CN117927998A - Mining area heating system intelligent regulation and control method based on data analysis - Google Patents
Mining area heating system intelligent regulation and control method based on data analysis Download PDFInfo
- Publication number
- CN117927998A CN117927998A CN202410333630.4A CN202410333630A CN117927998A CN 117927998 A CN117927998 A CN 117927998A CN 202410333630 A CN202410333630 A CN 202410333630A CN 117927998 A CN117927998 A CN 117927998A
- Authority
- CN
- China
- Prior art keywords
- region
- heat supply
- measured
- heating
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010438 heat treatment Methods 0.000 title claims abstract description 231
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000005065 mining Methods 0.000 title claims abstract description 30
- 238000007405 data analysis Methods 0.000 title claims abstract description 21
- 230000008859 change Effects 0.000 claims abstract description 141
- 238000005381 potential energy Methods 0.000 claims abstract description 59
- 230000004044 response Effects 0.000 claims abstract description 56
- 238000001228 spectrum Methods 0.000 claims description 47
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 39
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 28
- 238000004458 analytical method Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 230000009897 systematic effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 229910001006 Constantan Inorganic materials 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D3/00—Hot-water central heating systems
- F24D3/02—Hot-water central heating systems with forced circulation, e.g. by pumps
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D19/00—Details
- F24D19/10—Arrangement or mounting of control or safety devices
- F24D19/1006—Arrangement or mounting of control or safety devices for water heating systems
- F24D19/1009—Arrangement or mounting of control or safety devices for water heating systems for central heating
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D3/00—Hot-water central heating systems
- F24D3/10—Feed-line arrangements, e.g. providing for heat-accumulator tanks, expansion tanks ; Hydraulic components of a central heating system
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention relates to the technical field of heat supply regulation and control, in particular to an intelligent regulation and control method for a mining area heat supply system based on data analysis. According to the method, firstly, historical data including target temperature, pipeline temperature change time sequence, region temperature change time sequence and the like are acquired, and because temperature adjustment of different heat supply regions needs a certain time, response time lag exists in the system, meanwhile, temperature errors exist in the heat supply regions, so that response time lag parameters of the heat supply system and local errors of the heat supply regions are calculated, and then the response time lag parameters and the local errors of the heat supply regions are combined to obtain an expected error factor of the heat supply regions. In addition, energy loss exists in the heating process, so that the heating loss value is obtained by calculating the correlation between the heating potential energy and the pipeline temperature and the region temperature. And finally, adjusting the target temperature of the heating area based on the expected error factor and the heating loss value to compensate the energy loss and the error problem and improve the heating precision.
Description
Technical Field
The invention relates to the technical field of heat supply regulation and control, in particular to an intelligent regulation and control method for a mining area heat supply system based on data analysis.
Background
Mining areas typically include mining operations, engineering operations, etc., which typically need to be performed at a suitable temperature. By supplying heat, a warm working environment can be provided, and the working efficiency and comfort level of workers are improved; and the production equipment can be ensured to run in a proper temperature range, the risks of equipment faults and damages are reduced, and the continuity of the production flow is ensured.
The mining area is generally divided into different functional blocks according to different functions and requirements, so that more refined heat supply management is realized. In the prior art, when the temperature of each heating area is regulated and controlled, different target temperatures are usually set according to the heating requirements of each heating area, but because various conditions such as energy consumption loss, system response lag and the like occur in the heating process, the target temperatures set by experience have larger limitations, and more suitable heating temperatures cannot be provided for each heating area, so that the actual heating effect is low.
Disclosure of Invention
In order to solve the technical problem that the actual heating effect is low because a target temperature set by experience has larger limitation and can not provide more proper heating temperature for each heating area, the invention aims to provide an intelligent regulation and control method for a mining area heating system based on data analysis, and the adopted technical scheme is as follows:
acquiring target temperature, pipeline temperature change time sequence data, regional temperature change time sequence data, pipeline length, heat supply demand indexes and water pump power change time sequence data of each heat supply region in a mining area heat supply system in each historical data period of a preset historical period;
Obtaining response time lag parameters of the heating system according to differences among the pipeline temperature change time sequence data of all the heating areas in all the historical data periods; optionally selecting a heat supply area as an area to be measured, and predicting a pipeline temperature error value of the current data period according to pipeline temperature change time sequence data and heat supply requirement indexes of the area to be measured in each historical data period; obtaining an expected error factor of the current data period of the region to be measured according to the pipeline temperature error value of the current data period of the region to be measured and the response time lag parameter of the heating system;
According to the water pump power change time sequence data, the pipeline length, the pipeline temperature change time sequence data and the target temperature of the region to be detected in each historical data period, obtaining the heating potential energy of the region to be detected in each historical data period; obtaining an expected heating loss value of a current data period of the region to be measured according to heating potential energy of the region to be measured in all historical data periods, pipeline temperature change time sequence data and numerical distribution related conditions in the region temperature change time sequence data;
and carrying out self-adaptive adjustment on the target temperature of the region to be measured according to the expected heating loss value and the expected error factor of the current data period of the region to be measured, so as to obtain the final regulation and control temperature of the region to be measured.
Further, according to the differences between the time series data of the pipeline temperature changes of all the heating areas in all the historical data periods, the response time lag parameters of the heating system are obtained, and the method comprises the following steps:
Obtaining phase spectrums of all pipeline temperature change time sequence data based on Fourier transformation;
In all the heat supply areas, combining different heat supply areas two by two to obtain all the area combinations; in each historical data period, obtaining a residual spectrum according to the difference between the phase spectrums of the pipeline temperature change time sequence data of the two heating areas in each area combination;
Calculating to obtain a response time lag factor of the heating system in each historical data period according to the numerical values in the residual spectrum corresponding to all the region combinations in each historical data period;
And taking the standard deviation of the response time lag factors of all the historical data periods as the response time lag parameters of the heating system.
Further, according to the values in the residual spectrum corresponding to all the region combinations in each historical data period, a response time lag factor of the heating system in each historical data period is calculated, including:
In each historical data period, obtaining the total energy of the residual spectrum according to the numerical value in the residual spectrum corresponding to each region combination; the formula model of the total energy of the residual spectrum is:
wherein, Expressed inIn the history data period, the first-Combining total energy of the corresponding residual spectrum by the individual regions; expressed in/> In the history data period, the first-Combining total frequency items in the corresponding residual spectrum by the individual regions; /(I)Expressed inIn the history data period, the first-The/>, in the residual spectrum corresponding to each region combinationPhase angles corresponding to the frequency items; Representing an arctangent function;
The difference between the maximum total energy and the minimum total energy in the total energy of the residual spectrum corresponding to all the region combinations is taken as the response time lag factor of the historical daily heating system.
