CN113111589A - Training method of prediction model, method, device and equipment for predicting heat supply temperature - Google Patents
Training method of prediction model, method, device and equipment for predicting heat supply temperature Download PDFInfo
- Publication number
- CN113111589A CN113111589A CN202110450926.0A CN202110450926A CN113111589A CN 113111589 A CN113111589 A CN 113111589A CN 202110450926 A CN202110450926 A CN 202110450926A CN 113111589 A CN113111589 A CN 113111589A
- Authority
- CN
- China
- Prior art keywords
- data
- sample data
- heat exchange
- exchange station
- temperature
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 88
- 238000012549 training Methods 0.000 title claims abstract description 73
- 238000010438 heat treatment Methods 0.000 claims abstract description 70
- 230000002159 abnormal effect Effects 0.000 claims description 43
- 238000004422 calculation algorithm Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 19
- 238000012544 monitoring process Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 238000002790 cross-validation Methods 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 18
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000013106 supervised machine learning method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Abstract
The invention discloses a training method of a prediction model, relates to the field of Internet of things and the field of artificial intelligence, and particularly relates to the field of deep learning. The specific implementation scheme is as follows: obtaining sample data, wherein the sample data comprises historical observation data aiming at the heat exchange station; training the prediction model based on the sample data; and determining the use condition of the trained prediction model based on the value of the historical observation data in the sample data. The disclosure also discloses a training device of the prediction model, a method and a device for predicting the heating temperature, an electronic device and a storage medium.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence and the Internet of things, in particular to the technical field of deep learning, and specifically relates to a training method and device of a prediction model, a method and device for predicting heat supply temperature, electronic equipment and a storage medium.
Background
The heat exchange station is used as a hub in a centralized heating system and is connected with a heat source and a user end, and the heating temperature of the heat supply station is an important index for guaranteeing the heating demand of the user end.
In the process of implementing the embodiment of the present disclosure, the inventor finds that, in order to ensure that the heat supply temperature of the heat supply station adapts to the change of the heat load of the user terminal, the operation condition of the heat exchange station is often supervised and adjusted depending on manual experience, but the manual adjustment is difficult to ensure the adjustment effect, which affects the heat supply quality.
Disclosure of Invention
The present disclosure provides a training method and apparatus of a prediction model, a method and apparatus of predicting a heating temperature, an electronic device, and a storage medium.
According to a first aspect, there is provided a method of training a predictive model, the method comprising: obtaining sample data, wherein the sample data comprises historical observation data aiming at the heat exchange station; training the prediction model based on the sample data; and determining the use condition of the trained prediction model based on the value of the historical observation data in the sample data.
According to a second aspect, there is provided a method of predicting a heating temperature, the method comprising: monitoring observation data for the heat exchange station; determining the operation mode of the heat exchange station according to the observation data and the use condition of the prediction model; under the condition that the operation mode is determined to be the abnormal mode, determining the heat supply temperature of the heat exchange station aiming at a preset user by using an abnormal processing algorithm; and under the condition that the operation mode is determined to be the normal mode, determining the heat supply temperature of the heat exchange station aiming at the preset user by using a prediction model, wherein the prediction model is obtained by training by adopting the training method of the prediction model provided by the disclosure.
According to a third aspect, there is provided an apparatus for training a predictive model, the apparatus comprising: the sample data obtaining module is used for obtaining sample data, and the sample data comprises historical observation data aiming at the heat exchange station; the model training module is used for training the prediction model based on the sample data; and the condition determining module is used for determining the use condition of the trained prediction model based on the value of the historical observation data in the sample data.
According to a fourth aspect, there is provided an apparatus for predicting a heating temperature, the apparatus comprising: the data monitoring module is used for monitoring observation data aiming at the heat exchange station; the mode determining module is used for determining the operation mode of the heat exchange station according to the observation data and the using conditions of the prediction model; the first temperature determining module is used for determining the heat supply temperature of the heat exchange station aiming at a preset user by using an exception handling algorithm under the condition that the operation mode is determined to be an exception mode; and the second temperature determination module is used for determining the heat supply temperature of the heat exchange station aiming at the preset user by using the prediction model under the condition that the operation mode is determined to be the normal mode, wherein the prediction model is obtained by training by adopting the training device of the prediction model provided by the disclosure.
According to a fifth aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method provided in accordance with the present disclosure.
According to a sixth aspect, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method provided in accordance with the present disclosure.
According to a seventh aspect, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method provided according to the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram of an exemplary system architecture to which a training method of predictive models and/or a method of predicting heating temperatures may be applied, according to one embodiment of the present disclosure;
FIG. 2 is a flow diagram of a method of training a predictive model according to one embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a method of obtaining sample data according to one embodiment of the present disclosure;
FIG. 4 is a flow diagram of a method of predicting a heating temperature according to one embodiment of the present disclosure;
FIG. 5 is a flow diagram of a method of determining a heating temperature of a heat exchange station for a preset user using an exception handling algorithm according to one embodiment of the present disclosure;
FIG. 6 is a schematic diagram of the operating principle of a system for predicting a heating temperature according to an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of a training apparatus for predictive models, according to an embodiment of the present disclosure;
FIG. 8 is a schematic diagram of an arrangement for predicting a heating temperature according to an embodiment of the present disclosure; and
FIG. 9 is a schematic block diagram of an electronic device for implementing a method of predictive model training and/or a method of predicting heating temperature in embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of an exemplary system architecture to which a training method of a predictive model and/or a method of predicting a heating temperature may be applied, according to one embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.
