogeneous quality preferences and choose that quality that maximises their net utility. We examine firms’ assortment, production and pricing problem. We present a three-stage solution procedure that optimises the production quantity, quality specification and number of bins. In that regard, we show that for a manufacturing technology with known quality distribution and known distribution of customers’ quality preference, the optimal assortment and production quantity are set such that on average, the demand of each bin is exactly fulfilled. We examine the impact of an improved manufacturing technology, variation in consumer preferences and changing price premium on the optimal assortment, lot size, market share, yield loss and the overall profitability. We further show that when the quality distribution of the manufacturing process is unknown, downward substitution leads to product offering of higher quality and higher prices. Finally, we discuss practical considerations for pricing, technology and optimal product offerings, and explain the proliferation of bins witnessed in the last decade in the processor industry.     

Co-evolutionary genetic algorithm for multi-machine scheduling: Coping with high performance variability

Optimizing dispatching policy in a networked, multi-machine system is a formidable task for both field experts and operations researchers due to the problem's stochastic and combinatorial nature. This paper proposes an innovative variation of co-evolutionary genetic algorithm (CGA) for acquiring the adaptive scheduling strategies in a complex multi-machine system. The task is to assign each machine an appropriate dispatching rule that is harmonious with the rules used in neighbouring machines. An ordinary co-evolutionary algorithm would not be successful due to the high variability (i.e. noisy causality) of system performance and the ripple effects among neighbouring populations. The computing time for large enough populations to avoid premature convergence would be prohibitive. We introduced the notion of derivative contribution feedback (DCF), in which an individual rule for a machine takes responsibility for the first-order change of the overall system performance according to its participation in decisions. The DCFCGA effectively suppressed premature convergence and produced dispatching rules for spatial adaptation that outperformed other heuristics. The required time for knowledge acquisition was also favourably compared with an efficient statistical method. The DCF-CGA method can be utilized in a wide variety of genetic algorithm application problems that have similar characteristics and difficulties.     

一种轮询周期受限的EPON双级动态带宽分配算法

提出一种新的EPON上行带宽分配算法——轮询周期受限的双级动态带宽分配算法。这种算法结合用户等级协定和DiffServ的特点,采用周期受限的轮询方法和双级的带宽分配方式,在OLT端根据ONUi提供的业务队列情况对业务量进行估算,并授权带宽给ONUi,ONUi根据实际的业务量进行再分配。仿真结果表明,这种算法实现了高的带宽利用率,与DBAM相比有效地提高了EPON的QoS。     

Nanoscale topography of dynamic surfaces with ultrafast time resolution

We describe an optical system for detecting the movement of a surface with subnanosecond temporal and nanometer vertical displacement resolution. The system is fielded on an experiment to determine the distortion of a laser-ablated metal layer and compare the results with hydrodynamic simulations. We also discuss errors that can arise and potential means to mitigate them. The resultant data show one can examine dynamic changes to a reflective surface with accuracy down to tens of nanometers at hundreds of picoseconds time resolution.     

Neural networks to model dynamic systems with time delays

An algorithm is proposed to identify a neural network model that represents a nonlinear dynamic system with a multivariate time delay response. The algorithm consists of two major parts. The first one identifies the time delay vector for a given neural network structure. This task is accomplished by using an exhaustive integer enumeration algorithm that minimizes a statistical parameter to assess the performance of the neural network model. The second part uses a cross-validation strategy to identify the best neural network model. Since the structure that models a nonlinear system is usually unknown, the identification strategy consists of selecting several neural network structures and identifying the best time delay vector for each network. The modeling process starts with the simplest structure and progressively the complexity of the network is increased to end up with a complex structure. Finally, the network that offers the simplest structure with the best network performance is the one that exhibits the appropriate neural network structure with the corresponding optimal time delay vector. The Monte Carlo simulation technique was used to test the performance of the algorithm under the presence of linear and nonlinear relationships among several variables of dynamic systems and with a different time delay applied to each input variable. The introduced algorithm is used to detect a chemical reaction delay among enriched amyl acetate, acetic acid, water, and the pH of erythromycin sail. An appropriate neural network model was designed to model the pH of the erythromycin during a continuous extraction process. To the best of the authors knowledge the proposed algorithm is the only one currently available to identify time delay interactions in the multivariate input output variables of a system. The major drawback of the introduced algorithm is that it becomes very slow as the number of system inputs increases. This algorithm works efficiently in a system that involves five inputs or less.     

