Generation method of control model for energy saving, electronic equipment and storage medium

Abstract

The invention provides a generation method of a control model for energy saving, electronic equipment and a storage medium, and relates to the technical field of electronic equipment, and the method comprises the steps: obtaining initial sample data of a transformer substation; preprocessing the initial sample data to obtain illumination sample data; constructing a plurality of fuzzy rules according to the illumination sample data; establishing an initial control model according to a plurality of fuzzy rules; inputting the illumination sample data into the initial control model, and outputting a sample adjustment mode through a plurality of fuzzy rules; and according to the sample adjustment mode and the target illumination, adjusting the initial control model to obtain an illumination control model. According to the technical scheme provided by the invention, the initial control model is constructed according to the initial sample data, and then the initial control model is trained according to the initial sample data to obtain the illumination control model, so that the phenomena of glare and low illumination uniformity caused by too high illumination value of the working surface can be reduced, and the operation and maintenance safety of the transformer substation can be improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of electronic devices, and particularly relates to a method for generating a control model for energy saving, an electronic device, and a storage medium. BACKGROUND

[0002] In a power transmission system, while a substation converts different energy into electric energy, the substation itself also consumes part of the electric quantity to maintain the normal operation of the substation, and therefore the requirements for the substation in terms of energy saving and environmental protection and sustainable development are increasingly high.

[0003] In the related art, a proportional integral derivative (PID) control system can be used to perform fuzzy PID cascade control on an illumination system, to convert the deviation between the required standard illuminance and the actual illuminance into the opening degree of a louver. Moreover, when natural lighting cannot meet the standard illuminance, the opening number of lamps in the illumination system can be adjusted by the PID control system.

[0004] However, in the process of controlling the illumination system by the PID control system, the actual illuminance parameter of the working surface of the substation can be much larger than the parameter required by the relevant standard, and problems such as glare and non-uniform illuminance can occur. SUMMARY

[0005] The present application provides a method for generating a control model for energy saving, an electronic device, and a storage medium, which solves the problem that in the related art, in the process of controlling the illumination system by the PID control system, the actual illuminance parameter of the working surface of the substation can be much larger than the parameter required by the relevant standard, and problems such as glare and non-uniform illuminance can occur.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a method for generating a model for illumination control, which comprises:

[0008] obtaining initial sample data of a substation, the initial sample data comprising: environmental data, lamp distribution data, lamp adjustment mode, illuminance parameters of each room where a lamp is located, and target illuminance corresponding to each room;

[0009] preprocessing the initial sample data to obtain illumination sample data;

[0010] constructing a plurality of fuzzy rules according to the illumination sample data;

[0011] establishing an initial control model according to the plurality of fuzzy rules;

[0012] inputting the lighting sample data into the initial control model, outputting a sample adjustment mode through a plurality of fuzzy rules of the initial control model;

[0013] adjusting the initial control model according to the sample adjustment mode and the target illumination, to obtain a lighting control model.

[0014] Optionally, the inputting the lighting sample data into the initial control model, outputting a sample adjustment mode through a plurality of fuzzy rules of the initial control model, comprises:

[0015] inputting the lighting sample data into an input layer of the initial control model, processing the lighting sample data forwarded by the input layer through a fuzzification layer and a fuzzy rule layer of the initial control model, to generate a fuzzy adjustment mode;

[0016] de-fuzzifying the fuzzy adjustment mode through a de-fuzzification layer of the initial control model, to obtain the sample adjustment mode.

[0017] Optionally, the processing the lighting sample data forwarded by the input layer through the fuzzification layer and the fuzzy rule layer of the initial control model, to generate a fuzzy adjustment mode, comprises:

[0018] mapping the lighting sample data to a fuzzy set through the fuzzification layer, and calculating a membership degree of each data in the lighting sample data;

[0019] optimizing a plurality of the fuzzy rules through the fuzzy rule layer, and determining a weight of each of the fuzzy rules;

[0020] generating the fuzzy adjustment mode through a conclusion layer of the initial control model in combination with each of the fuzzy rules.

[0021] Optionally, the optimizing a plurality of the fuzzy rules through the fuzzy rule layer, and determining a weight of each of the fuzzy rules, comprises:

[0022] for each of the fuzzy rules, determining an influence factor of each data on the sample adjustment mode according to each data corresponding to the fuzzy rule in combination with a membership degree corresponding to each data;

[0023] adjusting the weight of the fuzzy rule corresponding to each data according to a parameter value of each of the influence factors, and deleting a fuzzy rule whose weight is less than a threshold value.

