Production Scheduling Research Articles

The Impacts of AI and ML on the Performance of Logistics and Supply Chain Management

Digital transformation is not a goal, but the benefits that businesses achieve from digital transformation are the desired goal. The successive developments in artificial intelligence technology represent a great opportunity to solve business problems. Artificial intelligence, especially machine learning methods, can be used to solve many problems facing the logistics and supply chain sector. Machine Learning (ML) techniques widely impact on many aspects of Logistics and Supply chain Management such as improving services levels for end customers, reducing costs, minimizing resource waste, and improving partners relationships. The problem of demand forecasting is one of the problems that affect production scheduling, inventory levels, partner costs, and customer satisfaction. Therefore, this research addresses these topics in some detail and provides a practical application to solve the research problem using some machine learning methods and tools. The research confirmed the accuracy of predictions and thus improved decisions and partner plans in supply chains. The research represents an analytical addition to previous research in the same field.

The single machine scheduling problem with bio-mathematical fatigue constraints

Despite the adverse impacts of occupational fatigue such as accidents and injuries in the manufacturing industry, it has not been systematically examined in the literature on production scheduling. In this paper, we integrate the classic bio-mathematical fatigue prediction model from the brain science literature into the simple single machine scheduling problem with sequence-dependent setup times. Then, we formulate the problem as a mixed-integer linear programming model and propose an adaptive large neighborhood search heuristic. The effectiveness of the heuristic is numerically validated through real cases. Finally, we argue that considering bio-mathematical fatigue prediction can lead to safer production schedules, notably reducing the fatigue working hours in our real case.

Implementation of the ANP method to overcome delays panel box raw materials in PT. Agrivito

Choosing raw material suppliers is one of the most crucial elements. If the raw materials supplied by the supplier are of poor quality, this will affect the quality of the product produced. If suppliers are unable to provide raw materials, production schedules will be disrupted and the company will not succeed in achieving its vision. PT. A is a company that produces electrical panel boxes. In making a box, raw materials are needed, namely sheet metal for all parts of the box shape. The raw material system at PT. A experienced problems with delays in raw materials so that the production process did not run smoothly, PT. GC, PT. SSL and PT. SIPA is the supplier that provides the raw material for the plate. This has a direct impact on the smooth production of the company. This research aims to supply raw materials from the three companies smoothly by selecting one company that to supply according to PT's needs. A. The method used in this research is the Analytic Network Process (ANP) method. Selection of raw material suppliers involves 6 criteria, 12 sub-criteria, and 3 alternative suppliers. The results of the calculation of the Analytic Network Process (ANP) method with the three best alternative suppliers based on the highest weight, PT SIPA obtained sub-criteria scores including ease of negotiation (0.63484), accuracy of quantities (0.63699), meeting sudden requests (0.63699), on-time delivery (0.63699), providing guarantees (0.66942), speed of responding to complaints (0.63699), and ability to respond to requests (0.63699). Meanwhile, PT GC excelled in the sub-criteria of meeting the increasing number of requests (0.73065), payment method (0.37129), free from physical contamination (0.73065), conformity to specifications (0.63699), and ease of communication (0.66942). Meanwhile for PT. SSL does not have the highest sub-criterion

Microbiome characterization of two fresh pork cuts during production in a pork fabrication facility.

The goal of this study was to characterize the microbial profile of two different fresh pork cuts, bootjack (BJ) trim and tenderloin (TL), through a 16S rRNA sequencing workflow developed specifically for investigating low-biomass fresh meat within a commercial production schedule. Additionally, this study aimed to determine a baseline Salmonella prevalence and enumeration profile across these two fresh pork cuts. Results showed that microbiome diversity was different between the BJ and TL, and also differed significantly by processing date. The relative abundance of key bacterial genera associated with food safety and spoilage was also different between the two meat types. However, over the course of the production shift, changes in the meat microbiome were limited in both the BJ and TL. The crude prevalence and enumerated burden of Salmonella were lower than what has been previously reported in similar fresh pork cuts, and all of the Salmonella-positive samples occurred on just two processing windows of 1-2 days each. Taken together, the results of this study suggest that the microbial profile of two fresh pork cuts is significantly different even within the same plant at the same time points, and that day-to-day variability within the production process likely influences both the fresh pork microbiome and Salmonella profile of these two meat types.IMPORTANCEModern pork processing involves a series of processes that begin with the handling and transport of the live animals, proceed through harvest and fabrication, and end with the packaging and distribution of fresh pork to the consumer. Each step in this process can alter the microbial community of fresh pork and influence the meat's safety and shelf life. However, little is known about the microbial ecology of individual, unprocessed pork cuts and if the diversity of the meat microbiome remains consistent throughout a production schedule. Additionally, the crude prevalence and enumeration of Salmonella have not been well established for individual fresh pork cuts throughout a production schedule. A more thorough understanding of the microbial profile at different stages of pork production will help processors determine processing steps that impact the microbial characteristics of fresh pork. This insight will help processors implement targeted intervention strategies to enhance food safety and quality.