Comparing dynamic risk-based scheduling methods with MRP via simulation

It is well known that material requirements planning (MRP) is a deterministic planning tool which heavily relies on accurate demand forecast, and that its performance under perturbed, constantly changing environment becomes questionable. Although many companies still use basic MRP as a planning tool, there are other alternative tools available. For example, Factory Physics Inc. has developed a tool called dynamic risk-based scheduling (DRS), which creates a set of policy parameters (e.g. work in process (WIP) level, lot sizes, re-order point, and re-order quantity) that work for a range of situations. The main objective of this paper is to compare DRS and MRP scheduling systems for single-machine and multi-machine systems via simulation. Their performance measures are compared for various systems assuming three levels of demand uncertainty. The simulation results suggest that DRS outperforms MRP in terms of robustness, fill rate and inventory level.     

Remanufacturing lotsizing with stochastic lead-time resulting from stochastic quality of returns

In the current paper, we model the duration of recovery of used products as a variable that depends on each unit’s quality. Because of the uncertainty related to returned units’ quality, the necessary time for the recovery of a lot is a random variable. We provide analytical expressions for the optimisation of recovery planning decisions under different assumptions regarding quality and demand characteristics. In addition, through an extensive numerical study, we examine the impact of the different parameters on the necessity to consider explicitly the stochastic nature of recovery lead-time. Moreover, we discuss the advisability of establishing procedures for the classification of returns according to their quality condition. As our findings indicate, overlooking quality uncertainty can increase related costs considerably because of poor process coordination. Furthermore, ignoring variability may result in undue overestimation of the efficiency of lot-sizing policies. On the other hand, the establishment of quality assessment procedures is worthwhile only when the stochastic behaviour of quality cannot be taken into account explicitly.     

Monitoring multivariate process variability with individual observations via penalised likelihood estimation

Excessive variation in a manufacturing process is one of the major causes of a high defect rate and poor product quality. Therefore, quick detection of changes, especially increases in process variability, is essential for quality control. In modern manufacturing environments, most of the quality characteristics that have to be closely monitored are multivariate by the nature of the applications. In these multivariate settings, the monitoring of process variability is considerably more difficult than monitoring a univariate variance, especially if the manufacturing environment only allows for the collection of individual observations. Some recent charts, such as the MaxMEWMV chart, the MEWMS chart and the MEWMC chart, have been proposed to monitor process variability specifically when the subgroup size is equal to 1. However, these methods do not take into account the engineering and operational understanding of how the process works. That is, when the process variability goes out of control, it is often the case that changes only occur in a small number of elements of the covariance matrix or the precision matrix. In this work, we propose a control charting mechanism that enhances the existing methods via penalised likelihood estimation of the precision matrix when only individual observations are available for monitoring the process variability. The average run length of the proposed chart is compared with that of the MaxMEWMV, MEWMS and MEWMC charts. A real example is also presented in which the proposed chart and the existing charts are applied and compared.     

Structural dynamic modifications via models

Structural dynamic modification techniques attempt to reduce dynamic design time and can be implemented beginning with spatial models of structures, dynamic test data or updated models. The models assumed in this discussion are mathematical models, namely mass, stiffness, and damping matrices of the equations of motion of a structure. These models are identified/ extracted from dynamic test data viz. frequency response functions (FRFs). Alternatively these models could have been obtained by adjusting or updating the finite element model of the structure in the light of the test data. The methods of structural modification for getting desired dynamic characteristics by using modifiers namely mass, beams and tuned absorbers are discussed.     