[0024] Optionally, before the generating the fuzzy adjustment mode through the conclusion layer of the initial control model in combination with each of the fuzzy rules, the method further comprises:

[0025] The weight of each of the fuzzy rules is normalized by a normalization layer.

[0026] Optionally, the adjusting the initial control model according to the sample adjustment mode and the target illuminance to obtain a lighting control model comprises:

[0027] The simulation illuminance of each of the rooms of the substation is obtained by simulating each of the luminaires of the substation according to the sample adjustment mode through a pre-set simulation model.

[0028] The illuminance difference of each of the rooms is obtained by comparing the simulation illuminance corresponding to the room with the target illuminance corresponding to the room.

[0029] The weight corresponding to each of the fuzzy rules of the fuzzy rule layer in the initial control model is adjusted according to the illuminance difference to obtain the lighting control model.

[0030] Optionally, the plurality of fuzzy rules comprises:

[0031] The luminaires adjustment mode is determined according to environmental data, illuminance parameters of each of the rooms where the luminaires are located, and target illuminance corresponding to each of the rooms, wherein the environmental data comprises weather data and / or time data.

[0032] The luminaires adjustment mode is determined according to luminaire distribution data, illuminance parameters of each of the rooms where the luminaires are located, and target illuminance corresponding to each of the rooms.

[0033] Optionally, the pre-processing the initial sample data to obtain lighting sample data comprises:

[0034] The initial sample data is cleaned to delete repeated data in the initial sample data.

[0035] The initial sample data is checked to complete missing data in the initial sample data to obtain the lighting sample data.

[0036] In a second aspect, an electronic device is provided, which comprises a memory and a processor, the memory is configured to store a computer program, and the processor is configured to execute the method in the first aspect or any of the implementation forms of the first aspect when the computer program is invoked.

[0037] In a third aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the method in the first aspect or any of the implementation forms of the first aspect.

[0038] The embodiment of the present application provides a kind of control model generation method for energy saving, by obtaining the initial sample data of substation, and the initial sample data is preprocessed, obtains lighting sample data, then according to lighting sample data, constructs multiple fuzzy rules, establishes initial control model based on multiple fuzzy rules, so that lighting sample data is input into initial control model, the output sample adjustment mode is output by multiple fuzzy rules of initial control model, and then initial control model can be adjusted according to sample adjustment mode and target illumination, and lighting control model is obtained.The scheme provided by the embodiment of the present application is constructed according to initial sample data Initial control model, then initial control model is trained according to initial sample data, and lighting control model is obtained, so that lighting control model can be combined with the environment (such as season and weather) where the substation is located to adjust the lamps of the substation, so that the illumination parameter of each room of the substation can be reduced to reduce the phenomenon of glare and uneven illumination of the working surface in each room of the substation, the working life of the lamps can be improved, and the energy consumption generated by the lamps can be reduced, so that the safety of the operation and maintenance of the substation can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 A scene schematic diagram of the lighting control scene of the substation involved in the control model generation method for energy saving provided by the embodiment of the present application is provided.

[0040] Figure 2 A schematic flow chart of the control model generation method for energy saving provided by the embodiment of the present application is provided.

[0041] Figure 3 A schematic flow chart of the control model generation method for energy saving provided by the embodiment of the present application is provided.

[0042] Figure 4 A structure block diagram of the control model generation device for energy saving provided by the embodiment of the present application is provided.

[0043] Figure 5 A structure schematic diagram of the electronic device provided by the embodiment of the present application is provided. DETAILED DESCRIPTION

[0044] In the following description, specific details are set forth such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it should be apparent to those skilled in the art that the present application can be practiced in other embodiments without these specific details. In other instances, well-known illumination control techniques, model training algorithms and electronic devices are not described in detail in order to avoid obscuring the description of the present application.

[0045] The terminology used in the following description merely to describe particular embodiments and is not intended to limit the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0046] In the power transmission system, the substation itself consumes part of the electricity while converting different energy into electric energy to maintain the normal operation of the substation, so the requirements for the substation in energy saving, environmental protection and sustainable development are also increasing.

[0047] In the related art, the lighting system can be controlled by a proportional integral derivative (PID) control system for fuzzy PID cascade control, and the deviation between the required standard illuminance and the actual illuminance is converted into the opening degree of the shutter. Moreover, when the natural lighting cannot meet the standard illuminance, the opening number of the lamps in the lighting system can be adjusted by the PID control system.