Metaheuristics for multi-objective scheduling problems in industry 4.0 and 5.0: a state-of-the-arts survey

The advent of Industry 4.0 and the emerging Industry 5.0 have fundamentally transformed manufacturing systems, introducing unprecedented levels of complexity in production scheduling. This complexity is further amplified by the integration of cyber-physical systems, Internet of Things, Artificial Intelligence, and human-centric approaches, necessitating more sophisticated optimization methods. This paper aims to provide a more comprehensive perspective on the application of metaheuristic algorithms in shop scheduling problems within the context of Industry 4.0 and Industry 5.0. Through a systematic review of recent literature (2015–2024), we analyze and categorize various metaheuristic approaches, including Evolutionary Algorithms (EAs), swarm intelligence, and hybrid methods, that have been applied to address complex scheduling challenges in smart manufacturing environments. We specifically examine how these algorithms handle multiple competing objectives such as makespan minimization, energy efficiency, production costs, and human-machine collaboration, which are crucial in modern industrial settings. Our survey reveals several key findings: 1) hybrid metaheuristics demonstrate superior performance in handling multi-objective optimization compared to standalone algorithms; 2) bio-inspired algorithms show promising results in addressing complex scheduling and multi-objective manufacturing environments; 3) tri-objective and higher-order multi-objective optimization problems warrant further in-depth exploration; and 4) there is an emerging trend towards incorporating human factors and sustainability objectives in scheduling optimization, aligned with Industry 5.0 principles. Additionally, we identify research gaps and propose future research directions, particularly in areas such as real-time scheduling adaptation, human-centric optimization, and sustainability-aware scheduling algorithms. This comprehensive review provides insights for researchers and practitioners in the field of industrial scheduling, offering a structured understanding of current methodologies and future challenges in the evolution from Industry 4.0 to 5.0.

Profitability of Using Advanced Irrigation Scheduling Methods for Cotton Production

As global demand for food and fiber rise with growing population, scarce resources such as water face significant challenges. Agricultural producers rely on irrigation to manage production variability, which intensifies the pressure on water resources. To address this, advanced irrigation scheduling techniques have been developed to improve water use efficiency and boost production. However, the adoption of these new technologies remains low due to uncertainties about their economic return. This study evaluated the economic efficiency of four advanced irrigation scheduling methods alongside a calendar-based method for cotton production. Field trials were conducted over five growing seasons from 2013 to 2017. We compared water usage and profitability between dryland production and advanced irrigation scheduling methods under conservation and conventional tillage practices. The advanced irrigation scheduling methods included the smart irrigation cotton app (Cotton App), University of Georgia smart sensor array, cotton water stress index, and Irrigator Pro. The calendar-based method used the University of Georgia Checkbook method (Checkbook). Results showed that irrigation improved cotton productivity and profitability during dry years. However, in wet years, irrigated cotton exhibited reduced yield and profitability compared to dryland production. Among the various irrigation methods, the Cotton App demonstrated the best performance in terms of yield and profit. The adoption of advanced irrigation scheduling techniques, particularly the Cotton App, appears promising for enhancing cotton productivity and profitability, while potentially reducing water usage compared to traditional calendar-based approaches like the Checkbook method.

