Heat supply equipment based on computing power and control method

Abstract

The invention discloses heat supply equipment based on computing power and a control method, and belongs to the technical field of heat supply control. The method comprises the following steps: acquiring heat supply data, and performing anomaly detection on the heat supply data; when the heat supply data is not abnormal, the distribution condition of the hot water in the heat supply pipe network is analyzed, and a flow analysis result and a pressure analysis result are obtained; optimizing the operation parameters of the heat supply network, and calculating the heat recovery efficiency of the heat supply network; constructing and training an autoregressive integral moving average model, inputting current power utilization related data and heat recovery efficiency, and outputting a thermal load demand prediction value; influence weights of the indoor temperature and the outdoor temperature on the thermal load demand are determined, a temperature difference is calculated, a temperature correction coefficient is calculated according to the temperature difference, and a thermal load demand prediction value is adjusted by using the temperature correction coefficient; setting a power corresponding relation, and adjusting the power of the electric boiler by stages; the operation time and the stop time of the electric boiler are calculated according to the operation state data of the electric boiler, and the electric boiler is set according to the operation time and the stop time obtained through calculation.

Description

Technical Field

[0001] The present invention relates to the technical field of heating control, and specifically, to a heating device and a control method based on computing power. Background Technique

[0002] With the increasing global emphasis on energy conservation and emission reduction, the heating system, as an important field of energy consumption, faces the urgent need to reduce energy consumption and improve energy utilization efficiency. Traditional heating systems mainly rely on manual experience for regulation, making it difficult to precisely adapt to complex and changing heating demands. In addition, people's requirements for indoor comfort are increasing day by day, expecting the heating system to achieve more precise temperature control to ensure that the indoor temperature is always maintained within a comfortable range.

[0003] In the prior art, the prediction of heat load demand often relies on simple empirical formulas or average analysis of historical data, and cannot fully consider the dynamic changes of various factors such as outdoor temperature, indoor human activities, and building thermal properties. The flow and pressure regulation of each branch pipeline in the heat network mainly rely on manual operation of valves, lacking real-time monitoring and automatic regulation mechanisms. The control of electric boilers usually adopts a fixed operation mode, such as starting and stopping at fixed times or simply adjusting according to a single temperature parameter. Summary of the Invention

[0004] The purpose of the present invention is to provide a heating device and a control method based on computing power to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] In the first aspect, the present application provides a heating device and a control method based on computing power, including the following steps:

[0007] Obtain the operating state data of the electric boiler, the relevant data of the heating system, and the relevant data of electricity consumption, perform preprocessing, and integrate to obtain heating data; perform anomaly detection on the heating data;

[0008] When there is no anomaly in the heating data, based on the relevant data of the heating system, according to the heat network flow and heat network pressure of each branch pipeline of the heat network, analyze the distribution of hot water in the heating pipeline network to obtain a flow analysis result and a pressure analysis result; based on the flow analysis result and the pressure analysis result, optimize the operating parameters of the heat network and calculate the heat recovery efficiency of the heat network;

[0009] Construct and train an autoregressive integrated moving average model, input the current relevant data of electricity consumption and the heat recovery efficiency, and output the predicted value of heat load demand;

[0010] Determine the influence weights of indoor temperature and outdoor temperature on the heat load demand, calculate the temperature difference, calculate the temperature correction coefficient based on the temperature difference, and use the temperature correction coefficient to adjust the predicted value of the heat load demand;

[0011] Based on the adjusted predicted value of the heat load demand, set the power correspondence relationship and adjust the power of the electric boiler in stages; based on the adjusted power of the electric boiler, calculate the operating time and stop time of the electric boiler in combination with the operating state data of the electric boiler, and set the electric boiler using the calculated operating time and stop time.

[0012] Combined with the first aspect, in the first implementation manner of the first aspect of the present application, the obtaining of the operating state data of the electric boiler, the relevant data of the heating system, and the relevant data of electricity consumption, performing preprocessing, and integrating to obtain heating data, including:

[0013] The operating state data of the electric boiler includes the temperature, pressure, power, and water level of the electric boiler; the relevant data of the heating system includes the indoor temperature, outdoor temperature, and heat network data, where the heat network data includes the heat network supply water temperature, heat network return water temperature, heat network flow rate, and heat network pressure; the relevant data of electricity consumption includes the grid voltage and grid current; data cleaning and data normalization are performed on the operating state data of the electric boiler, the relevant data of the heating system, and the relevant data of electricity consumption, and data association is performed based on time to integrate and obtain heating data.

[0014] Combined with the first aspect, in the second implementation manner of the first aspect of the present application, the abnormal detection of the heating data includes:

[0015] According to the design parameters and safe operating range of the electric boiler, determine the temperature thresholds of the heating element, hot water outlet, and furnace body surface; for the internal cavity pressure of the electric boiler, use the rated pressure of the electric boiler as the pressure threshold; use the rated power of the electric boiler as the power threshold; set upper and lower limit thresholds for the water tank water level of the electric boiler; according to the user comfort requirements and heating standards, set the range of indoor temperature; according to the local historical meteorological data, determine the range of outdoor temperature in different seasons and different time periods; in the heat network data thresholds, according to the design parameters and safe operating range of the heat network, determine the thresholds of the heat network supply water temperature, heat network return water temperature, heat network flow rate, and heat network pressure; according to the design parameters and safe operating range of the electric boiler, determine the grid voltage threshold and grid current threshold;

[0016] Set a judgment period, and compare the heating data with the corresponding thresholds within the judgment period to determine whether there is an abnormality in the heating data.