As shown in fig. 1, a system architecture 100 according to this embodiment may include a heat source 101, a heat exchange station 102, and a user end 103, the user end 103 including a plurality of users, such as user a, user B, and user C, and so on. The heat exchange station 102 is used as a hub in a centralized heating system and is connected with the heat source 101 and the user end 103, the operation condition of the heat exchange station directly influences the distribution and redistribution of heat, the heat supply quality of the user end 103 is related, and the heat supply temperature of the heat supply station 102 is an important index for guaranteeing the heat supply demand of the user end.
In the process of implementing the embodiment of the present disclosure, the inventor finds that the heat load required by the user side can be predicted through climate compensation based on the characteristics such as outdoor temperature, that is, the heat supply amount of the heat supply station is predicted, and the operation condition of the heat exchange station is dynamically adjusted to ensure that the heat supply amount adapts to the change of the heat load of the user side.
In order to predict the heat load required by the user end 103 (i.e. predict the heat supply amount of the heat supply station), a control method of a mathematical model may be adopted, for example, a mathematical model of the heat exchange station is established by using an automatic control theory, and a PID controller, a Fuzzy controller or a BP neural network controller is designed based on a control target. However, this method relies on mathematical simulation of the physical process. The heat exchange station is a nonlinear time-lag system with inertia, and mathematical modeling of the heat exchange station is difficult, even difficult. Generally, the method simplifies the mathematical model through order reduction and approximation, but the simplified model can cause the reduction of model precision and influence the control effect.
In order to predict the heat load required by the user end 103 (i.e. the heat supply amount of the heat supply station), a data-driven method can also be adopted, for example, by using the observation data of the heat exchange station, and using a supervised machine learning/deep learning model, such as multiple linear regression, support vector machine, neural network, etc., to perform regression prediction on the climate compensation coefficient. However, this method requires a large amount of available data, and for the case of no historical data, it is difficult to obtain data suitable for regression to model. And for the heat exchange station with changed working conditions such as overload, abnormal flow and the like, the prediction result of the historical model is not applicable. And in the modeling process, only outdoor temperature is used as an input characteristic, and climate compensation is performed only through weather data, so that the established single model cannot adapt to abnormal working conditions (such as working condition overload, flow abnormity and the like) of the heat exchange station.
In view of this, the embodiment of the present disclosure provides a method for training a prediction model, where the method includes obtaining sample data, where the sample data includes historical observation data for a heat exchange station; training the prediction model based on the sample data; and determining the use condition of the trained prediction model based on the value of the historical observation data in the sample data.
FIG. 2 is a flow diagram of a method of training a predictive model according to an embodiment of the present disclosure.
As shown in fig. 2, the training method 200 of the prediction model may include operations S210 to S230.
In operation S210, sample data is obtained.
For example, the sample data comprises historical observation data for the heat exchange station, and the historical observation data can comprise multi-dimensional data such as weather data in a historical time period, operation data of the heat exchange station, actual temperature fed back by a user end and the like. For example, the sample data further includes a target heating temperature set for the history period.
In operation S220, a prediction model is trained based on the sample data.
The prediction model can be a neural network model, and the neural network model can be trained on the basis of a machine learning or deep learning method by using sample data to obtain the trained neural network model as the prediction model. Machine learning or deep learning methods include, for example, Ridge Regression (Ridge Regression) methods, methods using Support Vector Machine (SVM) or Long-Short Term Memory network (LSTM) models, and the like.
The prediction model can be used to predict the heating temperature of the heating plant. For example, observation data including weather data, operating condition data, user-side feedback data, and set target heating temperature may be input into the prediction model, and the prediction model may output the heating temperature of the corresponding heating station. The heat supply temperature of the heat supply station predicted based on the prediction model can determine the heat supply amount of the heat supply station to guarantee the heat supply demand of the user side.
According to the embodiment of the disclosure, compared with the method that the heat supply amount of the heat supply station is predicted only by considering the influence of weather data on heat required by the user side in the related art, the method and the device for predicting the heat supply amount of the heat supply station can acquire multidimensional data such as the weather data, the operation condition data of the heat exchange station and the user side feedback data as sample data to train the prediction model, improve the accuracy and robustness of the prediction model, and further guarantee the accuracy of predicting the heat supply amount of the heat supply station by using the prediction model.
In operation S230, based on the values of the historical observation data in the sample data, the use condition of the trained prediction model is determined.
Due to the fact that target heating temperatures required by different user requirements are different, and due to the fact that the operating conditions of the heat exchange station can meet the conditions of working condition overload, abnormal flow or periodic adjustment, sample data under each working condition are different. Therefore, the use condition met by the sample data can be determined according to the target heat supply temperature in the sample data and the historical observation data, and the use condition represents the actual working condition corresponding to the sample data. And determining the use condition met by the sample data as the use condition of the trained prediction model, wherein the use condition of the prediction model represents that the prediction model is suitable for prediction of the heat supply temperature under the use condition, namely when the current working condition meets the use condition, the prediction model can be used for predicting the heat supply temperature.
