An industrial energy consumption deployment method and device based on identification resolution and a medium

Abstract

The application discloses an industrial energy consumption deployment method and device based on identification analysis, and a medium. The method comprises the following steps: determining an enterprise corresponding to a product according to identification information; acquiring energy data of the product according to an energy project of the enterprise through a plurality of edge devices, classifying the energy data in a grid according to an energy type, determining a grid energy consumption condition of the product according to the grid classified energy data, and determining energy consumption identification information of the product according to the grid energy consumption condition; determining an energy management and control scheme of the product according to the grid energy consumption condition through a cloud, determining management and control identification information of the product according to the energy management and control scheme; training a regression model according to the energy management and control scheme and the grid energy consumption condition, optimizing the energy project through the trained regression model to obtain optimization identification information; dynamically generating an energy consumption deployment identification code of the product, and determining an identification code of the product according to the energy consumption deployment identification code and the identification information.

Description

Technical Field

[0001] This application relates to the field of industrial internet technology, and in particular to an industrial energy consumption allocation method, equipment and medium based on identifier resolution. Background Technology

[0002] Under the impetus of the new infrastructure initiative, the development of the Industrial Internet has entered a fast track. The Industrial Internet comprehensively builds interconnectivity among people, machines, and things, supports the connection of information across all elements, the entire industrial chain, and the entire value chain of industrial manufacturing, greatly improves energy efficiency management in production, reduces resource consumption, and has become a new option to support low-carbon development.

[0003] Nowadays, factories and enterprises often lack the ability to manage comprehensive energy consumption during product production. They struggle to conduct detailed energy consumption management for various energy sources, such as water, electricity, heat, gas, personnel, equipment wear and tear, and comprehensive energy management. This can easily lead to varying degrees of economic losses, and in more serious cases, it can even endanger personal safety. Summary of the Invention

[0004] To address the aforementioned issues, this application proposes an industrial energy consumption allocation method based on identifier resolution, comprising: acquiring product identifier information; determining the enterprise corresponding to the product based on the identifier information; acquiring energy data of the product through multiple edge devices according to the energy projects of the enterprise; classifying the energy data into a grid according to energy type; determining the gridded energy consumption status of the product based on the gridded energy data; determining the energy consumption identifier information of the product based on the gridded energy consumption status, wherein the gridded energy consumption status includes active power and reactive power; uploading the gridded energy consumption status to the cloud; and using the cloud to allocate energy according to the identifier information... The energy management scheme for the product is determined based on the gridded energy consumption situation, and the management identification information of the product is determined based on the energy management scheme. A regression model is established through the edge device, and the regression model is trained according to the energy management scheme and the gridded energy consumption situation to optimize the energy project and obtain optimization data. The optimization identification information of the product is determined based on the optimization data. The energy allocation identification code of the product is dynamically generated based on the energy consumption identification information, the management identification information, and the optimization identification information, and the identification code of the product is determined based on the energy allocation identification code and the identification information.

[0005] In one example, the energy project is optimized using the trained regression model. Specifically, this includes: monitoring the energy power of the energy project, inputting the energy power into the regression model for calculation to obtain regression results, and automatically reducing some engineering equipment in the energy project based on the regression results to optimize the energy project.

[0006] In one example, a regression model is established using the edge device, and the regression model is trained based on the energy management scheme and the gridded energy consumption. Specifically, this includes: selecting the edge device with the highest correlation to the energy power according to the energy management scheme, and determining the energy change characteristics of the energy project based on the edge device; establishing a neural network model, and inputting the energy change characteristics and the energy power into the neural network model for model training to obtain the regression model.

[0007] In one example, the energy change characteristics and energy power are input into the neural network model for model training. Specifically, this includes: establishing a sliding window model; monitoring the energy project in real time through the sliding window model to obtain a training set for the neural network model; determining the training status of the neural network through the sliding window model to obtain a training completion signal for the neural network; and deleting the historical model training set from the model training set based on the training completion signal.

