1. Project Introduction

The generation of industrial big data provides a new research perspective for tapping the energy conservation potential of enterprises and evaluating the comprehensive energy efficiency of enterprises. In-depth learning based on the huge multi-source and heterogeneous energy measurement big data can refine the comprehensive energy efficiency of production processes at all levels, and deeply explore the potential for comprehensive energy efficiency improvement from different scales such as equipment, processes, and systems. At the equipment level, based on equipment measurement data and working condition data, explore the best process parameters or control parameters to improve the energy conversion rate of energy supply equipment and the energy utilization rate of energy-consuming equipment; at the process level, explore the corresponding relationship between product characteristics and energy efficiency, and optimize the connection relationship between processes and production rhythm on the premise of meeting product quality and production requirements to reduce energy waste caused by low-load equipment work; At the system level, explore long-term energy efficiency plans for energy conservation, optimize energy supply plans through big data analysis based on the overall energy efficiency situation of the enterprise and the enterprise development plan, and reasonably match the enterprise's production capacity development requirements.

Typical case:

(1) Shanghai Chlor-Alkali Chemical Co., Ltd. -Analysis of energy-saving potential of electrolytic cells

Big data analysis is applied to the F2 ionic membrane workshop of the enterprise's electrochemical plant. Through analyzing a large number of production operating condition data of electrolytic cell equipment, important key factors affecting the unit consumption and alkali concentration of caustic soda are found, thereby providing the best operating conditions for the electrolytic cell. Operating parameters allow electrolysis electricity to be reduced as much as possible while ensuring the quality and output of caustic soda.

(2) Shanghai Heavy Machinery Factory Co., Ltd. -Energy consumption forecast for heat treatment process plan

The energy consumption data of the enterprise's power department and forging factory is analyzed to predict the energy consumption of heating equipment under different process plans, which provides a decision-making basis for enterprises to formulate optimal process plans for energy conservation.

(3) Baosteel Industrial Furnace Engineering Technology Co., Ltd. -Analysis of energy-saving potential of steel industry heating furnaces

Build a heating furnace industry big data ontology model to realize comprehensive management of multi-source and heterogeneous heating furnace big data based on the Semantic Web; use deep learning of neural networks to build a heating furnace process model with energy consumption per ton of steel as the output, and use genetic algorithms to obtain The best equipment process parameters to reduce the energy consumption per ton of steel for the heating furnace.

(4) Shanghai Baosteel Energy Saving and Environmental Protection Technology Co., Ltd. --Analysis on energy-saving potential of waste heat boiler

Adopt Semantic Web technology to integrate big data in the waste heat boiler industry. Taking the main steam output and dust emissions of the waste heat boiler as the analysis objects, the steam model and dust model of the waste heat boiler are constructed using the Sequential Minimization Optimization (SMO) algorithm. Taking the maximum main steam flow rate of the waste heat boiler and the minimum dust content in the outlet flue gas as the optimization goals, the multi-objective particle swarm optimization algorithm is used to optimize the operating parameters of the waste heat boiler to provide reference for adjusting the operating parameters.

2. Project industrialization prospects and application fields

With the rapid development of Internet technology, energy equipment can achieve end-to-end connectivity and generate daily data. The Internet will be integrated into every aspect of energy industry production, including the collection, analysis, sharing and processing of energy data, which will bring about tremendous changes in energy production, transmission, storage and use patterns, and give birth to the energy Internet system. Compared with traditional energy systems, the overall energy efficiency of the energy Internet system will rely more on the in-depth mining and processing of data. Aiming at the data characteristics of the energy Internet system, study the energy Internet big data analysis technology. Through in-depth analysis and processing of energy big data, explore the energy conservation potential of enterprises, dynamically allocate energy production, transmission and consumption, and improve the efficiency of the entire energy industry and energy use efficiency.

The results are applicable to manufacturing enterprises of all sizes and production characteristics.

3. Expected cooperation methods and investment

Adopt industry-university-research cooperation method.