According to the embodiment of the disclosure, after the prediction model is obtained through training, the use condition is set for the prediction model according to the sample data, so that the prediction model is used only when the use condition is met, the prediction accuracy of the prediction model obtained through training in the use process can be improved, the heat supply quality is ensured, and the user experience is improved.
According to the embodiment of the disclosure, a plurality of prediction models can be trained according to different target heat supply temperatures and historical observation data under different working conditions, each prediction model has respective use conditions, and according to the use conditions met by the actual working conditions of the heat exchange station, the corresponding prediction model can be selected for predicting the heat supply temperature, so that the prediction accuracy is improved, heat supply on demand can be realized, the heat supply efficiency is improved, the energy consumption is reduced, and the environment is protected.
Fig. 3 is a schematic diagram of a method of obtaining sample data according to one embodiment of the present disclosure.
As shown in fig. 3, a plurality of (e.g., 100) candidate sample data 310 are first obtained, where each candidate sample data 310 includes historical observation data and a set target heating temperature. The historical observation data includes data of multiple dimensions, such as weather data, operation data, and user-side feedback data, where the data of each dimension includes multiple feature values, and the feature values of each dimension may be represented by small boxes in the candidate sample data 310.
The initial sample data satisfying the temperature constraint condition may be selected from the candidate sample data 310 according to the difference between the target heating temperature in the candidate sample data 310 and the actual temperature fed back by the user end. For example, the temperature constraint can be expressed as equation (1) as follows:
s.t.|Ttarget-Tclient|＜ε (1)
wherein, TtargetIs the target heating temperature, TclientIs the actual temperature fed back by the user end, and epsilon is a preset parameter.
The candidate sample data 310 that does not satisfy the formula (1) is removed to obtain a plurality of (for example, 50) sample data 320 to be selected. By selecting the sample data 320 to be selected from the multiple candidate sample data 310, the sample of the training model can be an effective and accurate sample, and thus, the accuracy of the trained model can be improved conveniently.
The target heat supply temperature and the multi-dimensional historical observation data in the sample data 320 to be selected may be further subjected to abnormal sample removal, where the abnormal sample removal may be, for example, removing sample data 320 to be selected whose characteristic value is outside a standard range, or determining abnormal sample data according to a statistical result of the sample data 320 to be selected, for example, removing sample data 320 to be selected whose value of a certain characteristic value is far greater than or far less than that of the certain characteristic value in other sample data 320 to be selected, in the sample data 320 to be selected, to obtain at least one (e.g., 40) initial sample data 330. The accuracy of the model obtained by training can be improved by removing abnormal sample data.
Feature data in the initial sample data 330 is selected using a feature selection algorithm, and the selected target data constitutes sample data 340 for model training. The feature selection algorithm may include chi-squared test and Mutual Information (Mutual Information), and may select feature data with a higher bid value from a plurality of feature data in the initial sample data 330, reject data with a smaller influence on model accuracy, reduce feature redundancy, and improve training efficiency.
It should be noted that the historical observation data includes observation data monitored when the operation mode of the heat exchange station is an abnormal mode, the abnormal mode may be, for example, the operation mode of the heat exchange station under the condition of overload in working condition or abnormal flow rate, and the model is trained according to the observation data in the abnormal processing mode, so that a new prediction model can be conveniently trained for the abnormal condition, and the automatic and efficient operation of the heat exchange station is facilitated.
In training the predictive model using the sample data, the predictive model may be trained using a cross-validation algorithm (e.g., K-fold cross-validation). For example, multiple rounds of training are performed using sample data, the sample data in each round of training is divided into training data and verification data, and the division manner is different for each round, that is, different training data and verification data are used for each round of training. The training data is used for training the model, and the verification data is used for verifying the prediction accuracy of the model after training. Multiple rounds of training can obtain multiple prediction models, a final model can be determined according to the prediction accuracy of the multiple models, or the multiple models are evaluated by using the average absolute error or the mean square error, and the optimal model is selected as the prediction model. The cross validation algorithm is used for training the model, so that the over-fitting condition can be avoided, and the accuracy of the model can be improved conveniently.
FIG. 4 is a flow diagram of a method of predicting a heating temperature according to one embodiment of the present disclosure.
As shown in fig. 4, the method 400 of predicting a heating temperature may include operations S410 to S420.
In operation S410, observation data for the heat exchange station is monitored.
For example, the working conditions can be monitored in real time to monitor current observation data of the heat exchange station, and the observation data may include current weather data, operation data, actual temperature fed back by the user end, and other multidimensional data.
In operation S420, it is determined whether the operation mode of the heat exchange station is a normal mode or an abnormal mode according to the observation data and the use condition of the prediction model.
For example, in the case where the difference between the observation data and the use condition of the prediction model is greater than a predetermined difference, the operation mode of the heat exchange station is determined to be an abnormal mode. And determining the operation mode of the heat exchange station as a normal mode under the condition that the difference between the observation data and the use condition of the prediction model is not larger than the preset difference.
In operation S430, in case that it is determined that the operation mode is the normal mode, a heating temperature of the heat exchange station for a preset user is determined using the prediction model.
For example, in the normal mode, the operation condition of the heat exchange station meets the use condition of the prediction model, so that the prediction of the heating temperature can be carried out by using the prediction model.
In operation S440, in case that it is determined that the operation mode is the abnormal mode, a heating temperature of the heat exchange station for a preset user is determined using an abnormality processing algorithm.