[0048] However, in the actual application, when the lighting system is controlled by the PID control system, the actual illuminance parameter of the working surface of the substation may be much larger than the parameter required by the relevant standard, and the problems of glare and non-uniform illuminance may occur.

[0049] Therefore, the application provides a method for generating a control model for energy saving. The initial sample data of the substation is obtained, and the initial sample data is preprocessed to obtain lighting sample data. A plurality of fuzzy rules are constructed according to the lighting sample data, and an initial control model is established based on the plurality of fuzzy rules. The lighting sample data is input into the initial control model, and the sample adjustment mode is output through the plurality of fuzzy rules of the initial control model. Then, the initial control model can be adjusted according to the sample adjustment mode and the target illuminance to obtain a lighting control model. The scheme provided in the embodiments of the application constructs an initial control model according to the initial sample data, and trains the initial control model according to the initial sample data to obtain a lighting control model. Therefore, the lighting control model can be used to adjust the lamps of the substation in combination with the environment (such as the season and the weather) of the substation, so that the illuminance parameter of the working surface in each room of the substation can be reduced to prevent the phenomenon of glare and non-uniform illuminance caused by the illuminance parameter of the working surface being too high in each room of the substation. The working life of the lamps can be improved, and the energy consumption of the lamps can be reduced, thereby improving the safety of the operation and maintenance of the substation.

[0050] Referring to Figure 1 , Figure 1A scene schematic diagram of a lighting control scene of a substation involved in a method for generating a control model for energy saving provided by the embodiment of the present application can include: a control terminal 110, a lighting system 120 and a collection device 130, wherein the lighting system 120 can include a plurality of lamps.

[0051] The control terminal 110 is connected with the collection device 130 and the lighting system 120 respectively. Moreover, the collection device 130 is used to collect the illuminance of each room in the substation to obtain the actual lighting data of the substation, which represents the corresponding illuminance of each room in the substation.

[0052] For example, the collection device 130 can be a photosensitive sensor, and the embodiment of the present application does not make specific limitation on the collection device 130.

[0053] It should be noted that in actual application, each lamp in the lighting system 120 can be at least one of a light emitting diode (LED) lamp, an arc lamp and an incandescent lamp, and the embodiment of the present application does not make specific limitation on the type of each lamp in the lighting system 120.

[0054] Figure 2 A schematic flow chart of a method for generating a control model for energy saving provided by the embodiment of the present application is applied to the control terminal in the lighting control scene of the above substation as an example but not limitation, see Figure 2 The method comprises:

[0055] Step 201, obtaining initial sample data of the substation.

[0056] The initial sample data includes: environmental data, lamp distribution data, lamp adjustment mode, illuminance parameter of each room where each lamp is located, and target illuminance corresponding to each room.

[0057] Moreover, the environmental data can include at least one of weather data and time data. Further, the time data can correspond to the weather data, the lamp distribution data, the lamp adjustment mode, the illuminance parameter of each room where each lamp is located, and the target illuminance corresponding to each room, so as to determine the relevant data corresponding to each room of the substation at different times.

[0058] For example, in the case of sunny weather, the rooms facing the north side in the substation need to turn on the lamps for lighting at various time periods of the day, the rooms facing the south side need to turn on the lamps for lighting only at the corresponding time period of the night, the rooms facing the east side need to turn on the lamps for lighting at the corresponding time period of the afternoon and the night, and the rooms facing the west side need to turn on the lamps for lighting at the corresponding time period of the morning and the night.

[0059] Correspondingly, the control terminal can obtain the initial sample data in the preset time period recorded continuously in the pre-set storage space, so that the initial sample data can be used for training in the subsequent steps to obtain the lighting control model.

[0060] It should be noted that in actual application, the initial sample data of different time periods, different seasons or different weather can be selected, so that the lighting control model for different situations can be trained; or the initial sample data in a long time period can be selected to train a lighting control model that can adapt to different time periods, different seasons and different weather. The selection of the initial sample data is not limited in the embodiments of the present application.

[0061] In step 202, the initial sample data is pre-processed to obtain lighting sample data.

[0062] After obtaining the initial sample data, the control terminal can first integrate the initial sample data, delete or complete the initial sample data, complete the pre-processing of the initial sample data, and obtain the lighting sample data, so that the lighting control model can be trained according to the lighting sample data in the subsequent steps.

[0063] Optionally, the control terminal can first clean the initial sample data, delete the repeated data in the initial sample data, and check the sample data to complete the missing data in the initial sample data to obtain the lighting sample data.

