Energy-saving and carbon-reduction control method and integrated management platform based on AI intelligent assistance

Abstract

The present application discloses an energy-saving and carbon-reduction control method and an integrated management platform based on AI intelligent assistance, the method comprising: obtaining the energy-saving data of each device in real time, and calculating the carbon emissions of each device according to each energy-saving data; obtaining the carbon emission plan and the characteristic curve of each device to determine the optimal carbon emissions of the target factory; determining the target power distribution plan of each device in the target factory in a preset time period in the future according to the optimal carbon emissions; receiving the plan execution data of each device, and calculating the actual carbon emissions and actual carbon savings of each device according to the plan execution data and the carbon emissions of each device; adding the attributes of the data object of each device in the data twin model of the target factory according to each device ID and the corresponding actual carbon emissions and actual carbon savings, so as to display the actual carbon savings and actual carbon emissions of each device in the target factory in real time through the data objects in the data twin model in the data twin module.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of energy-saving control technology, and in particular to an energy-saving and carbon-reduction control method and an integrated management platform based on AI intelligent assistance. Background Art

[0002] With the rapid development of global industrialization, as one of the main sources of energy consumption and carbon emissions, factories are increasingly concerned about energy conservation and carbon reduction. Motors and inverters are widely used power equipment in factories, and their energy consumption and carbon emissions account for a large proportion of the total energy consumption and carbon emissions of factories.

[0003] At present, factories usually ensure the normal operation of motors and inverters by regularly maintaining and inspecting them, and control the energy consumption and carbon emissions of motors and inverters by reducing the operating power of motors and inverters during specific time periods or reducing the operating time of motors and inverters when the load is low. However, the above methods are performed periodically and cannot monitor the operating status of motors and inverters in real time, which can easily lead to fluctuations in energy consumption and carbon emissions.

[0004] In order to solve the above problems, some factories have implemented real-time motor and inverter monitoring, that is, introducing automation systems, such as PLC (programmable logic controller), to control the start and stop and operating parameters of motors and inverters. However, the feedback mechanism of PLC is usually relatively simple, mainly relying on the limited data collected by sensors, and PLC can only perform simple preset tasks, such as starting and stopping the operation of motors and inverters in specific time periods, or reducing the running time of motors and inverters when the load is low. Although these preset tasks can reduce energy consumption to a certain extent, due to the lack of real-time data support, they are often unable to be dynamically adjusted according to the actual operating status of motors and inverters, so the effect on energy saving and carbon reduction is limited.

[0005] With respect to the above-mentioned prior art, there is currently no good solution for controlling the energy consumption and carbon emissions of motors and inverters. Summary of the invention

[0006] The embodiment of the present application provides an energy-saving and carbon-reduction control method and an integrated management platform based on AI intelligence assistance, which are used to achieve the above-mentioned purpose. The embodiment of the present application adopts the following technical solutions:

[0007] In a first aspect, an energy-saving and carbon-reduction control method based on AI intelligent assistance is provided, which is applied to a server, wherein the server is deployed with an integrated management platform, wherein the integrated management platform includes a data twin module, and the integrated management platform and the energy-saving management cloud control platform perform data transmission through a preset interface, wherein the method includes:

[0008] The energy-saving data of each device in the target factory is obtained in real time through the energy-saving management cloud control platform, and the carbon emissions of each device are calculated according to the energy-saving data of each device;

[0009] Obtaining a carbon emission plan of the target factory and a characteristic curve of each of the equipment, and using a first AI processing logic to determine an optimal carbon emission amount of the target factory according to the carbon emission plan and the characteristic curve of each of the equipment;

[0010] Adopting the second AI processing logic, determining the target power allocation plan for each of the equipment in the target factory in a preset time period in the future according to the optimal carbon emissions, and sending the target power allocation plan to the energy-saving management cloud control platform, so that the energy-saving management cloud control platform generates a device control instruction for each of the equipment according to the target power allocation plan, and sends the device control instruction to the corresponding equipment;

[0011] In response to receiving the plan execution data of each of the devices returned by the energy-saving management cloud control platform, calculating the actual carbon emissions and actual carbon savings of each of the devices in the target factory according to the plan execution data and the carbon emissions of each of the devices;

[0012] Obtain the device ID of each of the devices, and based on the device ID of each of the devices and the corresponding actual carbon emissions and the corresponding actual carbon savings, add attributes of the data object of each of the devices in the data twin model of the target factory, so as to display the actual carbon savings and the actual carbon emissions of each of the devices in the target factory in real time through the data objects in the data twin model in the data twin module.

[0013] In a possible implementation manner of the first aspect, the first AI processing logic includes:

[0014] Determine the operating range and upper limit carbon emission of each device according to the carbon emission plan and the characteristic curve of each device;

[0015] Constructing a multi-objective function, wherein the multi-objective function includes an objective function of minimizing total carbon emissions, an objective function of maximizing equipment efficiency, and an objective function of minimizing energy consumption cost, wherein the objective function of minimizing total carbon emissions is the main objective function, and the objective function of maximizing equipment efficiency and the objective function of minimizing energy consumption cost are secondary objective functions;

[0016] The operating range of each of the equipment and the upper limit carbon emissions of the target plant are used as first constraints of the main objective function, and the main objective function is solved by a preset first solution algorithm to obtain a first total carbon emissions;

[0017] The secondary objective function is used as a second constraint condition of the main objective function, and a preset second solution algorithm is used to solve the main objective function to obtain a second total carbon emission;

[0018] The smallest value between the first total carbon emissions and the second total carbon emissions is taken as the optimal carbon emissions of the target plant.

[0019] In another possible implementation manner of the first aspect, taking the secondary objective function as a second constraint condition of the main objective function, and using a preset second solution algorithm to solve the main objective function to obtain a second total carbon emissions includes:

[0020] Converting the secondary objective function into a second constraint condition, wherein the second constraint condition includes that a solution of the objective function of maximizing equipment efficiency is greater than or equal to a preset minimum efficiency, and a solution of the objective function of minimizing energy consumption cost is less than or equal to a preset maximum cost;

[0021] Using a preset second solving algorithm to solve the main objective function whose constraint condition is the second constraint condition, and using a preset optimization algorithm to solve the minimum energy consumption cost objective function, so as to optimize the expected energy consumption of each of the devices and minimize the value of the main objective function;

[0022] The minimum value of the main objective function is taken as the second total carbon emissions.

[0023] In another possible implementation manner of the first aspect, the second AI processing logic includes:

[0024] Obtain the predicted electricity demand and grid load for a preset time period in the future;

[0025] Dividing the future preset time period into a peak period and / or an off-peak period according to the predicted power demand and the grid load;

[0026] The target power distribution plan for each of the equipment in the target factory during the peak period and / or the off-peak period is determined according to the optimized expected energy consumption of each of the equipment and the optimal carbon emissions.

[0027] In another possible implementation manner of the first aspect, determining the target power distribution plan for each device of the target factory during the peak period and / or the off-peak period according to the optimized expected energy consumption of each device and the optimal carbon emissions includes:

[0028] When the future preset time period includes the peak period and the off-peak period, obtaining electricity price information of the peak period and the off-peak period;

[0029] Predicting the power demand of each device during the peak period and the off-peak period according to a pre-built regression model;

[0030] A total cost minimization objective function is constructed according to the electricity price information, the electricity demand of each of the devices during the peak period and the off-peak period, the expected energy consumption of each of the devices after optimization, and the optimal carbon emissions, wherein the total cost minimization includes minimizing the electricity cost and minimizing the carbon emission cost, and the third constraint condition of the total cost minimization objective function includes that the electricity allocated to each of the devices is greater than or equal to the corresponding electricity demand, the expected energy consumption of each of the devices is less than or equal to the allocated electricity, and the total carbon emissions generated by the electricity allocated to all of the devices is less than or equal to the optimal carbon emissions;

[0031] A preset genetic algorithm is used to solve the objective function of minimizing the total cost, and the power distribution plan corresponding to the optimal solution that satisfies all the third constraints and the objective function of minimizing the total cost is taken as the target power distribution plan.