[0017] Combined with the first aspect, in the third implementation manner of the first aspect of the present application, when the heating data is normal, based on the heating system-related data, according to the heating network flow rate and heating network pressure of each branch pipeline of the heating network, analyze the distribution of hot water in the heating pipeline network to obtain a flow analysis result and a pressure analysis result, including:

[0018] Calculate the proportion of the heating network flow rate of each branch pipeline in the total heating network flow rate to obtain the flow rate proportion; compare the actual heating network flow rate of each branch pipeline with the designed heating network flow rate to determine whether the distribution of the heating network flow rate meets the design expectations. The designed heating network flow rate is preset according to the heat load demand of the heating area and the pipeline network layout; draw a curve of the heating network flow rate of each branch pipeline changing with time to generate the fluctuation condition of the heating network flow rate to obtain the flow analysis result;

[0019] Analyze the distribution of the heating network pressure of each branch pipeline of the heating network. Under normal circumstances, the heating network pressure should gradually decrease along the water flow direction, and the pressure difference between each branch should be within the normal range; calculate the pressure loss according to the heating network pressure at both ends of each branch pipeline; judge the resistance condition of the pipeline by comparing the pressure losses of different branch pipelines; monitor the fluctuation condition of the heating network pressure of each branch pipeline to obtain the pressure analysis result.

[0020] Combined with the first aspect, in the fourth implementation manner of the first aspect of the present application, based on the flow analysis result and the pressure analysis result, optimize the operation parameters of the heating network and calculate the heat recovery efficiency of the heating network. Calculating the heat recovery efficiency of the heating network includes:

[0021] Based on the flow analysis result, adjust the flow distribution according to the difference between the flow rate proportion of each branch pipeline and the designed flow rate proportion. The designed flow rate proportion is preset according to the heat load demand of the heating area and the pipeline network layout; for the branch with a flow rate proportion lower than the designed flow rate proportion, increase the opening degree of the regulating valve on this branch pipeline to increase the heating network flow rate; combine the change of the heat load demand in the area where each branch is located to dynamically adjust the flow rate in real time; for the branch pipeline with a fluctuation range of the heating network flow rate greater than the set fluctuation range threshold within the user-set time period, check the problems of the user-side equipment and optimize the usage mode of the user-side equipment; when the fluctuation of the heating network flow rate is caused by air resistance in the pipeline, prompt to set an automatic air exhaust valve in the pipeline to automatically discharge the accumulated air according to the pressure change in the pipeline;

[0022] Based on the pressure analysis result, balance the pressure difference by adjusting the valve according to the comparison of the heating network pressure at the inlet of each branch pipeline and the heating network pressure of the adjacent branch; for the branch with the heating network pressure at the inlet higher than the set threshold, lower the upstream valve to reduce the pressure; for the branch with the heating network pressure at the inlet lower than the set threshold, increase the relevant valve to increase the pressure; when the overall heating network pressure distribution is abnormal, optimize by adjusting the operation parameters of the circulating pump;

[0023] Calculate the heat supply and return water heat, subtract the return water heat from the heat supply to obtain the heat recovery amount; use the specific heat capacity of water, the density of water, the heat network flow rate, the heat network supply temperature, and the lowest available temperature to calculate the theoretically recoverable heat; calculate the ratio of the heat recovery amount to the theoretically recoverable heat to obtain the heat recovery efficiency of the heat network.

[0024] Heat supply , return water heat , where c is the specific heat capacity of water. Under normal temperature and pressure, , indicating the heat absorbed (or released) when the unit mass of water rises (or falls) . is the density of water, taking . is the heat network flow rate, with the unit of . is the heat network supply temperature, with the unit of . is the heat network return water temperature, with the unit of . is the reference temperature, selecting as the reference temperature.

[0025] Calculate the heat recovery amount , and the formula is: .

[0026] Calculate the theoretically recoverable heat , and the formula is: . Among them, is the lowest available temperature, with the unit of . It is a temperature lower limit determined according to the specific application and technical conditions of the heat network. Heat below this temperature is difficult to be effectively utilized.

[0027] Calculate the heat recovery efficiency of the heat network , and the formula is: . Among them, the heat recovery efficiency is expressed as a percentage, reflecting the proportion of the actual recovered heat of the heat network in the theoretically recoverable heat. The higher this value, the better the heat recovery performance of the heat network.

[0028] Combined with the first aspect, in the fifth implementation manner of the first aspect of the present application, the constructing and training the autoregressive integrated moving average model inputs the current electricity consumption-related data and the heat recovery efficiency and outputs the predicted value of the heat load demand, including:

[0029] Collect historical normal power consumption - related data and the corresponding heat recovery efficiency, perform data pre - processing, and divide them into a training set and a test set according to a ratio; determine the autoregressive order, differencing order, and moving average order of the autoregressive integrated moving average model, and construct the autoregressive integrated moving average model; based on the training set, use the maximum likelihood estimation method to estimate the parameters of the constructed autoregressive integrated moving average model; during the training process, evaluate the autoregressive integrated moving average model by adjusting the model parameters and combining the AIC information criterion.

[0030] Input the current power - related data and heat recovery efficiency into the trained autoregressive integrated moving average model to output the predicted value of the heat load demand.

[0031] Combined with the first aspect, in the sixth implementation manner of the first aspect of this application, the determining the influence weights of the indoor temperature and the outdoor temperature on the heat load demand, calculating the temperature difference, calculating the temperature correction coefficient according to the temperature difference, and using the temperature correction coefficient to adjust the predicted value of the heat load demand includes:

[0032] Collect the indoor temperature, outdoor temperature, heat load demand data, and the operating status data of the electric boiler during the heating seasons in this region over the years. After expert evaluation, determine the influence weights of the indoor temperature and the outdoor temperature on the heat load demand.