[0064] Specifically, the control terminal can first establish the corresponding relationship between the time data and other data according to the time data included in the environmental data in the initial sample data, so that the other data corresponding to the time data can be traversed to determine whether there is repeated or missing data, and then the repeated data can be deleted and the missing data can be supplemented.

[0065] Further, in the process of supplementing the missing data, the control terminal can supplement the missing data according to the time data corresponding to the missing data, in combination with the initial sample data corresponding to the time data before and after the time data.

[0066] Alternatively, the control terminal can also supplement the missing data according to the environmental data corresponding to the missing data, in combination with other initial sample data corresponding to the same or similar environmental data. Of course, the control terminal can also supplement the missing data in other ways, and the application embodiments do not make specific limitations on the way of supplementing the missing data.

[0067] Step 203: constructing a plurality of fuzzy rules according to the lighting sample data.

[0068] The plurality of fuzzy rules can include determining the lamp adjustment mode according to the environmental data, the illuminance parameter of each room where each lamp is located, and the target illuminance corresponding to each room; and can also include determining the lamp adjustment mode according to the lamp distribution data, the illuminance parameter of each room where each lamp is located, and the target illuminance corresponding to each room.

[0069] In the actual operation process of the substation, due to different factors such as weather, season and time period, the mode of adjusting the lamps of the substation is affected by the above-mentioned factors. Therefore, based on the sorted lighting sample data, a plurality of fuzzy rules can be constructed, so that in the subsequent steps, a lighting control model can be constructed according to the plurality of fuzzy rules.

[0070] Specifically, the control terminal can select part of the data in the lighting sample data as the condition of the fuzzy rule according to the operation triggered by the user, and take the lamp adjustment mode in the lighting sample data as the target, so that a plurality of fuzzy rules can be constructed according to the various data in the lighting sample data.

[0071] For example, the fuzzy rule of the lamp adjustment mode can be determined according to the environmental data, the illuminance parameter of each room where each lamp is located, and the target illuminance corresponding to each room, or the fuzzy rule of the lamp adjustment mode can be determined according to the lamp distribution data, the illuminance parameter of each room where each lamp is located, and the target illuminance corresponding to each room, and the application embodiments do not make specific limitations on the constructed fuzzy rules.

[0072] It should be noted that the application embodiments take the operation triggered by the user to construct the fuzzy rule as an example for description, and in actual application, the control terminal can also self-learn the lighting sample data to automatically construct the fuzzy rule, and the application embodiments do not make specific limitations on the way of constructing the fuzzy rule.

[0073] Step 204: establishing an initial control model according to the plurality of fuzzy rules.

[0074] Corresponding to step 203, after the control terminal constructs a plurality of fuzzy rules according to the operation triggered by the user, the control terminal can generate an initial control model according to the plurality of fuzzy rules established, so that in the subsequent steps, the initial control model can be trained to obtain a lighting control model.

[0075] Specifically, the control terminal can construct the input layer, the fuzzification layer and the conclusion layer according to the pre-set parameters, and construct the fuzzy rule layer based on the generated multiple fuzzy rules, so that the input layer, the fuzzification layer, the fuzzy rule layer, the conclusion layer and the defuzzification layer arranged in sequence can be obtained, and then the initial control model can be composed.

[0076] It should be noted that in actual application, the control terminal can also construct the initial control model according to the parameters input by the user triggered operation, and the application embodiment does not make specific limitation on the way of constructing the initial control model.

[0077] For example, in the process of constructing the initial control model, the environment data, the lamp distribution data, the illuminance parameter of each lamp in the room, and the target illuminance corresponding to each room can be input in the input layer.

[0078] Correspondingly, for each item of input data, a corresponding membership function can be set in the initial control model, so that after inputting each item of data, the membership degree corresponding to each item of data can be determined according to the membership function corresponding to each item of data and in combination with the pre-set fuzzy rules, and then the corresponding sample adjustment mode can be output according to the membership degree.

[0079] Step 205, input the lighting sample data into the initial control model, and output the sample adjustment mode through the multiple fuzzy rules of the initial control model.

[0080] The sample adjustment mode is the adjustment mode of the initial control model output for each lamp in the substation, so that the lamps in the substation can further save energy and reduce emissions and reduce the energy consumption of the lamps under the condition of meeting the target illuminance.

[0081] After the control terminal generates the initial control model, the lighting sample data can be input into the initial control model to obtain the sample adjustment mode output by the initial control model, so that in the subsequent steps, the initial control model can be adjusted according to the sample adjustment mode, the training of the initial control model is completed, and the lighting control model is obtained.