[0032] In another possible implementation manner of the first aspect, the plan execution data includes an electric energy consumption value of each of the devices, and the calculating the actual carbon emissions and the actual carbon savings of each of the devices in the target factory according to the plan execution data and the carbon emissions of each of the devices includes:

[0033] Obtaining a carbon emission factor for each of the devices;

[0034] For each of the equipment, the product of the corresponding carbon emission factor and the corresponding electric energy consumption value is used as the actual carbon emission of each of the equipment in the target factory;

[0035] The difference between the carbon emission of each of the equipment and the corresponding actual carbon emission is used as the actual carbon saving of each of the equipment in the target factory.

[0036] In another possible implementation manner of the first aspect, according to the device ID of each device and the corresponding actual carbon emissions and the corresponding actual carbon savings, in the data twin model of the target plant, attributes of the data object of each device are added, so as to display the actual carbon savings and the actual carbon emissions of each device of the target plant in real time through the data objects in the data twin model in the data twin module, including:

[0037] Searching for a corresponding data object in the data twin model according to the device ID;

[0038] Adding the actual carbon emissions and the actual carbon savings corresponding to the device ID as new attributes to the attributes of the data object to update the data object of the data twin model;

[0039] Synchronizing the updated data object to the database of the data twin model;

[0040] In response to receiving a query instruction corresponding to the device ID, the updated data object corresponding to the device ID is called from the database, and the updated data object is displayed in the visualization interface of the data twin model to display the actual carbon emissions and the actual carbon savings corresponding to the device ID in real time.

[0041] In another possible implementation manner of the first aspect, the method further includes:

[0042] In response to receiving an interaction request from the associated platform to the integrated management platform, obtaining a version number of the associated platform;

[0043] The preset version control logic is used to route the version number to the corresponding API interface of the integrated management platform.

[0044] In a second aspect, the present application provides a server, including:

[0045] a memory configured to store instructions; and

[0046] The processor is configured to call the instructions from the memory and to implement the above-mentioned energy-saving and carbon-reduction control method based on AI intelligent assistance when executing the instructions.

[0047] In a third aspect, the present application provides an integrated management platform, the integrated management platform includes a data twin module, the integrated management platform and the energy-saving management cloud control platform perform data transmission through a preset interface, and further includes:

[0048] A first data acquisition module is used to acquire the energy-saving data of each device of the target factory in real time through the energy-saving management cloud control platform, and calculate the carbon emissions of each device according to the energy-saving data of each device;

[0049] a first AI calculation module, configured to obtain a carbon emission plan of the target plant and a characteristic curve of each of the equipment, and to determine an optimal carbon emission amount of the target plant according to the carbon emission plan and the characteristic curve of each of the equipment using a first AI processing logic;

[0050] A second AI calculation module is used to use a second AI processing logic to determine a target power allocation plan for each of the devices in the target factory in a preset future time period according to the optimal carbon emissions, and send the target power allocation plan to the energy-saving management cloud control platform, so that the energy-saving management cloud control platform generates a device control instruction for each of the devices according to the target power allocation plan, and sends the device control instruction to the corresponding device;

[0051] A second data acquisition module is used to calculate the actual carbon emissions and actual carbon savings of each device in the target factory according to the plan execution data and the carbon emissions of each device in response to receiving the plan execution data of each device returned by the energy-saving management cloud control platform;

[0052] A display module is used to obtain the device ID of each of the devices, and according to the device ID of each of the devices and the corresponding actual carbon emissions and the corresponding actual carbon savings, add attributes of the data object of each of the devices in the data twin model of the target factory, so as to display the actual carbon savings and the actual carbon emissions of each of the devices in the target factory in real time through the data objects in the data twin model in the data twin module.

[0053] Through the above technical solution, the energy-saving data of each device in the target factory is obtained in real time through the energy-saving management cloud control platform, and the carbon emissions of each device are calculated, which can effectively ensure the real-time monitoring of the equipment operation status, so that the energy consumption and carbon emission data can be updated in time, avoiding the lag of traditional regular maintenance and inspection methods. With the support of real-time data, the energy consumption and carbon emissions of the equipment can be evaluated more accurately; the first AI processing logic is adopted to determine the optimal carbon emissions of the target factory according to the carbon emission plan of the target factory and the characteristic curve of each device, and the operating characteristics of the equipment and the carbon emission target of the factory are comprehensively considered to obtain the optimal carbon emissions. While achieving the carbon emission target of the target factory, the operating efficiency of the equipment can also be ensured to avoid affecting production efficiency due to excessive energy saving. In addition, the second AI processing logic is adopted to determine the target power allocation plan for each device in the target factory in the future preset time period according to the optimal carbon emissions, and send the plan to the energy-saving management cloud control platform, realizing the dynamic adjustment of the equipment energy consumption, so that the operating parameters of the equipment can be optimized according to actual needs, and through the intelligent allocation of AI, it can minimize energy consumption and carbon emissions while ensuring production needs, and achieve the dual goals of energy saving and carbon reduction. According to the planned execution data of each device returned by the energy-saving management cloud control platform, the real-time evaluation of the energy-saving and carbon-reduction effect can be realized. Finally, the device ID of each device is obtained, and according to the device ID of each device and the corresponding actual carbon emissions and actual carbon savings, the attributes of the data object of each device are added in the data twin model of the target factory, so that the actual carbon savings and actual carbon emissions of each device in the target factory can be displayed in real time through the data objects in the data twin model in the data twin module, realizing the visualization of the energy-saving and carbon-reduction effect, so that the factory managers can intuitively understand the operation status and energy-saving and carbon-reduction effect of the equipment. Through the application of data twin technology, the factory can achieve more efficient energy-saving and carbon-reduction management. In summary, the above technical solution can realize the real-time monitoring and dynamic adjustment of equipment energy consumption and carbon emissions, and finally effectively control the energy consumption and carbon emissions of the equipment. It not only solves the hysteresis problem of traditional regular maintenance and inspection methods, but also overcomes the defects of the simple feedback mechanism of PLC and the lack of real-time data support. Through the application of AI intelligent computing and data twin technology, more accurate decision support can be provided to help factories achieve more efficient energy-saving and carbon-reduction management. Ultimately, through AI-assisted energy-saving and carbon-reduction control methods, real-time monitoring and dynamic adjustment of equipment energy consumption and carbon emissions are achieved, which can ultimately effectively control the energy consumption and carbon emissions of equipment.

[0054] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A first flow chart of an AI-assisted energy-saving and carbon-reduction control method provided in an embodiment of the present application;

[0056] Figure 2 An overall flow chart of an AI-assisted energy-saving and carbon-reduction control method provided in an embodiment of the present application;

[0057] Figure 3 A data interface transmission flow chart of an integrated management platform provided in an embodiment of the present application;

[0058] Figure 4 A schematic diagram of the structure of a comprehensive management platform provided in an embodiment of the present application;

[0059] Figure 5 A schematic diagram of one of the display pages of a comprehensive management platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0061] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0062] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0063] Figure 1The following schematically shows a flow chart of an energy-saving and carbon-reduction control method based on AI intelligent assistance according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides an energy-saving and carbon-reduction control method based on AI intelligent assistance, which is applied to a server. The server is deployed with an integrated management platform. The integrated management platform includes a data twin module. The integrated management platform and the energy-saving management cloud control platform transmit data through a preset interface. The method may include the following steps.