[0033] Obtain the actual temperature difference by subtracting the outdoor temperature from the indoor temperature; determine the standard temperature difference according to the local climate characteristics, heating standards, and the heat insulation performance of the building; calculate the difference between the actual temperature difference and the standard temperature difference to obtain the temperature difference deviation; based on the proportional relationship between the temperature difference deviation and the standard temperature difference, use a linear relationship algorithm to construct a temperature correction coefficient model; verify the temperature correction coefficient model using historical data, substitute the actual temperature differences at different time periods into the temperature correction coefficient model to calculate the correction coefficient, and perform optimization and adjustment by combining the comparison between the actual heat load demand and the predicted value of the heat load demand at that time.

[0034] Calculate the temperature correction coefficient based on the temperature correction coefficient model, linearly correct the predicted value of the heat load demand to obtain the adjusted predicted value of the heat load demand.

[0035] Combined with the first aspect, in the seventh implementation manner of the first aspect of this application, the setting the power correspondence relationship based on the adjusted predicted value of the heat load demand and adjusting the power of the electric boiler in stages includes:

[0036] Conduct performance tests on the electric boiler under different working conditions to obtain the performance test data of the electric boiler, and record the actual heating capacity of the electric boiler at different output powers; according to the actual heating capacity, associate it with the adjusted predicted value of the heat load demand, and through linear regression analysis, find the functional relationship between the heat load demand and the output power of the electric boiler; according to the established functional relationship, generate a power correspondence table, set the heat load demand interval, and calculate the corresponding electric boiler power value based on the heat load demand interval.

[0037] Record the electric boiler at different output powers The actual heating capacity under . Here Is the output power of the electric boiler, in kW; The unit of is kJ / h. The working condition is set by changing the operating conditions of the electric boiler (such as inlet water temperature, flow rate, etc.), and each working condition corresponds to a set of And Values.

[0038] Assume that there is a linear relationship between the heat load demand And the output power P of the electric boiler, that is , where a and b are regression coefficients to be determined.

[0039] According to the least squares method, the calculation formulas for the regression coefficients a and b are as follows:

[0040] ;

[0041] ;

[0042] Among them, n is the number of groups of test data, that is, the number of different working conditions, Is the output power of the electric boiler under the i-th working condition, Is the actual heating capacity of the electric boiler under the i-th working condition.

[0043] Set the heat load demand interval , assume that the starting value of the heat load demand is , and the ending value is .

[0044] For each heat load demand ( , k = 0, 1, 2,..., m, and ), according to the functional relationship obtained by linear regression , calculate the corresponding electric boiler power value P: ; Among them, Is the starting value of the heat load demand, Is the ending value of the heat load demand.

[0045] According to the characteristics of heat load demand in different time periods of a day, the time is divided into different stages; among them, in the night stage, according to the predicted value of the average heat load demand, the corresponding electric boiler power is found from the power correspondence table; in the day stage, the electric boiler power is dynamically adjusted according to the predicted values of heat load demand in different sub-stages.

[0046] Combined with the first aspect, in the eighth implementation manner of the first aspect of the present application, based on the adjusted electric boiler power, calculating the running time and stopping time of the electric boiler by combining the operation state data of the electric boiler, and setting the electric boiler by using the calculated running time and stopping time, includes:

[0047] Based on the electric boiler performance test data, determining the heat output capacity of the electric boiler at different powers; according to the adjusted predicted value of heat load demand, calculating the running time of the electric boiler at this power; through the analysis of historical operation data and actual tests, determining the heat loss coefficient and the system inertia time, so as to determine the stopping time; wherein, the heat loss coefficient is used to remove the influence of heat loss on the heat supply of the electric boiler, and the system inertia time represents the time that the system can continue to maintain heat supply after the electric boiler stops running;

[0048] Setting the electric boiler by using the calculated running time and stopping time of the electric boiler.

[0049] In the second aspect, the present application provides a heat supply device based on computing power, and the heat supply device is used to execute a control method of a heat supply device based on computing power.

[0050] Compared with the prior art, the beneficial effects of the present invention are:

[0051] 1. By constructing and training an autoregressive integrated moving average model, the present invention comprehensively considers multiple factors such as electricity consumption-related data and heat recovery efficiency, and can more accurately predict the heat load demand; at the same time, by combining the influence weight analysis of indoor and outdoor temperatures on the heat load demand, the predicted value is further optimized, enabling the heat supply system to make heat supply preparations in advance.

[0052] 2. Based on the flow rate and pressure data of each branch pipeline of the heat network, the present invention deeply analyzes the hot water distribution situation, realizes precise adjustment of the operating parameters of the heat network; by calculating the heat recovery efficiency of the heat network, continuously optimizing the heat network operation strategy, significantly improving the heat recovery efficiency and reducing energy consumption.

[0053] 3. According to the adjusted predicted value of heat load demand, the present invention sets the power correspondence relationship, precisely adjusts the electric boiler power in stages, combines the operation state data of the electric boiler and the flow rate and pressure of the pipe network, and intelligently calculates the running time and stopping time of the electric boiler, realizing refined control of the electric boiler. Description of the Drawings

[0054] Figure 1 It is a schematic diagram of the steps of a heat supply device and a control method based on computing power according to the present invention;

[0055] Figure 2 It is a curve graph showing the change of heat network flow rate over time of a heat supply device and a control method based on computing power according to the present invention. Specific embodiments

[0056] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0057] Embodiment: As Figure 1 - Figure 2 shown, the present invention provides a technical solution:

[0058] As Figure 1 shown in the schematic diagram of the steps of a heat supply device and a control method based on computing power according to the present invention, the present application provides a heat supply device and a control method based on computing power, including the following steps:

[0059] Step S100: Obtain the operation state data of the electric boiler, the relevant data of the heat supply system, and the relevant data of electricity consumption, perform preprocessing, and integrate to obtain heat supply data; perform anomaly detection on the heat supply data;

[0060] Specifically, the operation state data of the electric boiler includes the temperature, pressure, power, and water level of the electric boiler; the relevant data of the heat supply system includes the indoor temperature, outdoor temperature, and heat network data, where the heat network data includes the heat network supply water temperature, heat network return water temperature, heat network flow rate, and heat network pressure; the relevant data of electricity consumption includes the grid voltage and grid current; data cleaning and data normalization are performed on the operation state data of the electric boiler, the relevant data of the heat supply system, and the relevant data of electricity consumption, and data association is performed based on time to integrate and obtain heat supply data.

