Control method, system and device for regulating output electric power of control cabinet fan

Abstract

The application discloses a control method and system for regulating and controlling output electric power of a fan of a control cabinet and equipment thereof, and relates to the technical field of electric power regulation and control, and comprises the following steps: obtaining internal data and external data of the control cabinet based on time series data, wherein the internal data comprises an internal temperature value, an internal humidity value and an internal fan output electric power in an internal environment of the control cabinet, and the external data comprises an external temperature value and an external humidity value in an external environment; generating an internal fan output electric power prediction model of the control cabinet based on the multiple sets of internal data and external data; and calibrating an internal fan output electric power prediction value based on an electric power error parameter to generate a calibrated internal fan output electric power value of the control cabinet, thereby ensuring the accuracy of the internal fan output electric power prediction value predicted by the internal fan output electric power prediction model and the accuracy of the internal fan output electric power of the fan in the control cabinet, and improving the regulation and control accuracy of the remote control cabinet.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power regulation, and particularly relates to a control cabinet fan output electric power regulation method and system and a device thereof. BACKGROUND

[0002] Generally, in order to ensure that the electronic equipment in the control cabinet is in a stable working environment, the temperature and humidity values in the control cabinet are controlled within a certain range (the specific range is adaptively determined by the person skilled in the art according to the requirements of the actual electronic equipment installed in the control cabinet), and high temperature or high humidity will affect the stable operation of the electronic equipment installed in the control cabinet, so the working electric power of the fan, that is, the output electric power, is regulated to ensure that the internal environment of the control cabinet is in a stable state.

[0003] However, as a mechanical device, the fan in the control cabinet will inevitably produce mechanical fatigue or other factors that cause the preset working electric power of the fan during work to deviate from the actual working electric power (regulating the temperature and humidity in the control cabinet) during work, so that the output electric power of the fan is not accurately regulated. SUMMARY

[0004] In order to overcome the above technical problems, the purpose of the present application is to provide a control cabinet fan output electric power regulation method and device to solve the problem that the fan will inevitably produce mechanical fatigue or other factors that cause the preset working electric power of the fan during work to deviate from the actual working electric power (regulating the temperature and humidity in the control cabinet) during work, resulting in inaccurate regulation of the output electric power of the fan.

[0005] The purpose of the present application can be achieved by the following technical solutions:

[0006] Specifically, the present application provides a control cabinet fan output electric power regulation method, comprising the following steps:

[0007] S1: Obtain a plurality of sets of internal data and external data of the control cabinet based on time series data, wherein the internal data includes an internal temperature value, an internal humidity value and an internal fan output electric power in the internal environment of the control cabinet, and the external data includes an external temperature value and an external humidity value in the external environment;

[0008] S2: Generate an internal fan output electric power prediction model of the control cabinet based on the plurality of sets of internal data and external data;

[0009] S3: Generate an internal fan output electric power change model of the control cabinet based on the plurality of sets of internal data and external data;

[0010] S4: collecting internal data and external data of the control cabinet in real time, wherein the internal data collected in real time comprises an internal temperature value, an internal humidity value and a first internal fan output electric power;

[0011] S5: generating a second internal fan output electric power based on the internal data and the external data of the control cabinet collected in real time, using an internal fan output electric power change model;

[0012] S6: generating an electric power error parameter based on the first internal fan output electric power and the second internal fan output electric power;

[0013] S7: generating an internal fan output electric power prediction value of the control cabinet based on the internal data and the external data collected in real time, using an internal fan output electric power prediction model;

[0014] S8: calibrating the internal fan output electric power prediction value based on the electric power error parameter, to generate an internal fan output electric power calibration value of the control cabinet.

[0015] As a further scheme of the present application: the internal temperature value is an internal average temperature value of the control cabinet, and the internal humidity value is an internal average humidity value of the control cabinet.

[0016] As a further scheme of the present application: the S2 comprises the following steps:

[0017] S2.1: pre-collecting a plurality of sets of internal data and external data;

[0018] S2.2: generating a two-dimensional data set of the plurality of sets of internal data and external data based on time series data;

[0019] S2.3: training the two-dimensional data set using a recurrent neural network model to generate an internal fan output electric power prediction model;

[0020] S2.4: predicting the internal fan output electric power in the internal environment of the control cabinet based on the time series data, using the internal fan output electric power prediction model.