[0064] S110, obtaining energy-saving data of each device in the target factory in real time through the energy-saving management cloud control platform, and calculating the carbon emissions of each device based on the energy-saving data of each device;

[0065] S120, obtaining a carbon emission plan of the target factory and a characteristic curve of each device, and using a first AI processing logic to determine an optimal carbon emission amount of the target factory according to the carbon emission plan and the characteristic curve of each device;

[0066] S130, using the second AI processing logic to determine the target power allocation plan for each device in the target factory in a preset time period in the future according to the optimal carbon emissions, and sending the target power allocation plan to the energy-saving management cloud control platform, so that the energy-saving management cloud control platform generates a device control instruction for each device according to the target power allocation plan, and sends the device control instruction to the corresponding device;

[0067] S140, in response to receiving the plan execution data of each device returned by the energy-saving management cloud control platform, calculating the actual carbon emissions and actual carbon savings of each device in the target factory according to the plan execution data and the carbon emissions of each device;

[0068] S150. Obtain the device ID of each device, and according to the device ID of each device and the corresponding actual carbon emissions and the corresponding actual carbon savings, add the attributes of the data object of each device in the data twin model of the target factory, so as to display the actual carbon savings and actual carbon emissions of each device in the target factory in real time through the data objects in the data twin model in the data twin module.

[0069] In this embodiment, the energy-saving management cloud control platform obtains energy-saving data from each device of the target factory in real time through a preset interface. Among them, the energy-saving data includes the operating status, power consumption, operating time, etc. of the equipment, and the equipment includes motors and inverters. Through the energy-saving data, the carbon emissions of each device can be calculated. Specifically, the calculation formula for carbon emissions is usually based on the power consumption and operating time of the equipment, combined with the carbon emission coefficient. For example, if a device consumes 1 kilowatt-hour (kWh) of electricity in a certain unit time, it is equivalent to consuming 0.404 kg of standard coal, and the carbon emissions per kilowatt-hour are 0.272 kg, then the carbon emissions generated by the device in this unit time are 0.272 kg. In this way, the carbon emissions of each device can be monitored in real time, providing data support for subsequent energy-saving and carbon reduction decisions.

[0070] The integrated management platform obtains the carbon emission plan of the target factory and the characteristic curve of each device (including no-load characteristic curve and load characteristic curve). The characteristic curve describes the energy consumption characteristics of the equipment under different load conditions. The first AI processing logic can calculate the optimal carbon emissions of the target factory based on the energy consumption characteristics of the equipment under different load conditions and the carbon emission plan of the factory. Specifically, the first AI processing logic can analyze the characteristic curve of the equipment, identify the changes in energy consumption of the equipment under different load conditions, and combine the carbon emission targets of the factory to calculate an optimal carbon emission that can both meet production needs and minimize carbon emissions. For example, if the factory's goal is to reduce carbon emissions by 10% in the next month, the first AI processing logic can calculate a new carbon emission target based on the characteristic curve of the equipment and the current operating data to ensure that the emission reduction target is achieved while meeting production needs.

[0071] The second AI processing logic can determine the target power distribution plan for each device in the target factory in the future preset time period based on the optimal carbon emissions. The target power distribution plan can list in detail the power distribution of each device in different time periods to ensure that the operation of the equipment can meet the requirements of the optimal carbon emissions. For example, if a device has high energy consumption during peak hours, the second AI processing logic will recommend reducing the operating time of the device or reducing its operating power during peak hours to reduce carbon emissions. After the target power distribution plan is generated, it can be sent to the energy-saving management cloud control platform through the preset interface. The energy-saving management cloud control platform can generate corresponding equipment control instructions based on the power distribution plan and send them to the corresponding devices. For example, the energy-saving management cloud control platform may generate an instruction requiring a device to reduce its operating power during a specific time period to reduce carbon emissions.

[0072] When the energy-saving management cloud control platform receives the planned execution data of each device, the integrated management platform will calculate the actual carbon emissions and actual carbon savings of each device in the target factory based on these data and the carbon emissions of each device. Specifically, the platform will compare the planned execution data with the actual operation data to calculate the actual carbon emissions of each device after executing the target power distribution plan. Then, by comparing the actual carbon emissions with the planned carbon emissions, the actual carbon savings of each device are calculated. For example, if the actual carbon emissions of a device are 20 kg less than the planned carbon emissions after the plan is executed, then the actual carbon savings of the device are 20 kg. In this way, the integrated management platform can monitor the energy-saving and carbon-reduction effects of each device in real time.

[0073] After obtaining the actual carbon emissions and actual carbon savings of each device, the integrated management platform obtains the device ID of each device, and adds the attributes of the data object of each device in the data twin model of the target factory based on the device ID of each device and the corresponding actual carbon emissions and actual carbon savings. Among them, the attributes include the actual carbon emissions and actual carbon savings of the equipment, as well as other related operating data. Through the data twin model in the data twin module, the data object can display the actual carbon savings and actual carbon emissions of each device in the target factory in real time. For example, the data twin model can show that the actual carbon emissions of a certain device in a certain period of time are 50 kg and the actual carbon savings are 10 kg, so that factory managers can intuitively understand the operating status and energy-saving and carbon-reduction effects of each device.

[0074] In specific implementations, the integrated management platform can also perform fault detection on the motor. Specifically, the motor windings and front and rear bearings are preset with temperature sensors, and the motor casing is provided with a vibration sensor. The motor temperature, the temperature of the front and rear bearings, and the vibration state of the motor can be obtained according to the above sensors. In addition, the running state of the motor can also be obtained, and the motor parameters (such as current, voltage, etc.) can be collected through the frequency converter. The above data (motor temperature, front and rear bearing temperature, vibration state, running state, motor parameters) are sent to the integrated management platform. The preset AI algorithm in the integrated management platform can determine whether the motor is faulty based on the above data, and issue an early warning when the motor fails, such as Figure 5 As shown, "Motor 1 temperature abnormality 2024 / 09 / 08" indicates that the temperature of motor 1 is abnormal and a fault may occur, so as to remind the operator to check and maintain it.

[0075] In order to further improve management efficiency and intuitive operation, the comprehensive management platform integrates the BIM model to achieve real-time visual monitoring of the motor position and status. The specific implementation steps are as follows:

[0076] 1. BIM model import: Import the BIM model of the factory or equipment into the integrated management platform to ensure that each motor in the model has a unique identifier.

[0077] 2. Data mapping: Map the real-time collected motor data (such as temperature, vibration, operating status, etc.) with the motor identifier in the BIM model to ensure that the status information of each motor can be updated in real time in the BIM model.

[0078] 3. Visual interface: On the visual interface of the integrated management platform, operators can intuitively see the location, current status (such as normal, abnormal temperature, abnormal vibration, etc.) and related operating data (such as temperature curve, vibration frequency, etc.) of each motor through the BIM model.

[0079] The integrated management platform can realize real-time data call. Specifically, operators can directly call the real-time data of a motor, such as temperature, vibration status, etc., through the BIM model without switching to other interfaces. When the motor is abnormal, the corresponding motor icon in the BIM model will be highlighted and a warning message will pop up to remind the operator to deal with it in time.

[0080] By integrating motor condition monitoring with the BIM model, the comprehensive management platform can not only achieve early warning of motor failures, but also provide an intuitive, real-time visual monitoring interface, greatly improving the operation and maintenance efficiency and safety of industrial equipment.

[0081] The following takes the target factory as an example. Figure 5 As shown in Figure 1, the data twin model (BIM model) of the target factory has been imported into the integrated management platform. The BIM model contains the layout of the factory, and each motor has a unique identifier in the model (such as "motor 1", "motor 2", etc.).

[0082] The sensor data of each motor (such as temperature, vibration, operating status, etc.) is mapped to the motor identifier in the BIM model. For example, the temperature sensor data of "Motor 1" is associated with the "Motor 1" icon in the BIM model. The operator logs in to the integrated management platform and enters the BIM visualization interface. The operator clicks the "Motor 1" icon in the BIM model, and a detailed information window pops up. The window displays the current status of "Motor 1": Temperature: 95°C (abnormal), Vibration: 0.5mm / s (abnormal), Operating status: Running. When the temperature and vibration data of "Motor 1" are abnormal, the "Motor 1" icon in the BIM model will be highlighted, and a warning message will pop up: "Motor 1 temperature abnormality 2024 / 09 / 0814:30". After receiving the warning message, the operator can click the warning message to view the detailed abnormal data for further analysis and processing.