[0061] Further, according to the design parameters and safe operating range of the electric boiler, determine the temperature thresholds of the heating element, hot water outlet, and furnace body surface; for the internal cavity pressure of the electric boiler, use the rated pressure of the electric boiler as the pressure threshold; use the rated power of the electric boiler as the power threshold; set upper and lower limit thresholds for the water level in the water tank of the electric boiler; set the range of indoor temperature according to user comfort requirements and heating standards; determine the range of outdoor temperature in different seasons and different time periods according to local historical meteorological data; in the heat network data threshold, according to the design parameters and safe operating range of the heat network, determine the thresholds of heat network supply water temperature, heat network return water temperature, heat network flow rate, and heat network pressure; according to the design parameters and safe operating range of the electric boiler, determine the grid voltage threshold and grid current threshold;

[0062] Set a judgment period, and within the judgment period, compare the heating data with the corresponding thresholds to determine whether there is an abnormality in the heating data.

[0063] Step S200: When there is no abnormality in the heating data, based on the relevant data of the heating system, according to the heat network flow rate and heat network pressure of each branch pipeline of the heat network, analyze the distribution of hot water in the heating pipeline network to obtain a flow analysis result and a pressure analysis result; based on the flow analysis result and the pressure analysis result, optimize the operating parameters of the heat network and calculate the heat recovery efficiency of the heat network;

[0064] Specifically, calculate the proportion of the heat network flow rate of each branch pipeline in the total heat network flow rate to obtain the flow rate ratio; compare the actual heat network flow rate of each branch pipeline with the designed heat network flow rate to determine whether the heat network flow rate distribution meets the design expectation, and the designed heat network flow rate is preset according to the heat load demand of the heating area and the pipeline network layout; draw a curve of the heat network flow rate of each branch pipeline changing with time to generate the fluctuation situation of the heat network flow rate to obtain the flow analysis result;

[0065] Analyze the heat network pressure distribution of each branch pipeline of the heat network. Under normal circumstances, the heat network pressure should gradually decrease along the water flow direction, and the heat network pressure difference between branches should be within the normal range; calculate the pressure loss according to the heat network pressure at both ends of each branch pipeline; judge the resistance situation of the pipeline by comparing the pressure losses of different branch pipelines; monitor the fluctuation situation of the heat network pressure of each branch pipeline to obtain the pressure analysis result.

[0066] Further, based on the flow analysis results, adjust the flow distribution according to the difference between the flow ratio of each branch pipeline and the designed flow ratio. The designed flow ratio is preset according to the heat load demand of the heating area and the pipe network layout. For branches with a flow ratio lower than the designed flow ratio, increase the opening degree of the regulating valve on the branch pipeline to increase the heat network flow. Combine the changes in the heat load demand in the areas where each branch is located to dynamically adjust the flow in real time. For branch pipelines where the fluctuation range of the heat network flow is greater than the set fluctuation range threshold within the user-set time period, check for problems with the user-side equipment and optimize the usage method of the user-side equipment. When the heat network flow fluctuation is caused by air resistance in the pipeline, prompt to install an automatic air vent valve in the pipeline to automatically discharge the accumulated air according to the pressure change in the pipeline;

[0067] Based on the pressure analysis results, balance the pressure difference by adjusting the valves according to the comparison of the heat network pressure at the inlet of each branch pipeline and the heat network pressure of the adjacent branch. For branches with a heat network pressure at the inlet higher than the set threshold, lower the upstream valve to reduce the pressure. For branches with a heat network pressure at the inlet lower than the set threshold, increase the relevant valve to increase the pressure. When the overall heat network pressure distribution is abnormal, optimize by adjusting the operating parameters of the circulating pump.

[0068] Further, calculate the supply heat and return heat, and obtain the heat recovery amount by subtracting the return heat from the supply heat. Use the specific heat capacity of water, the density of water, the heat network flow, the heat network supply temperature, and the lowest available temperature to calculate the theoretically recoverable heat. Calculate the ratio of the heat recovery amount to the theoretically recoverable heat to obtain the heat recovery efficiency of the heat network.

[0069] In a specific embodiment, there is a small-scale heating pipe network system including three branch pipelines;

[0070] As Figure 2 shown in the heat network flow variation curve diagram over time of a heating equipment and control method based on computing power according to the present invention, for the heat network flow data, the electromagnetic flowmeter installed on the pipeline shows that the flow data is collected every 15 minutes within a certain time period, and the data is as follows (unit: )

[0071] Branch pipeline 1: Time: , Time: , Time: , Time: ;

[0072] Branch pipeline 2: Time: , Time: , Time: , Time: ;

[0073] Branch pipeline 3: Time: , Time: , Time: , Time: ;

[0074] The total heat network flow is obtained by adding the flows of each branch. Taking time as an example,

[0075] .