Optimising multi-element cut-off grades for a strategic production plan under geological uncertainty

ABSTRACT Mines operate in uncertain heterogenous environments, in which the most profitable material must be delineated from lower value-material. Traditionally, single-element cut-off grades provide this delineation and methods for optimising date back to the 1960s. Recent advancements have included geological uncertainty, multiple elements, and production scheduling; however, no method combines all three improvements. Two multi-element cut-off grade definitions are proposed herein, along with a reinforcement learning framework for optimising long-term multi-element cut-off grades under geological uncertainty for an optimal production plan. The method is applied to a gold-copper mining complex, and the performance of both cut-off grade definitions is compared.

Integrated scheduling of batch production and intermediate delivery with batch-position-based learning effect

Integrated scheduling of batch production and intermediate delivery with batch-position-based learning effect

A novel machine-learning rolling horizon heuristic for dynamic lot-sizing and job shop scheduling problems

This study introduces an innovative approach to production planning and scheduling under uncertain customer demands by integrating uncertainty directly into the algorithmic framework. We present a novel rolling horizon simulation-based constructive heuristic to minimise total costs, encompassing production, setup, inventory, and backlog costs. We leverage priority rules to enable the method to adapt in real-time to changes. Our contributions include not only a novel heuristic but also the integration of a coevolutionary genetic programming-based hyper-heuristic, significantly improving solution quality and computational efficiency. Compared to other rule-based heuristics, our method consistently outperforms with an average reduction in total costs of 1.78%. Furthermore, it outperforms deterministic and two-stage stochastic programming models within a one-hour time limit, with reductions of 18.20% and 6.53%, respectively. Incorporating mathematical programming models into a rolling horizon scheme led to slightly lower total costs, with an average reduction of 0.13% and 1.16%. However, in less than half an hour, the proposed method reached better results in two out of three cases. The results of an efficiency and robustness analysis highlight the proposed method as a robust solution for dynamic and complex real-world applications.

A Mixed Integer Linear Programming Model for Rapid Rescheduling in Ship and Offshore Unit Design Projects

Shipbuilding and offshore projects frequently require schedule adjustments due to unforeseen factors such as material supply delays, technical issues, and adverse weather conditions. These adjustments are often managed manually, resulting in significant time consumption and an increased risk of human error. Unlike production scheduling, little attention has been given to design scheduling, particularly in the context of rescheduling. To address this gap, this paper presents an optimization model that automates the rescheduling process for shipbuilding and offshore unit design projects. The model generates updated schedules that accommodate necessary changes while minimizing deviations from the initial schedule. In a real-world case involving 857 tasks, the model generated a schedule in under one second, preserving approximately 80% of the original schedule and achieving a 20% improvement in adherence compared to the original scheduling method. Furthermore, the model demonstrated exceptional scalability by efficiently generating optimized schedules for 108,700 tasks in under three minutes. These results demonstrate the model’s capability to provide rapid, efficient, and scalable rescheduling solutions, enabling quick and iterative refinement processes.

Optimal operation and offering strategy for profit‐seeking of a coal‐mine energy prosumer in a liberalised market

AbstractCoal mines consume electricity from grids while making use of various derived energy resources to generate heat and power. This allows coal mines to act as energy prosumers. This paper presents an integrated optimisation model of optimal operation and offers strategies for profit‐seeking of a coal‐mine energy prosumer in a liberalised market. The discussed problem is formulated as a tri‐stage bi‐level programming model. In the upper level, the coal mine‐integrated energy system (CMIES) operator decides the retail contract management, equipment operation plan, and retail electricity price offered to end‐users through three stages to maximise its expected profits at a predefined risk level. In the lower level, the end‐users react to the price bids offered by the CMIES operator under study and other market retailers to minimise their costs for energy procurement. Unlike previous approaches, the endogenous uncertainties associated with market subjects' strategic behaviours are explicitly considered. To solve the proposed problem efficiently, the Karush–Kuhn–Tucker conditions and multicut benders decomposition method are employed. The simulation results show that the collaborative optimisation of the energy cycle and production scheduling can reduce daily operating costs by nearly $3576 and carbon emissions by 6.72 tons, which verifies the effectiveness of the proposed method.