[0082] The initial control model can include multiple levels, and the control terminal can input the lighting sample data into the input layer of the initial control model, and then process the lighting sample data through other levels of the initial control model, and output the sample adjustment mode through the conclusion layer of the initial control model.

[0083] Optionally, as shown in Figure 3 Step 205 can include the following steps:

[0084] Step 2051, input the lighting sample data into the input layer of the initial control model, process the lighting sample data forwarded by the input layer through the fuzzification layer and the fuzzy rule layer of the initial control model, and generate a fuzzy adjustment mode.

[0085] Specifically, the control terminal can input the environment data, lamp distribution data, illuminance parameters of each room where each lamp is located, and target illuminance corresponding to each room in the lighting sample data into the input layer of the initial control model, pass the above data to the fuzzification layer of the initial control model through the input layer, perform fuzzification processing on the above data through the fuzzification layer, and process the fuzzified data through the conclusion layer to obtain a fuzzy adjustment mode.

[0086] Optionally, in the process of inputting part of the lighting sample data into the initial control model and processing the part of the lighting sample data by the initial control model, the input part of the lighting sample data can be first mapped to a fuzzy set through the fuzzification layer, the membership degree of each data in the lighting sample data is calculated through the membership function corresponding to each data, a plurality of fuzzy rules are optimized through the fuzzy rule layer, the weight of each fuzzy rule is determined, and finally the fuzzy adjustment mode is generated through the conclusion layer of the initial control model in combination with each fuzzy rule.

[0087] Further, in the process of optimizing the plurality of fuzzy rules, for each fuzzy rule, the control terminal can determine an influence factor of each data on the sample adjustment mode according to each data corresponding to the fuzzy rule in combination with the membership degree corresponding to each data, adjust the weight of the fuzzy rule corresponding to each data according to the parameter value of each influence factor, and delete the fuzzy rule whose weight is less than a threshold, so as to obtain the optimized fuzzy rule.

[0088] Step 2052, de-fuzzification of the fuzzy adjustment mode is performed through the de-fuzzification layer of the initial control model to obtain a sample adjustment mode.

[0089] Corresponding to step 2051, after obtaining the fuzzy adjustment mode, the initial control model of the control terminal can identify and process the fuzzy adjustment mode through the de-fuzzification layer in the initial control model to obtain a corresponding sample adjustment mode.

[0090] Specifically, the initial control model can pass the fuzzy adjustment mode to the de-fuzzification layer through the fuzzification layer, process the fuzzy adjustment mode through the de-fuzzification layer, inversely process the fuzzy adjustment mode in the opposite way of the fuzzification layer, obtain a sample adjustment mode, and thus the sample adjustment mode can be output through the output layer of the initial control model.

[0091] The fuzzy adjustment mode can be inversely processed in a centroid method to obtain a sample adjustment mode. The centroid method is used to calculate the "center of gravity" of the output membership function, so that the output sample adjustment mode can be determined, and the accuracy and practicability of the output are ensured.

[0092] It should be noted that in actual application, the initial control model can further include a normalization layer. The normalization layer is used to normalize the weights of the fuzzy rules, so that the fuzzy adjustment mode can be determined by the normalized fuzzy rules. Of course, the initial control model can further include other levels, and the application embodiments do not limit the levels included in the initial control model.

[0093] In step 206, the initial control model is adjusted according to the sample adjustment mode and the target illuminance to obtain a lighting control model.

[0094] After obtaining the sample adjustment mode output by the initial control model, the control terminal can compare the sample adjustment mode with the lamp adjustment mode recorded in the lighting sample data, and adjust the fuzzy rules in the initial control model in combination with the target illuminance of each room to obtain a lighting control model.

[0095] Optionally, the control terminal can first simulate each lamp of the substation according to the sample adjustment mode through a pre-set simulation model to obtain the simulation illuminance of each room of the substation. Moreover, for each room, the simulation illuminance corresponding to the room is compared with the target illuminance corresponding to the room to obtain the illuminance difference of the room, so that the weights corresponding to the plurality of fuzzy rules of the fuzzy rule layer in the initial control model can be adjusted according to the illuminance difference to obtain a lighting control model.

[0096] Specifically, after obtaining the sample adjustment mode, the control terminal can simulate the illuminance of each room in the substation in combination with the sample adjustment mode through a pre-set simulation model to determine the simulation illuminance of each room. Then, for each room, the control terminal can compare the simulation illuminance corresponding to the room with the target illuminance required by the room to obtain the illuminance difference therebetween.