[0076] For the heat network pressure data, pressure sensors are installed at the inlet and outlet of the pipeline respectively. The data are as follows (unit: MPa):

[0077] Branch pipeline 1: Inlet pressure data: Time: , Time: , Time: , Time: ; Outlet pressure data: Time: , Time: , Time: , Time: ;

[0078] Branch pipeline 2: Inlet pressure data: Time: , Time: , Time: , Time: ; Outlet pressure data: Time: , Time: , Time: , Time: ;

[0079] Branch pipe 3: Inlet pressure data: Time: , Time: , Time: , Time: ; Outlet pressure data: Time: , Time: , Time: , Time: ;

[0080] Other data are as follows: Specific heat capacity of water , Density of water , Heat supply temperature of the heat network °C, Return water temperature of the heat network °C, Minimum available temperature °C;

[0081] Design flow rate ratio: Branch pipe 1 is 30%, branch pipe 2 is 25%, and branch pipe 3 is 45%;

[0082] Design heat network flow rate: The total design flow rate is 100 m³ / h, then the design flow rate of branch pipe 1 is 30 m³ / h, the design flow rate of branch pipe 2 is 25 m³ / h, and the design flow rate of branch pipe 3 is 45 m³ / h;

[0083] Set the fluctuation amplitude threshold: ±10% (relative to the average flow rate);

[0084] Set the pressure threshold: The normal range of the inlet pressure is 0.35 - 0.45 MPa.

[0085] Perform flow analysis. Taking time as an example, the method is as follows:

[0086] Flow rate ratio of branch pipe 1 ;

[0087] Flow rate ratio of branch pipe 2 ;

[0088] Flow rate ratio of branch pipe 3 ;

[0089] Branch pipe 1: Difference between actual flow rate and design flow rate , Within the allowable error range (the error range is ±1 m³ / h), the flow rate distribution meets the design expectations.

[0090] Branch pipe 2: Difference between actual flow rate and design flow rate , meeting the design expectations.

[0091] Branch pipeline 3: Difference between actual flow rate and designed flow rate , exceeding the allowable error range, and the flow distribution does not meet the design expectations.

[0092] Calculate the average flow rate of branch pipeline 1 ;

[0093] Fluctuation range: , not exceeding the set fluctuation range threshold.

[0094] Similarly, calculate the average flow rate and fluctuation range of branch pipelines 2 and 3. The average flow rate of branch pipeline 2 is , and the fluctuation range is 0%; the average flow rate of branch pipeline 3 is , and the fluctuation range is , both not exceeding the threshold.

[0095] Conduct a pressure analysis, and the method is as follows:

[0096] Analyze the pressure distribution: Branch pipeline 1: , , the pressure decreases along the water flow direction, and compared with adjacent branches, the pressure difference is within the normal range (the normal range of the pressure difference between adjacent branches is ).

[0097] Branch pipeline 2: , , and the pressure distribution is normal.

[0098] Branch pipeline 3: , , and the pressure distribution is normal.

[0099] Calculate the pressure loss:

[0100] Pressure loss of branch pipeline 1 ;

[0101] Pressure loss of branch pipeline 2 ;

[0102] Pressure loss of branch pipeline 3 ;

[0103] Compare the pressure losses of each branch pipeline. The pressure loss of branch pipeline 1 is slightly higher than that of branch pipelines 2 and 3, but the difference is not significant, and no obvious resistance abnormality is found for the time being.

[0104] Fluctuation range of the inlet pressure of branch pipeline 1: , within the normal range.

[0105] Similarly analyze branch pipelines 2 and 3, and the pressure fluctuations are all within the normal range.

[0106] Since the actual flow rate of branch pipeline 3 is lower than the designed flow rate, the opening degree of the regulating valve on this branch pipeline will be increased. After adjustment, the flow rate of branch pipeline 3 at subsequent moments becomes: Time: , Time: .

[0107] At this time, recalculate the flow rate ratio. Taking the moment of as an example, the total flow rate is , and the flow rate ratio of branch pipeline 3 is , which is closer to the designed flow rate ratio of 45%.

[0108] The inlet pressure of branch pipeline 2 is lower than the set threshold value, and the opening degree of the relevant valve will be increased. After adjustment, the inlet pressure of branch pipeline 2 becomes: Time: , reaching the normal pressure range.

[0109] Calculate the heat recovery efficiency, and the method is as follows:

[0110] Calculate the heat supply and return water heat:

[0111] Taking branch pipeline 1 as an example, convert the flow rate unit from m³ / h to m³ / s. The specific conversion formula is: 1 m³ / h = 1÷3600 m³ / s; then the heat supply is ; the return water heat is ; similarly calculate the heat supply and return water heat of branch pipelines 2 and 3, and then summarize the heat supply and return water heat of each branch to obtain the total heat supply and total return water heat. Calculate the heat recovery amount .

[0112] Calculate the theoretically recoverable heat: .

[0113] Calculate the heat recovery efficiency: .

[0114] Step S300: Construct and train an autoregressive integrated moving average model. Input the current electricity-related data and heat recovery efficiency, and output the predicted value of heat load demand;

[0115] Specifically, collect historical normal electricity-related data and the corresponding heat recovery efficiency, perform data preprocessing, and divide them into a training set and a test set according to a ratio; determine the autoregressive order, differencing order, and moving average order of the autoregressive integrated moving average model, and construct the autoregressive integrated moving average model; based on the training set, use the maximum likelihood estimation method to estimate the parameters of the constructed autoregressive integrated moving average model; during the training process, evaluate the autoregressive integrated moving average model by adjusting the model parameters and combining the AIC information criterion;

[0116] Input the current electricity-related data and heat recovery efficiency into the trained autoregressive integrated moving average model to output the predicted value of the heat load demand.

