Factory energy linkage control method and system based on AI algorithm model
Through the factory energy linkage control method based on the AI algorithm model, a linkage scheduling strategy for energy-using equipment is established, which solves the problem of data linkage of energy-using equipment in the factory, improves energy utilization rate and reduces the energy consumption of a single product.
Patent Information
- Application Number
- CN202410548629.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-06
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Due to the discrete nature of energy-using equipment, existing factories cannot establish a linkage relationship with the secondary energy generation data, and cannot effectively guide the management of energy-using equipment, resulting in difficulty in rationalizing energy scheduling, high energy consumption for a single product and low energy utilization rate.
Using the factory energy linkage control method based on AI algorithm model, by collecting the energy usage historical data of energy consumption equipment and the energy flow historical data, establishing a mathematical model of artificial intelligence algorithms, generating the optimal linkage scheduling strategy, and implementing multiple sets of applications through PLC programming. Centralized linkage control of energy equipment, and data summary and strategy issuance using DCS software and energy control platform.
It realizes data linkage control of various energy-using equipment in the factory, improves the overall energy utilization rate, and reduces the energy consumption of producing a single product. It is suitable for most conventional factories.
Smart Images

Figure CN118915500A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of AI algorithm industrial control and relates to a factory energy linkage control method and system based on an AI algorithm model. Background Art
[0002] With the development and progress of industrial technology, factories are no longer just pursuing production volume. The goals of factory operation management include improving energy utilization, reducing energy consumption of individual product production, improving capacity utilization, reducing production costs, optimizing production planning and scheduling, improving product quality and ensuring operational safety. In order to achieve these goals, factory operation management needs to adopt a series of management strategies, technical tools and methods. In terms of improving energy utilization and reducing energy consumption of individual product production, some existing factories are lagging behind in management due to the discreteness of energy-consuming equipment. The energy usage data in the real-time production process cannot be linked with the secondary energy generation data, and the management of energy-consuming equipment cannot be effectively guided. It is impossible to solve the high energy consumption and low energy utilization rate of individual products caused by the rational scheduling of energy in the production process.
[0003] Therefore, there is an urgent need for a method and system that can control the linkage of multiple discrete energy-consuming devices in a factory, which can control the data of these energy-consuming devices in a linkage manner, improve the energy utilization rate of the entire factory, and reduce the energy consumption of producing a single product. Summary of the invention
[0004] The purpose of the present invention is to provide a factory energy linkage control method and system based on an AI algorithm model, which solves the problem of data linkage control of various energy-consuming equipment in the factory, improves the energy utilization rate of the entire factory, and reduces the energy consumption of producing a single product.
[0005] The technical solution adopted by the present invention is as follows:
[0006] A factory energy linkage control method based on an AI algorithm model establishes an artificial intelligence algorithm mathematical model based on the collected energy usage history data and energy flow history data of each energy-consuming equipment in the auxiliary workshop, obtains the optimal linkage scheduling strategy for the energy-consuming equipment, and sends it to the DCS software of the linkage control cabinet. The energy-consuming equipment in the combined auxiliary workshop is scheduled according to the optimal linkage scheduling strategy.
[0007] In order to better implement the present solution, further, the artificial intelligence algorithm mathematical model is generated based on a model in a model library including at least a linear regression model, a neural network model, a vector machine model or a random forest model.
[0008] In order to better implement this solution, further, according to the historical energy usage data and energy flow data of each energy-consuming equipment, after each model in the model library generates a model, one of the models in the model library is selected as the mathematical model of the artificial intelligence algorithm based on the errors between the data of each energy-consuming equipment predicted in each generated model and the real-time collected data of each energy-consuming equipment.
[0009] In order to better implement this solution, further, the linkage scheduling strategy includes: production strategy of each energy-consuming equipment in the auxiliary workshop, high energy consumption warning, energy consumption optimization suggestion and long-term energy consumption trend analysis.
[0010] A factory energy linkage control system based on an AI algorithm model, based on the aforementioned control method, includes an acquisition hardware module, a linkage control cabinet, a DCS software, and an AI-based energy management and control platform, wherein:
[0011] The acquisition hardware module uses sensors to establish communication with energy-consuming devices to perform real-time data acquisition and control of the energy-consuming devices;
[0012] The linkage control cabinet adopts PLC programming to realize centralized linkage control of multiple groups of energy-consuming equipment;
[0013] The DCS software is used to automatically execute a distributed computer control system of the energy management and control platform;
[0014] The energy management and control platform summarizes the historical data of energy-consuming equipment, establishes an artificial intelligence algorithm mathematical model, generates a linkage scheduling strategy for energy-consuming equipment, and sends it to the DCS software.