Penerapan Artificial Intelligence (AI) Untuk Optimasi Jadwal Produksi Di Industri Manufaktur Dalam Upaya Meningkatkan Produktivitas Kerja

Artificial Intelligence (AI) serves as a strategic solution capable of optimizing production schedules and significantly enhancing work productivity. The objectives of this study are to understand how Artificial Intelligence (AI) can optimize production scheduling in the manufacturing industry, identify the factors influencing the success of AI implementation in the production scheduling process, and determine the impact of AI implementation on work productivity in the manufacturing industry. The research method employed is qualitative. The findings of this study indicate that the implementation of AI provides efficiency, flexibility, and competitive advantages for the manufacturing industry. With the right strategies, this technology can achieve higher productivity, enhance company competitiveness, and support sustainable growth in the modern industrial era.

Automatic Production Planning and Scheduling of Size

Automatic production planning and scheduling are critical for optimizing manufacturing processes in modern industries. This approach integrates advanced algorithms, machine learning, and real-time data analysis to streamline resource allocation, minimize production bottlenecks, and enhance overall efficiency. By automating traditionally manual planning tasks, the system improves accuracy and responsiveness to dynamic production demands. Challenges such as implementation costs, integration with existing systems, and data reliability are addressed through scalable architectures and robust predictive models. This study investigates innovative methodologies to achieve seamless coordination, examining their impact on productivity, cost reduction, and adaptability in competitive markets Key Words: optics, photonics, light, lasers, templates, journals

Production scheduling with multi-robot task allocation in a real industry 4.0 setting

The demand for efficient Industry 4.0 systems has driven the need to optimize production systems, where effective scheduling is crucial. In smart manufacturing, robots handle material transfers, making precise scheduling essential for seamless operations. However, research often oversimplifies the Robotic Flexible Job Shop problem by focusing only on transportation time, ignoring resource allocation and robot diversity. This study addresses these gaps, tackling a Multi-Robot Flexible Job Shop (MRFJS) scheduling problem with limited buffers. It involves non-identical parallel machines and robots with varying capabilities overseeing material handling under blocking conditions. The case study is based on a real Industry 4.0 scenario, where the layout restricts each robotic arm’s access, requiring strategic buffer placement for part transfers. A Mixed-Integer Programming (MILP) model aims to minimize makespan, followed by a new Genetic Algorithm (GA) using Roy and Sussman’s Alternative Graph. Computational tests on various scales and real data from a manufacturing plant demonstrate the GA’s efficacy in solving complex scheduling problems in real-world production settings. Based on the data, the Proposed Genetic Algorithm (PGA), with an average Relative Deviation (ARD) of 0.25%, performed approximately 34% better compared to the Basic Genetic Algorithm (BGA), with an average ARD of 0.38%. This percentage indicates that the PGA significantly outperforms in solving complex scheduling problems.

Energy-Efficient Distributed Welding Shop Scheduling Based on Multi-Objective Seagull Algorithm

For the energy-efficient distributed welding shop scheduling problem, focusing on the scheduling of production in a distributed welding shop, a mathematical model is established with the objective of minimizing the makespan and total energy consumption. In order to solve this optimization problem, an improved multi-objective seagull algorithm (IMOSOA) is proposed. The algorithm introduces three main enhancements: designing a weight matrix based on multiple critical paths to update the number of welders allocated to each job, redesigning the discretization operations of the multi-objective seagull algorithm according to the characteristics of distributed welding shop, and incorporating a Pareto front selection strategy. This strategy uses a new crowding distance calculation to resolve cases where non-dominated solutions at the same dominance level have equal crowding distances, thereby improving the next generation of solutions. These improvements not only reduce the maximum completion time and total energy consumption but also enhance search efficiency. Finally, the IMOSOA is compared with other algorithms under different scale examples, and the results show that the energy consumption is at least 11.7% lower than that of the comparison algorithm, which verifies the superiority of the IMOSOA.

Research and Implementation of Adaptive Production Scheduling Algorithm in Digital Transformation and Upgrading of Manufacturing Industry

With the use of digital innovations including artificial intelligence (AI), the manufacturing business has been reshaped by the fourth industrial revolution. Yet, since rescheduling determinations are unpredictable and random mechanisms exist, controlling enhanced production scheduling still presents challenges. So, this study presents an innovative digital technologies-driven scheduling mechanism leveraging AI to tackle the difficulties of rescheduling in the aspect of production scheduling. A genetic-assisted beetle swarm optimization (GBSO) strategy is introduced for the flexible job shop problem (FJSP) with sequence-dependent configuration and constrained dual supplies. Then, rescheduling sequences are discovered using the support vector machine (SVM) approach. The Python environment is utilized for testing the suggested procedures, and the effectiveness of these approaches is examined in terms of scheduling latencies and the rate of rescheduling. This research demonstrated that the developed methodologies achieved the best performance in rescheduling frequency and scheduling latencies, thereby enhancing the manufacturing sector operations.