Sequential DOE via dynamic programming

The paper considers a sequential Design Of Experiments (DOE) scheme. Our objective is to maximize both information and economic measures over a feasible set of experiments. Optimal DOE strategies are developed by introducing information criteria based on measures adopted from information theory. The evolution of acquired information along various stages of experimentation is analyzed for linear models with a Gaussian noise term. We show that for particular cases, although the amount of information is unbounded, the desired rate of acquiring information decreases with the number of experiments. This observation implies that at a certain point in time it is no longer efficient to continue experimenting. Accordingly, we investigate methods of stochastic dynamic programming under imperfect state information as appropriate means to obtain optimal experimentation policies. We propose cost-to-go functions that model the trade-off between the cost of additional experiments and the benefit of incremental information. We formulate a general stochastic dynamic programming framework for design of experiments and illustrate it by analytic and numerical implementation examples.     

A rolling horizon simulation approach for managing demand with lead time variability

This paper proposes a rolling horizon (RH) approach to deal with management problems under dynamic demand in planning horizons with variable lead times using system dynamics (SD) simulation. Thus, the nature of dynamic RH solutions entails no inconveniences to contemplate planning horizons with unpredictable demands. This is mainly because information is periodically updated and replanning is done in time. Therefore, inventory and logistic costs may be lower. For the first time, an RH is applied for demand management with variable lead times along with SD simulation models, which allowed the use of lot-sizing techniques to be evaluated (Wagner-Whitin and Silver-Meal). The basic scenario is based on a real-world example from an automotive single-level SC composed of a first-tier supplier and a car assembler that contemplates uncertain demands while planning the RH and 216 subscenarios by modifying constant and variable lead times, holding costs and order costs, combined with lot-sizing techniques. Twenty-eight more replications comprising 504 new subscenarios with variable lead times are generated to represent a relative variation coefficient of the initial demand. We conclude that our RH simulation approach, along with lot-sizing techniques, can generate more sustainable planning results in total costs, fill rates and bullwhip effect terms.     

Integrated scheduling of production and delivery with time windows

This paper deals with an integrated scheduling problem in which orders have been processed by a distribution centre and then delivered to retailers within time windows. We propose a nonlinear mathematical model to minimise the time required to complete producing the product, delivering it to retailers and returning to the distribution centre. The optimal schedule and vehicle routes can be determined simultaneously in the model. In addition, two kinds of genetic-algorithm-based heuristics are designed to solve the large-scale problems. The conventional genetic algorithm provides the search with a high transition probability in the beginning of the search and with a low probability toward the end of the search. The adaptive genetic algorithm provides an adaptive operation rate control scheme that changes rate based on the fitness of the parents. The experimental results have shown that the solution quality of these two algorithms is not significant but that the adaptive genetic algorithm can save more time in finding the best parameter values of the genetic algorithm.     

Dynamic response to demand variability for precast production rescheduling with multiple lines

Production scheduling plays a crucial role in the prefabricated construction productivity and on-time delivery of precast components (PCs). However, previous studies mainly focused on the static scheduling of single production line without considering the demand variability in practice. To achieve dynamic production planning, a Two-level Rescheduling Model for Precast Production with multiple production lines is developed to minimise the rescheduling costs based on genetic algorithm, from the two levels of (1) selection of production line and (2) rescheduling of jobs based on PCs’ priority. Further, two scenarios of different and shared mould types are investigated to represent real-world production environments. Finally, a real case study is conducted to test the validity of proposed rescheduling model. 58.1 and 48.5% cost savings are achieved by comparison to no response to changes and heuristic rescheduling methods, respectively. This research contributes to the precast production theory by expanding the insight into dynamic rescheduling with multiple production lines. The methodology will promote the on-time delivery of PCs and enhance the dynamic precast production management.     