Further, the method for obtaining the heat supply demand index comprises the following steps:
in each historical data period, obtaining heat supply data of each heat supply area, wherein the heat supply data at least comprises: ambient temperature, number of people in daily activity in the heating area, and proper storage temperature of the equipment;
and scoring all the heat supply data in a manual label mode for each heat supply area, and acquiring the score average value of all the heat supply data as the heat supply demand index of each heat supply area.
Further, predicting the pipeline temperature error value of the current data period according to the pipeline temperature change time sequence data of the region to be measured in each historical data period and the heat supply requirement index includes:
In each historical data period, taking the standard deviation of all data values in the pipeline temperature change time sequence data of the region to be tested as a pipeline temperature error value;
Fitting heat supply demand indexes and pipeline temperature error values corresponding to all historical data periods based on a nonlinear fitting function to obtain a prediction equation;
acquiring heat supply data of a current data period of a region to be tested, inputting the heat supply data of the current data period of the region to be tested into a pre-trained neural network, and outputting heat supply requirement indexes of the current data period of the region to be tested; and taking the heat supply requirement index of the current data period of the region to be measured as the input of the prediction equation, and outputting the heat supply requirement index as the pipeline temperature error value of the current data period of the region to be measured.
Further, the obtaining the expected error factor of the current data period of the area to be measured according to the pipeline temperature error value of the current data period of the area to be measured and the response time lag parameter of the heating system includes:
sequentially carrying out proportional normalization on the pipeline temperature error value of the current data period of the region to be detected and the response time lag parameter of the heating system to obtain a first error factor and a second error factor respectively;
And taking the average value of the first error factor and the second error factor as an expected error factor of the current data period of the region to be detected.
Further, the obtaining the heating potential energy of the area to be measured in each historical data period according to the water pump power change time sequence data, the pipeline length, the pipeline temperature change time sequence data and the target temperature of the area to be measured in each historical data period includes:
in each historical data period, taking the ratio of the average value of water pump power change time sequence data of the area to be tested to the length of the pipeline of the area to be tested as push potential energy; taking the difference value between the value of the target temperature of the region to be measured and the first temperature value in the pipeline temperature change time sequence data of the region to be measured as the reverse natural potential energy; multiplying the normalized value of the push potential energy of the region to be measured by the inversely natural potential energy negative correlation mapped and normalized value, and taking the obtained product as the heating potential energy of the region to be measured in each historical data period.
Further, the obtaining the expected heating loss value of the current data period of the area to be measured according to the heating potential energy of the area to be measured in all the historical data periods, the pipeline temperature change time sequence data and the numerical distribution related conditions in the area temperature change time sequence data includes:
The same temperature value is used as a class in the pipeline temperature change time sequence data and the area temperature change time sequence data of each historical data period of the area to be detected;
based on a related entropy calculation formula, obtaining related entropy of pipeline temperature change time sequence data and region temperature change time sequence data according to the occurrence probability of various temperature values in the pipeline temperature change time sequence data and the occurrence probability of various temperature values in the region temperature change time sequence data in each historical data period of the region to be detected;
normalizing the ratio of the corresponding related entropy and the corresponding heating potential energy in each historical data period of the region to be measured to obtain a heating loss factor of the region to be measured in each historical data period;
Taking the average value of the heat supply loss factors corresponding to all the historical data periods of the area to be measured as the expected heat supply loss value of the current historical data period of the area to be measured.
Further, the self-adaptive adjustment of the target temperature of the area to be measured according to the expected heating loss value and the expected error factor of the current data period of the area to be measured to obtain the final regulation temperature of the area to be measured includes:
Multiplying the expected heating loss value of the current data period of the region to be measured by the expected error factor, and carrying out normalization processing to obtain an adjustment factor;
multiplying the sum of the adjustment factor and a preset first positive integer by the target temperature of the region to be measured to obtain the final regulation temperature of the region to be measured.
Further, the neural network is a 5-layer fully connected neural network.
The invention has the following beneficial effects:
Because the heat supply loss caused by transmission loss, response time lag of a heat supply system and the like exist in the heat supply process, the heat supply effect of each heat supply area is often not up to the heat supply effect expected by the preset target temperature, the invention provides an intelligent regulation and control method of a mining heat supply system based on data analysis, which comprises the steps of firstly acquiring each item of data of each heat supply area in the mining heat supply system in each data period in a preset history period, including target temperature, pipeline temperature change time sequence data, area temperature change time sequence data, pipeline length, heat supply demand index and water pump power change time sequence data, and preparing for the subsequent analysis process; further, since a certain time is required for temperature adjustment of different heat supply areas, when the heat source continuously transmits heat to each heat supply area, the temperature change curve of the heat supply area has a trend of steady-state fluctuation, and when the response time lag exists in the heat supply system, nodes with any temperature change in the temperature change time sequence data all contain different information, so that differences among the pipeline temperature change time sequence data of all the heat supply areas in all the historical data periods can be analyzed, and the response time lag parameters of the heat supply system can be obtained. In addition to the systematic errors of the heating system, there may be local errors in the heating areas, that is, errors between the heating requirement index and the actual heating conditions, where the errors may be predicted from the relationship between the pipeline temperature change time sequence data of each heating area and the heating requirement index, so as to obtain the pipeline temperature error value of the current data period of the heating area. And then combining the systematic error and the local error of the heating area to obtain the expected error factor of the current data period of the heating area. Further, the energy loss in the heating process is analyzed, and the heating system generally adopts a water pump to push hot water so as to realize heating, so that the energy loss is mainly reflected by heating potential energy, and the heating potential energy of the heating area is calculated according to water pump power change time sequence data, pipeline length, pipeline time sequence change data and target temperature of the area to be measured in each historical data period. The energy loss can be reflected by the correlation between the pipeline temperature and the actual temperature of the heat supply area, so that the heat supply potential energy is combined with the correlation between the pipeline temperature change time sequence data and the area temperature change time sequence data to obtain the expected heat supply loss value of the heat supply area. And finally, the target temperature of the heat supply area can be adjusted based on the expected error factor and the expected heat supply loss value of the heat supply area to obtain the final regulation and control temperature, so that the energy loss and the error problem in the heat supply process are effectively compensated, the heat supply precision of each heat supply area is improved, and the heat supply requirement of each heat supply area of the mining area is better met.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a mining area heating system intelligent regulation method based on data analysis according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects thereof of the intelligent regulation method for the mining area heating system based on data analysis according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a mining area heating system intelligent regulation method based on data analysis, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for intelligently controlling a heating system in a mining area based on data analysis according to an embodiment of the present invention is shown, the method includes the following steps:
Step S1: and acquiring target temperature, pipeline temperature change time sequence data, regional temperature change time sequence data, pipeline length, heat supply demand indexes and water pump power change time sequence data of each heat supply region in the mining area heat supply system in each historical data period of a preset historical period.
