Industrial equipment energy consumption dynamic prediction method of energy-carbon model
By obtaining the operating status data of industrial equipment in real time, establishing an energy carbon model and making predictions, the problem of inaccurate dynamic prediction of energy consumption in the existing technology is solved, and real-time optimization of energy and improvement of management efficiency is achieved.
Patent Information
- Application Number
- CN202510026245.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-08
- Publication Date
- 2025-06-06
AI Technical Summary
The prior art cannot accurately reflect the power consumption of industrial equipment, resulting in inaccuracy of dynamic prediction of energy consumption, which in turn affects the real-time optimization of energy and equipment management efficiency.
By obtaining the operating status data of industrial equipment in real time, calculate useful electricity data, electricity loss data, energy effective utilization rate and energy loss rate, and determine whether the equipment is in energy equilibrium state. If it is unbalanced, an energy carbon model is established, the carbon emission trend is predicted through differential, autoregressive and sliding average operations, and the energy carbon coefficient and intercept term are calculated using the covariance algorithm to dynamically adjust the energy input.
It improves the reliability and accuracy of dynamic prediction of industrial equipment energy consumption, realizes real-time energy optimization, reduces human intervention, and improves management efficiency.
Smart Images
Figure CN120106268A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of dynamic prediction of energy consumption, and in particular to a method for dynamic prediction of energy consumption of industrial equipment based on an energy-carbon model. Background Art
[0002] In practical applications, the energy-carbon model's industrial equipment energy consumption dynamic prediction system can be customized according to the needs of specific industries and enterprises, including the development of special prediction models for different production lines and equipment types in the steel, chemical, and electric power industries. Through accurate energy consumption prediction, enterprises can not only effectively reduce operating costs, but also actively respond to national and regional energy conservation and emission reduction policies and contribute to sustainable development. Since current industrial equipment only relies on single data to reflect the power consumption of industrial equipment, it is impossible to accurately reflect the power consumption of industrial equipment, which leads to an imbalance in the energy input to industrial equipment and reduces the accuracy of predicting the energy consumption dynamics of industrial equipment. When the accuracy of predicting the energy consumption dynamics of industrial equipment is reduced, the trend analysis is inaccurate, and the future direction of energy consumption changes cannot be accurately judged. It is impossible to dynamically adjust the energy input of industrial equipment and realize real-time optimization of energy, resulting in reduced management efficiency of industrial equipment. Summary of the invention
[0003] The purpose of the present invention is to provide a method for dynamically predicting the energy consumption of industrial equipment based on an energy-carbon model, which improves the reliability and accuracy of predicting the dynamic energy consumption of industrial equipment. At the same time, combined with the prediction results, the energy input of industrial equipment can be dynamically adjusted to achieve real-time optimization of energy and improve management efficiency, so as to solve the problems raised in the above background technology.
[0004] To achieve the above object, the present invention provides a method for dynamically predicting energy consumption of industrial equipment based on an energy-carbon model, comprising the following method steps: S1. Obtain the operating status data of industrial equipment in real time and calculate the input power data of industrial equipment. Calculate the useful power data, power loss data, energy effective utilization rate, energy loss rate and determine whether the industrial equipment is in an energy balance state according to the input power data of industrial equipment. S2. When industrial equipment is in an energy imbalance state, the carbon emissions are calculated based on the input industrial equipment power data and an energy-carbon model is established. The carbon emissions of the energy-carbon model are subjected to differential operation, autoregressive operation and sliding average operation, and then a comprehensive algorithm is used to predict the carbon emissions trend of industrial equipment based on the carbon emissions of differential operation, autoregressive operation and sliding average operation; S3 calculates the average electricity consumption data based on the input industrial equipment electricity data, and then calculates the average carbon emissions based on the carbon emissions. It uses the covariance algorithm to calculate the covariance of electricity consumption and carbon emissions based on the carbon emissions, average electricity consumption data, and average carbon emissions. It then calculates the energy-carbon coefficient and the energy-carbon intercept term and predicts the dynamic electricity consumption data. It then uses the predicted dynamic electricity consumption data to determine whether to adjust the power energy of the industrial equipment.