[0008] In one example, the method further includes: determining the mapping relationship between the energy project and process indicators according to the energy management scheme; dividing the regression model into optimization modules according to the mapping relationship; determining the constraints of the energy project, wherein the constraints include production conditions, product quality, and operational restrictions; and optimizing the energy project through the optimization modules according to the constraints to reduce the calculation process of the regression model.

[0009] In one example, before optimizing the energy project according to the constraints using the optimization module to reduce the extrapolation process of the regression model, the method further includes: obtaining the gridded energy consumption situation for different energy consumption standards through the regression model, wherein the gridded energy consumption situation includes high energy consumption, low energy consumption, and effective energy consumption; and optimizing and training the regression model using the gridded energy consumption situation to update the optimization module.

[0010] In one example, the energy data is classified into grids according to energy type, specifically including: determining the working level and energy type of the energy project, and classifying the energy project first according to the working level and energy type; determining the stage time of the energy project, and classifying the energy project second according to the stage time.

[0011] In one example, the method further includes: determining an energy project park map of the enterprise; determining the corresponding node position of the energy project in the energy project park map based on the identification information; and marking the relevant gridded energy consumption at the node position; determining the power threshold of the energy project based on the optimization data; comparing the energy power with the power threshold; if the energy power is greater than the power threshold, then performing engineering trimming on the edge device corresponding to the energy power, and issuing an alarm at the corresponding node position in the energy project park map.

[0012] On the other hand, this application also proposes an industrial energy allocation device based on identifier resolution, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the industrial energy allocation device based on identifier resolution to perform: the method as described in any of the above examples.

[0013] On the other hand, this application also proposes a non-volatile computer storage medium storing computer-executable instructions, characterized in that the computer-executable instructions are configured as described in any of the above examples.

[0014] By constructing a grid-based segmentation method and system for enterprise comprehensive energy consumption based on industrial internet identifier resolution, this system uses an identifier-based comprehensive grid-based segmentation method to manage the energy consumption of products throughout the entire product production process, including various energy sources such as water, electricity, heat, gas, personnel, equipment losses, and comprehensive management energy consumption. The system also implements grid-based node segmentation, energy consumption statistics, energy metering, product unit consumption statistics, and overall energy consumption balance management, ultimately reducing the enterprise's product unit consumption. Furthermore, the cumulative amount of the enterprise's total unit consumption over a period of time can correspond to the total energy consumption, which is conducive to energy consumption reform and exploring the level of process energy saving. Attached Figure Description

[0015] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0016] Figure 1 This is a flowchart illustrating an industrial energy consumption allocation method based on identifier resolution in an embodiment of this application.

[0017] Figure 2 This is a schematic diagram of an industrial energy allocation device based on identifier resolution in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0020] like Figure 1 As shown in the embodiment of this application, an industrial energy consumption allocation method based on identifier resolution is provided and applied in an energy consumption gridding system based on the Industrial Internet. This energy consumption gridding system includes multiple edge devices and a cloud, comprising:

[0021] S101: Obtain the product's identification information and determine the enterprise corresponding to the product based on the identification information.

[0022] The core of the Industrial Internet Identifier Resolution System includes the identifier code, which can be a QR code, barcode, etc., and acts as an "ID card" for machines and products. This identifier code records specific product information, such as identification information, which serves as the product's identity information, including product type, production information, etc. Based on this identification information, the corresponding enterprise can be identified.

[0023] S102: The energy data of the product is obtained by multiple edge devices according to the energy project of the enterprise. The energy data is classified into grids according to the energy type. The grid-based energy consumption of the product is determined according to the grid-based energy data. The energy consumption identification information of the product is determined according to the grid-based energy consumption. The grid-based energy consumption includes active power and reactive power.