[0015] In order to better implement the present solution, further, the artificial intelligence algorithm mathematical model established in the energy management and control platform is generated based on a model in a model library including at least a linear regression model, a neural network model, a vector machine model or a random forest model.
[0016] In order to better implement this solution, further, according to the historical energy usage data and energy flow data of each energy-consuming equipment, after each model in the model library generates a model, one of the models in the model library is selected as the mathematical model of the artificial intelligence algorithm based on the errors between the data of each energy-consuming equipment predicted in each generated model and the real-time collected data of each energy-consuming equipment.
[0017] In order to better implement this solution, further, the linkage scheduling strategy includes: production strategy of each energy-consuming equipment in the auxiliary workshop, high energy consumption warning, energy consumption optimization suggestion and long-term energy consumption trend analysis.
[0018] This solution first collects the energy usage historical data and energy flow historical data of each energy-consuming equipment in each auxiliary workshop of the factory. The historical data here is also the data of several times close to the current time, rather than the relatively long historical data. The energy usage historical data here refers to the energy consumption of each energy-consuming equipment during the collection period; the energy flow here refers to the flow of incoming energy from the production plant to the energy-consuming equipment during the production process. We conduct mathematical modeling for different data of each energy-consuming equipment at different times. Usually, we choose one of the linear regression model, neural network model, vector machine model or random forest model. In order to reduce the error, this solution will conduct mathematical modeling of these four models at the same time, and then compare the real-time energy usage real-time data and energy flow real-time data of each energy-consuming equipment collected in real time with the energy usage prediction data and energy flow prediction data of each energy-consuming equipment predicted by the four models, and finally select the most suitable model according to the error. Here, the energy-consuming equipment of different factories is different, and the error calculation is also different, but it is basically selected from common error calculation mathematical methods, including but not limited to weighted average, variance, standard deviation and other methods.
[0019] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:
[0020] 1. A factory energy linkage control method and system based on AI algorithm model, which establishes different mathematical models according to historical data, and selects the most suitable mathematical model according to real-time data, and then uses PLC programming to realize centralized linkage control of multiple groups of energy-consuming equipment, realizing data linkage control of various energy-consuming equipment in the factory, which can improve the energy utilization rate of the entire factory and reduce the energy consumption of producing a single product;
[0021] 2. A factory energy linkage control method and system based on an AI algorithm model. Different mathematical models are established according to historical data, and the most suitable mathematical model is screened out by real-time data. Then, PLC programming is used to realize centralized linkage control of multiple groups of energy-consuming equipment. It is suitable for most conventional factories and has a wide applicability. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative work, among which:
[0023] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, that is, the embodiments described are only part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.
[0025] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.
[0026] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0027] Below is a combination of the embodiments and the attached Figure 1 The features and properties of the present invention are described in further detail.
[0028] Embodiment 1
[0029] A preferred embodiment of the present invention provides a factory energy linkage control method based on an AI algorithm model, such as Figure 1 According to the collected historical data on energy usage and energy flow of each energy-consuming equipment in the auxiliary workshop, an artificial intelligence algorithm mathematical model is established to obtain the optimal linkage scheduling strategy for energy-consuming equipment, and send it to the DCS software of the linkage control cabinet to schedule and combine various energy-consuming equipment in the auxiliary workshop.
[0030] This solution first collects the historical data on energy usage and energy flow of each energy-consuming equipment in each auxiliary workshop of the factory. The historical data here are also data of times close to the current time, rather than relatively long historical data. The historical data on energy usage here refers to the energy consumption of each energy-consuming equipment during the collection time period; the energy flow here refers to the flow of incoming energy from the production plant to the energy-consuming equipment during the production process. We perform mathematical modeling on the different data of each energy-consuming equipment at different times to obtain the optimal linkage scheduling strategy for the energy-consuming equipment. This strategy is directly sent to the DCS software to schedule the various energy-consuming equipment in the combined auxiliary workshop to achieve the optimal linkage scheduling.
[0031] Embodiment 2
[0032] In this embodiment, based on the first embodiment, the artificial intelligence algorithm mathematical model is generated based on a model in a model library including at least a linear regression model, a neural network model, a vector machine model or a random forest model. After each model in the model library generates a model based on the energy usage history data and energy flow history data of each energy-consuming device, one of the models in the model library is selected as the artificial intelligence algorithm mathematical model based on the error between the data of each energy-consuming device predicted in each generated model and the real-time collected data of each energy-consuming device.