[0021] As a further scheme of the present application: the S2.3 comprises the following steps:

[0022] S2.31: pre-collecting N sets of training data, N being a positive integer, each set of training data comprising feature data and label data, wherein the feature data is an internal temperature value and an internal humidity value in the internal environment of the control cabinet and an external temperature value and an external humidity value in the external environment, and the label data is an internal fan output electric power;

[0023] S2.32: transform the feature data into a feature vector, the feature vector as an input of an inner fan output electric power prediction model, the inner fan output electric power predicted by the inner fan output electric power prediction model as an output, the inner fan output electric power in the label data as a prediction target, and the sum of all prediction accuracies as a training target;

[0024] S2.33: train the inner fan output electric power prediction model until the prediction accuracy reaches convergence.

[0025] As a further scheme of the present application: the calculation formula of the prediction accuracy is:

[0026] ;

[0027] Wherein is the prediction accuracy, is the inner fan output electric power of the inner fan output electric power prediction model corresponding to the i-th group of feature data, is the inner fan output electric power in the label data corresponding to the i-th group of feature data, 1≤n≤N.

[0028] As a further scheme of the present application: the S6 comprises the following steps:

[0029] S6.1: input the first inner fan output electric power and the second inner fan output electric power;

[0030] S6.2: generate an electric power error parameter based on the first inner fan output electric power and the second inner fan output electric power;

[0031] S6.3: sliding statistics on the electric power error parameter to generate an average error;

[0032] S6.4: using time series data decay correction based on the average error.

[0033] As a further scheme of the present application: the S7 comprises the following steps:

[0034] S7.1: real-time acquisition of internal data and external data of the control cabinet;

[0035] S7.2: based on the internal data and the external data, using the inner fan output electric power prediction model to predict the inner fan output electric power prediction value of the control cabinet based on the time series data;

[0036] S7.3: output the inner fan output electric power prediction value of the control cabinet based on the time series data.

[0037] As a further scheme of the present application: the S8 comprises the following steps:

[0038] S8.1: The input control cabinet generates an internal fan output electric power prediction value based on the timing data;

[0039] S8.2: The control cabinet generates an internal fan output electric power calibration value based on the electric power error parameter;

[0040] S8.3: The control cabinet adjusts the air cooling based on the internal fan output electric power calibration value.

[0041] Specifically, the second aspect of the present application provides a control cabinet fan output electric power adjustment system, comprising:

[0042] A temperature acquisition module for acquiring internal and external temperature values of the control cabinet and transmitting them to the processing module;

[0043] A humidity acquisition module for acquiring internal and external humidity values of the control cabinet and transmitting them to the processing module;

[0044] A fan module for acquiring the internal fan output electric power of the control cabinet and transmitting it to the processing module;

[0045] The processing module is used to execute the above-mentioned control cabinet fan output electric power adjustment method based on the characteristics collected by the temperature acquisition module, humidity acquisition module and fan module.

[0046] Specifically, the third aspect of the present application provides a control cabinet fan output electric power adjustment device, comprising:

[0047] A processor;

[0048] A storage for storing executable programs, wherein the processor is used to read the executable programs in the storage and execute the executable programs to realize the above-mentioned control cabinet fan output electric power adjustment method.

[0049] The present application has the following advantages:

[0050] In the present application, the electric power error parameter can be generated through the internal fan output electric power prediction model and the internal fan output electric power change model, the internal air cooling electric power prediction value is calibrated based on the electric power error parameter, the internal air cooling electric power calibration value of the control cabinet is generated, and the internal air cooling electric power prediction value is calibrated through the electric power error parameter, which can ensure the accuracy of the internal air cooling electric power prediction value predicted by the internal fan output electric power prediction model and ensure the accuracy of the internal fan output electric power of the fan in the control cabinet, thereby improving the adjustment accuracy of the remote control cabinet. BRIEF DESCRIPTION OF DRAWINGS

[0051] The present application will be further described below with reference to the accompanying drawings.

[0052] Figure 1 is a method flow chart of the control cabinet fan output electric power adjustment method of the present application.