[0024] Energy management is a typical application scenario for enterprise big data. Industrial Internet-based energy management can, to some extent, solve the problem of energy waste in the production process, making energy management more transparent and achieving energy conservation and efficient utilization. An industrial Internet-based energy grid-based system connects to industrial equipment via cloud gateways and edge devices. The data, after calibration and cleaning, is uploaded to the cloud. Monitoring data for each piece of industrial equipment requires setting up multiple edge devices on its production line. These edge devices collect data on the enterprise's industrial energy situation to display the enterprise's energy application and management projects. For example, different edge devices can monitor different types of industrial energy, including water, electricity, heat, and gas. These energy projects are then grid-classified according to energy type, dividing the energy input for product production in a specific industrial segment into a "grid" to accurately locate the corresponding energy information and analyze energy consumption. The energy consumption of the energy project is determined based on the energy type. Taking electricity as an example, this energy consumption includes active power and reactive power. Active power is the power required to ensure the normal operation and production of the equipment, while reactive power is the power that does not require the equipment to perform work and is not actually consumed, but its existence increases electricity costs and raises the company's production costs. This energy consumption data is then uploaded to the cloud.

[0025] S103: Upload the gridded energy consumption data to the cloud, determine the energy management scheme for the product based on the gridded energy consumption data through the cloud, and determine the management identification information for the product based on the energy management scheme.

[0026] Energy-related management and control schemes are stored in the cloud. A corresponding grid-based management and control scheme for a specific energy project is found in the cloud to optimize its energy consumption. When edge devices retrieve relevant grid-based management and control schemes from the cloud, the cloud determines the corresponding scheme based on the energy type and sends it to the relevant edge device. For example, the cloud determines a grid-based management and control scheme for electricity, finds the corresponding edge device, and sends the scheme to that device.

[0027] S104: Establish a regression model through the edge device, train the regression model according to the energy management scheme and the gridded energy consumption, optimize the energy project through the trained regression model, obtain optimization data, and determine the optimization identification information of the product based on the optimization data.

[0028] To address the issue of high energy consumption and low productivity in energy projects, a regression model is established for the project using edge devices. This model is then trained based on a grid-based management scheme and energy consumption data. This enables the regression model to intelligently search and aggregate data within the existing grid-based management scheme based on energy consumption, thereby optimizing the energy project and reducing energy waste.

[0029] S105: Dynamically generate the energy consumption allocation identification code of the product based on the energy consumption identification information, the control identification information and the optimization identification information, and determine the identification code of the product based on the energy consumption allocation identification code and the identification information.

[0030] The energy consumption labeling information, control labeling information, and optimization labeling information obtained in the above process are planned to generate an energy consumption allocation labeling code for the product. This energy consumption allocation labeling code can be updated according to changes in the above three labeling information, thus obtaining a dynamic energy consumption allocation labeling code. Then, based on the energy consumption allocation labeling code and the labeling information, the final product labeling code is obtained. By parsing this labeling code, the product's energy information can be obtained.

[0031] In one embodiment, after the regression model is trained, the edge device monitors the energy power of the energy project and inputs the energy power into the regression model to obtain the regression result. Based on this regression result, the edge device improves the energy project by reducing or eliminating equipment that generates reactive power for extended periods. This can be done by reducing the operating time or energy consumption of such equipment, or even shutting it down. The edge device uploads the reduction process and results to the cloud for project record keeping.

[0032] In one embodiment, different edge devices monitor different types of data for energy projects. For example, some edge devices monitor the energy security of the energy source, while others monitor its energy output. Based on the grid-based management scheme, the edge device with the highest correlation to energy output is selected. Then, using the least squares feature selection method, the energy change characteristics of the energy project are determined to reduce the learning difficulty. A TS neural network model is established, and the energy change characteristics and energy output are input into this model for training to obtain a regression model.

[0033] In one embodiment, a sliding window model is established to sequentially organize the monitored energy conditions, obtaining energy power at different times as the training set for the neural network model. The sliding window model is used to determine the training state of the neural network, obtaining a training completion signal. Based on the training completion signal, the historical model training set is deleted from the model training set.