[0097] Correspondingly, the control terminal can adjust the initial control model according to the illuminance difference to obtain a lighting control model. For example, if the simulation illuminance is higher than the target illuminance, the weight of the fuzzy rule with a higher weight in the initial control model can be adjusted downward, and the weight of the fuzzy rule with a lower weight can be adjusted upward, so that the simulation illuminance gradually approaches the target illuminance.

[0098] On the contrary, if the illuminance difference indicates that the simulation illuminance is lower than the target illuminance, the weight of the fuzzy rule with a higher weight in the initial control model can be continuously adjusted upwards, and the weight of the fuzzy rule with a lower weight can be adjusted downwards, so that the simulation illuminance continuously approaches the target illuminance.

[0099] The illuminance I(x, t) corresponding to the xth room in the substation at time t can be represented as:

[0100]

[0101] where k is a light efficiency coefficient, R i (t) is the reflection coefficient in the substation room, Q i (t) is the influence coefficient of the substation environment, λ is the light attenuation coefficient in the substation room, I ext (t) is the ambient light intensity.

[0102] Moreover, the control terminal can also determine the energy consumption generated when the lamps are controlled according to the sample adjustment mode in the simulation process of the simulation model. Therefore, in the process of adjusting the initial control model to obtain the lighting control model, the control terminal can adjust the weights corresponding to the multiple fuzzy rules in the fuzzy rule layer of the initial control model according to the energy consumption obtained by simulation, to obtain the lighting control model.

[0103] In summary, the model generation method for lighting control provided in the embodiments of the present application obtains initial sample data of a substation, pre-processes the initial sample data to obtain lighting sample data, constructs multiple fuzzy rules according to the lighting sample data, establishes an initial control model based on the multiple fuzzy rules, inputs the lighting sample data into the initial control model, and outputs a sample adjustment mode through the multiple fuzzy rules of the initial control model. Then, the initial control model can be adjusted according to the sample adjustment mode and a target illuminance to obtain a lighting control model. The scheme provided in the embodiments of the present application constructs an initial control model according to initial sample data, trains the initial control model according to the initial sample data to obtain a lighting control model, so that the lighting control model can be used to adjust the lamps in the substation in combination with the environment (such as the season and the weather) of the substation, thereby ensuring that the illuminance parameters of each room in the substation meet the target illuminance, reducing the phenomenon of glare and non-uniform illuminance caused by excessively high illuminance parameters of the working surface in each room in the substation, improving the working life of the lamps, reducing the energy consumption of the lamps, and improving the safety of the operation and maintenance of the substation.

[0104] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0105] A method for generating a control model for energy saving corresponding to the control model for energy saving described in the above embodiments, Figure 4 A structural block diagram of a device for generating a control model for energy saving provided by the embodiments of the present application is shown, only the part related to the embodiments of the present application is shown for ease of illustration.

[0106] Referring to Figure 4 The device comprises:

[0107] The acquisition module 401 is configured to acquire initial sample data of a substation, and the initial sample data comprises environmental data, luminaire distribution data, a luminaire adjustment mode, an illuminance parameter of a room where each luminaire is located, and a target illuminance corresponding to each room.

[0108] The preprocessing module 402 is configured to preprocess the initial sample data to obtain lighting sample data.

[0109] The rule construction module 403 is configured to construct a plurality of fuzzy rules according to the lighting sample data.

[0110] The model establishment module 404 is configured to establish an initial control model according to the plurality of fuzzy rules.

[0111] The input module 405 is configured to input the lighting sample data into the initial control model, and output a sample adjustment mode through the plurality of fuzzy rules of the initial control model.

[0112] The training module 406 is configured to adjust the initial control model according to the sample adjustment mode and the target illuminance to obtain a lighting control model.

[0113] Optionally, the input module 405 is specifically configured to input the lighting sample data into an input layer of the initial control model, process the lighting sample data forwarded by the input layer through a fuzzification layer and a fuzzy rule layer of the initial control model to generate a fuzzy adjustment mode, and de-fuzzify the fuzzy adjustment mode through a de-fuzzification layer of the initial control model to obtain the sample adjustment mode.

[0114] Optionally, the input module 405 is further specifically configured to map the lighting sample data to a fuzzy set through the fuzzification layer to calculate the membership degree of each data in the lighting sample data, optimize a plurality of fuzzy rules through the fuzzy rule layer, and determine the weight of each fuzzy rule, and generate the fuzzy adjustment mode in combination with each fuzzy rule through a conclusion layer of the initial control model.