[0053] Figure 2 is the generation process schematic diagram of the internal fan output electric power prediction model in the control cabinet fan output electric power regulation method of the present application;

[0054] Figure 3 is the training process schematic diagram of the recurrent neural network model in the control cabinet fan output electric power regulation method of the present application;

[0055] Figure 4 is the generation process schematic diagram of the electric power error parameter in the control cabinet fan output electric power regulation method of the present application;

[0056] Figure 5 is the system structure block diagram of the control cabinet fan output electric power regulation system of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0058] As one embodiment of the present application, as shown in Figures 1-5 , a control cabinet fan output electric power regulation method is disclosed. When monitoring the humidity inside the control cabinet, the following steps are taken, specifically:

[0059] S1: First, a plurality of sets of internal data and external data of the control cabinet based on time series data need to be acquired, wherein the internal data includes an internal temperature value, an internal humidity value and an internal fan output electric power in the internal environment of the control cabinet, and the external data includes an external temperature value and an external humidity value in the external environment. It should be noted that the internal temperature value, the internal humidity value and the internal fan output electric power in the internal environment of the control cabinet refer to the temperature, humidity and working electric power of the internal air-cooled motor of the control cabinet. Since the working electric power of the air-cooled motor of different specifications is different, the internal fan output electric power needs to be adaptively determined according to the working electric power of the air-cooled motor installed in the control cabinet. Temperature sensors and humidity sensors need to be arranged in the control cabinet, and the installation positions and data of the temperature sensors and humidity sensors are adaptively adjusted by a person skilled in the art according to the size of the space in the control cabinet and the positions of the internal equipment, so as to ensure that the temperature and humidity in the control cabinet can be accurately collected. The fan is usually arranged at the end or side of the control cabinet to provide a cooling air source for the internal environment of the control cabinet. During the operation of the fan, the fan can bring the air in the external environment of the control cabinet into the internal environment of the control cabinet. The air in the external environment includes the temperature and humidity (i.e. the external temperature value and the external humidity value in the external data). Therefore, the temperature and humidity in the internal environment of the control cabinet are closely related to the temperature and humidity in the air in the external environment and the working electric power of the fan (i.e. the internal fan output electric power). In general, in order to ensure that the electronic equipment in the control cabinet is in a stable working environment, the temperature value and the humidity value in the internal environment of the control cabinet need to be controlled within a certain range (the specific range is adaptively determined by a person skilled in the art according to the requirements of the actual electronic equipment installed in the control cabinet). If the temperature is too high or the humidity is too high, the stable operation of the electronic equipment installed in the control cabinet will be affected. Therefore, the working electric power of the fan, i.e. the internal fan output electric power, needs to be adjusted to ensure that the internal environment of the control cabinet is in a stable state (i.e. the internal temperature value and the internal humidity value are within a controllable range).

[0060] In order to ensure that the internal environment of the control cabinet can be finally controlled within a controllable range, the internal data and external data of the control cabinet need to be collected (adaptively arranged by a person skilled in the art according to the requirements). The meaning of time series data is that the internal data and external data of the control cabinet need to be marked with the corresponding time points during collection. In order to reduce the collection cost and efficiency of the internal data and external data of the control cabinet, the internal data and external data of different control cabinets can be collected at the same time to ensure the number of internal data and external data.

[0061] S2: generate an internal fan output electric power prediction model of the control cabinet based on multiple sets of internal data and external data, it should be noted that the number of multiple sets of internal data and external data is adaptively adjusted by a person skilled in the art according to the training of the specific internal fan output electric power prediction model, and the internal fan output electric power prediction model is trained successfully;

[0062] S3: generate an internal fan output electric power change model of the control cabinet based on multiple sets of internal data and external data, the number of multiple sets of internal data and external data is adaptively adjusted by a person skilled in the art according to the training of the specific internal fan output electric power change model, and the internal fan output electric power change model is trained successfully;

[0063] The generation method of the internal fan output electric power change model is fitting by using a computer, and specifically, multivariate regression fitting or a machine learning model (random forest or neural network) can be used:

[0064] The change relationship between the internal humidity value, the internal temperature value, the external humidity value, the external temperature value and the internal fan output electric power is obtained, and thus the internal fan output electric power change model is obtained;