[0034] In one embodiment, a mapping relationship between energy projects and process indicators is determined based on a grid-based management and control scheme. Based on this mapping relationship, an optimization module is created from the regression model to optimize the energy consumption of the engineering equipment before any reductions are made. Constraints on the energy project are determined, including production conditions, product quality, and operational limitations. Based on these constraints, the optimization module performs energy optimization on the energy project, reducing the computational complexity of the regression model. For example, under the pre-existing constraints of ensuring safe and orderly production conditions and qualified product quality, energy optimization of the engineering equipment can be performed first, simply by reducing the reactive power of the equipment.

[0035] In one embodiment, energy consumption data under different energy consumption standards is acquired. These energy consumption data include high energy consumption, low energy consumption, and effective energy consumption. The energy consumption standard serves as a critical threshold for optimizing the project. For example, for energy projects that are inherently high-energy-consuming, energy consumption data and their respective energy consumption standards from multiple high-energy-consuming projects are collected. The collected energy consumption data is then used to optimize and train the regression model, improving the accuracy of the regression module's judgment on the optimization threshold, and subsequently updating the optimization module.

[0036] In one embodiment, to address the high complexity and low information sharing of industrial equipment energy consumption information management, a two-row grid-based approach is used to divide energy projects. Based on industry information, the work level and energy type of the energy project are determined, and the energy project is first classified according to these factors. The work level includes at least workshop work, equipment work, and daily work; the energy type includes at least water, electricity, heat, and gas. After the first classification, the time period of the energy project is determined based on industry information, and the energy project is secondly classified according to this time period. The time period is divided into years, months, and days. This two-row grid-based approach allows for accurate monitoring and optimization of a specific energy source within a specific workshop during a specific time period.

[0037] In one embodiment, an energy project park map for the enterprise is established using edge device information collected from the cloud. Based on industry information, the corresponding node positions of energy projects within the energy project park map are determined, and relevant energy consumption information is marked at each node. For example, if a node in the map represents a piece of engineering equipment, an indicator light at that node will illuminate green when the equipment is generating active power and red when it is generating reactive power. A power threshold for the energy project is determined based on a reduction report, and the energy power is compared to the power threshold. If the energy power exceeds the power threshold, a reduction instruction is sent to the edge device corresponding to the energy power, causing the edge device to automatically reduce the amount of engineering equipment in the energy project according to the reduction instruction, and an alarm is triggered at the corresponding node position on the energy project park map.

[0038] In one embodiment, when it is confirmed that a piece of engineering equipment is performing reactive power operation for an extended period, the cause may be related to unreasonable project settings or quality issues with the equipment itself. The work log of the engineering equipment is reviewed to determine its remaining service life. Based on the remaining service life and regression results, the engineering tasks for the equipment are determined, and the equipment is then subject to project reduction based on these tasks. For example, if regression results indicate that a piece of engineering equipment is performing reactive power operation for too long, before reducing its workload, the remaining service life is used to determine the equipment's workload. If the workload is set too high, it is reduced accordingly. However, the workload cannot fall below a pre-set threshold. If it falls below the threshold, the equipment is considered unusable and is shut down to complete the project reduction.

[0039] like Figure 2 As shown in the illustration, this application also provides an industrial energy allocation device based on identifier resolution, comprising:

[0040] At least one processor; and,

[0041] A memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores instructions that can be executed by the at least one processor to enable the identifier-based industrial energy allocation device to perform the method described in any of the above embodiments.

[0043] This application also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as described in any of the above embodiments.