[0033] We choose one of the linear regression model, neural network model, vector machine model or random forest model. In order to reduce the error, this scheme will mathematically model these four models at the same time, and then compare the real-time data of energy usage and energy flow of each energy-consuming equipment collected in real time with the predicted data of energy usage and energy flow of each energy-consuming equipment predicted by the four models, and finally select the most suitable model according to the error. The energy-consuming equipment of different factories is different, and the error calculation is also different, but it is basically selected from common error calculation mathematical methods, including but not limited to weighted average, variance, standard deviation and other methods. Different mathematical models can be selected according to different conditions, and seasonal and conditional selections can be made to ensure that the mathematical model we implement is the best under the current environment.
[0034] The following is a brief description of the four models: linear regression model, neural network model, vector machine model and random forest model:
[0035] 1. Linear regression model
[0036] The linear regression model is used to describe the linear relationship between energy consumption and a set of independent variables (such as production volume, equipment operating time, ambient temperature, etc.). The formula of the linear regression model is as follows:
[0037] E=β0+β1*P+β2*S+β3*T+ε
[0038] Where: E represents energy consumption, P represents output, S represents equipment status (such as switch status, load, etc.), T represents ambient temperature, β0, β1, β2, β3 are regression coefficients, and ε is the error term.
[0039] 2. Neural network model:
[0040] For complex nonlinear relationships, a neural network model can be used. Neural networks learn and approximate complex functional relationships by simulating the connection mode of human brain neurons. Its internal structure and parameters are determined by training data.
[0041] 3. Support Vector Machine (SVM):
[0042] SVM is a classification and regression method that segments data by finding a hyperplane in a high-dimensional space. In energy consumption prediction, SVM can be used to predict the category or specific value of energy consumption.
[0043] 4. Random Forest
[0044] Random forest is an ensemble learning method based on decision trees. It improves prediction accuracy by building multiple decision trees and integrating their prediction results. In energy consumption prediction, random forest can handle multiple types of independent variables and automatically select important features.
[0045] Embodiment 3
[0046] This embodiment is a further supplementary explanation of the second embodiment, and the linkage scheduling strategy includes: production strategy of each energy-consuming equipment in the auxiliary workshop, high energy consumption warning, energy consumption optimization suggestion and long-term energy consumption trend analysis.
[0047] The production strategies of the energy-consuming equipment described here are collectively the optimal linkage scheduling strategy for the overall energy-consuming equipment, which refers to the combination of switch states or equipment parameter adjustment combinations of each energy-consuming equipment.
[0048] High energy consumption warning means that when the model predicts that the energy consumption of a certain period of time or a certain production link will exceed the preset threshold, the system should issue a high energy consumption warning. At this time, the following strategies can be adopted:
[0049] Optimize production processes and reduce unnecessary energy consumption;
[0050] Adjust equipment operating parameters to reduce energy consumption;
[0051] Consider adopting more energy-efficient equipment or technology.
[0052] Energy consumption optimization suggestions:
[0053] The model can analyze the energy consumption differences under different production conditions based on historical data and real-time data, and give optimization suggestions. For example:
[0054] When production is low, some equipment can be shut down to save energy;
[0055] Adjust the operation strategy of the cooling or heating system according to the ambient temperature and equipment temperature.
[0056] Long-term energy consumption trend analysis:
[0057] By analyzing long-term energy consumption data, the model can reveal seasonal and cyclical changes in energy consumption as well as long-term trends. This helps companies develop long-term optimal linkage scheduling strategies for overall energy-consuming equipment, such as:
[0058] Adjust production plans according to seasonal changes to reduce energy costs;
[0059] Develop a long-term equipment renewal or upgrade plan and gradually phase out high-energy-consuming equipment.
[0060] Embodiment 4
[0061] A preferred embodiment of the present invention provides a factory energy linkage control system based on an AI algorithm model, based on the aforementioned control method, including an acquisition hardware module, a linkage control cabinet, a DCS software and an AI-based energy management and control platform, wherein:
[0062] The acquisition hardware module uses sensors to establish communication with energy-consuming devices to perform real-time data acquisition and control of the energy-consuming devices;
[0063] The linkage control cabinet adopts PLC programming to realize centralized linkage control of multiple groups of energy-consuming equipment;
[0064] The DCS software is used to automatically execute a distributed computer control system of the energy management and control platform;
[0065] The energy management and control platform summarizes the historical data of energy-consuming equipment, establishes an artificial intelligence algorithm mathematical model, generates a linkage scheduling strategy for energy-consuming equipment, and sends it to the DCS software.
