Article Details

Abstract

Aiming at the problems of static, low efficiency, and single dimension in traditional manufacturing capacity analysis methods, this paper designs and implements a data-driven multi-dimensional capacity analysis report automatic generation system. By constructing a multi-source heterogeneous data fusion model, the system integrates three core modules: data preprocessing, multi-dimensional efficiency analysis, and automatic report generation. This paper adopts multi-thread parallel processing and a time-window-based data correlation algorithm to achieve efficient integration and real-time monitoring of production factors such as equipment and personnel. The system automatically generates visual reports including trend, year-on-year, and month-on-month analysis. It accurately identifies production bottlenecks (such as inefficient equipment and unreasonable personnel allocation) through statistical analysis logic and provides optimization suggestions, forming a closed-loop management from state perception to decision optimization. Application results show that this system significantly improves the efficiency and depth of capacity analysis and provides effective technical support for manufacturing enterprises to promote data-driven lean production.

Keywords

data-driven; multi-dimension; data fusion; manufacturing; capacity analysis; report generation; system design

References

1. [1] Xia Dinghe The Adjustment Strategy of Textile Industry Structure under the Background of Economic Globalization [J]. Dyeing and Finishing Technology, 2024, 46 (5): 17-19
2. [2] HOSSAIN M T，SHAHID M A，LIMON M G M，et al. Techniques, Applications, and Challenges in Textiles for A Sustainable Future [J/OL].Journal of Open Innovation: Technology, Market, and Complexity，2024，10（1）：100230[2025-08-28].https://doi.org/10.1016/j.joitmc.2024.100230.
3. [3] Zheng Xiaohu, Liu Zhengzheng, Chen Feng, etc The current situation and prospects of intelligent development in the textile industry [J]. Journal of Textile Science, 2023, 44 (8): 205-216
4. [4] Dong Kuiyong The Development History and Innovation Path of China's Cotton Textile Industry [J]. Cotton Textile Technology, 2023, 51 (10): 5-13
5. [5] Zhang Chao Four major paths for the transformation and upgrading of manufacturing industry in the era of artificial intelligence [J]. China Industry and Information Technology, 2025 (6): 42-47
6. [6] Qi Zun. Design and Implementation of Automatic Generation System for Testing Reports and Enterprise Reports [D]. Beijing: Beijing University of Posts and Telecommunications, 2020
7. [7] Ou Jiale, Yang Hongying, Zhang Kunli, etc Radiographic report generation by integrating multi view features [J]. Computer Engineering and Applications, 2025, 61 (10): 320-330
8. [8] Liu Lishihao Intelligent generation system for food safety sampling data analysis and report [D]. Beijing: Beijing Forestry University, 2022
9. [9] Jiang Lei Development of an automated generation system for final assembly reports of specialized mechanical products [J]. Mechanical Engineer, 2021 (5): 82-84
10. [10] Lu Faming, Zheng Jiajing, Bao Yunxia, et al. Multi threaded program deadlock detection based on lock augmented segmented graph [J]. Journal of Software, 2021, 32 (6): 1682-1700

About the authors

Sun Ping (1972-), female, Han nationality, from Fuzhou, Fujian Province, senior engineer, bachelor's degree, research direction: industrial Internet, industrial application of knowledge map, identification analysis application.