[0117] In a specific embodiment, the significant lag order is determined by observing the autocorrelation function (ACF) graph. After analysis, the autoregressive order p = 2 is determined. To make the data stationary, the difference processing is performed on the heat load demand data. Through the unit root test (ADF test), the difference order d = 1 is determined. Observe the partial autocorrelation function (PACF) graph to determine the significant lag order. The moving average order q = 1 is determined. An ARIMA(2,1,1) model is constructed.

[0118] Use the maximum likelihood estimation method to estimate the parameters of the constructed ARIMA model. During the training process, evaluate the model in combination with the AIC information criterion. The smaller the AIC value, the better the model fitting effect. Try different (p,d,q) combinations and select the model with the smallest AIC value.

[0119] Input the current electricity-related data and heat recovery efficiency into the trained model to predict the future heat load demand. In this embodiment, the heat load demand for the next 20 days is to be predicted; use the test set data to evaluate the prediction results. The evaluation indicators used are the mean square error (MSE), root mean square error (RMSE), and mean absolute error.

[0120] Step S400: Determine the influence weights of the indoor temperature and outdoor temperature on the heat load demand, calculate the temperature difference, calculate the temperature correction coefficient according to the temperature difference, and use the temperature correction coefficient to adjust the predicted value of the heat load demand;

[0121] Specifically, collect the indoor temperature, outdoor temperature, heat load demand data, and the operating status data of the electric boiler during the heating seasons in previous years in this area. After expert evaluation, determine the influence weights of the indoor temperature and outdoor temperature on the heat load demand;

[0122] Obtain the actual temperature difference by subtracting the outdoor temperature from the indoor temperature; determine the standard temperature difference according to the local climate characteristics, heating standards, and the building insulation performance; calculate the difference between the actual temperature difference and the standard temperature difference to obtain the temperature difference deviation; based on the proportional relationship between the temperature difference deviation and the standard temperature difference, construct a temperature correction coefficient model using a linear relationship algorithm; verify the temperature correction coefficient model using historical data, substitute the actual temperature differences at different time periods into the temperature correction coefficient model to calculate the correction coefficient, and perform optimization adjustment in combination with the comparison between the actual heat load demand and the predicted value of the heat load demand at that time;

[0123] Calculate the temperature correction coefficient based on the temperature correction coefficient model, and linearly correct the predicted value of the heat load demand to obtain the adjusted predicted value of the heat load demand.

[0124] In a specific embodiment, collect the indoor temperature, outdoor temperature, heat load demand data, and the operating status data of the electric boiler during the heating seasons in the past 10 years in this region. Invite 5 experts in the heating field to evaluate the influence weights of the indoor temperature and the outdoor temperature on the heat load demand according to their own experience and understanding of the local heating situation. The evaluation method is that each expert gives a weight ratio, and then the average value is taken. After the expert evaluation, it is determined that the influence weight of the indoor temperature on the heat load demand is 0.3, and the influence weight of the outdoor temperature on the heat load demand is 0.7.

[0125] Calculate the actual temperature difference, determine the standard temperature difference, and calculate the temperature difference deviation.

[0126] Adopt a linear relationship algorithm to construct a temperature correction coefficient model. The formula is: Temperature correction coefficient , where is the temperature difference deviation, is the standard temperature difference.

[0127] Taking November 5, 2015 as an example, the temperature correction coefficient .

[0128] Conduct model verification and optimization. The current predicted value of the heat load demand is 140 GJ. Calculate the temperature correction coefficient as 1.3 according to the current indoor temperature and outdoor temperature.

[0129] The adjusted predicted value of the heat load demand = the predicted value of the heat load demand × the temperature correction coefficient = 140×1.3 = 182 GJ.

[0130] Step S500: Based on the adjusted predicted value of the heat load demand, set the power correspondence relationship and adjust the power of the electric boiler in stages; based on the adjusted power of the electric boiler, calculate the operating time and stop time of the electric boiler in combination with the operating status data of the electric boiler, and set the electric boiler using the calculated operating time and stop time.

[0131] Specifically, conduct performance tests on the electric boiler under different working conditions to obtain the electric boiler performance test data, and record the actual heating capacity of the electric boiler at different output powers; according to the actual heating capacity, correlate it with the adjusted predicted value of the heat load demand, and through linear regression analysis, find the functional relationship between the heat load demand and the output power of the electric boiler; according to the established functional relationship, generate a power correspondence table, set the heat load demand interval, and calculate the corresponding electric boiler power value based on the heat load demand interval;

[0132] According to the characteristics of heat load demand in different time periods of a day, the time is divided into different stages; among them, in the night stage, according to the predicted value of the average heat load demand, the corresponding electric boiler power is found from the power correspondence table; in the day stage, the electric boiler power is dynamically adjusted according to the predicted values of heat load demand in different sub-stages.

[0133] Furthermore, based on the performance test data of the electric boiler, determine the heat output capacity of the electric boiler at different powers; according to the adjusted predicted value of heat load demand, calculate the operating time of the electric boiler at this power; through the analysis of historical operation data and actual tests, determine the heat loss coefficient and the system inertia time, so as to determine the stop time; where the heat loss coefficient is used to remove the influence of heat loss on the heat supply of the electric boiler, and the system inertia time represents the time that the system can continue to maintain heat supply after the electric boiler stops operating;

[0134] Set the electric boiler with the calculated operating time and stop time of the electric boiler.

[0135] In a specific embodiment, the electric boiler is tested under different working conditions, and the heat load demand is set There is a linear relationship with the output power P of the electric boiler .

[0136] According to the least square method, calculate the regression coefficients a and b:

[0137] It is known that n = 5, ;

[0138] ;

[0139] ;

[0140] .

[0141] ;

[0142] ;

[0143] So the functional relationship between the heat load demand and the output power of the electric boiler is . Generate the power correspondence table.