[0005] As a further improvement of the technical solution, the S1 specifically comprises the following method steps: S1.1. Calculate the input power data of industrial equipment by acquiring the operating status data of industrial equipment in real time, and record the motor efficiency, transmission efficiency and carbon emission factor of industrial equipment. Calculate the useful power data based on the input power data of industrial equipment, motor efficiency and transmission efficiency, and obtain the power loss data by subtracting the useful power data from the input power data of industrial equipment; S1.2. Calculate the effective energy utilization rate by inputting the industrial equipment power data and useful power data, calculate the energy loss rate of the industrial equipment by using the power loss data and the input industrial equipment power data, and then use the effective energy utilization rate, energy loss rate, input industrial equipment power data, useful power data and power loss data to judge whether the industrial equipment is in an energy balance state.
[0006] As a further improvement of the technical solution, the specific judgment of S1.2 in S1 includes: Case ①: When the energy effective utilization rate is within the set standard energy effective utilization rate range, the energy loss rate is within the set standard energy loss rate range, and the input industrial equipment power data, useful power data and power loss data are within the set corresponding range thresholds, the industrial equipment is judged to be in an energy balance state; Case ②: When the energy effective utilization rate is not within the set standard energy effective utilization rate range value or the energy loss rate is not within the set standard energy loss rate range value, or the input industrial equipment power data, useful power data and power loss data are not within the set corresponding range thresholds, the industrial equipment is determined to be in an energy imbalance state.
[0007] As a further improvement of the technical solution, the S2 specifically comprises the following method steps: S2.1. When industrial equipment is in an energy imbalance state, the carbon emissions are calculated based on the input industrial equipment power data and the power carbon emission factor. The energy-carbon model is established based on the input industrial equipment power data and the carbon emissions using a linear regression algorithm. The energy-carbon model uses a differential part algorithm to perform differential operations on the carbon emissions and; S2.2. The energy-carbon model is used to perform autoregressive and sliding average operations on carbon emissions, and a comprehensive algorithm is used to predict the trend of carbon emissions from industrial equipment based on the carbon emissions from differential operations, autoregressive operations, and sliding average operations.
[0008] As a further improvement of the technical solution, the implementation principle of S2.2 in S2 for predicting the trend of carbon emissions of industrial equipment using a comprehensive algorithm is as follows: Collect the carbon emissions of industrial equipment operated by differential operation, the carbon emissions of industrial equipment operated by autoregressive operation and the carbon emissions of industrial equipment operated by sliding average operation to predict the trend of carbon emissions of industrial equipment and obtain the predicted trend of carbon emissions of industrial equipment , the specific algorithm formula is: .
[0009] As a further improvement of the technical solution, the S3 specifically comprises the following method steps: S3.1. Calculate the average power consumption data based on the input power data of industrial equipment using the average algorithm, calculate the average carbon emissions based on the carbon emissions using the average algorithm, and calculate the covariance of power consumption and carbon emissions based on the carbon emissions, the average power consumption data and the average carbon emissions using the covariance algorithm; S3.2. Calculate the variance of carbon emissions based on carbon emissions and average carbon emissions using the variance algorithm, input the covariance of electricity consumption and carbon emissions, the variance of carbon emissions, the average electricity consumption data and the average carbon emissions into the energy-carbon model, and calculate the energy-carbon coefficient based on the covariance of electricity consumption and carbon emissions and the variance of carbon emissions. The energy-carbon model then calculates the energy-carbon intercept term based on the average electricity consumption data, the average carbon emissions and the energy-carbon coefficient. Use the predicted carbon emissions trend of industrial equipment, the energy-carbon coefficient and the energy-carbon intercept term to predict the dynamics of electricity consumption, calculate the target electricity consumption threshold based on carbon emissions, the energy-carbon coefficient and the energy-carbon intercept term, and then use the predicted dynamics of electricity consumption data and the target electricity consumption threshold to determine whether to adjust the power energy of industrial equipment.