For example, in the abnormal mode, the operation condition of the heat exchange station does not meet the use condition of the prediction model, and therefore, the heat supply temperature of the heat exchange station for a preset user can be determined by using a preset abnormal processing algorithm.
According to the embodiment of the disclosure, the observation data of the heat exchange station are obtained by monitoring the working condition in real time, the operation mode of the heat exchange station is judged according to the observation data and the use condition of the model, the prediction model is only used in the normal mode, and the preset exception handling algorithm is used in the exception mode, so that the accuracy of the determined heat supply temperature can be improved, and the heat utilization rate and the user experience are improved conveniently.
According to the embodiment of the disclosure, the observation data for the heat exchange station include the operation data of the heat exchange station, the weather data and the temperature data for the preset user, and compared with the prior art in which only the influence of the weather data on the heat supply amount is considered, the embodiment of the disclosure determines the heat supply temperature by integrating the multidimensional data, and can improve the accuracy of the determined heat supply temperature.
Fig. 5 is a flowchart of a method of determining a heating temperature of a heat exchange station for a preset user using an exception handling algorithm according to one embodiment of the present disclosure.
As shown in fig. 5, the method may include operations S541 to S543.
In operation S541, a target heating amount for the preset user is determined according to the target temperature value and the temperature data for the preset user.
For example, the target temperature value is a set target heating temperature, and the temperature data for the preset user may be a temperature fed back by the user terminal. The target heat supply amount for the preset user, that is, the heat supply amount required by the user, can be calculated according to the following formula (2).
Q1＝cm(t1-t2) (2)
Wherein Q is1Is the amount of heat supplied required by the user, t1Is the target heating temperature, t2Is the actual temperature fed back by the user end, c is the specific heat capacity of the heating liquid, and m is the mass of the heating liquid.
In operation S542, a current heating load of the heat exchange station is determined according to the operation data of the heat exchange station.
For example, the current heat supply amount Q of the heat exchange station can be determined directly by the sensor, or by the water outlet flow, the water outlet temperature and the water inlet temperature between the heat exchange station and the user terminal2。
In operation S543, an adjustment amount of the heating temperature is determined according to a deviation between the current heating amount and the target heating amount.
For example, the heat supply Q according to the user's needs1And the current heat supply Q of the heat exchange station2The deviation therebetween, the heating load Q to be adjusted can be determined3，Q3＝|Q1-Q2Supply adjusted on demand |, based on needHeat quantity Q3The heating temperature that needs to be adjusted can be determined.
For example, the heat supply to be adjusted may also take into account the transmission losses, in which case the heat supply Q to be adjusted3＝|(Q1+Q4)-Q2L, wherein Q4Related to weather data, transmission distance, etc.
According to the embodiment of the disclosure, the abnormal modes such as the emergency of the change of the working condition can be automatically switched to the abnormal processing algorithm under the cold start, and the data under the corresponding working condition is accumulated, so that the unattended operation is realized, and the human resources are saved.
According to the embodiment of the disclosure, the exception handling algorithm can be applied to adjustment of the heating temperature in the exception mode of the heat exchange station, and can also be applied to cold start handling under the condition that no historical observation data or working conditions change. By means of data accumulation in the abnormal mode, a new prediction model can be trained for abnormal conditions by adopting a supervised machine learning method aiming at the heat exchange station with accumulated observation data, and work automation and efficient operation of the heat exchange station are facilitated.
The prediction model comprises a plurality of models with different use conditions, and when the prediction model is used for determining the heat supply temperature of the heat exchange station for the preset user, a target model with the use conditions matched with the observation data can be selected from the plurality of models, the observation data is used as the input of the target model, and the target model can output the heat supply temperature. According to the service conditions met by the actual working conditions of the heat exchange station, the corresponding prediction model is selected to predict the heat supply temperature, so that the prediction accuracy can be improved, and the heat supply quality is ensured.
FIG. 6 is a schematic diagram of the operating principle of a system for predicting a heating temperature according to one embodiment of the present disclosure.
As shown in FIG. 6, the system 600 for predicting heating temperature includes a historical observation data acquisition module 610, a prediction model deployment module 620, a prediction module 630, a condition monitoring module 640, and an exception handling module 650.
The historical observation data obtaining module 610 is configured to obtain weather data, operation data, and client feedback data in a historical time period, and send the obtained historical observation data as sample data to the prediction model deploying module 620.
The prediction model deployment module 620 firstly performs data cleaning on the sample data, the cleaning step may include removing sample data which does not meet the temperature constraint condition and removing abnormal sample data, then performing feature selection on the remaining sample data to obtain sample data for model training, performing prediction model training using the sample data, determining the use condition of the prediction model, verifying and evaluating the trained prediction model by using a cross-validation algorithm to obtain an optimal prediction model, and performing deployment of the prediction module 630.
The working condition monitoring module 640 is used for monitoring the operating working condition data of the heating plant, judging whether the difference between the operating working condition data and the use condition of the prediction model is larger than a preset difference, and if the difference is larger than the preset difference, processing the operation by using the exception processing module 650. If the difference is not greater than the preset difference, the prediction model deployed by the prediction module 630 is used to predict the heating temperature of the heating plant.
