Determination Of Batch Size Research Articles

Ml-driven approaches to enhance inventory planning: Inoculant weight application in casting processes

This study addresses the complexities of inventory management in the casting industry, focusing on a proprietary inoculant crucial for casting process. The unpredictable nature of inoculant usage, influenced by various casting variables, challenges conventional calculations. To overcome these, expert opinions were gathered to identify features for accurate prediction of inoculant requirements, and an annual dataset was created. This dataset underwent data preprocessing to introduce new features and mitigate outliers. Machine learning models, including decision tree, random forest, least absolute shrinkage and selection operator (LASSO), elastic net regression, ridge regression, multiple linear regression, gradient boosting, extreme gradient boosting, and voting regression, were trained and tested. The voting regression algorithm, which combines decision tree and LASSO through hard voting, demonstrates that combining high-variance low-bias and low-variance high-bias algorithms can achieve competitive performance with low errorwithout overfitting. Predictions obtained using the voting regression algorithm for the entire year’s data were analyzed using batch size determination algorithms, Wagner-Whitin and Silver-Meal, with Wagner-Whitin providing cost advantage. This study highlights the potential of predicting materials with uncertain usage through AI techniques and historical data, minimizing inventory cost. The findings offer practical insights for managers, demonstrating how advanced predictive models can enhance decision-making, improve inventory planning, and achieve cost savings. This approach is valuable without needing additional investment in material requirement planning, especially where bill of materials’ reliability is reduced by environmental factors.

Recommended Best Practices for Lyophilization Validation 2021 Part II: Process Qualification and Continued Process Verification

This work describes the lyophilization process validation and consists of two parts. Part one (Part I: Process Design and Modeling) focuses on the process design and is described in the previous paper, while the current paper is devoted to process qualification and continued process verification. The goal of the study is to show the cutting edge of lyophilization validation based on the integrated community-based opinion and the industrial perspective. This study presents best practices for batch size determination and includes the effect of batch size on drying time, process parameters selection strategies, and batch size overage to compensate for losses during production. It also includes sampling strategies to demonstrate batch uniformity as well as the use of statistical models to ensure adequate sampling. Based on the LyoHUB member organizations survey, the best practices in determining the number of PPQ runs are developed including the bracketing approach with minimum and maximum loads. Standard practice around CQA and CPP selection is outlined and shows the advantages of using control charts and run charts for process trending and quality control. The case studies demonstrating the validation strategy for monoclonal antibody and the impact of the loading process on the lyophilization cycle and product quality as well as the special case of lyophilization for dual-chamber cartridge system are chosen to illustrate the process validation. The standard practices in the validation of the lyophilization process, special lyophilization processes, and their impact on the validation strategy are discussed.Graphical

Surrogate-based optimization with adaptive parallel infill strategy enhanced by inaccurate multi-objective search

In recent decades, surrogate-based optimization (SBO) has been developed to replace costly models with cheap surrogates to improve efficiency. In this article, an adaptive parallel infill strategy is proposed to balance exploration and exploitation over the design space during the optimization process of SBO. Within this method, an inaccurate search strategy is adopted to optimize the surrogate models, thereby helping to locate the exploitation point. An elite archive is exploited to store superior sampling points for batch sampling, while a customized batch size determination strategy is introduced. The proposed SBO method with its adaptive parallel sampling strategy is tested on six unconstrained and five constrained analytical cases with the optimization results compared to state-of-the-art optimization algorithms. The optimization of a 582-bar tower truss system is also performed and utilized to verify the proposed SBO method. The proposed SBO with the adaptive parallel sampling strategy shows excellent performance and better stability.

A fast algorithm for the estimation of statistical error in DNS (or experimental) time averages

Time- and space-averaging of the instantaneous results of DNS (or experimental measurements) represent a standard final step, necessary for the estimation of their means or correlations or other statistical properties. These averages are necessarily performed over a finite time and space window, and are therefore more correctly just estimates of the ‘true’ statistical averages. The choice of the appropriate window size is most often subjectively based on individual experience, but as subtler statistics enter the focus of investigation, an objective criterion becomes desirable. Here a modification of the classical estimator of averaging error of finite time series, i.e. ‘batch means’ algorithm, will be presented, which retains its speed while removing its biasing error. As a side benefit, an automatic determination of batch size is also included. Examples will be given involving both an artificial time series of known statistics and an actual DNS of turbulence.