[0010] As a further improvement of the technical solution, the specific judgment conditions of S3.2 in S3 in S3 include: Case 1: When the predicted dynamic data of electric energy consumption is greater than the target electric energy consumption threshold, the adjustment factor algorithm is triggered. The energy balance adjustment factor of the industrial equipment is calculated according to the input electric energy data of the industrial equipment and the target electric energy consumption threshold by using the adjustment factor algorithm. The electric energy of the industrial equipment is adjusted by the energy balance adjustment factor of the industrial equipment to make the energy of the industrial equipment balanced. If the energy balance adjustment factor of the industrial equipment is greater than 1, the electric energy input of the industrial equipment is increased. If the energy balance adjustment factor of the industrial equipment is less than 1, the electric energy input of the industrial equipment is reduced. Case 2: When the predicted power consumption dynamic data is less than the target power consumption threshold, the adjustment factor algorithm is not triggered.
[0011] Compared with the prior art, the present invention has the following beneficial effects: The invention discloses a method for dynamically predicting energy consumption of industrial equipment based on an energy-carbon model. The method calculates the variance of carbon emissions according to carbon emissions and average carbon emissions. The energy-carbon model calculates the energy-carbon coefficient according to the covariance of electric energy consumption and carbon emissions and the variance of carbon emissions. The energy-carbon model then calculates the energy-carbon intercept term according to the average electric energy consumption data, the average carbon emissions and the energy-carbon coefficient. The predicted carbon emissions trend of industrial equipment, the energy-carbon coefficient and the energy-carbon intercept term are used to predict the dynamics of electric energy consumption. The target electric energy consumption threshold is calculated according to the carbon emissions, the energy-carbon coefficient and the energy-carbon intercept term, and it is determined whether to adjust the electric energy of the industrial equipment. By comprehensively considering the carbon emissions trend, the energy-carbon coefficient and the energy-carbon intercept term, the electric energy consumption of the industrial equipment can be more accurately reflected, and it is avoided to rely on the singleness of the data, thereby improving the reliability and accuracy of predicting the dynamics of energy consumption of the industrial equipment. At the same time, combined with the prediction results, the energy input of the industrial equipment can be dynamically adjusted to realize the real-time optimization of energy, reduce human intervention and improve management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Figure 1 It is a flowchart of the overall steps of the present invention. DETAILED DESCRIPTION
[0013] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0014] Example 1 The present invention provides a method for dynamically predicting the energy consumption of industrial equipment based on an energy-carbon model. Figure 1 , comprising the following method steps: S1 has the following specific steps: S1. Obtain the operating status data of industrial equipment in real time to calculate the input power data of industrial equipment, calculate the useful power data, power loss data, energy effective utilization rate, energy loss rate based on the input power data of industrial equipment, and determine whether the industrial equipment is in an energy balance state.
[0015] S1.1. Obtain the operating status data of industrial equipment in real time through various sensors (including current sensors, voltage sensors, temperature sensors, and pressure sensors) installed at key parts of industrial equipment, and record the efficiency of the motors of industrial equipment. (the efficiency of the motor in converting electrical energy into mechanical energy) and transmission efficiency (the efficiency with which the electric motor converts electrical energy into mechanical energy), and the carbon emission factor for electrical energy , collect current data from the acquired operating status data , voltage data , Data collection time , according to the current data , voltage data , Data collection time Calculate input power data for industrial equipment , record the number of times the power data of industrial equipment is input and input time The unit of the input industrial equipment power data is kilowatt-hour / kWh, and dividing by 1000 means converting the unit of the input industrial equipment power data into watt-hour / Wh, and then converting the unit of the input industrial equipment power data into watt-hour / Wh. , Motor efficiency and transmission efficiency Calculate the useful power data of industrial equipment (referring to the effective power actually used by industrial equipment to complete its functions) , among which, useful power data The unit is kilowatt-hour / kWh, using the input industrial equipment power data Subtract useful energy data Get power loss data of industrial equipment , where the unit of power loss data is kilowatt-hour / kWh.
[0016] S1.2. By inputting the power data of industrial equipment and useful energy data Calculate the energy efficiency of industrial equipment , using power loss data and input industrial equipment energy data Calculate the energy loss rate of industrial equipment , Reuse energy effective utilization rate , Energy loss rate , Input industrial equipment power data , Useful power data and power loss data Make a judgment to determine whether the industrial equipment is in a state of energy balance.