The abnormal processing module 650 is used for performing data cleaning on the currently observed abnormal observation data, the data cleaning method is the same as the above, the current heat supply amount of the heat exchange station and the user temperature data fed back by the user side are determined according to the cleaned data, the heat supply amount required by the user is determined according to the set target temperature value and the user temperature value fed back by the user side, the heat supply amount is adjusted according to the deviation between the heat supply amount required by the user and the current heat supply amount of the heat exchange station, and then the heat supply temperature is corrected.
According to the embodiment of the disclosure, the abnormal observation data processed by the abnormal processing module 650 may be stored as sample data, and through the accumulation of data in the abnormal mode, a supervised machine learning method may be adopted to train the prediction model for the heat exchange station that has accumulated the observation data.
According to the embodiment of the disclosure, the observation data of the heat exchange station are obtained by monitoring the working condition in real time, the operation mode of the heat exchange station is judged according to the observation data and the use condition of the model, the prediction model is only used in the normal mode, and the preset exception handling algorithm is used in the exception mode, so that the accuracy of the determined heat supply temperature can be improved, and the heat utilization rate and the user experience are improved conveniently.
Based on the training method of the prediction model provided by the present disclosure, the present disclosure also provides a training device of the prediction model, which will be described in detail below with reference to fig. 7.
Fig. 7 is a schematic structural diagram of a training apparatus for a predictive model according to an embodiment of the present disclosure.
As shown in fig. 7, the training apparatus 700 for the prediction model of this embodiment may include a sample data obtaining module 710, a model training module 720, and a condition determining module 730.
The sample data obtaining module 710 is configured to obtain sample data, which includes historical observation data for the heat exchange station. In an embodiment, the sample data obtaining module 710 may be configured to perform the operation S210 described above, which is not described herein again.
The model training module 720 is configured to train the predictive model based on the sample data. In an embodiment, the model training module 720 may be configured to perform the operation S220 described above, which is not described herein again.
The condition determining module 730 is configured to determine a use condition of the trained prediction model based on a value of the historical observation data in the sample data. In an embodiment, the condition determining module 730 may be configured to perform the operation S230 described above, which is not described herein again.
According to an embodiment of the present disclosure, the sample data obtaining module 710 may include a data obtaining sub-module, a sample selecting sub-module, and a feature selecting sub-module. The data acquisition submodule is used for acquiring a plurality of candidate sample data, each candidate sample data comprises historical observation data, and the historical observation data comprises a plurality of characteristic data. The sample selection submodule is used for selecting initial sample data meeting the temperature constraint condition from a plurality of candidate sample data. And the characteristic selection submodule is used for selecting target data from a plurality of characteristic data in the initial sample data by using a characteristic selection algorithm to obtain the sample data consisting of the target data.
According to an embodiment of the present disclosure, the plurality of characteristic data includes an actual temperature value for a preset user. The sample selection submodule may include a selection unit and a culling unit. The selection unit is used for selecting sample data to be selected, wherein the absolute value of the difference between the actual temperature value and the target temperature value is smaller than a preset value, from the plurality of sample data to be selected. The eliminating unit is used for eliminating abnormal sample data from the sample data to be selected to obtain initial sample data.
According to the embodiment of the disclosure, the historical observation data comprises observation data monitored when the operation mode of the heat exchange station is an abnormal mode.
According to an embodiment of the disclosure, the model training module is specifically configured to train the prediction model based on the sample data by using a cross validation algorithm.
Based on the method for predicting the heating temperature provided by the present disclosure, the present disclosure also provides a device for predicting the heating temperature, which will be described in detail below with reference to fig. 7.
Fig. 8 is a schematic structural diagram of an apparatus for predicting a heating temperature according to an embodiment of the present disclosure.
As shown in fig. 8, the apparatus 800 for predicting a heating temperature of this embodiment may include a data monitoring module 810, a mode determination module 820, a first temperature determination module 830, and a second temperature determination module 840.
The data monitoring module 810 is used to monitor the observed data for the heat exchange station. In an embodiment, the data monitoring module 810 may be configured to perform the operation S410 described above, which is not described herein again.
The mode determination module 820 is configured to determine an operation mode of the heat exchange station according to the observation data and the usage condition of the prediction model. The prediction model is obtained by training by adopting a training device of the prediction model provided by the disclosure. In an embodiment, the mode determining module 820 may be configured to perform the operation S420 described above, which is not described herein again.
The first temperature determination module 830 is configured to determine a heating temperature of the heat exchange station for a preset user by using an exception handling algorithm if the operation mode is determined to be the exception mode. In an embodiment, the first temperature determining module 830 may be configured to perform the operation S430 described above, and is not described herein again.
The second temperature determination module 840 is configured to determine a heating temperature of the heat exchange station for a preset user using the prediction model if the operation mode is determined to be the normal mode. In an embodiment, the second temperature determining module 840 may be configured to perform the operation S440 described above, which is not described herein again.
According to an embodiment of the present disclosure, the mode determination module is specifically configured to: and determining the operation mode of the heat exchange station as an abnormal mode under the condition that the difference between the observation data and the use condition of the prediction model is larger than a preset difference.
According to an embodiment of the disclosure, the observation data for the heat exchange station comprises operating data of the heat exchange station, weather data and temperature data for a preset user.