Optimisation of multi-stage supply chain systems by integrated simulation-variable neighbourhood search algorithm

In this paper, multi–stage supply chain systems (SCSs) controlled by kanban system are appraised a new simulation metaheuristics approach. In the kanban system, decision making is based on determination of batch size for each kanban. This paper simulates supply chain system regarding the costs under just–in–time (JIT) production philosophy. Since the adopted model is of backward type, the desired output is given in order to find the parameters and/or the structure of the model producing the output. This backward problem is non–analytic and often seems to be even more complex than the forward one. This paper applies genetic algorithm (GA) and variable neighbourhood search (VNS) to optimise the simulation model. A simple real–coded GA and VNS is presented and used to change the simulation model parameters. With each new set of parameters, a simulation run is performed. From the statistics gathered by running the simulation, a goal function is constructed to measure the quality of these parameters. GA and VNS and GA–VNS successfully provide a parameter set to demonstrate its capability to solve such difficult backward problems even in the area of complex simulation model optimisation specially when there is no prior knowledge of simulation model behaviour.

Determination of batch size at a bottleneck machine in manufacturing systems

In manufacturing systems, there often exists a bottleneck machine whose capacity is equal to or less than the market demand. Any idle or waste time at the bottleneck machine directly impacts the output of the entire plant because it results in a loss of throughput. In order to maximize the capacity utilization by less setup losses at the bottleneck machine, the parts are often produced in batches. Traditionally, most batch sizing decisions are made based on the economic order quantity model where setup and inventory holding costs are considered. This paper presents an alternative method to determine batch size at a bottleneck machine. We present a new objective function and cost factors for batch sizing and investigate queuing and throughput models. A linear search algorithm is introduced to find the optimal throughput rate and batch size at the same time. Numerical examples are examined to see how the batching algorithm works.

The design of a capacity requirements planning system for flexible manufacturing systems

Abstract The operating and manufacturing characteristics of a flexible manufacturing system (FMS) mean that a traditional planning procedure of material requirements planning (MRP) and capacity requirements planning (CRP) cannot be followed. Thus the planning works between the master production schedule and the shop-floor control (SFC) systems are analysed and reassigned to the MRP, CRP and SFC systems. A CRP system designed for FMS is presented in this paper. It determines the requested capacities by carrying out part type selection, batch size determination and process plan selection, and by estimting tool slot requests. If there is insufficient capacity, the CRP system calculates the overtime hours required to complete the production of demand quantity for a specified part type.

Simulating the impact of process capability on lot sizes in batch manufacturing

Many of the manufacturing systems can be considered as job shops which process products in batches through multiple work centers either for stock or for assembly elsewhere. Typically, such manufacturing systems rely on lot sizing models that primarily use setup costs to determine the batch sizes. While setup costs are important in batch size determination, other factors such as quality of the production process in terms of defectives produced, machine breakdowns and material shortage could also influence the in-process inventory costs and the delivery of the final products to the customers. The various factors that influence work-in-process inventories in batch manufacturing systems will be discussed and a simulation model will be developed. Further, a hypothetical manufacturing system will be simulated to analyze the interactions between the batch sizes and the process capability of the work centers processing these batches.

A simulation-based method to aid the improvement of manufacturing flexibility

Manufacturing organizations today are under increasing pressure to supply high quality products with short delivery times and at low cost. These competitive pressures make it essential for the company's manufacturing resources, whether a highly automated or traditional manual system, to be operated in the most efficient and flexible way possible. One useful measure of the flexibility of a manufacturing system is the manufacturing lead times of its products: shorter lead times contribute to greater flexibility. The drive for reduced lead times is an important aspect of the Just-In-Time (JIT) manufacturing philosophy. JIT is normally seen as an essentially experimental process of continuous small improvements, achieved by exposing one constraint at a time and eliminating its cause. However, this process often involves a risk of disruptions to production as problems come to light. This paper proposes an approach to achieving lead time reductions without the need for the risks of disruption involved in the normal JIT approach. If a simulation model of the manufacturing system is used for the experimental aspects of implementation, rather than the real system, then many of the problems might be anticipated, and hence addressed, before production is affected. The approach is based on the use of a simulation model to evaluate the overall performance of the system under given conditions. Proposed enhancements to the system can then be evaluated to assess their impact before the need to implement the changes in the real system. The approach is illustrated by its application to the problem of batch size determination and its effects on lead time performance. Results indicate that the approach may be suitable for application in a wide range of manufacturing companies.