[0017] The specific judgment conditions of S1.2 in S1 include: Case 1: When the energy efficiency is Within the set standard energy efficiency range, the energy loss rate Within the set standard energy loss rate range, and input industrial equipment power data , Useful power data and power loss data When the energy levels are respectively within the set corresponding range thresholds, it is determined that the industrial equipment is in an energy balance state; Case ②: When the energy efficiency is Not within the set standard energy efficiency range or energy loss rate The energy loss rate is not within the set standard range, or the input industrial equipment power data , Useful power data and power loss data When the energy consumption of the industrial equipment is not within the set corresponding range threshold, it is determined that the industrial equipment is in an energy imbalance state.
[0018] S2 has the following specific steps: S2. When industrial equipment is in an energy imbalance state, the carbon emissions are calculated based on the input industrial equipment power data and an energy-carbon model is established. The carbon emissions of the energy-carbon model are subjected to differential operation, autoregressive operation and sliding average operation, and then a comprehensive algorithm is used to predict the carbon emissions trend of industrial equipment based on the carbon emissions of differential operation, autoregressive operation and sliding average operation; S2.1. When industrial equipment is in an energy imbalance state, according to the input industrial equipment power data and electricity carbon emission factor Calculating the carbon footprint of industrial equipment , recording carbon emissions from industrial equipment , using linear regression algorithm based on the input industrial equipment power data and carbon emissions from industrial equipment The energy-carbon model is established. The energy-carbon model uses the differential partial algorithm to calculate the carbon emissions of industrial equipment. and time to calculate carbon emissions conduct The carbon emissions of industrial equipment from differential operations are obtained , where 1 refers to the constant term, refers to the lag operator, refers to the order of difference, which is used to make the time series stable. Refers to time Carbon emissions from industrial equipment calculated at the time of use.
[0019] The steps to establish the energy-carbon model using the linear regression algorithm are as follows: Step 1: Input the power data of industrial equipment and carbon emissions from industrial equipment Input into the linear model for normalized learning, and the linear model outputs the corresponding model parameters and .
[0020] Step 2: Input industrial equipment power data , Carbon emissions from industrial equipment , model parameters and Building an energy-carbon model , the specific algorithm formula is: ; in, refers to the intercept in the linear model, Refers to the input of industrial equipment power data and carbon emissions from industrial equipment The error in the linear model output is input into the linear model. This formula is used to establish an energy-carbon model. Through the energy-carbon model, the long-term trend of carbon emissions can be analyzed to provide data support for the formulation of energy and carbon emission policies.
[0021] S2.2 Carbon emissions from industrial equipment through energy-carbon model , Calculate the time of carbon emissions and hysteresis operator conduct The carbon emissions of industrial equipment are obtained by autoregressive operation, and then the carbon emissions of industrial equipment are calculated by the sliding average algorithm through the energy-carbon model. , Calculate the time of carbon emissions and hysteresis operator conduct A sliding average operation is performed, and a comprehensive algorithm is used to predict the trend of industrial equipment carbon emissions based on the carbon emissions of industrial equipment through differential operation, autoregressive operation and sliding average operation. The seasonality of industrial equipment carbon emissions is eliminated through differential operation, the autoregressive operation captures the autocorrelation of industrial equipment carbon emissions, and the sliding average operation smoothes the industrial equipment carbon emissions data, which can reduce the prediction error of the model and enhance the robustness of the model.
[0022] The algorithm formula of industrial equipment carbon emissions based on autoregressive operation is: ; Among them, 1 refers to the constant term, refers to the first autoregressive coefficient, Refers to the The autoregressive coefficients, In refers to the order of the autoregressive term, Refers to time Carbon emissions from industrial equipment calculated at Refers to time The carbon emissions of industrial equipment calculated at the time of the calculation are used to perform autoregressive operations on the carbon emissions of industrial equipment. By fitting the autocorrelation in the data, the fitting effect of the energy-carbon model can be improved, thereby improving the prediction accuracy.
[0023] The implementation steps of using the sliding average partial algorithm to perform sliding average operation on the carbon emissions of industrial equipment are as follows: Step 1: Collect carbon emissions from industrial equipment , Calculate the time of carbon emissions and hysteresis operator , the lag operator Input the sliding model to learn and output the corresponding sliding coefficient and error term .