Mining areas typically include mining operations, engineering operations, etc., which typically need to be performed at a suitable temperature. And through the heat supply, can provide warm operational environment, improve staff's work efficiency and comfort level, can also ensure production facility and move in suitable temperature range simultaneously, reduce the risk of equipment trouble and damage, ensure production process's continuity. In addition, in the whole mining area, different heat supply areas can be divided according to different functions and requirements, so that finer heat supply management is realized, however, because the conditions of energy loss, system response delay, local temperature error and the like exist in the actual heat supply process, the heat supply according to the preset target temperature in the heat supply system can not provide a better heat supply effect, and the intelligent regulation and control method for the mining area heat supply system based on data analysis is provided in the embodiment of the invention.
Because the historical data has great reference value for temperature regulation of the current data period, firstly, acquiring various data of various heat supply areas in a mining area heat supply system under each historical data period in a preset historical period, wherein the various data comprise target temperature, pipeline temperature change time sequence data, area temperature change time sequence data, pipeline length, heat supply requirement indexes and water pump power change time sequence data; the time sequence data of the temperature change of the area is the actual temperature data of the heating area. The acquisition method of the pipeline temperature change time sequence data and the regional temperature change time sequence data can be obtained by utilizing a temperature sensor, the pipeline length data can be obtained according to the pipeline distribution diagram of each heat supply region, and the acquisition method of the heat supply demand index can be obtained according to a manual scoring mode. It should be noted that, in this embodiment of the present invention, the total number of history data periods is recorded asAnd the data period is set to be one day, and the preset history period is selected to be one month; the specific period and time setting can be adjusted according to the implementation scenario, and are not limited herein.
Preferably, in one embodiment of the present invention, the method for obtaining a heat supply demand index includes:
In each historical data period, heat supply data of each heat supply area is obtained, wherein the heat supply data at least comprises: ambient temperature, number of people in the heating area, and proper temperature for storing the equipment.
For each heating area, obtaining scores obtained by scoring all heating data in a manual label mode; and then calculating the score average value of all the heat supply data as the heat supply requirement index of each heat supply area.
It should be noted that, the score range is 0-10 points, where 0 represents the lowest heat supply requirement, and 10 points represent the highest heat supply requirement, for example, if the environment temperature is lower, the score should be higher, the number of daily activities in the heat supply area is higher, the score should be higher, and the storage suitable temperature of the device is lower, the score should be lower; in other embodiments of the present invention, the type of heating data of each heating area may be changed, which is not limited herein.
So far, each data index of each heating area can be obtained under each historical data period in the preset historical period, and can be used in the subsequent analysis process.
Step S2: obtaining response time lag parameters of the heating system according to differences among the pipeline temperature change time sequence data of all the heating areas in all the historical data periods; optionally selecting a heat supply area as an area to be measured, and predicting a pipeline temperature error value of the current data period according to pipeline temperature change time sequence data and heat supply requirement indexes of the area to be measured in each historical data period; and obtaining an expected error factor of the current data period of the region to be measured according to the pipeline temperature error value of the current data period of the region to be measured and the response time lag parameter of the heating system.
For a heating system, controlling different temperatures of a plurality of heating areas may cause response time lag of the system to temperature change, because the temperature adjustment of the different heating areas requires a certain time, when the target temperature exists, the response time lag can cause deviation between real-time temperature data and adjustment quantity of the heating system and cause continuous accumulation of errors with time, meanwhile, when the heat source continuously transmits the heat to each heating area due to radiation of the heat, pipeline temperature change time sequence data of the heating area has steady fluctuation trend, and nodes with any temperature change in the temperature change time sequence data can contain different information due to the existence of response time lag of the heating system, so that the difference between the pipeline temperature change time sequence data of the heating area can be analyzed, and the response time lag of the heating system can be evaluated.
Preferably, in one embodiment of the present invention, the obtaining the response time lag parameter of the heating system according to the difference between the time series data of the pipe temperature change of all the heating areas in all the historical data periods includes:
the delay of the system response time lag is time lag, which belongs to transverse position deviation, and the phase can describe the position information in the temperature time sequence data, so when the response time lag exists in the heating system, the node with any temperature change in the pipeline temperature change time sequence data can contain different phase information, and the response time lag of the heating system can be better represented by analyzing the phase information, so that the phase spectrum of all the pipeline temperature change time sequence data is obtained firstly based on Fourier transformation.
When the difference between the phase spectrums of the pipeline temperature change time sequence data of different heat supply areas is analyzed, the different heat supply areas can be combined in pairs in all the heat supply areas to obtain all the area combinations; and in each historical data period, according to the difference between the phase spectrums of the pipeline temperature change time sequence data of the two heat supply areas in each area combination, obtaining a residual spectrum, wherein the residual spectrum can represent the difference condition between information contained in the pipeline temperature change time sequence data of different heat supply areas.
And then calculating to obtain a response time lag factor of the heating system in each historical data period according to the numerical values in the residual spectrum corresponding to all the region combinations in each historical data period, wherein the response time lag factor is obtained by the following steps:
because the abscissa of the phase spectrum is a frequency term and the ordinate is a phase angle, the abscissa of the residual spectrum is also a frequency term, the ordinate is also a phase angle, and the phase angle corresponding to the frequency term in the residual spectrum can represent the difference between information contained in the pipeline temperature change time sequence data of two heat supply areas, so that the numerical value in the residual spectrum can be analyzed, thereby obtaining the total energy of the residual spectrum, and the total energy of the residual spectrum is used for representing the response time lag factor of a heat supply system in each historical data period, wherein the formula model of the total energy of the residual spectrum is as follows:
wherein, Expressed inIn the history data period, the first-Combining total energy of the corresponding residual spectrum by the individual regions; expressed in/> In the history data period, the first-Combining total frequency items in the corresponding residual spectrum by the individual regions; /(I)Expressed inIn the history data period, the first-The/>, in the residual spectrum corresponding to each region combinationPhase angles corresponding to the frequency items; Representing an arctangent function.
In a formula model of the residual spectrum, the phase angle of each frequency term in the residual spectrum can be used for representing the energy value of the corresponding frequency term in the residual spectrum, meanwhile, the angle is converted into a real number through arc tangent conversion of the phase angle, so that the calculation is more convenient, and finally, the values after the arc tangent conversion of the phase angles of all the frequency terms in the residual spectrum are accumulated, so that the total energy of the residual spectrum can be obtained.
Based on the above process, the total energy of the residual spectrum corresponding to each region combination in each historical data period can be obtained, and the difference value between the maximum total energy and the minimum total energy can be used as the response time lag factor of the heating system in each historical data period.
Finally, the standard deviation of the response time lag factors of all the historical data periods is used as the response time lag parameter of the heating system and is recorded as. The reason for selecting the standard deviation is that the standard deviation can effectively measure the discrete degree of a group of data, so as to provide a quantization index for representing the response time lag parameter of the heating system.