[0066] The acquisition hardware module described in this solution collects various data of energy-consuming equipment to obtain a series of data including at least the working power of the energy-consuming equipment. The energy management and control platform then receives these data and establishes an artificial intelligence algorithm mathematical model based on them to generate a linkage scheduling strategy for different energy-consuming equipment. The strategy is then sent to the DCS software in the linkage control cabinet, and the DCS software generates a control electrical signal that is then controlled by the linkage control cabinet.
[0067] Embodiment 5
[0068] In this embodiment, based on the fourth embodiment, the artificial intelligence algorithm mathematical model established in the energy management and control platform is generated based on a model in a model library including at least a linear regression model, a neural network model, a vector machine model or a random forest model. According to the energy usage history data and energy flow history data of each energy-consuming device, after each model in the model library generates a model, one of the models in the model library is selected as the artificial intelligence algorithm mathematical model based on the error between the data of each energy-consuming device predicted in each generated model and the real-time collected data of each energy-consuming device.
[0069] Embodiment 6
[0070] This embodiment is a further supplementary explanation of the fifth embodiment, and the linkage scheduling strategy includes: production strategy of each energy-consuming equipment in the auxiliary workshop, high energy consumption warning, energy consumption optimization suggestion and long-term energy consumption trend analysis.
[0071] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions and improvements made by any technician familiar with the field within the spirit and principle of the present invention should be included in the scope of protection of the present invention.
Claims
1. A factory energy linkage control method based on an AI algorithm model, characterized by: Based on the collected historical data on energy usage and energy flow of each energy-consuming equipment, an artificial intelligence algorithm mathematical model is established to obtain the optimal linkage scheduling strategy for the energy-consuming equipment, and the energy-consuming equipment is scheduled and combined according to the optimal linkage scheduling strategy.
2. According to claim 1, a factory energy linkage control method based on an AI algorithm model is characterized in that: The artificial intelligence algorithm mathematical model is generated based on a model in a model library including at least a linear regression model, a neural network model, a vector machine model or a random forest model.
3. The factory energy linkage control method based on the AI algorithm model according to claim 2 is characterized by: According to the historical data of energy usage and energy flow of each energy-consuming equipment, after each model in the model library generates a model, one of the models in the model library is selected as the mathematical model of the artificial intelligence algorithm based on the errors between the data of each energy-consuming equipment predicted in each generated model and the real-time collected data of each energy-consuming equipment.
4. The method for controlling factory energy linkage based on AI algorithm model according to claim 1 is characterized in that: The linkage scheduling strategy includes: production strategy for each energy-consuming equipment in the auxiliary workshop, high energy consumption warning, energy consumption optimization suggestions and long-term energy consumption trend analysis.
5. A factory energy linkage control system based on an AI algorithm model, based on the control method of claim 1, characterized in that: It includes acquisition hardware modules, linkage control cabinets, DCS software and energy management and control platforms, among which: The acquisition hardware module establishes communication with the energy-consuming device to perform real-time data acquisition and control on the energy-consuming device; The linkage control cabinet centrally controls multiple groups of energy-consuming equipment; The DCS software executes the distributed computer control system of the energy management and control platform; The energy management and control platform summarizes the historical data of energy-consuming equipment, establishes an artificial intelligence algorithm mathematical model, generates a linkage scheduling strategy for energy-consuming equipment, and sends it to the DCS software.
6. The factory energy linkage control system based on the AI algorithm model according to claim 5 is characterized by: The artificial intelligence algorithm mathematical model established in the energy management and control platform is generated based on a model in a model library that includes at least a linear regression model, a neural network model, a vector machine model or a random forest model.
7. The factory energy linkage control system based on the AI algorithm model according to claim 6 is characterized by: According to the historical data of energy usage and energy flow of each energy-consuming equipment, after each model in the model library generates a model, one of the models in the model library is selected as the mathematical model of the artificial intelligence algorithm based on the errors between the data of each energy-consuming equipment predicted in each generated model and the real-time collected data of each energy-consuming equipment.
8. The plant energy linkage control system based on the AI algorithm model according to claim 5 is characterized in that: The linkage scheduling strategy includes: production strategy for each energy-consuming equipment in the auxiliary workshop, high energy consumption warning, energy consumption optimization suggestions and long-term energy consumption trend analysis.
