Computers & Industrial Engineering最新文献

This study evaluates the catalytic effects of advanced manufacturing industry clusters and unified large markets on regional economic development from a computer science perspective, revealing their underlying mechanisms. It employs a Gated Recurrent Network (GRN) model optimized with Gradient Boosting Decision Tree (GBDT) technology to conduct empirical analysis through comprehensive data collection and analysis. The primary objectives are to assess these catalytic effects, highlight the importance of innovation and environmental indicators, determine the contribution levels of various factors, and test the computational fit and predictive accuracy of the model. Key findings indicate that the GBDT-GRN model demonstrates a significant improvement in data computation accuracy, ranging from 20% to 52%, and an increase in response time by 23% to 52%. The model achieves a computational fit of 92% to 99% when analyzing regional economic development. The proposed GBDT-GRN model is highly accurate and reliable in evaluating catalytic effects, providing strong support for policy-making and business decision-making. Innovation and environmental indicators play a crucial role, with varying contributions from different factors. This study offers an effective solution for sequence data prediction problems, supports policy-making and business decisions, and points to promising directions for future research.

While conventional production planning approaches prioritize short-term efficiency and economic gains, the sustainability development objectives emphasize a holistic perspective, integrating eco-friendly practices, social responsibility, and economic viability. Nevertheless, the existing literature overlooks a gap in understanding the role of socio-economic factors in labor-intensive production processes. In this regard, this research aims at investigating the impact of social factors, such as labor skill level and experience, on production planning, with a specific focus on glass wall panel manufacturing. The research integrates sustainability socioeconomics, as embodied by an empirically developed labor learning curve, with the MINLP (Mixed-Integer Nonlinear Programming) scheduling model. The results show that the integrated socio-economic scheduling approach outperforms traditional scheduling approach, reducing idle time up to 43% and promoting more balanced production distribution. Despite slightly higher upfront production costs, the integrated model offers long-term cost savings through reduced idle time and overtime, making it a viable option for companies seeking to improve productivity and worker satisfaction. The implementation of this work is recommended to maintain a sustainable, safe, and healthy work environment while also considering long-term economic benefits rather than short-term profits.

Sub-assembly is the basic stage of ship hull construction. It is necessary to optimize the scheduling of sub-assembly to shorten its assembly cycle and ensure the normal execution of subsequent processes. The scheduling problem of sub-assembly is an NP-hard problem that should take into consideration both spatial layout and temporal schedule. In this work, a mathematical model for scheduling the sub-assembly is established, and a Q-learning based hyper-heuristic with multi-spatial layout rule selection is proposed. Specifically, a spatial layout method based on multi-rule selection is proposed first. In various scenarios, distinct spatial layout rules are chosen to derive an appropriate spatial arrangement. Subsequently, a hyper-heuristic algorithm based on Q-learning is crafted to optimize the scheduling sequence and the selection of spatial layout rules. As a verification, numerical experiments are carried out in cases of different scales collected from a large shipyard. The effectiveness of the proposed algorithm is verified by comparing it with different spatial layout algorithms, various heuristic operators, existing well-known hyper-heuristic methods, and other Q-learning based scheduling methods. The results suggest that the proposed algorithm outperforms other comparison algorithms in most testing cases.

Based on large-scale data collection and high-speed transmission, Industrial Internet of Things (IIoT) promotes the rapid development of intelligent manufacturing. IIoT systems are usually disturbed by complex external factors, which lead to high-dimensional nonstationary operating data. Besides, unexpected data transmission interruptions, sensor failures, and network delays lead to data loss. This paper proposes a distribution & communication strategy for monitoring high-dimensional nonstationary processes with missing values in IIoT scenarios. First, a deep learning-based imputation network is proposed to impute the missing values. Then a decomposition strategy based on degree of cointegration is proposed, which decomposes a high-dimensional nonstationary process into multiple blocks. And a communication strategy is proposed to mine the internal relationship between different blocks. Finally, faulty information is detected by a distributed framework. Two real cases from IIoT are applied to illustrate the monitoring performance of the proposed method. The results show that the proposed method outperforms existing benchmarks in data imputation and monitoring performance.

The widespread use of the Internet and smart devices has led to a fast growth in online shopping, offering new chances for online retailers to boost profits. However, this expansion has also brought various challenges, such as the heavy workload faced by delivery riders. To meet customers’ delivery time preferences and increase earnings, riders often work long hours, especially during busy periods. This study explores how historical delivery data can be used to balance workload in on-time attended home delivery. Drawing on the actual delivery operations and data of an online shopping platform, we propose a framework that combines delivery demand and customer behavior predictors with an adaptive incentive system to balance rider workload. Specifically focusing on same-day attended home delivery, we introduce a method to forecast future delivery demand, an algorithm to estimate customer choice behavior using a simple model, and an adaptive incentive system to influence customer decisions and achieve workload balance. We show that as order volume increases, the proposed incentive system achieves the pre-determined workload target. Using real data, we conduct numerical experiments which not only underscore the superior predictive performance of our models but also affirm the efficacy of the proposed incentive structure.

The economic emission dispatch (EED) aims to minimize the fuel and pollutant emission costs of generator units under various complex constraints. Optimizing the EED problem is of crucial importance for alleviating the current energy and environmental pressures. In this work, nearly all known complex constraints in the EED problem, including the valve-point effect, transmission line power loss, prohibited operating zones, and ramp-rate limits, are taken into account, and an enhanced version of butterfly optimization algorithm (FDCDLBOA) is proposed to solve it. First, a new adaptive fragrance is employed to optimize the instability caused by target differences and improve the convergence performance. Second, the proposed dimension differential learning strategy evolves the position of individuals with the help of superior dimensional information in the population, and this extensive learning exchange can balance global and local search, maintain diversity, and get rid of local optima. Third, the Fitness-Distance-Constraint (FDC) guide selection method is employed for the first time to handle the complex constraints of EED problems, enhancing the ability of individuals to bypass the infeasible search areas. After evaluating the proposed FDCDLBOA on CEC 2022 test suite, it is applied to solve 8 EED cases, encompassing small-, medium- and large-scale systems. Notably, the 280-generator case is the first large-scale test to exceed 200 generators. Compared with 9 representative algorithms, FDCDLBOA performs outstandingly in terms of robustness, improvement index (IF), mean constraint violation (MV), feasibility rate (FR) and Quade multiple comparison, among which IF, MV, FR, and Quade are all employed for evaluating the EED problem for the first time. The presented results confirm that the proposed method effectively enhances the robustness of high-quality solutions and the ability to handle complex constraints, demonstrating strong competitiveness and potential in solving the EED problem.

Crowdsourcing has become an integral part of various industrial systems, with evolutionary dynamics playing a crucial role in group interactions within structured populations. This paper explores the significance of understanding population dynamics in crowdsourcing, particularly in the context of manufacturer crowds delivering manufacturing services. To ensure the platform’s prosperity, it is essential to address the key challenge of matching and balancing different manufacturers’ fulfillment capacities.

To tackle this challenge, we present a population dynamics model and a Moran process formulation based on evolutionary cooperation-competition game theory. These tools offer valuable insights into the growth rate of specific user types participating in crowdsourcing activities. Moreover, we have devised an optimization strategy that utilizes the population dynamics model and Moran process simulations to effectively stimulate user growth.

To demonstrate the efficacy of our approach, we focus on the application of tank trailer crowdsourced manufacturing. Through a comprehensive testing case study, we showcase how our proposed model can effectively motivate and balance manufacturers’ participation levels in a tournament-based bidding process for crowdsourcing.

This study provides a new perspective on the drone delivery problems (DDP) by conceptualizing the vertical space in multiple flight levels. The main advantage of drone delivery is efficiency in utilizing free three-dimension aerial space, enabling numerous travels at multiple flight levels. However, the operational efficiency tradeoff exists according to the flight level, particularly in metropolitan cities with countless skyscrapers. Operation on the upper level requires less detour on horizontal movement, but it needs more time on the vertical movement of drones to reach the upper level. This study introduces a novel DDP by dividing the vertical airspace into multiple flight levels, thereby providing an opportunity to increase overall delivery efficiency based on realistic constraints faced by cities. We formulate this problem into a mathematical model and suggest a new supervised machine learning approach called SPML (Sequential Prediction Machine Learning). The SPML has three phases. In the first phase, customers are sequenced by priority. The second phase uses a supervised machine learning model trained by the data collected from solving the mixed-integer linear programming (MILP) model to assign customers to the depot. The third phase is distributing jobs to drones by using dynamic programming.

In an era of social progress and policy changes, some hospitals have diversified their services by incorporating internet hospitals. However, since the development of internet hospitals has been delayed and their management model remains ambiguous, this paper employs game theory to establish an internet medical system. By categorizing patients based on their severity and their acceptance of telemedicine, and by devising the centralized and decentralized management models, the paper assesses the quality of service and management practices of internet hospitals. The findings reveal that under decentralized management, internet hospitals can enhance the quality of service in physical hospitals. Nevertheless, the disparity in quality of physical hospitals in the two medical systems under the centralized management mode requires clarification. In addition, the paper delves into hospital revenue and patient utility, indicating that while the establishment of internet hospitals may not consistently increase healthcare system revenue, it can significantly improve patient utility, especially in remote areas. These results provide valuable insights into the management and expansion of internet hospitals.

Water is a crucial resource for all forms of life, yet it is becoming increasingly scarce. A significant portion of water loss in urban and industrial areas is attributed to leaks. Addressing this issue is critical for enhancing efficiency, sustainability, and resource conservation. This paper presents a novel two-phase approach for leak detection and localization in water distribution systems using wavelet decomposition and machine learning for depth analysis of pressure signals. The first phase, Leak Detection, utilizes wavelet analysis to extract significant features from the daily pressure signal data. These features are then inputted into a Random Forest classifier, achieving a classification accuracy of 99% for distinguishing between “Leak” and “No Leak” scenarios. Following the detection, the Leak Localization phase aims to pinpoint the leak’s location using strategically placed sensors within the system. To facilitate understanding and application of our methodology, we have developed a user-friendly, web-based application designed for the detection and localization of water leaks on any given day. Extensive testing in a WDS named “L-Town” has validated our system’s ability to accurately identify leaks. The combination of wavelet-based signal analysis and the Random Forest algorithm forms an effective framework for advanced leak detection in water distribution systems. This approach holds great promise for future research and practical implementations in water management.