CN-122022843-A - Energy-saving carbon reduction intelligent management system

Abstract

The invention relates to the technical field of energy conservation and carbon reduction, and discloses an energy conservation and carbon reduction intelligent management method which is characterized by comprising the steps of obtaining real-time operation data of each process node of an industrial production line, wherein the real-time operation data at least comprises energy consumption data, material flow data and equipment state parameters. According to the method, the carbon flow network model is built, the carbon intensity of each process node is defined as a dynamic state variable, and the carbon intensity transfer relation among the process nodes is built, so that quantitative tracking of the dynamic flow and accumulation processes of carbon emission along a production line is realized, the problem that the specific distribution of carbon emission in a production chain cannot be positioned due to the fact that the energy consumption of a terminal is only monitored in the prior art is solved, and a real-time data basis is provided for refined carbon footprint accounting.

Inventors

• SHAO YUANYUAN

Assignees

• 宁波煜燊科技有限公司

Dates

Publication Date

20260512

Application Date

20260130

Claims (6)

1. 1. The intelligent management method for energy conservation and carbon reduction is characterized by comprising the steps of obtaining real-time operation data of each process node of an industrial production line, wherein the real-time operation data at least comprises energy consumption data, material flow data and equipment state parameters; Based on the real-time operation data, constructing and updating a carbon flow network model, wherein the carbon flow network model defines the carbon intensity of each process node as a state variable, and establishes a carbon intensity transfer relation among the process nodes; Calculating the responsible carbon emission of each process node based on the carbon flow network model, and dynamically distributing carbon budget for each process node according to the total carbon emission target; And sending the process parameter set values to corresponding process nodes, and driving an executing mechanism to adjust.
2. 2. The method of claim 1, wherein the updating of the carbon flow network model further comprises: constructing a physical information neural network model for each process node; The physical information neural network model takes a controllable set value, upstream carbon intensity, environmental parameters and equipment state characteristics of a process node as input, and predicts direct carbon emission, product output rate and output carbon intensity of the process node as output; And adding a physical constraint loss term derived from a carbon intensity transfer equation of the carbon flow network model into a training loss function of the physical information neural network model.
3. 3. The method as recited in claim 2, further comprising: Establishing a reduced order model based on a first sex principle for key high-energy-consumption equipment in a production line; And taking the equipment efficiency characteristic output by the reduced order model as one of the input characteristics of the physical information neural network model of the corresponding process node.
4. 4. The method of claim 3, further comprising, after issuing the process parameter set point to the corresponding process node: And locally taking the received technological parameter set value as a tracking target at each process node, executing model prediction control based on a local prediction model of the process node, and generating and executing a control instruction for an executing mechanism.
5. 5. The method of claim 4, further comprising, prior to acquiring the real-time operational data: Dividing the continuous production process into a plurality of process nodes according to the production process flow and the material flow direction; assigning a unique node identifier to each process node; And configuring a data acquisition point, a data processing unit and a control loop corresponding to each process node according to the node identifier.
6. 6. An energy-saving and carbon-reduction intelligent management system, characterized by being used for realizing the method of any one of claims 1-5, comprising: The data acquisition layer (100) comprises a sensor network (101), an intelligent instrument (102) and a material metering device (103) and is used for acquiring real-time operation data of each process node of the industrial production line; The edge computing layer (200) comprises a plurality of edge computing nodes (201), each edge computing node corresponds to one process node and is used for preprocessing the real-time operation data and operating a process-level local prediction model and a control algorithm; A central server layer (300) comprising a model server (301) for storing and updating a carbon flow network model, an optimization server (302) for performing the dynamic allocation of carbon budgets and solving global optimization problems as claimed in claim 1, and a database (303) for storing data and model parameters; a control execution layer (400) comprising a distributed controller (401) and an actuator (402) for receiving control instructions and driving field devices; and the communication network (500) is connected with the data acquisition layer, the edge calculation layer, the central server layer and the control execution layer and is used for transmitting data and control instructions.

Description

Energy-saving carbon reduction intelligent management system Technical Field The invention relates to the technical field of energy conservation and carbon reduction, in particular to an energy conservation and carbon reduction intelligent management system. Background Under the guidance of a double-carbon target, the industrial field is used as a core source of carbon emission, and an accurate and efficient energy-saving carbon reduction management system is required to be constructed so as to realize the monitoring, traceability and regulation of carbon emission. The carbon management technology in the current industrial production process is mostly focused on the acquisition and statistics of terminal energy consumption data, and the total carbon emission is converted by metering the consumption of the total electric energy, the fuel gas and the like of the production line and combining the fixed emission factors, so that the macroscopic control of the whole carbon emission level is realized. However, the prior art has obvious limitations that an industrial production line usually comprises a plurality of process nodes connected in series or in parallel, the material consumption, the energy utilization efficiency and the carbon emission characteristics of each process are obviously different, and the traditional management mode can only acquire terminal summarized data, can not track the dynamic flowing and accumulating process of carbon emission along a production chain, and is difficult to position the distribution condition of the carbon emission on specific processes and equipment. The black box type management mode causes that enterprises cannot accurately identify high-carbon emission links, a targeted energy-saving carbon reduction optimization strategy is difficult to formulate, and fine and real-time data support cannot be provided for full life cycle carbon footprint accounting of products, so that industrial carbon management is restricted from macroscopic control to accurate and intelligent upgrading. In order to solve the technical bottleneck, a smart management technology capable of quantitatively tracking the carbon emission distribution of the whole production process is needed, carbon emission association among process nodes is opened through constructing a refined carbon flow control model, accurate depiction of the dynamic change process of carbon emission in a production chain is realized, and core support is provided for refined carbon management and carbon footprint accounting of industrial enterprises. Disclosure of Invention The invention aims to solve the technical problem of providing an energy-saving carbon reduction intelligent management system aiming at the defects in the prior art. In order to solve the technical problems, the invention adopts the following technical scheme: The intelligent management method for energy conservation and carbon reduction is characterized by comprising the steps of obtaining real-time operation data of each process node of an industrial production line, wherein the real-time operation data at least comprises energy consumption data, material flow data and equipment state parameters; Based on the real-time operation data, constructing and updating a carbon flow network model, wherein the carbon flow network model defines the carbon intensity of each process node as a state variable, and establishes a carbon intensity transfer relation among the process nodes; Calculating the responsible carbon emission of each process node based on the carbon flow network model, and dynamically distributing carbon budget for each process node according to the total carbon emission target; And sending the process parameter set values to corresponding process nodes, and driving an executing mechanism to adjust. Preferably, the updating of the carbon flow network model further includes: constructing a physical information neural network model for each process node; The physical information neural network model takes a controllable set value, upstream carbon intensity, environmental parameters and equipment state characteristics of a process node as input, and predicts direct carbon emission, product output rate and output carbon intensity of the process node as output; And adding a physical constraint loss term derived from a carbon intensity transfer equation of the carbon flow network model into a training loss function of the physical information neural network model. Preferably, before acquiring the real-time operation data, the method further comprises: Establishing a reduced order model based on a first sex principle for key high-energy-consumption equipment in a production line; And taking the equipment efficiency characteristic output by the reduced order model as one of the input characteristics of the physical information neural network model of the corresponding process node. Preferably, after the process parameter set value is issued to the correspondi