It should be noted that the process of obtaining the phase spectrum based on fourier transform is a technical means well known to those skilled in the art, and will not be described herein.
In addition to the systematic errors of the heating system, there may be local errors in the heating areas, that is, errors between the heating demand index and the actual heating conditions, where the errors may be predicted from the relationship between the pipeline temperature change time sequence data of each heating area and the heating demand index, so as to obtain the pipeline temperature error value of the current data period. For convenience of explanation and explanation, one heating area may be selected as a region to be measured among all the heating areas, and the method for acquiring some indexes in this embodiment of the present invention is explained by analyzing the region to be measured.
Preferably, in one embodiment of the present invention, predicting a pipeline temperature error value of a current data period according to pipeline temperature change time sequence data of a region to be measured in each historical data period and a heat supply requirement index includes:
and in each historical data period, acquiring standard deviations of all data values in the pipeline temperature change time sequence data of the region to be detected as pipeline temperature error values.
And then, fitting the heat supply demand index and the pipeline temperature error value corresponding to all the historical data periods based on a nonlinear fitting function to obtain a prediction equation, wherein the independent variable is the heat supply demand index, and the dependent variable is the pipeline temperature error value.
And then, acquiring heat supply data of the current data period of the region to be tested, and taking the heat supply data of the current data period of the region to be tested as input data of a pre-trained neural network, wherein the pre-trained neural network can output heat supply requirement indexes of the current data period of the region to be tested. Wherein, neural network selects 5 layers of full-connected neural network, and the training process roughly includes: and (3) heating data and heating demand indexes of the areas to be tested in all historical data periods are calculated according to 7:3, dividing the proportion into a training set and a verification set, inputting heat supply data and heat supply requirement indexes of the training set into a neural network, and training by adopting a gradient descent method until a loss function converges, so as to complete the training process of the neural network; the loss function uses a mean square error function.
And finally, taking the heat supply requirement index of the current data period of the region to be detected as the input of a prediction equation, and obtaining an output result as the pipeline temperature error value of the current data period of the region to be detected.
It should be noted that, the training method of the neural network is a process well known to those skilled in the art, and will not be described herein in detail.
The system error of the heating system, namely the response time lag parameter, is obtained through analysis, the local temperature error of the current data period of the region to be detected, namely the pipeline temperature error value of the current data period, is predicted, and then the system error and the pipeline temperature error value can be integrated to obtain the expected error factor of the current data period of the region to be detected.
Preferably, in one embodiment of the present invention, obtaining an expected error factor of a current data cycle of a region to be measured according to a pipeline temperature error value of the current data cycle of the region to be measured and a response time lag parameter of a heating system includes:
firstly, carrying out proportional normalization on the pipeline temperature error value of the current data period of the region to be detected to obtain a first error factor, and similarly, carrying out proportional normalization on the response time lag parameter of the heating system to obtain a second error factor.
And then the first error factor and the second error factor are integrated, namely, the average value of the first error factor and the second error factor is used as the expected error factor of the current data period of the area to be detected. The area to be measured is a heating areaFor example, the current data period is noted asThe formula model of the expected error factor of the current data period of the region to be measured can be specifically, for example:
wherein, Representing the region to be measuredInAn expected error factor for each data cycle; /(I)A response time lag parameter indicative of a heating system; /(I)Representing the region to be measuredAtPipeline temperature error values for each data cycle; /(I)Representing a hyperbolic tangent function.
In the formula model of the expected error factor, based on the analysis, the response time-lag parameter representing the system error and the pipeline temperature error value representing the local temperature error of the heating area can generate a certain influence on the temperature regulation and control of the heating area, and the response time-lag parameter and the pipeline temperature error value are in a coexistence relation, so that the response time-lag parameter and the pipeline temperature error value are respectively normalized in a positive proportion, and then the average value of the response time-lag parameter and the pipeline temperature error value is obtained, thereby obtaining the expected error factor of the area to be measured.
So far, the expected error factor is obtained by analyzing the error in the heating process, and the method can be used in the subsequent temperature regulation and control process.
Step S3: according to the water pump power change time sequence data, the pipeline length, the pipeline temperature change time sequence data and the target temperature of the region to be detected in each historical data period, obtaining the heating potential energy of the region to be detected in each historical data period; and obtaining the expected heat supply loss value of the current data period of the region to be measured according to the heat supply potential energy of the region to be measured in all the historical data periods, the pipeline temperature change time sequence data and the numerical distribution related conditions in the region temperature change time sequence data.
In the above process, the error condition in the heating process is analyzed, and in view of the fact that when the heating system transmits the heat source to each heating area, pipeline arrangement, building structures and the like can cause loss and attenuation of the heat source, the energy attenuation factor should be considered when the temperature is finally regulated.
In the embodiment of the present invention, the heating system adopts a forced circulation manner, that is, hot water is pushed by using a water pump, so as to realize heating of each heating area, so that energy required during heating, that is, heating potential energy, can represent energy loss or loss to a certain extent, and heating potential energy can be represented by factors such as a change condition of water pump power and a length of a pipeline, so that in one embodiment of the present invention, heating potential energy of a region to be measured in each historical data period is obtained according to water pump power change time sequence data, a length of a pipeline, pipeline temperature change time sequence data and a target temperature of the region to be measured in each historical data period, and the method includes:
Because the heat supply mode is that the water pump pushes hot water, the work done by the water pump when pushing hot water can be quantified at first, namely, the energy required by pushing the hot water is represented, and the specific method is as follows: in each historical data period, calculating the average value of all power data values in the water pump power change time sequence data of the area to be measured, taking the average value as the water pump power average value, representing the average size of the water pump power in the heat supply process, and taking the ratio of the average value to the length of the pipeline of the area to be measured as push potential energy.
Because the essential purpose of heating is heating, the contrast between the heating process and the natural temperature is also quantified when the heating potential energy is calculated, namely the energy required for overcoming the natural temperature in the heating process is represented, and the specific method is as follows: the temperature value of the first moment in the pipeline temperature change time sequence data of the region to be measured represents the initial temperature value of the heat supply pipeline when the region to be measured supplies heat, and the target temperature of the region to be measured represents the final temperature value required by the region to be measured, so that the difference value between the value of the target temperature of the region to be measured and the first temperature value in the pipeline temperature change time sequence data of the region to be measured can be used as the reverse natural potential energy.