[0115] Optionally, the input module 405 is further configured to determine, for each fuzzy rule, an influence factor of each piece of data on the sample adjustment mode according to each piece of data corresponding to the fuzzy rule and in combination with the membership degree corresponding to each piece of data; adjust the weight of the fuzzy rule corresponding to each piece of data according to the parameter value of each influence factor, and delete the fuzzy rule with a weight less than a threshold value.

[0116] Optionally, the device further comprises:

[0117] The normalization module 407 is configured to normalize the weight of each fuzzy rule through a normalization layer.

[0118] Optionally, the training module 406 is configured to simulate each luminaire of the substation according to the sample adjustment mode through a pre-set simulation model to obtain a simulation illuminance of each room of the substation; compare the simulation illuminance corresponding to each room with the target illuminance corresponding to each room to obtain an illuminance difference of each room; and adjust the weight corresponding to the plurality of fuzzy rules of the fuzzy rule layer in the initial control model according to the illuminance difference to obtain the lighting control model.

[0119] Optionally, the plurality of fuzzy rules comprise:

[0120] The luminaire adjustment mode is determined according to the environmental data, the illuminance parameter of each room where each luminaire is located, and the target illuminance corresponding to each room, wherein the environmental data comprises weather data and / or time data.

[0121] The luminaire adjustment mode is determined according to the luminaire distribution data, the illuminance parameter of each room where each luminaire is located, and the target illuminance corresponding to each room.

[0122] Optionally, the preprocessing module 402 is configured to clean the initial sample data, delete repeated data in the initial sample data, check the sample data, and complete the missing data in the initial sample data to obtain the lighting sample data.

[0123] In summary, the embodiment of the present application proposes a control model generation device for energy saving. The initial sample data of the substation is obtained, and the initial sample data is preprocessed to obtain lighting sample data. A plurality of fuzzy rules are constructed according to the lighting sample data, and an initial control model is established based on the plurality of fuzzy rules. The lighting sample data is input into the initial control model, and the sample adjustment mode is output through the plurality of fuzzy rules of the initial control model. The initial control model can be adjusted according to the sample adjustment mode and the target illuminance to obtain a lighting control model. The scheme provided in the embodiment of the present application constructs an initial control model according to initial sample data, and trains the initial control model according to the initial sample data to obtain a lighting control model. Therefore, the lighting control model can be used to adjust the lamps of the substation in combination with the environment (such as season and weather) of the substation, so that the phenomenon of glare and uneven illuminance caused by excessively high illuminance parameters of the work surface in each room of the substation can be reduced on the premise that the illuminance parameters of each room of the substation meet the target illuminance. The working life of the lamps can be improved, and the energy consumption of the lamps can be reduced, thereby improving the safety of the operation and maintenance of the substation.

[0124] Based on the same inventive concept, the embodiment of the present application also provides a terminal device. Figure 5 The structure schematic diagram of the electronic device provided in the embodiment of the present application is shown in Figure 5 The electronic device provided in the embodiment includes a memory 51 and a processor 52. The memory 51 is used to store a computer program 53. The processor 52 is used to execute the method described in the above method embodiment when the computer program 53 is called.

[0125] The electronic device provided in the embodiment can execute the above method embodiment, and the implementation principle and technical effects are similar, which will not be described here.

[0126] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the method described in the above method embodiment.

[0127] The embodiment of the present application also provides a computer program product. When the computer program product runs on an electronic device, the electronic device executes the method described in the above method embodiment.

[0128] The integrated units described above, if implemented in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable storage medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk and the like. In some jurisdictions, according to legislation and patent practice, the computer readable medium can not be an electrical carrier signal and a telecommunication signal.

[0129] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0130] Those of ordinary skill in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0131] In the embodiments provided in the present application, it should be understood that the disclosed devices / apparatuses and methods can be implemented in other ways. For example, the above-described device / apparatus embodiments are merely schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between devices or units, which can be electrical, mechanical or other forms.

[0132] It should be understood that the term "includes" when used in the specification and the appended claims herein, specifies the presence of stated features, integers, steps, operations, elements, and / or components but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0133] It should also be understood that the term "and / or" when used in the specification and the appended claims herein, means any one or more of the associated listed items and includes multiples of those items (for example, "a and / or b" means one or more of the items a and / or b). In addition, it is also possible in the context of the present application for some of the items to be optionally included in some embodiments and to be required in other embodiments. In addition, the terms "comprises", "comprising", "includes", "including" and the like are to be considered as specifying "consisting of" or "consisting essentially of" to the implied elements or methods of any such combination and are not to be interpreted in an open-ended fashion unless otherwise indicated by the language of the specification.