[0083] Operators can directly call the historical data of "Motor 1" through the BIM model, view the historical data of temperature and vibration, and analyze the causes of abnormalities. The real-time data and warning information of all motors will be recorded in the database of the integrated management platform to facilitate subsequent analysis and report generation.

[0084] Figure 2 The overall process diagram of an energy-saving and carbon-reduction control method based on AI intelligent assistance provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the integrated management platform can exchange data with the energy-saving management cloud control platform, and at the same time, it can determine the optimal carbon emissions and electricity distribution plan through AI, and return the electricity distribution plan to the energy-saving management cloud control platform for execution, thereby realizing real-time monitoring and dynamic adjustment of equipment energy consumption and carbon emissions, helping factories achieve more efficient energy-saving and carbon reduction management.

[0085] This embodiment obtains the energy-saving data of each device in the target factory in real time through the energy-saving management cloud control platform, and calculates the carbon emissions of each device, which can effectively ensure the real-time monitoring of the equipment operation status, so that the energy consumption and carbon emission data can be updated in time, avoiding the lag of traditional regular maintenance and inspection methods. With the support of real-time data, the energy consumption and carbon emissions of the equipment can be evaluated more accurately; the first AI processing logic is adopted to determine the optimal carbon emissions of the target factory according to the carbon emission plan of the target factory and the characteristic curve of each device, and the operating characteristics of the equipment and the carbon emission target of the factory are comprehensively considered to obtain the optimal carbon emissions. While achieving the carbon emission target of the target factory, the operating efficiency of the equipment can also be ensured to avoid affecting production efficiency due to excessive energy saving. In addition, the second AI processing logic is adopted to determine the target power allocation plan for each device in the target factory in the future preset time period according to the optimal carbon emissions, and the plan is sent to the energy-saving management cloud control platform, realizing the dynamic adjustment of the equipment energy consumption, so that the operating parameters of the equipment can be optimized according to actual needs. Through the intelligent allocation of AI, it can minimize energy consumption and carbon emissions while ensuring production needs, and achieve the dual goals of energy saving and carbon reduction. According to the planned execution data of each device returned by the energy-saving management cloud control platform, the real-time evaluation of the energy-saving and carbon-reduction effect can be realized. Finally, the device ID of each device is obtained, and according to the device ID of each device and the corresponding actual carbon emissions and actual carbon savings, the attributes of the data object of each device are added in the data twin model of the target factory, so that the actual carbon savings and actual carbon emissions of each device in the target factory can be displayed in real time through the data objects in the data twin model in the data twin module, realizing the visualization of the energy-saving and carbon-reduction effect, so that the factory managers can intuitively understand the operation status and energy-saving and carbon-reduction effect of the equipment. Through the application of data twin technology, the factory can achieve more efficient energy-saving and carbon-reduction management. In summary, the above technical solution can realize the real-time monitoring and dynamic adjustment of equipment energy consumption and carbon emissions, and finally effectively control the energy consumption and carbon emissions of the equipment. It not only solves the hysteresis problem of traditional regular maintenance and inspection methods, but also overcomes the defects of the simple feedback mechanism of PLC and the lack of real-time data support. Through the application of AI intelligent computing and data twin technology, more accurate decision support can be provided to help factories achieve more efficient energy-saving and carbon-reduction management. Ultimately, through AI-assisted energy-saving and carbon-reduction control methods, real-time monitoring and dynamic adjustment of equipment energy consumption and carbon emissions are achieved, which can ultimately effectively control the energy consumption and carbon emissions of equipment.

[0086] In one implementation of this embodiment, the first AI processing logic includes the following steps:

[0087] S210, determining the operating range and upper limit carbon emission of each device according to the carbon emission plan and the characteristic curve of each device;

[0088] S220, constructing a multi-objective function, wherein the multi-objective function includes an objective function of minimizing total carbon emissions, an objective function of maximizing equipment efficiency, and an objective function of minimizing energy consumption cost, wherein the objective function of minimizing total carbon emissions is the main objective function, and the objective function of maximizing equipment efficiency and the objective function of minimizing energy consumption cost are secondary objective functions;

[0089] S230, taking the operating range of each device and the upper limit carbon emissions of the target plant as the first constraint conditions of the main objective function, and using a preset first solution algorithm to solve the main objective function to obtain a first total carbon emissions;

[0090] S240, using the secondary objective function as a second constraint condition of the primary objective function, and using a preset second solution algorithm to solve the primary objective function to obtain a second total carbon emission;

[0091] S250: Taking the minimum value between the first total carbon emissions and the second total carbon emissions as the optimal carbon emissions of the target plant.

[0092] In this embodiment, the operating range and upper limit carbon emissions of each device are first determined according to the carbon emission plan and the characteristic curve of each device. First, the carbon emission plan provides the carbon emission target of the factory in a specific time period, such as the monthly or annual carbon emission upper limit. The characteristic curve describes the energy consumption characteristics of the equipment under different load conditions, including the power consumption when no-load and load. Through the carbon emission plan and the characteristic curve of each device, the operating range of each device under different load conditions can be determined. For example, the characteristic curve of a device may show a rated power of 200KW and a rated current of 400A, but the actual operating current is between 200A-400A, and the power consumption is between 100 kilowatts (kW)-200 kilowatts (kW). Based on these data, it can be determined that the operating range of the device is 50% to 100% load. Next, combined with the carbon emission plan, the upper limit carbon emissions of each device are calculated. For example, if the factory's goal is to not exceed 1,000 kilograms of carbon emissions per month, and the equipment runs for 100 hours in a month, then the upper limit carbon emissions of the equipment is 10 kilograms per hour (kg / h). In this way, the operating range and upper carbon emissions limit for each device can be determined.

[0093] In order to determine the optimal carbon emissions of the target plant, a multi-objective function is first constructed, which includes the objective function of minimizing total carbon emissions, the objective function of maximizing equipment efficiency, and the objective function of minimizing energy consumption costs. The objective function of minimizing total carbon emissions is the main objective function, which aims to minimize the total carbon emissions of the plant. The objective function of maximizing equipment efficiency and the objective function of minimizing energy consumption costs are secondary objective functions, which aim to improve the operating efficiency of the equipment and reduce energy consumption costs, respectively. Specifically, the objective function of minimizing total carbon emissions can be expressed as:

[0094]

[0095] Among them, C i represents the carbon emissions of the i-th equipment. The objective function of maximizing equipment efficiency can be expressed as:

[0096]

[0097] Among them, E i represents the efficiency of the i-th device. The minimum energy cost objective function can be expressed as:

[0098]

[0099] Among them, P i represents the energy consumption cost of the i-th device.

[0100] By constructing the above objective function, it is possible to optimize the operating efficiency and energy consumption cost of the equipment while reducing carbon emissions.

[0101] The operating range of each device and the upper limit of carbon emissions of the target plant are taken as the first constraints of the main objective function, and the preset first solution algorithm is used to solve the main objective function to obtain the first total carbon emissions. Specifically, the operating range and upper limit of carbon emissions of each device are first taken as constraints and added to the main objective function. For example, if the operating range of a device is 50% to 100% load and the upper limit of carbon emissions is 10 kilograms per hour (kg / h), then the constraints can be expressed as:

[0102] 50%≤L i ≤100%, C i ≤10kg / h;

[0103] Among them, L i represents the load of the i-th device. Next, a preset first solution algorithm (such as linear programming or genetic algorithm) is used to solve the main objective function to obtain the first total carbon emissions. For example, through the linear programming algorithm, under the premise of satisfying all constraints, an equipment operation plan that minimizes the total carbon emissions can be found.

[0104] The secondary objective function is used as the second constraint of the main objective function, and the main objective function is solved by the preset second solution algorithm to obtain the second total carbon emissions. Specifically, the secondary objective function (maximizing the equipment efficiency objective function and the minimum energy consumption cost objective function) is first added as a constraint to the main objective function. For example, if the constraints of the maximizing equipment efficiency objective function and the minimum energy consumption cost objective function are:

[0105] E i ≥E min , P i ≤P max ;

[0106] Among them, E min and P max They represent the minimum value of equipment efficiency and the maximum value of energy consumption cost respectively. Next, a preset second solution algorithm (such as a multi-objective optimization algorithm) is used to solve the main objective function to obtain the second total carbon emissions. For example, through the multi-objective optimization algorithm, it is possible to find an equipment operation plan that minimizes the total carbon emissions while satisfying all constraints, while optimizing the efficiency and energy consumption cost of the equipment.