用应变片法确定混凝土动态起裂时间的研究

在混凝土等准脆性材料的动态起裂韧度K_(1d)测试中,准确确定试件裂尖的起裂时间是测试工作的关键。采用分离式霍普金森压杆系统,对圆孔裂纹平台巴西圆盘混凝土试件进行动态径向冲击试验,通过在裂尖粘贴应变片的方法来确定起裂时间。讨论了应变片在裂纹尖端的粘贴位置、粘贴方向等因素对起裂时间测试值的影响,结果表明裂尖应变片的最佳粘贴方式是:在裂纹延长线上或在裂尖并与裂纹垂直的线上,都距离裂尖3 mm左右,且粘贴方向与裂纹延长线垂直。给出了考虑贴片位置和试件厚度的起裂时间计算公式。     

Dynamic re-order point inventory control with lead-time uncertainty: analysis and empirical investigation

A new forecast-based dynamic inventory control approach is discussed in this paper. In this approach, forecasts and forecast uncertainties are assumed to be exogenous data known in advance at each period over a fixed horizon. The control parameters are derived by using a sequential procedure. The merits of this approach as compared to the classical one are presented. We focus on a single-stage and single-item inventory system with non-stationary demand and lead-time uncertainty. A dynamic re-order point control policy is analysed based on the new approach and its parameters are determined for a given target cycle service level (CSL). The performance of this policy is assessed by means of empirical experimentation on a large demand data set from the pharmaceutical industry. The empirical results demonstrate the benefits arising from using such a policy and allow insights to be gained into other pertinent managerial issues.     

Crane scheduling with time windows in circuit board production lines

This paper studies a crane scheduling problem with time windows in a flow-shop type production system. Feasibility of a state of the system is first discussed. Then, based on the insight derived from the mathematical programming formulation of feasibility, an optimization-based heuristic algorithm for real-time scheduling of the system is developed. Computer simulation on randomly generated problems shows that this algorithm has an excellent performance in maximizing throughput without defective jobs.     

Cycle time reduction via machine-to-operation qualification

In the utopian factory every machine in a workstation would be qualified to perform every operation supported by that workstation (e.g., able to run every associated photolithography layer of the semiconductor wafer fabrication process). In real world factories this is unlikely to be either practical or even feasible. As a consequence, one of the more vexing problems involved in determination of factory configuration and operation is that of deciding which operations are to be run on what machine, so as to optimise overall factory performance. In this paper the decision of the allocation of machine-to-operation qualifications in a semiconductor wafer fabrication photolithography workstation is employed to illustrate this problem. Factory performance, as achieved by both conventional and optimal means, is compared via simulations of a model of a semiconductor wafer fabrication facility. The improvement, in factory performance–and estimated cost savings–was found to be substantial.     

Parameter estimation with variable sampling time via generalized block pulse functions

Abstract

Parameter estimation with variable sampling time is developed in this paper, using a continuous model. The input‐output variables are approximated by using generalized block pulse series expansion. A method of determining the sampling interval is proposed. The algorithm depends on the variations of the input and output variables. Parameter estimation is carried out by using a least‐squares estimation with exponential data weighting. Two examples are presented to demonstrate that the method exhibits satisfactory results.     

A dynamic method for the production lot sizing with machine failures

This paper presents a dynamic method to deal with two economic lot sizing models with exponential machine failures. Its main difference from the static method is that the machine failure is separately treated from the perspective of failure realisation. The optimal lot size is derived through the equation between the incurred average cost and the marginal cost, which has to be performed for each lot due to the random failures. In the first no-resumption model, the simulation shows that two methods have the similar performance as the lot number increases. For the resumable model, we propose a zero-inventory resumption policy that always resumes the production after each machine failure but delays the resumption until the on-hand inventory is depleted. The simulation result indicates that the new policy by the dynamic method outperforms the initial abort/resume policy, and it also shows the convergence as the production continues.