[0065] S4: real-time acquisition of internal data and external data of the control cabinet, wherein the real-time acquired internal data includes the internal temperature value, the first internal fan output electric power and the internal fan output electric power, it should be noted that the internal data of the control cabinet is determined by the temperature sensor, the humidity sensor and the fan (working electric power of the fan) inside the control cabinet, and the external data of the control cabinet is determined by the temperature sensor and the humidity sensor outside the control cabinet, although the internal data of the control cabinet, i.e. the internal temperature value, the internal humidity value and the first internal fan output electric power, can be quickly determined by the temperature sensor, the humidity sensor and the fan inside the control cabinet, but after a long time of work, the fan will produce certain errors due to its own mechanical fatigue or other factors, i.e. the working electric power of the controlled fan is inconsistent with the actual working electric power of the fan, which will result in that the first internal fan output electric power is not accurate enough, and the control of the internal temperature value and the internal humidity value in the internal environment of the control cabinet will also be inaccurate, thereby affecting the operation of the electronic equipment installed in the control cabinet;

[0066] S5: Based on the real-time collected internal and external data of the control cabinet, the second internal fan output power of the control cabinet is generated using the internal fan output power change model. It should be noted that the second internal fan output power of the control cabinet is generated using the internal fan output power change model based on the real-time collected internal and external data of the control cabinet. This second internal fan output power is generated based on the changes in the internal fan output power change model, avoiding errors generated by the fan itself. This is because the second internal fan output power of the control cabinet generated by the internal fan output power change model using the real-time collected internal and external data of the control cabinet is the actual working power of the fan.

[0067] S6: Based on the output power of the first internal fan and the output power of the second internal fan, an electrical power error parameter is generated. By generating the electrical power error parameter based on the output power of the first internal fan and the output power of the second internal fan, the working power of the fan inside the control cabinet can be calibrated, ensuring that the output power of the fan inside the control cabinet is accurate, thus improving the accuracy of the control of the remote control cabinet.

[0068] S7: Based on real-time collected internal and external data, the internal fan output power prediction model is used to predict the predicted value of the internal cooling power of the control cabinet. By using the internal fan output power prediction model based on real-time collected internal and external data, the internal cooling power of the fan in the future control cabinet internal environment can be predicted. Those skilled in the art can pre-set the humidity threshold (temperature threshold) in the control cabinet internal environment. If the internal humidity value (temperature value) of the control cabinet regulated by the predicted internal cooling power value is greater than or equal to the humidity threshold (temperature threshold), it indicates that the control cabinet will be in an unfavorable working environment. The internal cooling power of the fan can be controlled in advance to avoid the control cabinet being in an unfavorable working environment and to keep the control cabinet in a stable working environment.

[0069] S8: Based on the power error parameter, the predicted value of the internal air-cooled power is calibrated to generate the calibration value of the internal air-cooled power of the control cabinet. By calibrating the predicted value of the internal air-cooled power through the power error parameter, the accuracy of the predicted value of the internal air-cooled power of the internal fan output power prediction model can be guaranteed, ensuring the accuracy of the output power of the internal fan of the control cabinet and improving the accuracy of the control of the remote control cabinet.

[0070] As one embodiment of the present invention, such as Figures 1-5As shown, the internal temperature value is the average internal temperature value of the control cabinet, and the internal humidity value is the average internal humidity value of the control cabinet. A plurality of temperature sensors and humidity sensors need to be arranged inside and outside the control cabinet. The installation positions and data of the temperature sensors and humidity sensors are adaptively adjusted by a person skilled in the art according to the size of the space inside the control cabinet and the positions of the devices inside the control cabinet, so that the temperature and humidity inside the control cabinet can be accurately collected. Specifically, the average temperature collected by the plurality of temperature sensors in the internal environment of the control cabinet is taken as the internal temperature value of the control cabinet, and the average humidity collected by the plurality of humidity sensors in the internal environment of the control cabinet is taken as the internal humidity value of the control cabinet. In addition, it should be noted that the values collected by the plurality of temperature sensors or humidity sensors can also be differentiated in terms of coefficients according to the positions of the devices inside the control cabinet. For example, the temperature sensor or humidity sensor close to the position of the device inside the control cabinet (core position) gives a high coefficient, for example, 1.2-1.5. The temperature sensor or humidity sensor close to the edge position of the control cabinet gives a low coefficient, for example, 0.5-0.8. The specific adaptive adjustment is made by a person skilled in the art according to the on-site situation of the control cabinet and the internal space.

[0071] As one embodiment of the present application, as Figures 1-5 As shown, S2 includes the following steps:

[0072] S2.1: Pre-collecting a plurality of internal data and external data. It should be noted that the number of internal data and external data collected is adaptively adjusted by a person skilled in the art according to the specific training of the internal fan output electric power prediction model. In order to reduce the collection cost and efficiency of the internal data and external data of the control cabinet, the internal data and external data of different control cabinets can be collected at the same time to ensure the number of internal data and external data.