According to an embodiment of the disclosure, the observation data for the heat exchange station comprises operating data of the heat exchange station and temperature data for a preset user. The first temperature determination module includes a first heat determination submodule, a second heat determination submodule, and an adjustment amount determination submodule. The first heat determining submodule is used for determining a target heating load for a preset user according to the target temperature value and the temperature data for the preset user. And the second heat determining submodule is used for determining the current heat supply amount of the heat exchange station according to the operation data of the heat exchange station. And the adjustment quantity determining submodule is used for determining the adjustment quantity of the heat supply temperature according to the deviation between the current heat supply quantity and the target heat supply quantity.
According to an embodiment of the present disclosure, the device 800 for predicting a heating temperature may further include a storage module, configured to store the heating temperature and the observation data determined by the exception handling algorithm as sample data for training the prediction model, when the operation mode is determined to be the exception mode.
According to an embodiment of the present disclosure, the prediction model includes a plurality of models that are different in use condition. The second temperature determination module 840 may include a model determination sub-module and a temperature determination sub-module. The model determination submodule is used for selecting a target model with the use condition matched with the observation data from a plurality of models. The temperature determination submodule is used for taking the observation data as the input of the target model to obtain the heating temperature.
It should be noted that, in the technical solution of the present disclosure, the acquisition, storage, application, and the like of the personal information of the related user all conform to the regulations of the relevant laws and regulations, and do not violate the common customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 9 illustrates a schematic block diagram of an electronic device 900 that may be used to implement the training method of the predictive model and/or the method of predicting the heating temperature of embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 9, the apparatus 900 includes a computing unit 901, which can perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)902 or a computer program loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The calculation unit 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
Various components in device 900 are connected to I/O interface 805, including: an input unit 906 such as a keyboard, a mouse, and the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, optical disk, or the like; and a communication unit 909 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 901 performs various methods and processes described above, such as a training method of a prediction model and/or a method of predicting a heating temperature. For example, in some embodiments, the training method of the predictive model and/or the method of predicting the heating temperature may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 900 via ROM 902 and/or communications unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the method of training a predictive model and/or the method of predicting a heating temperature described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured by any other suitable means (e.g. by means of firmware) to perform a training method of a predictive model and/or a method of predicting the heating temperature.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server may be a cloud Server, which is also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in a traditional physical host and a VPS service ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (25)
1. A method of training a predictive model, comprising:
obtaining sample data, wherein the sample data comprises historical observation data aiming at the heat exchange station;
training the predictive model based on the sample data; and
and determining the use condition of the trained prediction model based on the value of the historical observation data in the sample data.
2. The method of claim 1, wherein said obtaining sample data comprises:
obtaining a plurality of alternative sample data, wherein each alternative sample data comprises the historical observation data, and the historical observation data comprises a plurality of characteristic data;
selecting initial sample data meeting a temperature constraint condition from the plurality of candidate sample data; and
and selecting target data from a plurality of feature data in the initial sample data by using a feature selection algorithm, and obtaining sample data consisting of the target data.
3. The method of claim 2, wherein the plurality of characteristic data comprises an actual temperature value for a preset user; said selecting initial sample data from said plurality of candidate sample data that satisfies a temperature constraint comprises:
selecting sample data with the absolute value of the difference between the actual temperature value and the target temperature value smaller than a preset value from the plurality of candidate sample data as sample data to be selected; and
and removing abnormal sample data from the sample data to be selected to obtain the initial sample data.
4. A method according to any one of claims 1 to 3, wherein:
the historical observation data includes: and the operation mode of the heat exchange station is observation data monitored under the condition of an abnormal mode.
5. The method of claim 1, wherein training the predictive model based on the sample data comprises:
and training the prediction model by adopting a cross validation algorithm based on the sample data.
6. A method of predicting a heating temperature, comprising:
monitoring observation data for the heat exchange station;
determining the operation mode of the heat exchange station according to the observation data and the using conditions of the prediction model;
under the condition that the operation mode is determined to be an abnormal mode, determining the heat supply temperature of the heat exchange station aiming at a preset user by using an abnormal processing algorithm; and
determining a heating temperature of the heat exchange station for the preset user using the prediction model in case that the operation mode is determined to be a normal mode,
wherein the prediction model is obtained by training by the method of any one of claims 1 to 5.
7. The method according to claim 6, wherein determining the operating mode of the heat exchange station comprises:
and determining the operation mode of the heat exchange station as an abnormal mode under the condition that the difference between the observation data and the use condition of the prediction model is larger than a preset difference.
8. A method according to claim 6 or 7, wherein the observation data for the heat exchange station comprises operating data of the heat exchange station, weather data and temperature data for the preset user.
9. The method according to claim 6, wherein the observation data for the heat exchange station comprise operating data of the heat exchange station and temperature data for the preset user; determining a heating temperature of the heat exchange station for a preset user using the exception handling algorithm comprises:
determining a target heat supply amount for the preset user according to the target temperature value and the temperature data for the preset user;
determining the current heat supply amount of the heat exchange station according to the operation data of the heat exchange station; and
and determining the adjustment amount of the heat supply temperature according to the deviation between the current heat supply amount and the target heat supply amount.
10. A method according to any of claims 6 to 9, further comprising, in the event that the operating mode is determined to be an abnormal mode:
storing the heat supply temperature and the observation data determined using the exception handling algorithm as sample data for training the predictive model.
11. The method of claim 6, wherein the predictive model comprises a plurality of models that differ in terms of use; determining a heating temperature of the heat exchange station for the preset user using the predictive model comprises:
selecting a target model from the plurality of models whose usage conditions match the observation data; and
and obtaining the heat supply temperature by taking the observation data as the input of the target model.