And finally multiplying the normalized value of the push potential energy of the region to be measured in each historical data period by the inversely natural potential energy negative correlation mapped and normalized value, and taking the obtained product as the heating potential energy of the region to be measured in each historical data period. The area to be measured is a heating areaFor example, the formula model of heating potential energy may specifically be, for example:
wherein, Expressed inIn each historical data period, the region to be measuredIs a heating potential energy of the air conditioner; /(I)Expressed inIn each historical data period, the region to be measuredIs a water pump power average value; /(I)Expressed inIn each historical data period, the region to be measuredIs a pipe length of (2); /(I)Expressed inIn each historical data period, the region to be measuredA first temperature value in the pipeline temperature change time sequence data; /(I)Expressed inIn each historical data period, the region to be measuredIs set at the target temperature of (2); /(I)Expressed as natural constantAn exponential function of the base; /(I)Representing the normalization function.
In a formula model of heating potential energy, calculating the ratio of the average power value of a water pump in a region to be detected to the length of a pipeline in each day of a history period to obtain push potential energyAt this time, when the average power value of the water pump is lower and the length of the pipeline is longer, the efficiency of the water pump for pushing hot water is lower, meanwhile, the distance of the hot water to be transmitted is further, the pushing potential energy is smaller, and the loss of energy in the transmission process is larger; similarly, in each day of the history period, calculating the difference between the target temperature value of the region to be measured and the first temperature value in the pipeline temperature change time sequence data of the region to be measured to obtain the anti-natural potential energyAt this time, when the first temperature value in the pipeline temperature change time sequence data of the region to be measured is smaller, the inverse natural potential energy is larger, which means that more energy is needed to enable the temperature of the region to be measured to reach the target temperature, so that more energy loss can be generated in the heating process, and the heating potential energy is reduced, so that the inverse natural potential energy is subjected to negative correlation mapping and normalization, and the value after logic relation correction and pushing potential energy normalization is multiplied, so that the heating potential energy of the region to be measured is obtained.
The energy required by the region to be measured in the daily heat supply process in the historical period is analyzed, so that the heat supply potential energy is obtained and is used as one of indexes for subsequently evaluating the energy loss in the heat supply process.
Because the hot water in the heat supply process is sent to the heat supply area through the pipeline, the temperature of the heat supply area and the temperature of the heat supply pipeline should show a certain correlation, so the correlation can be analyzed to obtain the loss of heat energy in the transmission process, and the heat supply loss in the heat supply process is more specifically evaluated by combining the heat supply potential energy.
Preferably, in one embodiment of the present invention, obtaining a predicted heating loss value of a current data period of a region to be measured according to heating potential energy of the region to be measured in all historical data periods, pipeline temperature change time sequence data, and numerical distribution correlation conditions in the region temperature change time sequence data includes:
When analyzing the related situation, the related entropy can be adopted to characterize the related situation, firstly, the same temperature value is used as a class in the time sequence data of the pipeline temperature change of each historical data period of the region to be detected, and the occurrence probability of each class of temperature value is counted; and in the time sequence data of the temperature change of each historical data period of the region to be detected, the same temperature value is used as a class, and the occurrence probability of each class of temperature value is counted. At this time, in each historical data period, the pipeline temperature change time sequence data of the region to be detected and the temperature value at each moment in the region temperature change time sequence data correspond to one occurrence probability.
And then based on a related entropy calculation formula, obtaining the related entropy of the pipeline temperature change time sequence data and the region temperature change time sequence data according to the occurrence probability of various temperature values in the pipeline temperature change time sequence data and the occurrence probability of various temperature values in the region temperature change time sequence data in each historical data period of the region to be detected.
Finally, the relevant entropy representing the relevant condition is combined with the heating potential energy, and the ratio of the relevant entropy corresponding to each historical data period of the region to be measured to the corresponding heating potential energy is normalized to obtain the heating loss factor of the region to be measured in each historical data period; and taking the average value of the heat supply loss factors corresponding to all the historical data periods of the area to be measured as the expected heat supply loss value of the current data period of the area to be measured. The area to be measured is a heating areaFor example, the equation model for the expected heating loss value is:
wherein, Representing the region to be measuredAn expected heating loss value for the current data period; /(I)Representing a total number of historical data periods; /(I)Expressed inIn each historical data period, the region to be measuredIs a heating duration of (a); /(I)Expressed inIn each historical data period, the region to be measuredIs a heating potential energy of the air conditioner; /(I)Expressed inIn each historical data period, the region to be measured, In the time-series data of the temperature change of the pipelineProbability of occurrence of temperature values at each moment; /(I)Expressed inIn each historical data period, the region to be measuredIn the time series data of the regional temperature change of (1)Probability of occurrence of temperature values at each moment; /(I)Expressed as natural constantAn exponential function of the base.
In the formula model of the heating loss value, the relative entropy between the pipe temperature change time series data and the area temperature change time series data of the area to be measured in each historical data period in the historical period is calculated, namelyThe value represents the amount of uncertain information which is generated when the temperature value distributions in the two temperature change time series data are replaced with each other, and the larger the value is, the lower the correlation between the temperature values of the two temperature change time series data is, the larger the value is, and the larger heat supply loss exists in the heat transfer process, so that the temperature value of the area cannot be changed along with the change of the temperature value of the pipeline; based on the analysis in the above process, when the heating potential of the region to be measured in each historical data period in the historical period is smaller, the larger heating loss in the heating process can be represented, so that the heating potential is combined with the obtained value of the related entropy, and the ratio of the related entropy to the heating potential is normalized to obtain the heating loss factor of the region to be measured in each historical data period, namely; And finally, integrating the heat supply loss factors of the region to be measured in all the historical data periods of the historical period to obtain a more representative average value which is used as the expected heat supply loss value of the current data period of the region to be measured.
In other embodiments of the present invention, when analyzing the heat supply potential energy of the area to be measured in all the historical data periods, the pipeline temperature change time sequence data and the numerical distribution correlation conditions in the area temperature change time sequence data to obtain the expected heat supply loss value of the current data period of the area to be measured, the pearson correlation coefficient may be used for characterization, and the specific method may be:
and in each historical data period of the historical period, calculating a pearson correlation coefficient between pipeline temperature change time sequence data and region temperature change time sequence data of the region to be detected, multiplying a difference value of a preset second positive integer and the pearson correlation coefficient by heating potential energy in each historical data period of the historical period of the region to be detected, and normalizing the obtained product to obtain a heating loss factor of the region to be detected in each historical data period of the historical period.
And finally taking the average value of the heat supply loss factors corresponding to all the historical data periods of the area to be measured as the expected heat supply loss value of the current data period of the area to be measured. The area to be measured is a heating areaFor example, the current data period is noted asThe equation model for the expected heating loss value for the data cycle is:
wherein, Representing the region to be measuredFirstExpected heating loss values for each data cycle; /(I)Representing a total number of historical data periods; /(I)Expressed inIn each historical data period, the region to be measuredIs a heating potential energy of the air conditioner; /(I)Is shown in the firstIn each historical data period, the region to be measuredA pearson correlation coefficient between the pipe temperature change timing data and the zone temperature change timing data; /(I)Representing a normalization function; /(I)Representing a preset second positive integer.