A decision network application to batch size determination for single-stage systems

The decision network approach to batch sizing problems presented in this paper arrives at a solution by a technique similar in style to critical path analysis in which much of the information is presented in a network diagram. This allows it to provide a visual representation of the problem and analysis is carried out by forward passes through the network. It is shown that decision networks can be applied to deterministic and stochastic problems.

An industrial study of the effects of batch sizes on the performance of the overall manufacturing system

The determination of batch sizes involves considering the complex relationships between the batch size and a number of other elements including manufacturing lead time, work in progress levels, and finished stock levels. Most approaches to batch size determination have used analytical approaches which become untenable when full scale practical manufacturing systems are considered. Furthermore most studies of the effects of batch size have concentrated on relatively small systems which fail to fully reflect the size and complexity of practical manufacturing systems. In this paper an actual batch manufacturing system is studied. This system consists of 78 separate work centers manufacturing 487 different part numbers with each part routing containing up to 110 operations (average 46). The shop manufactures high precision gears.

Determination of batch sizes in multi-product, multi-stage situation and assessment on capacity utilization

Abstract This paper describes the method of determining batch sizes in a multi-product, multi-stage situation and presents a Decision Support System (DSS) for capacity utilization. A heuristic model has been developed for modifying the optimal batch sizes in a manner such that machine hour and labour productivity constraints are not violated. The capacity utilization so determined will also suggest and identify the need for reduction of number of set-ups.

Note—On the Optimality of Integer Lot Size Ratios in “Economic Lot Size Determination in Multi-Stage Assembly Systems”

The proof of a well known theorem by Crowston and Wagner in Crowston, Wagner, and Williams (Crowston, W. B., M. H. Wagner, J. F., Williams. 1973. Economic lot size determination in multi-stage assembly systems. Management Sci. 19 (5, January) 517–527.) is shown here to be defective. According to this theorem, an optimal solution to the batch size determination problem for multi-echelon production/inventory assembly structures is characterized by a set of lot sizes, such that the lot size at each stage must be an integer multiple of the lot size at its successor stage. The theorem has been said to apply to uncapacitated assembly systems having constant final product demand over an infinite horizon, with no backlogs or lost sales permitted, where lot sizes must be rational numbers and time invariant. While the theorem supposedly applied to the case of both finite production rates and infinite production rates, the proof dealt only with the case of instantaneous production. Also, the proof implicitly assumed that lots were processed at any given stage only after unchanging spans of time. In this paper we show that with or without this implicit assumption, the theorem does hold true for the special case of instantaneous processing in two-level assembly systems; that is, configurations where there is only one successor stage in the entire system. However, we also show by counterexample that without this implicit assumption, the theorem is invalid for more general assembly structures. Furthermore, in the appendix of this paper we show that the proof is defective at the point where Crowston and Wagner extend their results for two-level systems to more general assembly systems. Thus it is an open question whether or not the theorem is valid for all assembly structures when processing at any given stage must occur only after unchanging spans of time.

Economic Batch-Size Determination for Multi-Product Scheduling

In the determination of batch-sizes in batch production, different criteria can be used as guiding principles, depending on the specified objectives. In a production schedule consisting of several products, an optimum solution for the whole production schedule is sought. At the same time it is necessary to ensure that the total production costs of each individual product will not exceed a certain pre-determined value. Solutions for overall optimization of the schedule with respect to maximum profit per batch, or with respect to maximum return on the total cost of production of the batch, have already been published. This paper suggests a method for determining the economic batch-sizes when it is desirable to maximize the rate of return per unit time for a multi-product schedule.