12. An apparatus for training a predictive model, comprising:
the system comprises a sample data obtaining module, a data processing module and a data processing module, wherein the sample data obtaining module is used for obtaining sample data, and the sample data comprises historical observation data aiming at the heat exchange station;
a model training module for training the prediction model based on the sample data; and
and the condition determining module is used for determining the use condition of the trained prediction model based on the value of the historical observation data in the sample data.
13. The apparatus of claim 12, wherein the sample data obtaining module comprises:
the data acquisition submodule is used for acquiring a plurality of alternative sample data, each alternative sample data comprises the historical observation data, and the historical observation data comprises a plurality of characteristic data;
the sample selection submodule is used for selecting initial sample data meeting the temperature constraint condition from the plurality of candidate sample data; and
and the characteristic selection submodule is used for selecting target data from a plurality of characteristic data in the initial sample data by using a characteristic selection algorithm to obtain the sample data consisting of the target data.
14. The apparatus of claim 13, wherein the plurality of characteristic data comprises an actual temperature value for a preset user; the sample selection submodule includes:
a selecting unit, configured to select, from the multiple candidate sample data, sample data in which an absolute value of a difference between the actual temperature value and the target temperature value is smaller than a predetermined value as sample data to be selected; and
and the rejecting unit is used for rejecting abnormal sample data from the sample data to be selected to obtain the initial sample data.
15. The apparatus of any one of claims 12-14, wherein:
the historical observation data includes: and the operation mode of the heat exchange station is observation data monitored under the condition of an abnormal mode.
16. The apparatus of claim 12, wherein the model training module is specifically configured to:
and training the prediction model by adopting a cross validation algorithm based on the sample data.
17. An apparatus for predicting a heating temperature, comprising:
the data monitoring module is used for monitoring observation data aiming at the heat exchange station;
the mode determining module is used for determining the operation mode of the heat exchange station according to the observation data and the using condition of the prediction model;
the first temperature determination module is used for determining the heat supply temperature of the heat exchange station aiming at a preset user by using an exception handling algorithm under the condition that the operation mode is determined to be an exception mode; and
a second temperature determination module for determining a heating temperature of the heat exchange station for the preset user using the prediction model if the operation mode is determined to be a normal mode,
wherein the prediction model is obtained by training by using the device of any one of claims 12-16.
18. The apparatus of claim 17, wherein the mode determination module is specifically configured to:
and determining the operation mode of the heat exchange station as an abnormal mode under the condition that the difference between the observation data and the use condition of the prediction model is larger than a preset difference.
19. The apparatus of claim 17 or 18, wherein the observation data for the heat exchange station comprises operating data of the heat exchange station, weather data and temperature data for the preset user.
20. The apparatus of claim 17, wherein the observed data for the heat exchange station comprises operating data of the heat exchange station and temperature data for the preset user; the first temperature determination module includes:
the first heat determining submodule is used for determining a target heating load for the preset user according to a target temperature value and the temperature data for the preset user;
the second heat determining submodule is used for determining the current heat supply amount of the heat exchange station according to the operation data of the heat exchange station; and
and the adjustment quantity determining submodule is used for determining the adjustment quantity of the heat supply temperature according to the deviation between the current heat supply quantity and the target heat supply quantity.
21. The apparatus of any of claims 17-20, further comprising:
and the storage module is used for storing the heat supply temperature and the observation data determined by the abnormal processing algorithm under the condition that the operation mode is determined to be the abnormal mode, so as to be used as sample data for training the prediction model.
22. The apparatus of claim 17, wherein the predictive model comprises a plurality of models that differ in terms of use; the second temperature determination module includes:
a model determination sub-module for selecting a target model from the plurality of models for which the usage condition matches the observation data; and
and the temperature determination submodule is used for taking the observation data as the input of the target model to obtain the heat supply temperature.
23. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 11.
24. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 11.
25. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110450926.0A CN113111589A (en) | 2021-04-25 | 2021-04-25 | Training method of prediction model, method, device and equipment for predicting heat supply temperature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110450926.0A CN113111589A (en) | 2021-04-25 | 2021-04-25 | Training method of prediction model, method, device and equipment for predicting heat supply temperature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113111589A true CN113111589A (en) | 2021-07-13 |
Family
ID=76720226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110450926.0A Pending CN113111589A (en) | 2021-04-25 | 2021-04-25 | Training method of prediction model, method, device and equipment for predicting heat supply temperature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111589A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114138030A (en) * | 2021-10-29 | 2022-03-04 | 西安北方华创微电子装备有限公司 | Temperature control method and semiconductor process equipment |
| CN114623693A (en) * | 2022-04-13 | 2022-06-14 | 深圳市佳运通电子有限公司 | Control method for intelligent output temperature of heating furnace of upstream and downstream stations of oil field |
| 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 |
| CN115146790A (en) * | 2022-06-30 | 2022-10-04 | 北京百度网讯科技有限公司 | Training method of deep learning model, and determination method and device of heat exchange data |
| CN115374866A (en) * | 2022-08-26 | 2022-11-22 | 呼伦贝尔安泰热电有限责任公司海拉尔热电厂 | Method for identifying abnormal heat behavior of user in central heating |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109992866A (en) * | 2019-03-25 | 2019-07-09 | 新奥数能科技有限公司 | Training method, device, readable medium and the electronic equipment of load forecasting model |
| CN111561733A (en) * | 2020-05-18 | 2020-08-21 | 瑞纳智能设备股份有限公司 | Heating household valve adjusting method, system and equipment based on GBDT |
| CN111561734A (en) * | 2020-05-18 | 2020-08-21 | 瑞纳智能设备股份有限公司 | Heating household valve adjusting method, system and equipment based on artificial intelligence |
| WO2020259421A1 (en) * | 2019-06-28 | 2020-12-30 | 深圳前海微众银行股份有限公司 | Method and apparatus for monitoring service system |
| WO2021042339A1 (en) * | 2019-09-05 | 2021-03-11 | 阿里巴巴集团控股有限公司 | Heat dissipation control and model training method, device and system, and storage medium |
-
2021
- 2021-04-25 CN CN202110450926.0A patent/CN113111589A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109992866A (en) * | 2019-03-25 | 2019-07-09 | 新奥数能科技有限公司 | Training method, device, readable medium and the electronic equipment of load forecasting model |
| WO2020259421A1 (en) * | 2019-06-28 | 2020-12-30 | 深圳前海微众银行股份有限公司 | Method and apparatus for monitoring service system |
| WO2021042339A1 (en) * | 2019-09-05 | 2021-03-11 | 阿里巴巴集团控股有限公司 | Heat dissipation control and model training method, device and system, and storage medium |
| CN111561733A (en) * | 2020-05-18 | 2020-08-21 | 瑞纳智能设备股份有限公司 | Heating household valve adjusting method, system and equipment based on GBDT |
| CN111561734A (en) * | 2020-05-18 | 2020-08-21 | 瑞纳智能设备股份有限公司 | Heating household valve adjusting method, system and equipment based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 张海静;加玛力汗・库马什;张建良;吴建中;: "基于GUI界面的供热负荷预测分析", 自动化博览, no. 07 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114138030A (en) * | 2021-10-29 | 2022-03-04 | 西安北方华创微电子装备有限公司 | Temperature control method and semiconductor process equipment |
| CN114138030B (en) * | 2021-10-29 | 2022-11-18 | 西安北方华创微电子装备有限公司 | Temperature control method and semiconductor process equipment |
| CN114623693A (en) * | 2022-04-13 | 2022-06-14 | 深圳市佳运通电子有限公司 | Control method for intelligent output temperature of heating furnace of upstream and downstream stations of oil field |
| CN114623693B (en) * | 2022-04-13 | 2024-01-30 | 深圳市佳运通电子有限公司 | Control method for intelligent output temperature of heating furnace of upstream and downstream stations of oil field |
| CN115146790A (en) * | 2022-06-30 | 2022-10-04 | 北京百度网讯科技有限公司 | Training method of deep learning model, and determination method and device of heat exchange data |
| 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 |
| CN115374866A (en) * | 2022-08-26 | 2022-11-22 | 呼伦贝尔安泰热电有限责任公司海拉尔热电厂 | Method for identifying abnormal heat behavior of user in central heating |
| CN115374866B (en) * | 2022-08-26 | 2023-08-11 | 呼伦贝尔安泰热电有限责任公司海拉尔热电厂 | User abnormal heat behavior identification method in central heating |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113111589A (en) | Training method of prediction model, method, device and equipment for predicting heat supply temperature | |
| US20200166905A1 (en) | Optimal machining parameter selection using a data-driven tool life modeling approach | |
| CN104809051B (en) | Method and apparatus for predicting exception and failure in computer application | |
| US11556484B2 (en) | Minimizing energy consumption by peripheral machines | |
| CN112000459A (en) | Method for expanding and contracting service and related equipment | |
| CN104636874B (en) | Detect the method and apparatus of service exception | |
| Yang et al. | Aero-material consumption prediction based on linear regression model | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| JP7145821B2 (en) | Failure probability evaluation system and method | |
| CN117176560B (en) | Monitoring equipment supervision system and method based on Internet of things | |
| US7720553B2 (en) | Service metric portfolio management | |
| CN111008724A (en) | Price prediction method and device, electronic equipment and readable storage medium | |
| CN114818913A (en) | Decision generation method and device | |
| CN114500339A (en) | Node bandwidth monitoring method and device, electronic equipment and storage medium | |
| CN110826196B (en) | Industrial equipment operation data processing method and device | |
| CN116011677A (en) | Time sequence data prediction method and device, electronic equipment and storage medium | |
| CN116414608A (en) | Abnormality detection method, abnormality detection device, abnormality detection apparatus, and storage medium | |
| CN116384876A (en) | Spare part dynamic inventory-production control method, system and medium based on wiener process | |
| CN115759751A (en) | Enterprise risk prediction method and device, storage medium, electronic equipment and product | |
| US9507344B2 (en) | Index generation and embedded fusion for controller performance monitoring | |
| EP3462338A1 (en) | Data processing device, data analyzing device, data processing system and method for processing data | |
| CN110413482B (en) | Detection method and device | |
| KR20210077200A (en) | Electronic device, method, and computer readable medium for estimating sales rate of fishery products | |
| JP7043261B2 (en) | Systems and methods for equipment inspection of model prediction controllers and estimators | |
| CN113360486B (en) | Data prediction method, device, electronic equipment and medium |
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 |