In the formula model of the expected heat loss value, since the hot water is conveyed to the heat supply area through the pipeline, if the temperature of the heat supply area increases along with the increase of the temperature of the pipeline, that is, the two show positive correlation, the more the Pearson coefficient is close to 1, the less the heat loss in the heat supply process is considered, so that the area to be measured is calculatedThe pearson correlation coefficient between the pipeline temperature change time sequence data and the region temperature change time sequence data is obtained by making a difference between a preset second positive integer and the pearson correlation coefficientThe smaller the difference, the smaller the heating loss, and conversely, the larger the difference, the larger the heating loss; based on the analysis in the process, when the heating potential of the region to be measured is smaller in each historical data period of the historical period, the larger heating loss in the heating process can be represented, so that the difference valueCombining with heating potential energy, multiplying the two, and normalizing the product to obtain heating loss factorAnd finally, integrating the heat supply loss factors of the region to be measured in all historical data periods to obtain a more representative average value which is used as the expected heat supply loss value of the current data period of the region to be measured. /(I)
The second positive integer is presetThe specific value is 1, and can be adjusted, and is not limited herein.
The expected heat loss value of the current data period of the region to be measured is obtained by analyzing the heat loss in the heat supply process, and the expected heat loss value can be used in the subsequent temperature regulation and control process.
Step S4: and carrying out self-adaptive adjustment on the target temperature of the region to be measured according to the expected heating loss value and the expected error factor of the current data period of the region to be measured, so as to obtain the final regulation and control temperature of the region to be measured.
Errors and heat loss which can be generated in the heating process are analyzed in the process, so that the self-adaptive compensation can be performed on the heating temperature of the current data period based on the errors and the heat loss, the heating accuracy is improved, and the heating effect is ensured.
Preferably, in one embodiment of the present invention, adaptively adjusting a target temperature of a region to be measured according to a heating loss value and an expected error factor of a current data period of the region to be measured to obtain a final regulation temperature of the region to be measured, including:
Firstly, multiplying an expected heating loss value of a current data period of a region to be measured by an expected error factor, and then carrying out normalization processing to obtain an adjustment factor.
And finally multiplying the sum of the adjustment factor and the preset first positive integer by the target temperature of the region to be measured to obtain the final temperature of the region to be measured. The area to be measured is a heating areaFor example, the current data period is noted asThe formula model of the final regulation temperature of the region to be measured in the data period can be specifically, for example:
wherein, Representing the region to be measuredFirstFinal regulation and control temperature of each data period; /(I)Representing the region to be measuredFirstExpected heating loss values for each data cycle; /(I)Representing the region to be measuredFirstA data period expected error factor; /(I)Representing the region to be measuredIs set at the target temperature of (2); /(I)Representing a normalization function; /(I)Representing a preset first positive integer.
In a final temperature regulation formula model, the expected error factor of the region to be measured characterizes the system error and the local temperature error of the region to be measured; meanwhile, the heat supply loss value of the region to be measured characterizes the heat loss generated when the region to be measured supplies heat in the heat supply process, so that the expected error factor of the region to be measured and the heat supply loss value can be integrated, and the result obtained by multiplying the expected error factor and the heat supply loss value is normalized to obtain the adjustment factorThe adjustment factor reflects the adjustment degree of the target temperature, then the preset first positive integer is added with the adjustment factor, and the obtained sum is multiplied with the target temperature of the region to be measured, so that the temperature of the region to be measured can be adaptively adjusted.
It should be noted that, in order to prevent the temperature from being excessively high, the preset first positive integer is set to 1 in this embodiment of the present invention, and the specific value may be adjusted according to the implementation scenario, which is not limited herein.
In summary, in the heating process, there may be a heating loss caused by a transmission loss and a response time lag of the heating system, which often results in a heating effect generated by that the heating effect of each heating area cannot reach a preset target temperature, so the embodiment of the invention firstly obtains each item of data of each heating area in the mining area heating system in each historical data period in a preset historical period, including the target temperature, the pipeline temperature change time sequence data, the area temperature change time sequence data, the pipeline length, the heating requirement index and the water pump power change time sequence data, so as to prepare for a subsequent analysis process; further, since a certain time is required for temperature adjustment of different heat supply areas, when the heat source continuously transmits heat to each heat supply area, the temperature change curve of the heat supply area has a trend of steady-state fluctuation, and when the response time lag exists in the heat supply system, nodes with any temperature change in the temperature change time sequence data all contain different information, so that differences among the pipeline temperature change time sequence data of all the heat supply areas in all the historical data periods can be analyzed, and the response time lag parameters of the heat supply system can be obtained. In addition to the systematic errors of the heating system, there may be local errors in the heating areas, that is, errors between the heating requirement index and the actual heating conditions, where the errors may be predicted from the relationship between the pipeline temperature change time sequence data of each heating area and the heating requirement index, so as to obtain the pipeline temperature error value of the current data period of the heating area. And then combining the systematic error and the local error of the heating area to obtain the expected error factor of the current data period of the heating area. Further, the energy loss in the heating process is analyzed, and the heating system generally adopts a water pump to push hot water so as to realize heating, so that the energy loss is mainly reflected by heating potential energy, and the heating potential energy of the region to be measured in each historical data period is calculated according to the water pump power change time sequence data, the pipeline length, the pipeline time sequence change data and the target temperature of the region to be measured in each historical data period. The energy loss can be reflected by the correlation between the pipeline temperature and the actual temperature of the heat supply area, so that the heat supply potential energy is combined with the correlation between the pipeline temperature change time sequence data and the area temperature change time sequence data to obtain the expected heat supply loss value of the heat supply area. And finally, the target temperature of the heat supply area can be adjusted based on the expected error factor and the expected heat supply loss value of the heat supply area, so that the energy loss and the error problem in the heat supply process are effectively compensated, the heat supply precision of each heat supply area is improved, and the heat supply requirement of each heat supply area of the mining area is better met.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. An intelligent regulation and control method for a mining area heating system based on data analysis is characterized by comprising the following steps:
acquiring target temperature, pipeline temperature change time sequence data, regional temperature change time sequence data, pipeline length, heat supply demand indexes and water pump power change time sequence data of each heat supply region in a mining area heat supply system in each historical data period of a preset historical period;
Obtaining response time lag parameters of the heating system according to differences among the pipeline temperature change time sequence data of all the heating areas in all the historical data periods; optionally selecting a heat supply area as an area to be measured, and predicting a pipeline temperature error value of the current data period according to pipeline temperature change time sequence data and heat supply requirement indexes of the area to be measured in each historical data period; obtaining an expected error factor of the current data period of the region to be measured according to the pipeline temperature error value of the current data period of the region to be measured and the response time lag parameter of the heating system;
According to the water pump power change time sequence data, the pipeline length, the pipeline temperature change time sequence data and the target temperature of the region to be detected in each historical data period, obtaining the heating potential energy of the region to be detected in each historical data period; obtaining an expected heating loss value of a current data period of the region to be measured according to heating potential energy of the region to be measured in all historical data periods, pipeline temperature change time sequence data and numerical distribution related conditions in the region temperature change time sequence data;
and carrying out self-adaptive adjustment on the target temperature of the region to be measured according to the expected heating loss value and the expected error factor of the current data period of the region to be measured, so as to obtain the final regulation and control temperature of the region to be measured.