Measuring Complexity in Manufacturing: Integrating Entropic Methods, Programming and Simulation.

This research addresses complexity in manufacturing systems from an entropic perspective for production improvement. The main objective is to develop and validate a methodology that develops an entropic metric of complexity in an integral way in production environments, through simulation and programming techniques. The methodological proposal is composed of six stages: (i) Case study, (ii) Hypothesis formulation, (iii) Discrete event simulation, (iv) Measurement of entropic complexity by applying Shannon's information theory, (v) Entropy analysis, and (vi) Statistical analysis by ANOVA. The results confirm that factors such as production sequence and product volume significantly influence the structural complexity of the workstations, with station A being less complex (0.4154 to 0.9913 bits) compared to stations B and C, which reached up to 2.2084 bits. This analysis has shown that optimizing production scheduling can reduce bottlenecks and improve system efficiency. Furthermore, the developed methodology, validated in a case study of the metalworking sector, provides a quantitative framework that combines discrete event simulation and robust statistical analysis, offering an effective tool to anticipate and manage complexity in production. In synthesis, this research presents an innovative methodology to measure static and dynamic complexity in manufacturing systems, with practical application to improve efficiency and competitiveness in the industrial sector.

Research on flexible weaving planning based on NSGA-II algorithm

Facing the shift in the weaving industry from mass production to a more diversified, small-batch production model, traditional production scheduling systems are no longer capable of meeting the demand for rapid market response. To address this issue, this paper first analyzes the production process of a weaving workshop, identifying key scheduling challenges such as order allocation, equipment selection, and operation sequencing. Based on this analysis, a flexible job shop multi-objective scheduling model tailored for weaving workshops is developed. To handle the multiple constraints and optimization goals inherent in the model, an improved NSGA-II algorithm is proposed. This algorithm combines artificial bee colony (ABC) algorithm for population initialization with simulated annealing (SA) for population filtering. Simulation examples and case studies from actual workshops demonstrate that the improved NSGA-II algorithm outperforms other algorithms in solving the scheduling problem for weaving workshops. The proposed multi-objective scheduling model and its improved algorithm provide accurate and efficient optimization solutions for workshop scheduling.

Transportation and production collaborative scheduling optimization with multi-layer coding genetic algorithm for non-pipelined wells.

The marginal wells in low-permeability oil fields are characterized by small storage size, scattered distribution, intermittent production, etc. The construction of large-scale gathering pipelines has large investment. So the current production mode is featured by single well tank oil storage, oil tank truck transportation and manual tank truck scheduling. At present, oil well production and crude oil transportation scheduling mainly rely on manual formulation, which has poor coordination and seriously restricts the release of oil well production capacity and the reduction of transportation cost. A mixed-integer linear programming (MILP) model representation was proposed in our previous work. The scale of the built model variables is huge, and the model solution time is long. In this paper, a genetic algorithm based on multi-layer coding is proposed. The first layer of the design code is the driving path of the oil tanker, and the second layer is the crude oil loading and unloading amount and the cumulative time. The algorithm expands the search domain by flipping, exchanging and shifting the code. In the case analysis part, the exact algorithm and the genetic algorithm designed in this paper are used to solve cases of different scales (5, 10, 30 and 200 oil wells) respectively, and the correctness and effectiveness of the algorithm are verified. The results show that, compared with the exact algorithm, the genetic algorithm designed in this paper can quickly solve a feasible scheduling scheme under different oil well scales, especially in the case of large-scale (200 wells) oil well groups. The optimal one-time result in the calculation example (200 wells) takes 1062.3s to run, and the total driving distance of all tank trucks in the obtained feasible scheme is 11280km. This study can guide oilfields to quickly formulate dispatching plans and minimize travel distances in non-pipeline well tanker dispatching.

Computer-based production planning, scheduling and control: A review

Computer-based production planning, scheduling and control: A review