[0073] S2.2: Generating a two-dimensional data set of a plurality of internal data and external data based on time series data. It should be noted that the internal temperature value, internal humidity value, internal fan output electric power, external temperature value and external humidity value in the internal data and external data are marked with time points. The time points should include the date and the specific time point, which can be accurate to seconds. The internal temperature value, internal humidity value, internal fan output electric power, external temperature value and external humidity value marked by the time points are collected together to obtain a two-dimensional data set.

[0074] S2.3: training the two-dimensional data set using a recurrent neural network model to generate an internal fan output power prediction model, it should be noted that the recurrent neural network (RNN) is a deep learning model specially designed to process sequence data, and its core function is to capture the time-dependent relationship and dynamic change in the data. Unlike traditional neural networks, RNN introduces a loop structure to enable the network to pass the hidden state of the previous time step to the current time step, thereby retaining historical information and affecting the current output. This feature makes it perform well in natural language processing, speech recognition, time series prediction and other fields; the architecture of RNN realizes the encoding and transmission of time dimension information through the loop connection of hidden state, and the input of each time step not only includes the current data, but also combines the hidden state of the previous time step, thereby dynamically updating the memory content of the network. This mechanism enables RNN to simulate the way humans understand the current situation based on historical experience.

[0075] Therefore, through the recurrent neural network model, the working power of the fan of the control cabinet based on time series data prediction (internal fan output power) can be obtained.

[0076] S2.4: predicting the internal humidity value in the control cabinet internal environment based on time series data using the internal fan output power prediction model, it should be noted that the skilled person in the art can train the internal fan output power in the control cabinet internal environment based on time series data according to the specific training of the internal fan output power prediction model. In order to ensure the accuracy of the predicted internal fan output power in the control cabinet internal environment, the time length of the predicted time series data should be set to a threshold, for example, 24 to 36 hours, that is, the internal fan output power in the control cabinet internal environment after 24 to 36 hours in the future is predicted. When the internal fan output power corresponding to the predicted internal temperature value (internal humidity value) of the control cabinet reaches the preset temperature threshold (humidity threshold) in the art, an early warning can be made through the monitoring background, thereby improving the safety supervision of the control cabinet.

[0077] As one embodiment of the present application, as shown in Figures 1-5 S2.3 includes the following steps:

[0078] S2.31: pre-collecting N groups of training data, N being a positive integer, each group of training data including feature data and label data, wherein the feature data is the internal temperature value, internal humidity value in the control cabinet internal environment, and the external temperature value and external humidity value in the external environment, and the label data is the internal fan output power;

[0079] It should be noted that the internal temperature value is the internal temperature value collected by the control cabinet in the internal environment when collecting each group of training data;

[0080] The internal humidity value is the internal humidity value collected by the control cabinet in the internal environment when each set of training data is collected.

[0081] The external temperature value is the external temperature value collected by the control cabinet in the external environment when each set of training data is collected.

[0082] The external humidity value is the external humidity value collected by the control cabinet in the external environment when each set of training data is collected.

[0083] The label data is the internal fan output electric power collected by the control cabinet in the internal environment when each set of training data is collected.

[0084] S2.32: Convert the feature data into a feature vector, the feature vector as the input of the internal fan output electric power change model, the internal fan output electric power predicted by the internal fan output electric power change model as the output, the internal fan output electric power in the label data as the prediction target, and the sum of all prediction accuracies as the training target, wherein the calculation formula of the prediction accuracy is: , wherein is the prediction accuracy, is the internal fan output electric power predicted by the internal fan output electric power change model corresponding to the i-th set of feature data, is the internal fan output electric power in the label data corresponding to the i-th set of feature data;

[0085] S2.33: Train the internal fan output electric power prediction model until the prediction accuracy reaches convergence, and stop training. It should be noted that the convergence standard is adaptively adjusted by a person skilled in the art according to the specific model training situation, for example, the sum of prediction accuracies can be set to ≦0.01, that is, when the sum of prediction accuracies is 0.01, the model training is considered to be completed.