2. The intelligent regulation and control method for a district heating system based on data analysis according to claim 1, wherein the obtaining response time lag parameters of the heating system according to differences between time series data of pipe temperature changes of all heating areas in all historical data periods comprises:
Obtaining phase spectrums of all pipeline temperature change time sequence data based on Fourier transformation;
In all the heat supply areas, combining different heat supply areas two by two to obtain all the area combinations; in each historical data period, obtaining a residual spectrum according to the difference between the phase spectrums of the pipeline temperature change time sequence data of the two heating areas in each area combination;
Calculating to obtain a response time lag factor of the heating system in each historical data period according to the numerical values in the residual spectrum corresponding to all the region combinations in each historical data period;
And taking the standard deviation of the response time lag factors of all the historical data periods as the response time lag parameters of the heating system.
3. The intelligent regulation and control method for the heating system of the mining area based on data analysis according to claim 2, wherein the calculating to obtain the response time lag factor of the heating system in each historical data period according to the numerical values in the residual spectrum corresponding to all the area combinations in each historical data period comprises the following steps:
In each historical data period, obtaining the total energy of the residual spectrum according to the numerical value in the residual spectrum corresponding to each region combination; the formula model of the total energy of the residual spectrum is:
wherein/> Expressed inIn the history data period, the first-Combining total energy of the corresponding residual spectrum by the individual regions; /(I)Expressed inIn the history data period, the first-Combining total frequency items in the corresponding residual spectrum by the individual regions; /(I)Expressed inIn the history data period, the first-The/>, in the residual spectrum corresponding to each region combinationPhase angles corresponding to the frequency items; /(I)Representing an arctangent function;
The difference between the maximum total energy and the minimum total energy in the total energy of the residual spectrum corresponding to all the region combinations is taken as the response time lag factor of the historical daily heating system.
4. The intelligent regulation and control method for a district heating system based on data analysis according to claim 1, wherein the method for obtaining the heat supply requirement index comprises the following steps:
in each historical data period, obtaining heat supply data of each heat supply area, wherein the heat supply data at least comprises: ambient temperature, number of people in daily activity in the heating area, and proper storage temperature of the equipment;
For each heating area, obtaining scores obtained by scoring all heating data in a manual label mode; and calculating the score average value of all the heat supply data as the heat supply requirement index of each heat supply area.
5. The intelligent regulation and control method for a district heating system based on data analysis according to claim 4, wherein predicting the pipeline temperature error value of the current data period according to the pipeline temperature change time sequence data and the heat supply demand index of the region to be measured in each historical data period comprises:
In each historical data period, taking the standard deviation of all data values in the pipeline temperature change time sequence data of the region to be tested as a pipeline temperature error value;
Fitting heat supply demand indexes and pipeline temperature error values corresponding to all historical data periods based on a nonlinear fitting function to obtain a prediction equation;
acquiring heat supply data of a current data period of a region to be tested, inputting the heat supply data of the current data period of the region to be tested into a pre-trained neural network, and outputting heat supply requirement indexes of the current data period of the region to be tested; and taking the heat supply requirement index of the current data period of the region to be measured as the input of the prediction equation, and outputting the heat supply requirement index as the pipeline temperature error value of the current data period of the region to be measured.
6. The intelligent regulation and control method for a heating system of a mining area based on data analysis according to claim 1, wherein the obtaining the expected error factor of the current data period of the region to be measured according to the pipeline temperature error value of the current data period of the region to be measured and the response time lag parameter of the heating system comprises the following steps:
sequentially carrying out proportional normalization on the pipeline temperature error value of the current data period of the region to be detected and the response time lag parameter of the heating system to obtain a first error factor and a second error factor respectively;
And taking the average value of the first error factor and the second error factor as an expected error factor of the current data period of the region to be detected.
7. The intelligent regulation and control method for a district heating system based on data analysis according to claim 1, wherein the obtaining the heating potential energy of the district to be measured in each historical data period according to the water pump power change time sequence data, the pipeline length, the pipeline temperature change time sequence data and the target temperature of the district to be measured in each historical data period comprises:
in each historical data period, taking the ratio of the average value of water pump power change time sequence data of the area to be tested to the length of the pipeline of the area to be tested as push potential energy; taking the difference value between the value of the target temperature of the region to be measured and the first temperature value in the pipeline temperature change time sequence data of the region to be measured as the reverse natural potential energy; multiplying the normalized value of the push potential energy of the region to be measured by the inversely natural potential energy negative correlation mapped and normalized value, and taking the obtained product as the heating potential energy of the region to be measured in each historical data period.
8. The intelligent regulation and control method for a heating system of a mining area based on data analysis according to claim 1, wherein the obtaining the expected heating loss value of the current data period of the region to be measured according to the heating potential energy of the region to be measured in all historical data periods, the pipeline temperature change time sequence data and the numerical distribution related conditions in the region temperature change time sequence data comprises the following steps:
The same temperature value is used as a class in the pipeline temperature change time sequence data and the area temperature change time sequence data of each historical data period of the area to be detected;
based on a related entropy calculation formula, obtaining related entropy of pipeline temperature change time sequence data and region temperature change time sequence data according to the occurrence probability of various temperature values in the pipeline temperature change time sequence data and the occurrence probability of various temperature values in the region temperature change time sequence data in each historical data period of the region to be detected;
normalizing the ratio of the corresponding related entropy and the corresponding heating potential energy in each historical data period of the region to be measured to obtain a heating loss factor of the region to be measured in each historical data period;
Taking the average value of the heat supply loss factors corresponding to all the historical data periods of the area to be measured as the expected heat supply loss value of the current historical data period of the area to be measured.
9. The intelligent regulation and control method for a heating system of a mining area based on data analysis according to claim 1, wherein the adaptively adjusting the target temperature of the area to be measured according to the expected heating loss value and the expected error factor of the current data period of the area to be measured to obtain the final regulation and control temperature of the area to be measured comprises:
Multiplying the expected heating loss value of the current data period of the region to be measured by the expected error factor, and carrying out normalization processing to obtain an adjustment factor;
multiplying the sum of the adjustment factor and a preset first positive integer by the target temperature of the region to be measured to obtain the final regulation temperature of the region to be measured.