[0024] Step 2: Based on the carbon emissions of industrial equipment , Calculate the time of carbon emissions , hysteresis operator , sliding coefficient and error term conduct The sliding average operation is performed to obtain the carbon emissions of industrial equipment by the sliding average operation. The specific algorithm formula is: ; in, Refers to the first sliding coefficient, Refers to the The sliding coefficient, In refers to the order of the sliding average term, Refers to time Carbon emissions from industrial equipment calculated at Refers to time Carbon emissions from industrial equipment calculated at refers to the first error term, Refers to the The formula is used to perform a sliding average operation on the carbon emissions of industrial equipment. By smoothing the data, the impact of noise on the model can be reduced and the stability and reliability of the model can be improved.
[0025] The implementation principle of S2.2 in S2 for predicting the carbon emission trend of industrial equipment using a comprehensive algorithm: Collect the carbon emissions of industrial equipment operated by differential operation, the carbon emissions of industrial equipment operated by autoregressive operation and the carbon emissions of industrial equipment operated by sliding average operation to predict the trend of carbon emissions of industrial equipment and obtain the predicted trend of carbon emissions of industrial equipment , the specific algorithm formula is: ; Among them, this formula is used to predict the trend of carbon emissions from industrial equipment. The seasonality of carbon emissions from industrial equipment is eliminated through differential operation, the autoregressive operation is used to capture the autocorrelation of carbon emissions from industrial equipment, and the sliding average operation is used to smooth the carbon emissions data from industrial equipment. This can reduce the prediction error of the model and enhance the robustness of the model.
[0026] S3 has the following specific steps: S3 calculates the average electricity consumption data based on the input industrial equipment electricity data, and then calculates the average carbon emissions based on the carbon emissions. It uses the covariance algorithm to calculate the covariance of electricity consumption and carbon emissions based on the carbon emissions, average electricity consumption data, and average carbon emissions. It then calculates the energy-carbon coefficient and the energy-carbon intercept term and predicts the dynamic electricity consumption data. It then uses the predicted dynamic electricity consumption data to determine whether to adjust the power energy of the industrial equipment.
[0027] S3.1. Using the average algorithm to input the power data of industrial equipment , the number of times the industrial equipment power data is input and input time Calculate average power consumption data ,in, Refers to time Input the power data of industrial equipment at any time, and then use the average algorithm to calculate the carbon emissions of industrial equipment. and carbon emissions from industrial equipment Calculating average carbon emissions , using the covariance algorithm according to the number of times the industrial equipment power data is input , enter time , Carbon emissions from industrial equipment , average power consumption data , average carbon emissions Calculate the covariance of electricity consumption and carbon emissions to obtain the covariance of electricity consumption and carbon emissions ,Through covariance analysis, abnormal fluctuations in electricity consumption and carbon ,emissions can be identified, and timely measures can be taken to make adjustments, ,which can improve the comprehensive performance of the prediction.
[0028] The algorithm formula for calculating the covariance of electricity consumption and carbon emissions using the covariance algorithm is: ; Among them, this formula is used to calculate the covariance of electricity consumption and carbon emissions. Through covariance analysis, abnormal fluctuations in electricity consumption and carbon emissions can be identified, and timely measures can be taken to make adjustments.
[0029] S3.2. Using variance algorithm to calculate carbon emissions from industrial equipment , carbon emissions from industrial equipment and average carbon emissions Calculating the variance of carbon emissions from industrial facilities , the covariance of electricity consumption and carbon emissions , Variance of carbon emissions from industrial equipment , average power consumption data and average carbon emissions The input energy-carbon model is based on the covariance of electricity consumption and carbon emissions. and the variance of carbon emissions from industrial equipment Calculate the energy-carbon coefficient The energy carbon model is then based on the average electricity consumption data , average carbon emissions Energy Carbon Coefficient Calculate the energy carbon intercept , using the predicted carbon emissions trends of industrial equipment , Energy-carbon coefficient Energy carbon intercept Carry out dynamic prediction of power consumption and obtain the predicted dynamic data of power consumption , based on the carbon emissions of industrial equipment , Energy-carbon coefficient Energy carbon intercept Calculate target power consumption threshold , and then use the predicted power consumption dynamic data and target power consumption threshold By comprehensively considering the carbon emission trend, energy-carbon coefficient and energy-carbon intercept term, it is possible to more accurately reflect the electricity consumption of industrial equipment and avoid relying on the singleness of data. This improves the reliability and accuracy of predicting the energy consumption dynamics of industrial equipment. At the same time, combined with the prediction results, the energy input of industrial equipment can be dynamically adjusted to achieve real-time optimization of energy, reduce human intervention and improve management efficiency.