[0086] As one embodiment of the present application, as shown in Figures 1-5 , S6 includes the following steps:

[0087] S6.1: Input the first internal fan output electric power and the second internal fan output electric power, then:

[0088] ;

[0089] , wherein is the instantaneous electric power error at the t-th time point, is the internal fan output electric power predicted by the internal fan output electric power prediction model at the t-th time point, is the internal fan output electric power of the internal fan of the control cabinet at the t-th time point;

[0090] S6.2: generating an electric power error parameter based on the first inner fan output electric power and the second inner fan output electric power, wherein The electric power error parameter can be for the first inner fan output electric power and the second inner fan output electric power;

[0091] S6.3: performing a sliding statistics on the electric power error parameter to generate an average error, specifically:

[0092] ;

[0093] ;

[0094] wherein is a sliding window length, for example, when M=3, it represents the average error of the instantaneous electric power error of the last three time points each time, t is greater than or equal to , is the window period average error, is the error standard deviation, is the instantaneous electric power error at time point t for k;

[0095] S6.4: using a time series data decay correction based on the average error, specifically:

[0096] ;

[0097] τ;

[0098] wherein, is the time point t correction error, is a forgetting factor, is a natural constant, is a data collection interval, τ is a time constant, for example, one time (3600 seconds), τ is specifically set by a person skilled in the art;

[0099] Then, based on the correction error calibration :

[0100] ;

[0101] is the calibrated inner fan output electric power calibration value.

[0102] As an embodiment of the present application, as shown in Figures 1-5 S7 includes the following steps:

[0103] S7.1: Collecting internal data and external data of the control cabinet in real time, collecting the internal temperature value, internal humidity value and internal fan output electric power in the internal environment of the control cabinet in real time through the temperature sensor, humidity sensor and fan arranged inside the control cabinet, collecting the external temperature value and external humidity value in the external environment of the control cabinet in real time through the temperature sensor and humidity sensor arranged outside;

[0104] S7.2: Based on the internal data and external data, using the internal fan output electric power prediction model to predict the internal air-cooled electric power prediction value of the control cabinet based on the time series data, specifically, marking the internal temperature value, internal humidity value and internal fan output electric power and the external temperature value and external humidity value in the internal data and external data with time points, the time points should include the date and specific time points, which can be accurate to seconds, collecting the internal temperature value, internal humidity value and internal fan output electric power and the external temperature value and external humidity value marked with time points together to obtain a two-dimensional data set, training the two-dimensional data set using a recurrent neural network model to generate an internal fan output electric power prediction model;

[0105] S7.3: Outputting the internal air-cooled electric power prediction value of the control cabinet based on the time series data, using the internal fan output electric power prediction model to predict the internal air-cooled electric power prediction value in the internal environment of the control cabinet based on the time series data.

[0106] As one embodiment of the present application, as shown in Figures 1-5 S8 includes the following steps:

[0107] S8.1: Inputting the internal air-cooled electric power prediction value of the control cabinet based on the time series data, that is, inputting the internal air-cooled electric power prediction value predicted by the internal fan output electric power prediction model into the calibration system;

[0108] S8.2: Generating the internal air-cooled electric power calibration value of the control cabinet based on the electric power error parameter, specifically: inputting the first internal fan output electric power and the second internal fan output electric power, then:

[0109] ;

[0110] Wherein is the instantaneous electric power error at the t time point, is the internal fan output electric power predicted by the internal fan output electric power prediction model at the t time point, is the internal fan output electric power of the internal fan of the control cabinet at the t time point;

[0111] Generating the error parameter based on the first internal fan output electric power and the second internal fan output electric power, wherein may be the electric power error parameter of the first internal fan output electric power and the second internal fan output electric power;

[0112] The sliding statistics of the electric power error parameter generates the average error, specifically:

[0113] ;

[0114] ;

[0115] Wherein M is the length of the sliding window, for example, M=5, which means that the average error of the instantaneous electric power error of the last 5 time points is calculated each time, t is greater than or equal to , is the average error of the window period, is the error standard deviation, is the instantaneous electric power error at time point t is k;

[0116] The time series data attenuation correction is used based on the average error, specifically:

[0117] ;

[0118] τ;

[0119] Wherein, is the time point t correction error, is the forgetting factor, the value range is (0, 1), is a natural constant, is the data acquisition interval, τ is the time constant, for example, one time (3600 seconds), τ is specifically set by the person skilled in the art;

[0120] Then, the corrected error is used to calibrate :

[0121] ;

[0122] is the calibrated internal fan output electric power calibration value;

[0123] S8.3: The internal fan output electric power calibration value of the output control cabinet is output, the internal fan electric power calibration value is taken as the actual working electric power of the fan of the control cabinet, the internal fan electric power prediction value is calibrated through the electric power error parameter, which can ensure the accuracy of the internal fan electric power prediction value predicted by the internal fan electric power prediction model, and then the internal fan electric power calibration value is sent to the monitoring background. The monitoring background can accurately control the internal fan to regulate and control the internal environment of the control cabinet through the internal fan electric power calibration value, so as to ensure the normal work of the control cabinet.