[0107] The smallest value between the first total carbon emissions and the second total carbon emissions is taken as the optimal carbon emissions of the target plant. Specifically, the first total carbon emissions and the second total carbon emissions are first compared, and the smaller value is selected as the optimal carbon emissions of the target plant. For example, if the first total carbon emissions are 1,000 kg and the second total carbon emissions are 950 kg, then the optimal carbon emissions are 950 kg. In this way, under the premise of meeting all constraints, the equipment operation plan that minimizes the total carbon emissions can be found, while optimizing the efficiency and energy consumption cost of the equipment. Finally, a scientific and reasonable optimal carbon emissions is obtained, which provides decision support for the energy conservation and carbon reduction management of the factory.

[0108] This implementation method realizes multi-objective optimization of equipment energy consumption and carbon emissions, and can ultimately effectively control the energy consumption and carbon emissions of equipment. It not only solves the lag problem of traditional regular maintenance and inspection methods, but also overcomes the limitations of the simple PLC feedback mechanism and lack of real-time data support. Through the application of AI intelligent computing and multi-objective optimization technology, more accurate decision support can be provided to help factories achieve more efficient energy conservation and carbon reduction management. Ultimately, the factory's energy consumption and carbon emissions can be significantly reduced.

[0109] In one implementation of this embodiment, the secondary objective function is used as the second constraint condition of the main objective function, and the main objective function is solved by a preset second solution algorithm to obtain a second total carbon emission, including the following steps:

[0110] S310, converting the secondary objective function into a second constraint condition, where the second constraint condition includes that the solution of the objective function of maximizing equipment efficiency is greater than or equal to a preset minimum efficiency, and the solution of the objective function of minimizing energy consumption cost is less than or equal to a preset maximum cost;

[0111] S320, using a preset second solving algorithm to solve a main objective function whose constraint condition is the second constraint condition, and using a preset optimization algorithm to solve a minimum energy consumption cost objective function, so as to optimize the expected energy consumption of each device and minimize the value of the main objective function;

[0112] S330. Taking the minimum value of the main objective function as the second total carbon emissions.

[0113] In this embodiment, the sub-objective function is first converted into a second constraint. Specifically, the sub-objective function includes a maximization equipment efficiency objective function and a minimum energy consumption cost objective function. In order to convert these sub-objective functions into constraints, it is first necessary to set a preset minimum efficiency and maximum cost. For example, assume that the preset minimum efficiency is 90% and the maximum cost is 0.6 yuan per kilowatt-hour. Then, the solution of the maximization equipment efficiency objective function is greater than or equal to the preset minimum efficiency, and the solution of the minimum energy consumption cost objective function is less than or equal to the preset maximum cost, as the second constraint. Specifically, the second constraint can be expressed as:

[0114] E i ≥0.9, P i ≤0.6;

[0115] Among them, E i represents the efficiency of the ith device, P i represents the energy consumption cost of the i-th device.

[0116] Afterwards, a preset second solving algorithm is used to solve the main objective function whose constraint condition is the second constraint condition, and a preset optimization algorithm is used to solve the minimum energy consumption cost objective function to optimize the expected energy consumption of each device and minimize the value of the main objective function. Specifically, the second constraint condition is first added to the main objective function to form a new optimization problem. Then, the preset second solving algorithm (such as a multi-objective optimization algorithm) is used to solve the above new optimization problem to obtain the minimum value of the main objective function. At the same time, a preset optimization algorithm (such as linear programming or genetic algorithm) is used to solve the minimum energy consumption cost objective function to optimize the expected energy consumption of each device. For example, through a linear programming algorithm, a device operation plan that minimizes the energy consumption cost can be found under the premise of satisfying all constraints. In this way, the energy consumption cost of the equipment can be optimized while reducing carbon emissions.

[0117] The minimum value of the main objective function is taken as the second total carbon emissions. Specifically, first compare the minimum values ​​of the main objective function under different constraints, and select the minimum value as the second total carbon emissions. For example, if the minimum value of the main objective function under the first constraint is 1,000 kg of carbon emissions, and the minimum value under the second constraint is 950 kg of carbon emissions, then the second total carbon emissions are 950 kg. In summary, under the premise of meeting all constraints, we can find an equipment operation plan that minimizes the total carbon emissions while optimizing the efficiency and energy consumption cost of the equipment. Finally, a reasonable second total carbon emissions is obtained.

[0118] This implementation method can provide more accurate decision-making support through the application of AI intelligent computing and multi-objective optimization technology, help factories achieve more efficient energy conservation and carbon reduction management, significantly reduce the factory's energy consumption and carbon emissions, and achieve multi-objective optimization of equipment energy consumption and carbon emissions, ultimately effectively controlling the energy consumption and carbon emissions of equipment.

[0119] In one implementation of this embodiment, the second AI processing logic includes the following steps:

[0120] S410, obtaining predicted power demand and grid load conditions for a future preset time period;

[0121] S420, dividing the future preset time period into peak period and / or off-peak period according to the predicted power demand and grid load;

[0122] S430, determining a target power distribution plan for each device in the target factory during peak and / or off-peak periods according to the expected energy consumption of each device after optimization and the optimal carbon emissions.

[0123] In the second AI processing logic, the predicted electricity demand and grid load for a preset time period in the future are first obtained. Specifically, the electricity demand for a period of time in the future is first predicted through historical data and current electricity consumption trends. For example, if it is summer, it is predicted that the daily electricity demand will gradually increase in the next week because the use of air conditioners will increase. At the same time, the load conditions of the power grid are obtained, including the current load, peak load, and load fluctuations of the power grid. For example, the power grid may reach peak load from 2 to 4 pm every day, and the load is lower from 1 to 5 am. Through these data, we can fully understand the electricity demand and grid load conditions for the preset time period in the future, providing a basis for subsequent power distribution plans.

[0124] According to the predicted electricity demand and grid load, the future preset time period is divided into peak period and / or off-peak period. Specifically, by first analyzing the predicted electricity demand and grid load data, the peak period and off-peak period of electricity demand and grid load can be identified. For example, if the forecast shows that the electricity demand and grid load reach their peak values ​​from 2 to 4 pm every day, then this period can be classified as a peak period. If the forecast shows that the electricity demand and grid load are lower from 1 to 5 am every day, then this period can be classified as an off-peak period. In the above manner, the future preset time period can be divided into different time periods to facilitate the subsequent determination of the target electricity distribution plan.

[0125] Specifically, according to the expected energy consumption and optimal carbon emissions of each device after optimization, the target power distribution plan for each device in the target factory during peak and / or off-peak periods is determined. Specifically, the expected energy consumption and optimal carbon emissions of each device can be combined to formulate power distribution plans for each device in different time periods. For example, if the expected energy consumption of a device during peak periods is high, the operating time of the device can be reduced or its operating power can be reduced during peak periods to reduce carbon emissions. During off-peak periods, the operating time of the device can be increased or its operating power can be increased to make full use of the electricity during low-load periods. While meeting electricity demand, carbon emissions can be minimized to achieve the goal of energy conservation and carbon reduction.

[0126] This embodiment uses the second AI processing logic to achieve dynamic adjustment of the target power distribution plan to help the target factory achieve more efficient energy conservation and carbon reduction management, effectively control the energy consumption and carbon emissions of the equipment, and thus significantly reduce the energy consumption and carbon emissions of the factory.