[0030] The specific judgment conditions of S3.2 in S3 include: Case 1: When the predicted power consumption dynamic data Greater than the target power consumption threshold When the adjustment factor algorithm is triggered, the adjustment factor algorithm is used to input the power data of industrial equipment. and target power consumption threshold Calculation of energy balance adjustment factors for industrial plants , through the energy balance adjustment factor of industrial equipment Regulate the power energy of industrial equipment to balance the energy of industrial equipment. If the energy balance adjustment factor of industrial equipment is greater than 1, increase the power energy input of industrial equipment. If the energy balance adjustment factor of industrial equipment is less than 1, reduce the power energy input of industrial equipment. Case 2: When the predicted power consumption dynamic data Less than the target power consumption threshold , the adjustment factor algorithm is not triggered.
[0031] The algorithm formula for calculating the variance of carbon emissions of industrial equipment using the variance algorithm is: ; Among them, this formula is used to calculate the variance of carbon emissions from industrial equipment. By analyzing the changes in the variance over time, it can predict future carbon emission trends and provide a basis for long-term planning.
[0032] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A method for dynamic prediction of energy consumption of industrial equipment based on an energy-carbon model, characterized in that: The method comprises the following steps: S1. Obtain the operating status data of industrial equipment in real time and calculate the input power data of industrial equipment. Calculate the useful power data, power loss data, energy effective utilization rate, energy loss rate and determine whether the industrial equipment is in an energy balance state according to the input power data of industrial equipment. S2. When industrial equipment is in an energy imbalance state, the carbon emissions are calculated based on the input industrial equipment power data and an energy-carbon model is established. The carbon emissions of the energy-carbon model are subjected to differential operation, autoregressive operation and sliding average operation, and then a comprehensive algorithm is used to predict the carbon emissions trend of industrial equipment based on the carbon emissions of differential operation, autoregressive operation and sliding average operation; S3 calculates the average electricity consumption data based on the input industrial equipment electricity data, and then calculates the average carbon emissions based on the carbon emissions. It uses the covariance algorithm to calculate the covariance of electricity consumption and carbon emissions based on the carbon emissions, average electricity consumption data, and average carbon emissions. It then calculates the energy-carbon coefficient and the energy-carbon intercept term and predicts the dynamic electricity consumption data. It then uses the predicted dynamic electricity consumption data to determine whether to adjust the power energy of the industrial equipment.
2. The method for dynamic prediction of industrial equipment energy consumption based on an energy-carbon model according to claim 1 is characterized in that: The S1 specifically includes the following steps: S1.
1. Calculate the input power data of industrial equipment by acquiring the operating status data of industrial equipment in real time, and record the motor efficiency, transmission efficiency and carbon emission factor of industrial equipment. Calculate the useful power data based on the input power data of industrial equipment, motor efficiency and transmission efficiency, and obtain the power loss data by subtracting the useful power data from the input power data of industrial equipment; S1.
2. Calculate the effective energy utilization rate by inputting the industrial equipment power data and useful power data, calculate the energy loss rate of the industrial equipment by using the power loss data and the input industrial equipment power data, and then use the effective energy utilization rate, energy loss rate, input industrial equipment power data, useful power data and power loss data to judge whether the industrial equipment is in an energy balance state.