[0124] As an embodiment of the present application, as Figures 1-5As shown, the control cabinet fan output electric power regulating system is disclosed, comprising:

[0125] The temperature acquisition module is used for acquiring the internal and external temperature values of the control cabinet and transmitting them to the processing module. It should be noted that the temperature acquisition module is a temperature sensor arranged in the internal and external environments of the control cabinet.

[0126] The humidity acquisition module is used for acquiring the internal and external humidity values of the control cabinet and transmitting them to the processing module. The humidity acquisition module is a humidity sensor arranged in the internal and external environments of the control cabinet. The installation positions and data of the temperature sensor and the humidity sensor are adaptively adjusted by the person skilled in the art according to the size of the internal space of the control cabinet and the position of the internal equipment, so as to ensure that the temperature and humidity in the internal space of the control cabinet can be accurately acquired. Specifically, the average temperature acquired by the multiple temperature sensors in the internal environment of the control cabinet is taken as the internal temperature value of the control cabinet, and the average humidity acquired by the multiple humidity sensors in the internal environment of the control cabinet is taken as the internal humidity value of the control cabinet. In addition, it should be noted that the values acquired by the multiple temperature sensors or humidity sensors can also be differentiated in terms of coefficients according to the position of the internal equipment of the control cabinet. For example, the temperature sensor or humidity sensor close to the internal equipment position (core position) of the control cabinet is given a high coefficient, for example, 1.2-1.5, and the temperature sensor or humidity sensor close to the edge position of the internal equipment of the control cabinet is given a low coefficient, for example, 0.5-0.8. The specific adaptive adjustment is made by the person skilled in the art according to the on-site situation of the control cabinet and the internal space.

[0127] The fan module is used for acquiring the internal fan output electric power of the control cabinet and transmitting it to the processing module. It should be noted that the fan module is a fan arranged in the internal space of the control cabinet. The fan is usually arranged at the end or side of the control cabinet to provide a cooling air source for the internal environment of the control cabinet. During the operation of the fan, the fan can bring the air in the external environment of the control cabinet into the internal space of the control cabinet.

[0128] The processing module is used for executing the control cabinet fan output electric power regulating method based on the internal and external data of the control cabinet acquired by the temperature acquisition module, the humidity acquisition module and the fan module, that is, based on the time sequence data. The internal fan output electric power is calibrated by the electric power error parameter to ensure the accuracy of the internal fan output electric power predicted by the internal fan output electric power prediction model. Then, the internal fan output electric power calibration value is transmitted to the monitoring background. The monitoring background can accurately control the fan to regulate the internal environment of the control cabinet through the internal fan output electric power calibration value, thereby ensuring the normal operation of the control cabinet.

[0129] As one embodiment of the present application, as Figures 1-5As shown, the control device for controlling the output electric power of the control cabinet fan is disclosed, which comprises a processor and a storage, the storage comprises but is not limited to a U disk, a hard disk and other executable programs that can be carried, the executable program executes the control method for controlling the output electric power of the control cabinet fan in the above embodiment, and the processor comprises but is not limited to a microprocessor or a PLC that can read and run the executable program in the storage.

[0130] The above describes one embodiment of the present application in detail, but the content is only the preferred embodiment of the present application and cannot be considered as limiting the implementation range of the present application. Any equivalent changes and improvements made according to the application scope of the present application should still belong to the patent coverage range of the present application.