[0127] In one implementation of this embodiment, determining a target power distribution plan for each device in a target factory during peak hours and / or off-peak hours according to the expected energy consumption and optimal carbon emissions of each device after optimization includes the following steps:

[0128] S510, when the future preset time period includes a peak period and a non-peak period, obtaining the electricity price information of the peak period and the non-peak period;

[0129] S520, predicting the power demand of each device during peak hours and off-peak hours according to a pre-built regression model;

[0130] S530, constructing a total cost minimization objective function according to the electricity price information, the electricity demand of each device during peak and off-peak periods, the expected energy consumption of each device after optimization, and the optimal carbon emissions, wherein minimizing the total cost includes minimizing the electricity cost and minimizing the carbon emission cost, and the third constraint condition of the total cost minimization objective function includes that the electricity allocated to each device is greater than or equal to the corresponding electricity demand, the expected energy consumption of each device is less than or equal to the allocated electricity, and the total carbon emissions generated by the electricity allocated to all devices is less than or equal to the optimal carbon emissions;

[0131] S540, using a preset genetic algorithm to solve the objective function of minimizing the total cost, and taking the power distribution plan that satisfies all third constraints and minimizes the total cost objective function to achieve the optimal solution as the target power distribution plan.

[0132] When the future preset time period includes a peak period and an off-peak period, the electricity price information of the peak period and the off-peak period is obtained. Specifically, the electricity price information of different time periods in the future preset time period can be obtained from the power market or the power supplier. For example, the electricity price during the peak period may be 0.8 yuan per kilowatt-hour, while the electricity price during the off-peak period may be 0.6 yuan per kilowatt-hour.

[0133] Afterwards, the power demand of each device during peak and off-peak periods is predicted based on the pre-built regression model. Specifically, the power demand of each device in the future preset time period can be predicted by the pre-built regression model using historical data and current power consumption trends. For example, if the power demand of a device has gradually increased every day in the past week, it is predicted that the power demand of the device in the next week will also gradually increase. In this way, the system can accurately predict the power demand of each device during peak and off-peak periods, and provide data support for subsequent power allocation plans. Among them, the regression model is built based on historical data, which may include power consumption records, production plans, weather conditions, etc. of the equipment. The machine learning algorithm model can be trained with historical data to obtain a regression model that can predict future power demand based on input features (time, production plan, weather, etc.). For example, for a motor, the model predicts that 80kWh of electricity will be required per hour during the future peak period (such as 9:00-17:00 on weekdays), while only 30kWh will be required per hour during the off-peak period (such as 22:00-6:00 at night). The above forecasts are made for each piece of equipment in the factory separately, taking into account the characteristics and usage patterns of the equipment.

[0134] The objective function of minimizing the total cost is constructed based on the electricity price information, the electricity demand of each device during peak and off-peak periods, the expected energy consumption of each device after optimization, and the optimal carbon emissions. Specifically, minimizing the total cost includes minimizing the electricity cost and minimizing the carbon emission cost. The electricity cost can be calculated by the electricity price and the electricity demand, and the carbon emission cost can be calculated by the carbon emissions and the carbon emission coefficient. The third constraint condition of the objective function of minimizing the total cost includes that the electricity allocated to each device is greater than or equal to the corresponding electricity demand, the expected energy consumption of each device is less than or equal to the allocated electricity, and the total carbon emissions generated by the electricity allocated to all devices is less than or equal to the optimal carbon emissions.

[0135] Specifically, in order to ensure the normal operation of the equipment, it should be ensured that each device can meet the basic power demand during operation. At this time, the first constraint condition is set that the power allocated to each device is greater than or equal to the corresponding power demand; in order to ensure that the actual energy consumption of the equipment does not exceed the allocated power, so as to avoid equipment overload or excessive power consumption, thereby reducing power costs and carbon emissions, the second constraint condition is set at this time to limit the expected energy consumption of the equipment, so that the expected energy consumption of each device is less than or equal to the allocated power; in order to ensure that the total carbon emissions of the entire factory do not exceed the set optimal carbon emissions and achieve energy conservation and carbon reduction, the third constraint condition is set that the total carbon emissions generated by the allocated electricity to all equipment are less than or equal to the optimal carbon emissions.

[0136] When implementing it, you first need to define variables, such as X ij Represents the amount of electrical energy allocated to device i in period j. Then, construct the objective function:

[0137] min(∑(x ij ×P j )+α×∑(x ij ×E i ));

[0138] Where P j is the electricity price in period j, E i is the carbon emission factor of equipment i, and α is the weight coefficient of carbon emission cost. At the same time, three key constraints need to be considered: (1) x ij ≥D ij , where D ij is the predicted power demand of device i in time period j; (2) C i ≤x ij , where C i is the expected energy consumption of device i.

[0139] (3)∑(x ij ×E i )≤Cmax;

[0140] Where Cmax is the optimal carbon emission. The objective function constructed based on the above three constraints can not only consider economic costs, but also incorporate environmental factors into the decision-making process, thereby achieving a balance between economic and environmental benefits. By reasonably setting the weight coefficient α, the relative importance of economic and environmental goals can be adjusted, so that the final optimization result can better meet the specific needs and policy requirements of the enterprise.

[0141] In summary, the power distribution plan that minimizes the total cost can be found under the premise of satisfying all constraints.

[0142] A preset genetic algorithm is used to solve the objective function of minimizing the total cost, and the power distribution plan corresponding to the optimal solution that satisfies all the third constraints and minimizes the total cost objective function is used as the target power distribution plan. Specifically, the genetic algorithm is an optimization algorithm that gradually optimizes the objective function by simulating natural selection and genetic mechanisms. First, the objective function of minimizing the total cost and the third constraint are input into the genetic algorithm, and through multiple iterations, the power distribution plan that satisfies all constraints and minimizes the total cost is found. For example, through the genetic algorithm, it is possible to find an equipment operation plan that minimizes the total cost while satisfying all constraints.

[0143] For the case where the future preset time period only includes the peak period or only includes the off-peak period, the above steps S510-S540 can also be implemented, but during the implementation process, the chromosome encoding in the genetic algorithm will be simplified. For example, for a problem with 10 devices, if the future preset time period only includes the peak period or only includes the off-peak period, only a 10-dimensional real number encoding chromosome may be required, instead of the previous 240 dimensions, to reduce the computational complexity and speed up the solution.

[0144] This implementation method can effectively control the energy consumption and carbon emissions of equipment through AI intelligent calculation and dynamic adjustment of equipment energy consumption and carbon emissions, and can provide more accurate decision support to help factories achieve more efficient energy conservation and carbon reduction management. Ultimately, it can significantly reduce the energy consumption and carbon emissions of the factory.

[0145] In one implementation of this embodiment, the planned execution data includes the power consumption value, actual operation parameters (power, current, voltage, etc.) and operation time of each device, and the actual carbon emissions and actual carbon savings of each device in the target factory are calculated according to the planned execution data and the carbon emissions of each device, including the following steps:

[0146] S610, obtaining a carbon emission factor for each device;

[0147] S620: For each device, the product of the corresponding carbon emission factor and the corresponding electric energy consumption value is used as the actual carbon emission of each device in the target factory;

[0148] S630: The difference between the carbon emission of each device and the corresponding actual carbon emission is used as the actual carbon saving of each device in the target factory.

[0149] First, obtain the carbon emission factor of each device. Specifically, the carbon emission factor is a constant that represents the amount of carbon emissions generated per unit of electricity consumption. The carbon emission factor is usually provided by electricity suppliers or related agencies and reflects the carbon emissions in the electricity production process. For example, if a region calculates that the carbon emissions per kilowatt-hour are 0.272 kg based on the carbon emission factor, it means that for every kilowatt-hour of electricity consumed, 0.272 kg of carbon emissions will be generated.

[0150] For each device, the product of the corresponding carbon emission factor and the corresponding electricity consumption value is used as the actual carbon emissions of each device in the target factory. Specifically, the actual carbon emissions of each device can be calculated based on the electricity consumption value and carbon emission factor of each device. For example, if a device consumes 1 kilowatt-hour (kWh) of electricity in a certain unit time, which is equivalent to consuming 0.404 kg of standard coal, and the carbon emissions per kilowatt-hour are 0.272 kg, then the actual carbon emissions generated by the device in the unit time are 0.272 kg. In the above way, the actual carbon emissions of each device can be accurately calculated.