[0044] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0045] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0046] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0047] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0048] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0049] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0050] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0051] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0052] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0053] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0054] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An industrial energy consumption allocation method based on identifier resolution, characterized in that, include: Obtain the product's identification information, and determine the enterprise corresponding to the product based on the identification information; The energy data of the product is obtained by multiple edge devices according to the energy project of the enterprise. The energy data is classified into grids according to the energy type. The grid-based energy consumption of the product is determined based on the grid-based energy data. The energy consumption identification information of the product is determined based on the grid-based energy consumption. The grid-based energy consumption includes active power and reactive power. The gridded energy consumption data is uploaded to the cloud, and the cloud determines the energy management plan for the product based on the gridded energy consumption data. The energy management plan is then used to determine the management identification information for the product. A regression model is established through the edge device. The regression model is trained according to the energy management scheme and the gridded energy consumption. The trained regression model is used to optimize the energy project, obtain optimization data, and determine the optimization identification information of the product based on the optimization data. The energy consumption allocation identification code of the product is dynamically generated based on the energy consumption identification information, the control identification information, and the optimization identification information, and the identification code of the product is determined based on the energy consumption allocation identification code and the identification information. The energy project is optimized using the trained regression model, specifically including: The energy power of the energy project is monitored, and the energy power is input into the regression model for calculation to obtain the regression result. Based on the regression result, some engineering equipment of the energy project is automatically reduced to optimize the energy of the energy project. A regression model is established through the edge device, and the model is trained based on the energy management scheme and the gridded energy consumption. Specifically, this includes: Based on the energy management scheme, the edge device with the highest correlation to the energy power is selected, and the energy change characteristics of the energy project are determined based on the edge device; A neural network model is established, and the energy change characteristics and energy power are input into the neural network model for model training to obtain the regression model; The energy consumption labeling information, control labeling information, and optimization labeling information are planned to generate an energy consumption allocation labeling code for the product. The energy consumption allocation labeling code is updated according to changes in the energy consumption labeling information, control labeling information, and optimization labeling information to obtain a dynamic energy consumption allocation labeling code. Based on the dynamic energy consumption allocation labeling code and the labeling information, a product identification code is obtained. The energy information of the product is obtained by parsing the product identification code.

2. The method according to claim 1, characterized in that, The energy change characteristics and energy power are input into the neural network model for model training, specifically including: A sliding window model is established to monitor the energy project in real time, thereby obtaining a training set for the neural network model. The training state of the neural network is determined by the sliding window model to obtain a training completion signal for the neural network, and the historical model training set is deleted from the model training set based on the training completion signal.

3. The method according to claim 1, characterized in that, The method further includes: The mapping relationship between the energy project and the process indicators is determined according to the energy management plan, and the regression model is divided into optimization modules according to the mapping relationship. The constraints of the energy project are determined, including production conditions, product quality, and operational limitations. Based on the constraints, the energy project is optimized using the optimization module to reduce the calculation process of the regression model.

4. The method according to claim 3, characterized in that, The method further includes optimizing the energy project according to the constraints using the optimization module to reduce the time required for the regression model calculation process. The gridded energy consumption situation under different energy consumption standards is obtained through the regression model, wherein the gridded energy consumption situation includes high energy consumption, low energy consumption, and effective energy consumption. The regression model is optimized and trained based on the gridded energy consumption data in order to update the optimization module.

5. The method according to claim 1, characterized in that, The energy data is categorized into grids based on energy type, specifically including: The working level and energy type of the energy project are determined, and the energy project is classified for the first time according to the working level and energy type; The phase time of the energy project is determined, and the energy project is classified a second time according to the phase time.

6. The method according to claim 1, characterized in that, The method further includes: Determine the energy project park map of the enterprise, determine the corresponding node position of the energy project in the energy project park map according to the identification information, and mark the relevant gridded energy consumption at the node position; The power threshold of the energy project is determined based on the optimized data, and the energy power is compared with the power threshold. If the energy power is greater than the power threshold, the edge device corresponding to the energy power will be engineered and an alarm will be triggered at the corresponding node location in the energy project park map.

7. An industrial energy allocation device based on identifier resolution, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the identifier-based industrial energy allocation device to perform the method described in any one of claims 1-6.

8. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are configured to be the method as described in any one of claims 1-6.

Images