10. The intelligent regulation and control method for the district heating system based on data analysis according to claim 5, wherein the neural network is a 5-layer fully connected neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410333630.4A CN117927998B (en) | 2024-03-22 | 2024-03-22 | Mining area heating system intelligent regulation and control method based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410333630.4A CN117927998B (en) | 2024-03-22 | 2024-03-22 | Mining area heating system intelligent regulation and control method based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117927998A true CN117927998A (en) | 2024-04-26 |
| CN117927998B CN117927998B (en) | 2024-06-28 |
Family
ID=90754329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410333630.4A Active CN117927998B (en) | 2024-03-22 | 2024-03-22 | Mining area heating system intelligent regulation and control method based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117927998B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2232352C2 (en) * | 2002-02-28 | 2004-07-10 | Виктор Александрович Белошенко | Heat supply object monitoring method and process for testing heating system of buildings |
| KR20130089111A (en) * | 2012-02-01 | 2013-08-09 | 한국에너지기술연구원 | Estimating method for heat loss of secondary pipeline for district heating of apartment complex |
| EP3082010A1 (en) * | 2015-04-17 | 2016-10-19 | Fourdeg Oy | A system for dynamically balancing a heat load and a method thereof |
| CN111583062A (en) * | 2020-05-08 | 2020-08-25 | 常州英集动力科技有限公司 | Thermoelectric cooperative regulation and control method and system based on heat supply network transmission time delay and heat storage characteristics |
| CN115095907A (en) * | 2022-07-15 | 2022-09-23 | 唐山学院 | Intelligent heat supply energy-saving regulation and control method and system based on deep learning and storage medium |
| CN115186456A (en) * | 2022-06-27 | 2022-10-14 | 广东电网有限责任公司广州供电局 | Heating system observability recovery method considering pipeline temperature quasi-dynamic state |
| CN115789957A (en) * | 2022-11-24 | 2023-03-14 | 阳光慧碳科技有限公司 | Energy supply regulation and control method, device, equipment and storage medium |
| CN116993227A (en) * | 2023-09-22 | 2023-11-03 | 北明天时能源科技(北京)有限公司 | Heat supply analysis and evaluation method, system and storage medium based on artificial intelligence |
| CN117057481A (en) * | 2023-09-14 | 2023-11-14 | 华能苏州热电有限责任公司 | Load prediction method for heating system |
| CN117110362A (en) * | 2023-06-25 | 2023-11-24 | 河北华通科技股份有限公司 | Pipeline heat loss monitoring method, device, equipment and medium based on Internet of things |
-
2024
- 2024-03-22 CN CN202410333630.4A patent/CN117927998B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2232352C2 (en) * | 2002-02-28 | 2004-07-10 | Виктор Александрович Белошенко | Heat supply object monitoring method and process for testing heating system of buildings |
| KR20130089111A (en) * | 2012-02-01 | 2013-08-09 | 한국에너지기술연구원 | Estimating method for heat loss of secondary pipeline for district heating of apartment complex |
| EP3082010A1 (en) * | 2015-04-17 | 2016-10-19 | Fourdeg Oy | A system for dynamically balancing a heat load and a method thereof |
| CN111583062A (en) * | 2020-05-08 | 2020-08-25 | 常州英集动力科技有限公司 | Thermoelectric cooperative regulation and control method and system based on heat supply network transmission time delay and heat storage characteristics |
| CN115186456A (en) * | 2022-06-27 | 2022-10-14 | 广东电网有限责任公司广州供电局 | Heating system observability recovery method considering pipeline temperature quasi-dynamic state |
| CN115095907A (en) * | 2022-07-15 | 2022-09-23 | 唐山学院 | Intelligent heat supply energy-saving regulation and control method and system based on deep learning and storage medium |
| CN115789957A (en) * | 2022-11-24 | 2023-03-14 | 阳光慧碳科技有限公司 | Energy supply regulation and control method, device, equipment and storage medium |
| CN117110362A (en) * | 2023-06-25 | 2023-11-24 | 河北华通科技股份有限公司 | Pipeline heat loss monitoring method, device, equipment and medium based on Internet of things |
| CN117057481A (en) * | 2023-09-14 | 2023-11-14 | 华能苏州热电有限责任公司 | Load prediction method for heating system |
| CN116993227A (en) * | 2023-09-22 | 2023-11-03 | 北明天时能源科技(北京)有限公司 | Heat supply analysis and evaluation method, system and storage medium based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117927998B (en) | 2024-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
| CN105805822B (en) | Heating energy-saving control method based on neural network prediction and system | |
| EP3483517B1 (en) | System and method for predicting load of and controlling subway heating, ventilation, and air conditioning system | |
| CN107726442B (en) | Heat supply network balance regulation and control method | |
| CN110392515A (en) | A kind of Cooling and Heat Source equipment room energy-conserving control method and system based on historical data | |
| CN107120721A (en) | A kind of central heating dynamic gas candidate compensation method | |
| US11774122B2 (en) | Building control system with adaptive online system identification | |
| US11215375B2 (en) | Building control system with heat disturbance estimation and prediction | |
| CN116680661B (en) | Multi-dimensional data-based automatic gas regulator pressure monitoring method | |
| CN110410942A (en) | A kind of Cooling and Heat Source machine room energy-saving optimal control method and system | |
| CN104633829A (en) | Building cooling station energy-saving control device and method thereof | |
| US11236917B2 (en) | Building control system with zone grouping based on predictive models | |
| CN104636800A (en) | Freezing station system neural network optimization unit based on least square weighted and method thereof | |
| US20200371482A1 (en) | Building control system with heat load estimation using deterministic and stochastic models | |
| CN118194607B (en) | Dynamic modeling method and system for boiler unit data | |
| CN114841410A (en) | Heat exchange station load prediction method and system based on combination strategy | |
| CN107247407B (en) | Big data self-learning correction control system and method based on cloud architecture | |
| CN111476439A (en) | Heating household valve adjusting method, system and equipment based on gray time sequence | |
| CN117927998B (en) | Mining area heating system intelligent regulation and control method based on data analysis | |
| CN113449909A (en) | Cold load prediction method of cold accumulation air conditioner based on improved long-term and short-term memory network | |
| CN113701232B (en) | Heat supply system building-level regulation and control method and system based on temperature diversity analysis | |
| US20240288179A1 (en) | Acquiring a user consumption pattern of domestic hot water and controlling domestic hot water production based thereon | |
| KR101525010B1 (en) | Apparatus and method for energy management by temperature | |
| CN116823008A (en) | Park energy utilization efficiency evaluation method, system, equipment and storage medium | |
| Dubovoi et al. | Smart control of multi-zone object heating with multi-source system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |