Hierarchical dynamics-aware deep learning for electricity consumption prediction in discrete manufacturing enterprises

Background: Against the backdrop of the transformation and upgrading of the manufacturing industry, lean manufacturing has emerged as a systematic and advanced production paradigm that has deeply permeated the entire value chain of enterprises. Objective: However, there is a lack of systematic and effective lean technology paradigms in aspects such as lean practice processes and improving manufacturing process efficiency. Moreover, a comprehensive analysis of the current status and development strategies of lean technologies in discrete manufacturing enterprises has yet to be conducted to address issues such as the fragmentation of lean technology applications and the ambiguity of implementation strategies in discrete manufacturing enterprises. Methods: This paper conducts an extensive review of the literature on lean technologies and transformation methods in discrete manufacturing enterprises. A multi-stage data analysis approach (including data identification, screening, eligibility assessment, classification, and comprehensive analysis) is utilized to analyze 369 highly relevant documents. Results: The main contributions of this study are as follows: (1) A comprehensive review of existing lean manufacturing technologies and methods is provided, classifying, comparing, and summarizing the current status of lean technology and strategy applications, and delineating nine categories of lean technology application directions. (2) A “5P” theoretical framework (Philosophy, Process, People, Problem-solving, and Product) is proposed, redefining a lean technology framework that covers the value streams of discrete manufacturing. (3) Future application trends of lean technologies in discrete manufacturing are summarized and predicted, and an implementation strategy for lean technologies tailored to small and medium-sized discrete manufacturing enterprises, along with six lean technology development strategies, are proposed. The results indicate that many enterprises have derived diversified methods based on their own circumstances, which compensate for the deficiencies of the original lean models. Discussion and Conclusions: This paper organizes these methods to serve as a reference for future research on the lean technology system. The proposed strategies include formulating lean transformation strategies for discrete manufacturing enterprises, enhancing proactive lean capabilities, adapting to passive lean factors, and creating value for the enterprises’ reasonable lean needs from three levels: strategic philosophy, objective principles, and tool technologies. This research will play a guiding role in promoting the coordinated development of lean implementation and achieving high-quality development in discrete manufacturing enterprises.

This paper uses NVIVO as a software tool to study the realization of digital transformation in discrete manufacturing enterprises in Grounded theory. To explore the key influencing factors of digital transformation, in-depth interviews were conducted with 43 employees of typical discrete manufacturing enterprises in China, and qualitative analysis of the interview raw data was conducted. Firstly, the original data were open coded to identify the initial categories of digital transformation behaviors. Secondly, based on the open coding, the connections that exist at the conceptual level between different initial categories are summarized and inducted. Finally, the relationships between the core categories and other categories are analyzed, and the typical relationships between each category are summarized. Based on the analysis of the raw data statements, the dimensions of the direct and indirect roles of discrete manufacturing enterprises in realizing digital transformation are summarized, and the role model of the influencing elements of digital transformation in discrete manufacturing enterprises is constructed to analyze the behavior of digital transformation in discrete manufacturing enterprises. The research results show that there are five main influencing factors for digital transformation. The digital transformation measures of discrete manufacturing enterprises are proposed accordingly.

Order to discrete manufacturing enterprises typical business process as background, analyzes its in the order lifecycle process. Extract the key nodes information in the business process, business process model, data chain model is established. Finally, the use of middleware technology for the actual situation of discrete manufacturing enterprises, established the order lifecycle execution process architecture model. Has important significance for discrete manufacturing enterprise order lifecycle information management system.

Managing Functional Conflicts and Response Time Delays Of Customer Orders in Discrete Manufacturing Workflows

<p indent="0mm">In the realm of intelligent manufacturing, discrete manufacturing enterprises are in urgent need of enhancing control levels in their production processes. Therefore, addressing the critical issue of leveraging next-generation information technology for precise and rapid control over disruptive events has become imperative to accelerate progress in intelligent manufacturing. This paper commences by elucidating the temporal logic behind production anomaly control, thereby clarifying the core research problem. Subsequently, it delves into characterizing and modeling production anomalies, encompassing representation of production elements, process modeling, and an overview of current anomaly modeling approaches. Furthermore, a detailed exposition is provided on the optimization of production anomaly scheduling while analyzing existing methods based on “perceive-evaluate-schedule-optimize”. Additionally, this paper explores closed-loop control logic within manufacturing processes that include data collection, anomaly prediction, and real-time control. Moreover, significant emphasis is placed on discussing the potential advantages and challenges associated with applying next-generation artificial intelligence information technology in anomaly control. Finally, considering the current research status and industry requirements for intelligent manufacturing systems, prospective future trends in anomaly control technology are presented.

To address common challenges faced by discrete manufacturing enterprises during digital and intelligent transformation—such as inconsistent material coding conventions, difficulties in coordinating multi-source BOM data, and disruptions in end-to-end lifecycle traceability—this paper proposes an MES-based framework for unified code generation, management, and traceability. The proposed framework adopts a bidirectionally linked “one item, two codes” strategy and establishes a structured model consisting of a static material code and a dynamic batch code. Through configurable coding rules, the framework enables unique identification of object attributes and dynamic mapping to production batches. By integrating a rule-parsing engine with a full-chain indexing mechanism, the system achieves closed-loop process management spanning BOM import, automatic code assignment, and shop-floor execution. Engineering practice demonstrates that the proposed system effectively mitigates conflicts caused by multiple codes for the same item and significantly improves material identification efficiency and quality traceability accuracy in complex manufacturing scenarios.

The objective of this study is to monitor manufacturing energy consumption (MEC) in a discrete manufacturing enterprise, where energy is consumed everywhere and anytime with creating ubiquitous MEC data. The ubiquitous manufacturing (UbiM) technology, including radio frequency identification (RFID) technique, is employed to automate real-time data acquisition and processing for an order fulfilment. An MEC model for the order fulfilment is constructed according to the bill of materials (BOM). In this model, the computation is triggered by an RFID read event (RRE) enabling a digital energy metre to acquire energy consumption value of a workstation for processing a certain material, and then the acquired value is assigned to an energy consumption event (ECE). To reflect the effect of an ECE on energy consumption of a production task, a station-material energy consumption matrix (smECM) is constructed to store the relevant event data, which plays a key role in alleviating MEC monitoring restrictions caused by big energy data. By operating the matrix, the MEC monitoring information can be effectively extracted. To assist manufacturing enterprises to better employ it, the proposed method was demonstrated by monitoring MEC of an order in an auto-part manufacturer.

Characteristic of Auto electronic parts production industry are introduced at first. And with the background of the practical demands of Auto electronic parts production industry, with model of Browser/Server (B/S) and program as Microsoft.NET, Visual C++, SQLSever2000 was introduced. Meanwhile, this architecture of Manufacturing Execution System (MES) design theory and database structural charts of the whole system are presented. Information integration and production scheduling optimization function of MES implement information fusion and combination between PCS and ERP, realization the optimization control and management of the Auto electronic parts enterprise production process, which improves enterprise's synthesis competition ability. The two layers integrated automation system production indexes and scheduling as the design core realization optimization of production scheduling indexes. The MES that adopting this method is achieved the integration of management and control. This system has been applied to the Auto electronic parts plant and the production efficiency is increased. The successful implementation of this system has explored a new method for the overall optimization of the large systems in discrete manufacturing enterprise.

Research on flexible job shop scheduling under finite transportation conditions for digital twin workshop

To optimize the production logistics in discrete manufacturing enterprises, we put forward a new thought of workstation-oriented production logistics for the solution of low picking efficiency and high delivery cost of JIT (Just in Time) mode. A distribution model is constructed to minimize the total distribution time in workshop. An improved genetic algorithm is designed to solve the proposed optimization model. Finally, a case study is presented to demonstrate the feasibility and validity of the proposed model.

The variety of product types and spesifications make new product development (NPD) tasks tough work in discrete manufacturing enterprises, which makes it a common strategy to refer to similar outcomes (e.g. the product drawings, work instructions, etc.) of former tasks during NPD processes. To improve the efficiency of discovering similar historical outcomes, this paper presents a novel approach to measure the similarity between task execution contexts in process-aware information systems, and exploit it for runtime task knowledge recommendation. In our framework, the measurement of similarity is preceded by 1) modeling the task context with ontology theory, 2) using the ontology matching algorithms to evaluate the similarities between the corresponding context ontology entities of different tasks instances. The TD-IDF is then utilized to compute the context cohesion between the user’s current task and historical tasks, and the tasks with the highest similarity will be recommended to the task executors, along with their outcomes. Comparative evaluation is performed using TF-IDF, Levenshtein and Affine Gaps, and results demonstrate that the proposed approach achieves good precision and recall, and is efficient in task knowledge recommendation.

Production costs and total completion time minimization for three-stage mixed-model assembly job shop scheduling with lot streaming and batch transfer

The large airport terminal is the city's transportation hub and logistics center, and its building electricity consumption is twice or even higher than that of general large public buildings. Energy-saving and consumption reduction of the terminal building is not only the need to improve the operational efficiency and reduce the operation cost of the airport but also the need to realize the goal of "double carbon" in China. In this study, a large airport terminal in Beijing is taken as the research object. According to the characteristics of its main electrical equipment system, and the measured data of passenger flow from January 2020 to February 2023, combined with Pearson correlation analysis, K-means cluster analysis and multiple regression analysis, the influence and correlation characteristics of building scale, passenger flow and outdoor meteorological parameters on its electricity consumption are analyzed. The results show that: 1) The daily electricity consumption of the terminal can be analyzed by five levels according to the daily passenger flow, namely, 10,000 < N ≤ 30,000,30,000 < N ≤ 50,000, 50,000 < N ≤ 70,000, 70,000 < N ≤ 100,000, and 100,000 < N ≤ 130,000; 2) The electricity consumption of the terminal can be divided into three categories: basic electricity consumption related to the building scale of the terminal, variable electricity consumption I related to passenger flow, and variable electricity consumption II related to outdoor air temperature and passenger flow. Based on this, the terminal's daily electricity consumption prediction model is constructed, and the measured data verify the model's effectiveness. 3) Put forward the evaluation reference value of the daily electricity consumption of different passenger flow in this terminal, When the year passenger flow reaches the design value of 45 million, the normal daily electricity consumption level ranges from 0.44 to 0.48 kW·h/(m2·day). The research results can provide methods and evaluation reference for electricity consumption prediction, and accurate control of electricity consumption of main equipment systems in airport terminal.

Electricity consumption and load prediction method for Chinese rural residences based on the randomness and seasonality in electricity usage behavior

Electricity consumption prediction is an important part of power planning and the basis of power dispatch planning. The SVM and GBDT algorithms that were optimized by the PSO algorithm are used to build the machine learning-based electricity consumption prediction model in this paper. The decomposed and reconstructed high-frequency signals and low-frequency signals are optimized by the particle swarm algorithms SVM and GBDT for power consumption prediction, respectively. Improve the clustering performance of the traditional fuzzy C-mean algorithm for unbalanced data. The performance of the algorithms is analyzed in two different application scenarios, namely, artificial dataset and power users' real measurement dataset. Power consumption prediction in the manufacturing industry is performed. It is found that the ARI, FMI, and AMI index values of the improved algorithms proposed in this paper are 0.9543, 0.9347, and 0.9344, respectively, on the grid user-measured dataset, while the traditional DPC and K-means clustering algorithms are less effective. The machine learning algorithm optimized after wavelet decomposition increased R² by 8.98%, MAPE decreased by 19.78%, and RMSE decreased by 11.53% compared to PSO-GBDT, and the predictive evaluation indexes were all improved, and the two machine learning algorithms in this paper optimized by wavelet decomposition combined with PSO have good predictive effect R² increased from 0.801 to 0.842, and the two machine learning algorithms designed in this paper based on wavelet decomposition have good predictive effect R² increased from 0.801 to 0.842. The designed machine learning model for electricity consumption prediction based on wavelet decomposition and PSO has excellent performance, and the design expectation has been fulfilled. This paper makes a useful exploration and proposes an effective method for accurate prediction of electricity consumption in the manufacturing industry.