[0144] According to the characteristics of heat load demand in different time periods of a day, a day is divided into the following stages

[0145] Night stage (22:00 - 06:00);

[0146] Daytime stage: morning sub-stage (06:00 - 09:00), forenoon sub-stage (09:00 - 12:00), noon sub-stage (12:00 - 14:00), afternoon sub-stage (14:00 - 18:00), evening sub-stage (18:00 - 22:00); obtain the predicted values of heat load demand and power adjustment for each stage.

[0147] Determine the heat output capacity at different powers. Taking the morning sub-stage as an example, the predicted value of heat load demand , corresponding to the electric boiler power , and the heat output capacity . The running time .

[0148] Determine the heat loss coefficient and the system inertia time through the analysis of historical operation data and actual tests.

[0149] The stop time , taking the morning sub-stage as an example: , and the stop time is obtained as 0.246h.

[0150] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be encompassed within the present invention. Any reference signs in the claims should not be regarded as limiting the claimed claim.

Claims

1. A control method for a heat supply device based on computing power, characterized in that, It includes the following steps: Obtain the operation status data of the electric boiler, the relevant data of the heating system, and the relevant data of electricity consumption, perform preprocessing, and integrate to obtain heating data; perform anomaly detection on the heating data; When there is no anomaly in the heating data, based on the relevant data of the heating system, according to the heating network flow rate and heating network pressure of each branch pipeline of the heating network, analyze the distribution of hot water in the heating pipeline network to obtain the flow analysis result and the pressure analysis result; Based on the flow analysis result and the pressure analysis result, optimize the operation parameters of the heating network and calculate the heat recovery efficiency of the heating network; Construct and train an autoregressive integrated moving average model, input the current relevant data of electricity consumption and the heat recovery efficiency, and output the predicted value of the heat load demand; Determine the influence weights of the indoor temperature and the outdoor temperature on the heat load demand, calculate the temperature difference, calculate the temperature correction coefficient according to the temperature difference, and use the temperature correction coefficient to adjust the predicted value of the heat load demand; Based on the adjusted predicted value of the heat load demand, set the power correspondence relationship and adjust the power of the electric boiler in stages; Based on the adjusted power of the electric boiler, combine the operation status data of the electric boiler to calculate the operation time and stop time of the electric boiler, and set the electric boiler using the calculated operation time and stop time.

2. The control method of a heat supply device based on computing power according to claim 1, characterized in that The obtaining of the operation status data of the electric boiler, the relevant data of the heating system, and the relevant data of electricity consumption, performing preprocessing, and integrating to obtain heating data includes: The operation status data of the electric boiler includes the temperature, pressure, power, and water level of the electric boiler; the relevant data of the heating system includes the indoor temperature, outdoor temperature, and heating network data, where the heating network data includes the heating network supply water temperature, heating network return water temperature, heating network flow rate, and heating network pressure; the relevant data of electricity consumption includes the grid voltage and grid current; perform data cleaning and data normalization on the operation status data of the electric boiler, the relevant data of the heating system, and the relevant data of electricity consumption, and perform data association based on time to integrate and obtain heating data.

3. The control method of a heat supply device based on computing power according to claim 1, characterized in that, The performing of anomaly detection on the heating data includes: According to the design parameters and safe operation range of the electric boiler, determine the temperature thresholds of the heating element, hot water outlet, and furnace body surface; for the internal cavity pressure of the electric boiler, use the rated pressure of the electric boiler as the pressure threshold; use the rated power of the electric boiler as the power threshold; set upper and lower limit thresholds for the water tank water level of the electric boiler; according to the user comfort requirements and heating standards, set the range of the indoor temperature; according to the local historical meteorological data, determine the range of the outdoor temperature in different seasons and different time periods; in the heating network data thresholds, according to the design parameters and safe operation range of the heating network, determine the thresholds of the heating network supply water temperature, heating network return water temperature, heating network flow rate, and heating network pressure; according to the design parameters and safe operation range of the electric boiler, determine the grid voltage threshold and grid current threshold; Set a judgment period, and within the judgment period, compare the heating data with the corresponding thresholds to judge whether there is an anomaly in the heating data.

4. The control method of a heat supply device based on computing power according to claim 1, characterized in that, When there is no anomaly in the heating data, based on the relevant data of the heating system, according to the heating network flow rate and heating network pressure of each branch pipeline of the heating network, analyze the distribution of hot water in the heating pipeline network to obtain the flow analysis result and the pressure analysis result, including: Calculate the proportion of the heat network flow of each branch pipeline in the total heat network flow to obtain the flow proportion; compare the actual heat network flow of each branch pipeline with the designed heat network flow to determine whether the heat network flow distribution meets the design expectations, where the designed heat network flow is preset according to the heat load demand of the heating area and the pipe network layout; draw the curve of the heat network flow of each branch pipeline changing with time to generate the fluctuation of the heat network flow and obtain the flow analysis result; Analyze the heat network pressure distribution of each branch pipeline of the heat network. Under normal circumstances, the heat network pressure should gradually decrease along the water flow direction, and the heat network pressure difference between branches should be within the normal range; calculate the pressure loss according to the heat network pressure at both ends of each branch pipeline; judge the resistance of the pipeline by comparing the pressure losses of different branch pipelines; monitor the fluctuation of the heat network pressure of each branch pipeline to obtain the pressure analysis result.

