Application of Machine Learning and Rule Scheduling in a Job-Shop Production Control System

Zhao, Yong-Ping; Zhang, H.

doi:10.2507/ijsimm20-2-co10

Cited by 22 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the employees surveyed, ML applications are mainly used in production processes; however, they are not widely distributed, being used in the chemical industry with maintenance applications. ML has been gaining in popularity, for example, in the production processes of biofuels (Rodríguez-Rángel et al, 2022;Xing et al, 2021), and in various production control systems (Zhao & Zhang, 2021).…”

Section: Ai Solutions Used In My Enterprisementioning

confidence: 99%

The state of development of artificial intelligence in polish industry: opinions of employees

Kądzielawski

2022

International Journal of Contemporary Management

View full text Add to dashboard Cite

Purpose The purpose of the article is to show how employees of industrial organizations perceive the development of artificial intelligence (AI) within them and to gather their opinions on what AI solutions are most commonly used in Polish industry. The literature review pointed to the lack of knowledge on how employees of Polish industrial companies perceive the development of AI in their respective companies and what AI solutions they already use. Design/methodology/approach Literature review and surveys were used to collect the data. The study was carried out using a survey questionnaire. The sample was taken with a specific aim in mind: first, 30 entities were selected for that purpose, while in the second stage the employees (managers and specialists) were chosen from among those. Findings In most cases, employees are not afraid of losing their jobs due to the development of AI systems in their industries. They are positive about the use of solutions that include AI elements. In the opinion of the vast majority of respondents, modern technologies, including AI, help them in their work and facilitate it. Most popular current industrial applications are: robotic process automation technologies, Cognex cameras using neural networks, machine-learning and data technologies, distributed control systems (DSCs), enterprise resource planning (ERP)) systems, and security information and event management (SIEM) systems. Practical implication-Results of this research can be useful for developing programs aimed at reducing the fear and anxiety associated with the ongoing Industrial Revolution. Originality/value The presented research results are the only ones that show the opinions of employees regarding artificial intelligence in Polish organizations.

show abstract

Section: Ai Solutions Used In My Enterprisementioning

confidence: 99%

The state of development of artificial intelligence in polish industry: opinions of employees

Kądzielawski

2022

International Journal of Contemporary Management

View full text Add to dashboard Cite

show abstract

“…So far, no tools have been developed to support the strategic management of human resources. However, the quality of management decisions at the tactical and operational planning level can be improved with dedicated optimization methods and computerized decision support systems [39][40][41][42][43][44].…”

Section: Manpower Planning and The Construction Enterprisementioning

confidence: 99%

Conceptual Framework of a Simulation-Based Manpower Planning Method for Construction Enterprises

2022

View full text Add to dashboard Cite

The authors put forward a concept of a method to support workforce demand planning intended for construction contractors. The construction business suffers from shortages of skilled labor. The method facilitates analyzing the possibilities of project-to project resource sharing and uncertainties in the flow of new orders, both characteristics of construction. Construction contractors’ manpower planning is based on a production plan. A precise and deterministic plan is possible only for a short planning horizon covering a fixed set of acquired orders. New orders are won irregularly, and the type and quantity of work they involve is uncertain. For this reason, the authors argue for using a simulation model of the company’s production plan. Such a plan facilitates mapping the variability in the number of orders, their start dates and delivery times, as well as workloads. Simulating the flow of prospective orders helps assess the degree of utilization of the enterprise's human resources and the influence of the size of employment on the timeliness of the execution of individual projects. This provides a basis for determining reasonable employment levels. The approach helps determine the demand for manpower and provides the data necessary in the process of staff development and recruitment. Moreover, it provides a tool for assessing the feasibility of using in-house resources to fulfill new orders and the need to hire subcontractors. The novelty presented in the article is the method of manpower planning in construction companies, making it possible to take into account risk conditions in acquiring new orders and the variability of construction process execution times due to factors disturbing the work flow. The concept of the method was the basis for the development of a simulation model of the construction company's order execution under random conditions, allowing for the evaluation of the effects of maintaining different levels of employment of the workforce in terms of the degree of utilization of the production potential and timeliness of individual projects. Thus, the result of the research is a tool supporting the decision making of construction managers in human resources management practice.

show abstract

“…DRL combined with scheduling rules can make up for the deficiency of traditional scheduling methods in the application of historical data, and obtain a scheduling scheme that meets the needs of production. Zhao et al [13] proposed job-shop production control system based on DRL, and validated the effectiveness of the job-shop production control system combing with DRL and scheduling rules. Wang et al [14] proposed a framework based on DRL and iterative greedy algorithm for solving flow shop scheduling, which makes full use of local search to improve the quality of the solution.…”

Section: Introductionmentioning

confidence: 99%

Optimization of job shop scheduling problem based on deep reinforcement learning

Qiao,

Duan,

et al. 2023

Evol. Intel.

View full text Add to dashboard Cite

Aiming at the optimization problem of minimizing the maximum completion time in job shop scheduling, a deep reinforcement learning optimization algorithm is proposed. First, a deep reinforcement learning scheduling environment is built based on the disjunctive graph model, and three channels of state characteristics are established. The action space consists of 20 designed combination scheduling rules. The reward function is designed based on the proportional relationship between the total work of the scheduled operation and the current maximum completion time. The deep convolutional neural network is used to construct action network and target network, and the state features are used as inputs to output the Q value of each action. Then, the action is selected by using the action validity exploration and exploitation strategy. Finally, the immediate reward is calculated and the scheduling environment is updated. Experiments are carried out using benchmark instances to verify the algorithm. The results show that it can balance solution quality and computation time effectively, and the trained agent has good generalization ability to the scheduling problem in the non-zero initial state.

show abstract

Application of Machine Learning and Rule Scheduling in a Job-Shop Production Control System

Cited by 22 publications

References 26 publications

The state of development of artificial intelligence in polish industry: opinions of employees

The state of development of artificial intelligence in polish industry: opinions of employees

Conceptual Framework of a Simulation-Based Manpower Planning Method for Construction Enterprises

Optimization of job shop scheduling problem based on deep reinforcement learning

Contact Info

Product

Resources

About