Claims

1. A method of regulating the output electric power of a control cabinet fan, characterized in that, The application is applied to air cooling of a control cabinet, and comprises the following steps: S1: obtaining multiple sets of internal data and external data of the control cabinet based on time series data, wherein the internal data comprises an internal temperature value, an internal humidity value and an internal fan output electric power in an internal environment of the control cabinet, and the external data comprises an external temperature value and an external humidity value in an external environment; S2: generating an internal fan output electric power prediction model of the control cabinet based on the multiple sets of internal data and external data; S3: generating an internal fan output electric power change model of the control cabinet based on the multiple sets of internal data and external data; S4: collecting internal data and external data of the control cabinet in real time, wherein the internal data collected in real time comprises an internal temperature value, an internal humidity value and a first internal fan output electric power; S5: generating a second internal fan output electric power by using the internal fan output electric power change model based on the internal data and external data of the control cabinet collected in real time; S6: generating an electric power error parameter based on the first internal fan output electric power and the second internal fan output electric power; S7: generating an internal fan output electric power prediction value of the control cabinet by using the internal fan output electric power prediction model based on the internal data and external data collected in real time; S8: calibrating the internal fan output electric power prediction value based on the electric power error parameter to generate an internal fan output electric power calibration value of the control cabinet.

2. The method of claim 1, wherein, The internal temperature value is an internal average temperature value of the control cabinet, and the internal humidity value is an internal average humidity value of the control cabinet.

3. The method of claim 1, wherein, The S2 comprises the following steps: S2.1: collecting multiple sets of internal data and external data in advance; S2.2: generating a two-dimensional data set of the multiple sets of internal data and external data based on time series data; S2.3: training the two-dimensional data set by using a recurrent neural network model to generate the internal fan output electric power prediction model; S2.4: predicting the internal fan output electric power in the internal environment of the control cabinet by using the internal fan output electric power prediction model based on time series data.

4. The method of claim 3, wherein, The S2.3 comprises the following steps: S2.31: collecting N sets of training data in advance, N being a positive integer, each set of training data comprising feature data and label data, wherein the feature data comprises an internal temperature value and an internal humidity value in the internal environment of the control cabinet and an external temperature value and an external humidity value in the external environment, and the label data comprises an internal fan output electric power; S2.32: converting the feature data into a feature vector, the feature vector being used as an input of the internal fan output electric power change model, the internal fan output electric power predicted by the internal fan output electric power prediction model being used as an output, the internal fan output electric power in the label data being used as a prediction target, and the sum of all prediction accuracies being minimized as a training target; S3.33: training the internal fan output electric power prediction model until the prediction accuracy reaches convergence.

5. The method of claim 4, wherein, The calculation formula of the prediction accuracy is: ； wherein is the prediction accuracy, is the inner fan output electric power predicted by the inner fan output electric power prediction model corresponding to the i-th set of feature data, is the inner fan output electric power in the label data corresponding to the i-th set of feature data, 1≤n≤N.

6. The method of claim 1, wherein, The S6 comprises the following steps: S6.1: inputting the first internal fan output electric power and the second internal fan output electric power; S6.2: generating the electric power error parameter based on the first internal fan output electric power and the second internal fan output electric power; S6.3: performing sliding statistics on the electric power error parameter to generate an average error; S6.4: using time series data attenuation correction based on average error.

7. The method of claim 1, wherein, The S7 includes the following steps: S7.1: collecting internal data and external data of the control cabinet in real time; S7.2: based on the internal data and the external data, using the internal fan output power prediction model to predict the internal fan output power prediction value of the control cabinet based on time series data; S7.3: outputting the internal fan output power prediction value of the control cabinet based on time series data.

8. The method of claim 7, wherein, The S8 includes the following steps: S8.1: inputting the internal fan output power prediction value of the control cabinet based on time series data; S8.2: generating the internal fan output power calibration value of the control cabinet based on the electric power error parameter; S8.3: regulating the air cooling of the control cabinet based on the internal fan output power calibration value.

9. A control system for regulating the output electrical power of a control cabinet fan, characterized in that, It includes: temperature acquisition module, for collecting internal temperature value and external temperature value of the control cabinet and conveying to the processing module; humidity acquisition module, for collecting internal humidity value and external humidity value of the control cabinet and conveying to the processing module; fan module, for collecting internal fan output power of the control cabinet and conveying to the processing module; processing module, for executing the regulation method of the control cabinet fan output power according to any one of claims 1-8 based on the characteristics collected by the temperature acquisition module, the humidity acquisition module and the fan module.

10. A device for regulating the output electric power of a control cabinet fan, characterized in that It includes: a processor; a storage for storing executable programs, wherein the processor is used to read the executable programs in the storage and execute the executable programs to realize the regulation method of the control cabinet fan output power according to any one of claims 1-8.

Images