3. The method for dynamic prediction of energy consumption of industrial equipment based on an energy-carbon model according to claim 2 is characterized in that: The specific judgment of S1.2 in S1 includes: Case ①: When the energy effective utilization rate is within the set standard energy effective utilization rate range, the energy loss rate is within the set standard energy loss rate range, and the input industrial equipment power data, useful power data and power loss data are within the set corresponding range thresholds, the industrial equipment is judged to be in an energy balance state; Case ②: When the energy effective utilization rate is not within the set standard energy effective utilization rate range value or the energy loss rate is not within the set standard energy loss rate range value, or the input industrial equipment power data, useful power data and power loss data are not within the set corresponding range thresholds, the industrial equipment is determined to be in an energy imbalance state.
4. The method for dynamic prediction of energy consumption of industrial equipment based on an energy-carbon model according to claim 2 is characterized in that: The S2 specifically includes the following steps: S2.
1. When industrial equipment is in an energy imbalance state, the carbon emissions are calculated based on the input industrial equipment power data and the power carbon emission factor. The energy-carbon model is established based on the input industrial equipment power data and the carbon emissions using a linear regression algorithm. The energy-carbon model uses a differential part algorithm to perform differential operations on the carbon emissions and; S2.
2. The energy-carbon model is used to perform autoregressive and sliding average operations on carbon emissions, and a comprehensive algorithm is used to predict the trend of carbon emissions from industrial equipment based on the carbon emissions from differential operations, autoregressive operations, and sliding average operations.
5. The method for dynamic prediction of energy consumption of industrial equipment based on an energy-carbon model according to claim 4 is characterized in that: The implementation principle of S2.2 in S2 for predicting the trend of carbon emissions of industrial equipment using a comprehensive algorithm is as follows: Collect the carbon emissions of industrial equipment operated by differential operation, the carbon emissions of industrial equipment operated by autoregressive operation and the carbon emissions of industrial equipment operated by sliding average operation to predict the trend of carbon emissions of industrial equipment and obtain the predicted trend of carbon emissions of industrial equipment , the specific algorithm formula is: 。 6. The method for dynamic prediction of industrial equipment energy consumption based on an energy-carbon model according to claim 4 is characterized in that: The S3 specifically includes the following steps: S3.
1. Calculate the average power consumption data based on the input power data of industrial equipment using the average algorithm, calculate the average carbon emissions based on the carbon emissions using the average algorithm, and calculate the covariance of power consumption and carbon emissions based on the carbon emissions, the average power consumption data and the average carbon emissions using the covariance algorithm; S3.
2. Calculate the variance of carbon emissions based on carbon emissions and average carbon emissions using the variance algorithm, input the covariance of electricity consumption and carbon emissions, the variance of carbon emissions, the average electricity consumption data and the average carbon emissions into the energy-carbon model, and calculate the energy-carbon coefficient based on the covariance of electricity consumption and carbon emissions and the variance of carbon emissions. The energy-carbon model then calculates the energy-carbon intercept term based on the average electricity consumption data, the average carbon emissions and the energy-carbon coefficient. Use the predicted carbon emissions trend of industrial equipment, the energy-carbon coefficient and the energy-carbon intercept term to predict the dynamics of electricity consumption, calculate the target electricity consumption threshold based on carbon emissions, the energy-carbon coefficient and the energy-carbon intercept term, and then use the predicted dynamics of electricity consumption data and the target electricity consumption threshold to determine whether to adjust the power energy of industrial equipment.
7. The method for dynamic prediction of energy consumption of industrial equipment based on an energy-carbon model according to claim 6 is characterized by: The specific judgment conditions of S3.2 in S3.3 include: Case 1: When the predicted dynamic data of electric energy consumption is greater than the target electric energy consumption threshold, the adjustment factor algorithm is triggered. The energy balance adjustment factor of the industrial equipment is calculated according to the input electric energy data of the industrial equipment and the target electric energy consumption threshold by using the adjustment factor algorithm. The electric energy of the industrial equipment is adjusted by the energy balance adjustment factor of the industrial equipment to make the energy of the industrial equipment balanced. If the energy balance adjustment factor of the industrial equipment is greater than 1, the electric energy input of the industrial equipment is increased. If the energy balance adjustment factor of the industrial equipment is less than 1, the electric energy input of the industrial equipment is reduced. Case 2: When the predicted power consumption dynamic data is less than the target power consumption threshold, the adjustment factor algorithm is not triggered.