5. The control method of a heat supply device based on computing power according to claim 1, wherein, Based on the flow analysis result and the pressure analysis result, optimize the operation parameters of the heat network and calculate the heat recovery efficiency of the heat network, including: Based on the flow analysis result, adjust the flow distribution according to the difference between the flow proportion of each branch pipeline and the designed flow proportion, where the designed flow proportion is preset according to the heat load demand of the heating area and the pipe network layout; for the branch with a flow proportion lower than the designed flow proportion, increase the opening of the regulating valve on this branch pipeline to increase the heat network flow; combine the change of the heat load demand in the area where each branch is located to adjust the flow in real time and dynamically; for the branch pipeline with a fluctuation range of the heat network flow greater than the set fluctuation amplitude threshold within the user-set time period, check the problems of the user-side equipment and optimize the usage mode of the user-side equipment; when the heat network flow fluctuation is caused by air resistance in the pipeline, prompt to set an automatic air vent valve in the pipeline to automatically discharge the accumulated air according to the pressure change in the pipeline; Based on the pressure analysis result, adjust the valve to balance the pressure difference according to the comparison of the heat network pressure at the inlet of each branch pipeline and the heat network pressure of the adjacent branch; for the branch with the heat network pressure at the inlet higher than the set threshold, lower the upstream valve to reduce the pressure; for the branch with the heat network pressure at the inlet lower than the set threshold, increase the relevant valve to increase the pressure; when the overall heat network pressure distribution is abnormal, optimize it by adjusting the operation parameters of the circulating water pump; Calculate the supply heat and return heat, and subtract the return heat from the supply heat to obtain the heat recovery amount; use the specific heat capacity of water, the density of water, the heat network flow, the heat network supply temperature and the lowest available temperature to calculate the theoretically recoverable heat; calculate the ratio of the heat recovery amount to the theoretically recoverable heat to obtain the heat recovery efficiency of the heat network.

6. The control method of a heat supply device based on computing power according to claim 1, characterized in that, Construct and train an autoregressive integrated moving average model, input the current electricity-related data and heat recovery efficiency, and output the predicted value of the heat load demand, including: Collect historical normal electricity consumption-related data and corresponding heat recovery efficiency, perform data preprocessing, and divide them into a training set and a test set according to a certain proportion; determine the autoregressive order, differencing order, and moving average order of the autoregressive integrated moving average model, and construct the autoregressive integrated moving average model; based on the training set, use the maximum likelihood estimation method to estimate the parameters of the constructed autoregressive integrated moving average model; during the training process, evaluate the autoregressive integrated moving average model by adjusting the model parameters and combining the AIC information criterion. Input the current electricity consumption-related data and heat recovery efficiency into the trained autoregressive integrated moving average model, and output the predicted value of the heat load demand.

7. The control method of a heat supply device based on computing power according to claim 1, characterized in that, The determination of the influence weights of indoor temperature and outdoor temperature on the heat load demand, the calculation of the temperature difference, the calculation of the temperature correction coefficient based on the temperature difference, and the use of the temperature correction coefficient to adjust the predicted value of the heat load demand include: Collect the indoor temperature, outdoor temperature, heat load demand data, and electric boiler operation status data during the heating seasons of previous years in this region. After expert evaluation, determine the influence weights of indoor temperature and outdoor temperature on the heat load demand. Obtain the actual temperature difference by subtracting the outdoor temperature from the indoor temperature; determine the standard temperature difference according to the local climate characteristics, heating standards, and building insulation performance; calculate the difference between the actual temperature difference and the standard temperature difference to obtain the temperature difference deviation; based on the proportional relationship between the temperature difference deviation and the standard temperature difference, use a linear relationship algorithm to construct a temperature correction coefficient model; verify the temperature correction coefficient model using historical data, substitute the actual temperature differences at different time periods into the temperature correction coefficient model to calculate the correction coefficient, and perform optimization and adjustment in combination with the comparison between the actual heat load demand and the predicted value of the heat load demand at that time. Calculate the temperature correction coefficient based on the temperature correction coefficient model, and linearly correct the predicted value of the heat load demand to obtain the adjusted predicted value of the heat load demand.

8. A control method for a heat supply device based on computing power according to claim 1, characterized in that, Based on the adjusted predicted value of the heat load demand, set the power correspondence relationship and adjust the power of the electric boiler in stages, including: Conduct performance tests on the electric boiler under different working conditions to obtain the electric boiler performance test data, and record the actual heating capacity of the electric boiler at different output powers; according to the actual heating capacity, correlate it with the adjusted predicted value of the heat load demand, and through linear regression analysis, find the functional relationship between the heat load demand and the output power of the electric boiler; according to the established functional relationship, generate a power correspondence table, set the heat load demand interval, and calculate the corresponding electric boiler power value based on the heat load demand interval. According to the characteristics of the heat load demand at different time periods in a day, divide the time into different stages; among them, during the night stage, according to the average predicted value of the heat load demand, look up the corresponding electric boiler power from the power correspondence table; during the day stage, dynamically adjust the electric boiler power according to the predicted values of the heat load demand in different sub-stages.

9. The control method of a heat supply device based on computing power according to claim 1, characterized in that, Based on the adjusted power of the electric boiler, calculate the operation time and stop time of the electric boiler in combination with the electric boiler operation status data, and use the calculated operation time and stop time to set the electric boiler, including: Based on the performance test data of the electric boiler, determine the heat output capacity of the electric boiler at different powers; according to the adjusted predicted value of the heat load demand, calculate the operating time of the electric boiler at this power; through the analysis of historical operation data and actual tests, determine the heat loss coefficient and the system inertia time, so as to determine the stop time; wherein, the heat loss coefficient is used to remove the influence of heat loss on the heat supply of the electric boiler, and the system inertia time represents the time that the system can continue to maintain heat supply after the electric boiler stops operating; Set the electric boiler using the calculated operating time and stop time of the electric boiler's operating time and stop time.

10. A heat supply device based on computing power, characterized in that The heating device is used to execute the control method of a heating device based on computing power described in any one of claims 1 to 9.

Images