[0151] The difference between the carbon emissions of each device and the corresponding actual carbon emissions is used as the actual carbon savings of each device in the target factory. Specifically, the actual carbon savings of each device can be calculated by comparing the carbon emissions of each device with the actual carbon emissions. For example, if the carbon emissions of a device are 60 kg and the actual carbon emissions are 50 kg, then the actual carbon savings of the device is 10 kg.

[0152] This implementation method realizes real-time monitoring and dynamic adjustment of equipment energy consumption and carbon emissions, and can ultimately effectively control the energy consumption and carbon emissions of the equipment.

[0153] In one implementation of this embodiment, according to the device ID of each device and the corresponding actual carbon emissions and the corresponding actual carbon savings, in the data twin model of the target factory, the attributes of the data object of each device are added to display the actual carbon savings and the actual carbon emissions of each device of the target factory in real time through the data objects in the data twin model in the data twin module, including the following steps:

[0154] S710, searching for a corresponding data object in the data twin model according to the device ID;

[0155] S720, adding the actual carbon emissions and actual carbon savings corresponding to the device ID as new attributes to the attributes of the data object to update the data object of the data twin model;

[0156] S730, synchronizing the updated data object to the database of the data twin model;

[0157] S740. In response to receiving a query instruction corresponding to the device ID, call the updated data object corresponding to the device ID from the database, and display the updated data object in the visualization interface of the data twin model to display the actual carbon emissions and actual carbon savings corresponding to the device ID in real time.

[0158] In this embodiment, the corresponding data object is searched in the data twin model according to the device ID. The data twin model is a virtual factory model that contains detailed information of all equipment and systems in the factory. Each device has a corresponding data object in the data twin model, which contains the basic information and operation data of the device. The corresponding data object can be searched in the data twin model according to the device ID of the device. For example, if the device ID of a certain device is "M12345", the data object with ID "M12345" can be searched in the data twin model.

[0159] After that, the actual carbon emissions and actual carbon savings corresponding to the device ID are added as new attributes to the data object's attributes to update the data object of the data twin model. Specifically, the actual carbon emissions and actual carbon savings of each device can be added as new attributes to the corresponding data object. For example, if the actual carbon emissions of a device are 50 kg and the actual carbon savings are 10 kg, these two values ​​can be added as new attributes to the data object of the device, and the data object of each device can be updated in real time to ensure that the data in the data twin model is always up to date.

[0160] Synchronize the updated data object to the database of the data twin model. Specifically, the updated data object can be saved to the database of the data twin model for subsequent query and analysis. For example, the data object with ID "M12345" can be saved to the database together with its actual carbon emissions and actual carbon savings to ensure the consistency and integrity of the data and facilitate subsequent visualization.

[0161] In response to receiving a query instruction corresponding to the device ID, the updated data object corresponding to the device ID is called from the database, and the updated data object is displayed in the visualization interface of the data twin model to display the actual carbon emissions and actual carbon savings corresponding to the device ID in real time. Specifically, when a user or system issues a query instruction, the updated data object corresponding to the device ID can be called from the database, and the data can be displayed in the visualization interface of the data twin model. For example, if a user queries the actual carbon emissions and actual carbon savings of a device with an ID of "M12345", the data object can be called from the database, and its actual carbon emissions of 50 kg and actual carbon savings of 10 kg can be displayed in the visualization interface. In this way, the actual carbon emissions and actual carbon savings of each device can be displayed in real time, providing intuitive data support for the factory's energy conservation and carbon reduction management.

[0162] This implementation can visualize the actual carbon emissions and actual carbon savings of the equipment in the data twin model, so that factory managers can intuitively understand the operating status of the equipment and the energy-saving and carbon-reduction effects.

[0163] In one implementation of this embodiment, the following steps are also included:

[0164] S810, in response to receiving an interaction request from the associated platform to the integrated management platform, obtaining a version number of the associated platform;

[0165] S820. Use the preset version control logic to route the version number to the corresponding API interface of the integrated management platform.

[0166] Figure 3 A data interface transmission flow chart of a comprehensive management platform provided by an embodiment of the present application is shown. Figure 3 As shown, in response to receiving an interaction request from an associated platform to the integrated management platform, the version number of the associated platform is obtained. Specifically, when an associated platform (such as other systems or applications) sends an interaction request to the integrated management platform, the version number of the associated platform can be automatically identified and obtained. The version number is an identifier used to distinguish different versions of software or systems. For example, if the associated platform is an energy management system, its version number may be "V1.2.3". The version number can be extracted from the interaction request to provide a basis for subsequent version control.

[0167] The preset version control logic is used to route the version number to the corresponding API interface of the integrated management platform. Specifically, the obtained version number can be routed to the corresponding API interface in the integrated management platform according to the preset version control logic. The version control logic usually includes a mapping table, which records the API interfaces corresponding to different version numbers. For example, if an associated platform with a version number of "V1.2.3" needs to access a specific function of the integrated management platform, the request can be routed to the corresponding API interface according to the mapping table. This ensures that associated platforms of different versions can correctly access the corresponding functions of the integrated management platform, avoiding functional anomalies or data errors caused by version incompatibility.

[0168] This implementation method realizes version control of the interaction between the association platform and the integrated management platform, ensuring that different versions of the association platform can correctly access the corresponding functions of the integrated management platform. It not only solves the system anomaly problem caused by traditional version incompatibility, but also improves the stability and reliability of the system. Through the preset version control logic, a more accurate API interface routing can be provided to help the association platform achieve more efficient system integration.

[0169] The present application also provides a server, including:

[0170] a memory configured to store instructions; and

[0171] The processor is configured to call instructions from the memory and implement the above-mentioned energy-saving and carbon-reduction control method based on AI intelligent assistance when executing the instructions.

[0172] The present application also provides a comprehensive management platform. Figure 4 A schematic diagram of the structure of a comprehensive management platform provided by an embodiment of the present application is shown. Figure 4 As shown, the integrated management platform includes a data twin module. The integrated management platform and the energy-saving management cloud control platform transmit data through a preset interface, and also include:

[0173] The first data acquisition module 10 is used to acquire the energy-saving data of each device of the target factory in real time through the energy-saving management cloud control platform, and calculate the carbon emissions of each device according to the energy-saving data of each device;

[0174] The first AI calculation module 20 is used to obtain the carbon emission plan of the target factory and the characteristic curve of each device, and use the first AI processing logic to determine the optimal carbon emission of the target factory according to the carbon emission plan and the characteristic curve of each device;

[0175] The second AI calculation module 30 is used to determine the target power allocation plan for each device in the target factory in a preset time period in the future according to the optimal carbon emissions by using the second AI processing logic, and send the target power allocation plan to the energy-saving management cloud control platform, so that the energy-saving management cloud control platform generates a device control instruction for each device according to the target power allocation plan, and sends the device control instruction to the corresponding device;

[0176] The second data acquisition module 40 is used to calculate the actual carbon emissions and actual carbon savings of each device in the target factory according to the plan execution data and the carbon emissions of each device in response to receiving the plan execution data of each device returned by the energy-saving management cloud control platform;

[0177] The display module 50 is used to obtain the device ID of each device, and according to the device ID of each device and the corresponding actual carbon emissions and the corresponding actual carbon savings, add the attributes of the data object of each device in the data twin model of the target factory, so as to display the actual carbon savings and actual carbon emissions of each device in the target factory in real time through the data objects in the data twin model in the data twin module.

[0178] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0179] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0180] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0182] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0183] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0184] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0185] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0186] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An energy-saving and carbon-reduction control method based on AI intelligent assistance, characterized in that: Applied to a server, the server is deployed with an integrated management platform, the integrated management platform includes a data twin module, the integrated management platform and the energy-saving management cloud control platform perform data transmission through a preset interface, and the method includes: The energy-saving data of each device in the target factory is obtained in real time through the energy-saving management cloud control platform, and the carbon emissions of each device are calculated according to the energy-saving data of each device, wherein the devices include motors and inverters; Obtaining a carbon emission plan of the target factory and a characteristic curve of each of the equipment, and using a first AI processing logic to determine an optimal carbon emission amount of the target factory according to the carbon emission plan and the characteristic curve of each of the equipment; Adopting the second AI processing logic, determining the target power allocation plan for each of the equipment in the target factory in a preset time period in the future according to the optimal carbon emissions, and sending the target power allocation plan to the energy-saving management cloud control platform, so that the energy-saving management cloud control platform generates a device control instruction for each of the equipment according to the target power allocation plan, and sends the device control instruction to the corresponding equipment; In response to receiving the plan execution data of each of the devices returned by the energy-saving management cloud control platform, calculating the actual carbon emissions and actual carbon savings of each of the devices in the target factory according to the plan execution data and the carbon emissions of each of the devices; Obtain the device ID of each of the devices, and based on the device ID of each of the devices and the corresponding actual carbon emissions and the corresponding actual carbon savings, add attributes of the data object of each of the devices in the data twin model of the target factory, so as to display the actual carbon savings and the actual carbon emissions of each of the devices in the target factory in real time through the data objects in the data twin model in the data twin module.

2. The method according to claim 1, characterized in that The first AI processing logic includes: Determine the operating range and upper limit carbon emission of each device according to the carbon emission plan and the characteristic curve of each device; Constructing a multi-objective function, wherein the multi-objective function includes an objective function of minimizing total carbon emissions, an objective function of maximizing equipment efficiency, and an objective function of minimizing energy consumption cost, wherein the objective function of minimizing total carbon emissions is the main objective function, and the objective function of maximizing equipment efficiency and the objective function of minimizing energy consumption cost are secondary objective functions; The operating range of each of the equipment and the upper limit carbon emissions of the target plant are used as first constraints of the main objective function, and the main objective function is solved by a preset first solution algorithm to obtain a first total carbon emissions; The secondary objective function is used as a second constraint condition of the main objective function, and a preset second solution algorithm is used to solve the main objective function to obtain a second total carbon emission; The smallest value between the first total carbon emissions and the second total carbon emissions is taken as the optimal carbon emissions of the target plant.

3. The method according to claim 2, characterized in that The method of using the secondary objective function as a second constraint condition of the main objective function and using a preset second solution algorithm to solve the main objective function to obtain a second total carbon emission includes: Converting the secondary objective function into a second constraint condition, wherein the second constraint condition includes that a solution of the objective function of maximizing equipment efficiency is greater than or equal to a preset minimum efficiency, and a solution of the objective function of minimizing energy consumption cost is less than or equal to a preset maximum cost; Using a preset second solving algorithm to solve the main objective function whose constraint condition is the second constraint condition, and using a preset optimization algorithm to solve the minimum energy consumption cost objective function, so as to optimize the expected energy consumption of each of the devices and minimize the value of the main objective function; The minimum value of the main objective function is taken as the second total carbon emissions.

4. The method according to claim 3, characterized in that: The second AI processing logic includes: Obtain the predicted electricity demand and grid load for a preset time period in the future; Dividing the future preset time period into a peak period and / or an off-peak period according to the predicted power demand and the grid load; The target power distribution plan for each of the equipment in the target factory during the peak period and / or the off-peak period is determined according to the optimized expected energy consumption of each of the equipment and the optimal carbon emissions.

5. The method according to claim 4, characterized in that Determining the target power distribution plan for each device in the target factory during the peak period and / or the off-peak period according to the optimized expected energy consumption of each device and the optimal carbon emissions includes: When the future preset time period includes the peak period and the off-peak period, obtaining electricity price information of the peak period and the off-peak period; Predicting the power demand of each device during the peak period and the off-peak period according to a pre-built regression model; A total cost minimization objective function is constructed according to the electricity price information, the electricity demand of each of the devices during the peak period and the off-peak period, the expected energy consumption of each of the devices after optimization, and the optimal carbon emissions, wherein the total cost minimization includes minimizing the electricity cost and minimizing the carbon emission cost, and the third constraint condition of the total cost minimization objective function includes that the electricity allocated to each of the devices is greater than or equal to the corresponding electricity demand, the expected energy consumption of each of the devices is less than or equal to the allocated electricity, and the total carbon emissions generated by the electricity allocated to all of the devices is less than or equal to the optimal carbon emissions; A preset genetic algorithm is used to solve the objective function of minimizing the total cost, and the power distribution plan corresponding to the optimal solution that satisfies all the third constraints and the objective function of minimizing the total cost is taken as the target power distribution plan.

6. The method according to claim 1, characterized in that The planned execution data includes the power consumption value of each of the devices, and the actual carbon emissions and actual carbon savings of each of the devices in the target factory are calculated based on the planned execution data and the carbon emissions of each of the devices, including: Obtaining a carbon emission factor for each of the devices; For each of the equipment, the product of the corresponding carbon emission factor and the corresponding electric energy consumption value is used as the actual carbon emission of each of the equipment in the target factory; The difference between the carbon emission of each of the equipment and the corresponding actual carbon emission is used as the actual carbon saving of each of the equipment in the target factory.

7. The method according to claim 1, characterized in that According to the device ID of each device and the corresponding actual carbon emissions and the corresponding actual carbon savings, in the data twin model of the target plant, attributes of the data object of each device are added to display the actual carbon savings and the actual carbon emissions of each device of the target plant in real time through the data objects in the data twin model in the data twin module, including: Searching for a corresponding data object in the data twin model according to the device ID; Adding the actual carbon emissions and the actual carbon savings corresponding to the device ID as new attributes to the attributes of the data object to update the data object of the data twin model; Synchronizing the updated data object to the database of the data twin model; In response to receiving a query instruction corresponding to the device ID, the updated data object corresponding to the device ID is called from the database, and the updated data object is displayed in the visualization interface of the data twin model to display the actual carbon emissions and the actual carbon savings corresponding to the device ID in real time.

8. The method according to claim 1, characterized in that The method further comprises: In response to receiving an interaction request from the associated platform to the integrated management platform, obtaining a version number of the associated platform; The preset version control logic is used to route the version number to the corresponding API interface of the integrated management platform.

9. A server, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instruction from the memory and to implement the energy-saving and carbon-reduction control method based on AI intelligent assistance according to any one of claims 1 to 8 when executing the instruction.

10. An integrated management platform, characterized in that: The energy conservation and carbon reduction control method based on AI intelligence assistance applied to any one of claims 1 to 8, wherein the integrated management platform includes a data twin module, and the integrated management platform and the energy conservation management cloud control platform perform data transmission through a preset interface, and further includes: A first data acquisition module is used to acquire the energy-saving data of each device of the target factory in real time through the energy-saving management cloud control platform, and calculate the carbon emissions of each device according to the energy-saving data of each device; a first AI calculation module, configured to obtain a carbon emission plan of the target plant and a characteristic curve of each of the equipment, and to determine an optimal carbon emission amount of the target plant according to the carbon emission plan and the characteristic curve of each of the equipment using a first AI processing logic; A second AI calculation module is used to use a second AI processing logic to determine a target power allocation plan for each of the devices in the target factory in a preset future time period according to the optimal carbon emissions, and send the target power allocation plan to the energy-saving management cloud control platform, so that the energy-saving management cloud control platform generates a device control instruction for each of the devices according to the target power allocation plan, and sends the device control instruction to the corresponding device; A second data acquisition module is used to calculate the actual carbon emissions and actual carbon savings of each device in the target factory according to the plan execution data and the carbon emissions of each device in response to receiving the plan execution data of each device returned by the energy-saving management cloud control platform; A display module is used to obtain the device ID of each of the devices, and according to the device ID of each of the devices and the corresponding actual carbon emissions and the corresponding actual carbon savings, add attributes of the data object of each of the devices in the data twin model of the target factory, so as to display the actual carbon savings and the actual carbon emissions of each of the devices in the target factory in real time through the data objects in the data twin model in the data twin module.

Images