[0134] As used in the description of the application and the appended claims herein, the term "if" can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon [the described condition or event] being detected" or "in response to [the described condition or event] being detected", depending on the context.

[0135] In addition, the terms "first", "second", "third", etc. as used in the description of embodiments herein and in the appended claims are used for differentiation only and do not denote or imply relative importance.

[0136] Reference throughout this specification to "one embodiment" or "an embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearances of the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", and so on, in various places throughout this specification are not necessarily all referring to the same embodiment, unless otherwise specifically specified. The terms "comprising", "including", "having" and their variants are meant to encompass the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0137] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limiting the technical solutions of the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still make modifications to the technical solutions recorded in the foregoing embodiments, or equivalently replace some or all of the technical features thereof; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating a control model for energy saving, characterized in that: The method comprises: Acquire initial sample data of the substation, the initial sample data including: environmental data, lamp distribution data, lamp adjustment method, illumination parameters of the room where each lamp is located, and target illumination corresponding to each room; Preprocessing the initial sample data to obtain lighting sample data; constructing a plurality of fuzzy rules according to the lighting sample data; Establishing an initial control model according to a plurality of the fuzzy rules; Inputting the lighting sample data into the initial control model, and outputting a sample adjustment method according to the multiple fuzzy rules of the initial control model; The initial control model is adjusted according to the sample adjustment method and the target illumination to obtain a lighting control model.

2. The method according to claim 1, characterized in that Inputting the lighting sample data into the initial control model, and outputting a sample adjustment method according to the multiple fuzzy rules of the initial control model, including: Inputting the lighting sample data into the input layer of the initial control model, processing the lighting sample data forwarded by the input layer through the fuzzification layer and the fuzzy rule layer of the initial control model to generate a fuzzy adjustment method; The fuzzy adjustment mode is defuzzified by a defuzzification layer of the initial control model to obtain the sample adjustment mode.

3. The method according to claim 2, characterized in that The processing of the lighting sample data forwarded by the input layer through the fuzzification layer and the fuzzy rule layer of the initial control model to generate a fuzzy adjustment method includes: Mapping the lighting sample data to a fuzzy set through the fuzzification layer, and calculating the degree of membership of each item of data in the lighting sample data; Optimizing a plurality of the fuzzy rules through the fuzzy rule layer and determining a weight of each of the fuzzy rules; The fuzzy adjustment method is generated by combining the conclusion layer of the initial control model with each of the fuzzy rules.

4. The method according to claim 3, characterized in that The step of optimizing the plurality of fuzzy rules through the fuzzy rule layer and determining the weight of each fuzzy rule includes: For each of the fuzzy rules, according to each data corresponding to the fuzzy rule and in combination with the membership degree corresponding to each data, determine the influence factor of each data on the sample adjustment method; According to the parameter value of each influencing factor, the weight of the fuzzy rule corresponding to each data is adjusted, and the fuzzy rules with a weight less than a threshold are deleted.

5. The method according to claim 2, characterized in that Before generating a fuzzy adjustment mode by combining each of the fuzzy rules through the conclusion layer of the initial control model, the method further includes: The weight of each fuzzy rule is normalized through a normalization layer.

6. The method according to claim 1, characterized in that The adjusting the initial control model according to the sample adjustment method and the target illumination to obtain a lighting control model includes: By using a preset simulation model and according to the sample adjustment method, each lamp of the substation is simulated to obtain the simulated illumination of each room of the substation; For each of the rooms, comparing the simulated illuminance corresponding to the room with the target illuminance corresponding to the room to obtain an illuminance difference of the room; According to the illumination difference, weights corresponding to a plurality of fuzzy rules in the fuzzy rule layer in the initial control model are adjusted to obtain the lighting control model.

7. The method according to any one of claims 1 to 6, characterized in that: The plurality of fuzzy rules include: determining a lamp adjustment method according to environmental data, an illumination parameter of a room where each lamp is located, and a target illumination corresponding to each room, wherein the environmental data includes weather data and / or time data; The lamp adjustment method is determined according to the lamp distribution data, the illumination parameters of the room where each lamp is located, and the target illumination corresponding to each room.

8. The method according to any one of claims 1 to 6, characterized in that: The preprocessing of the initial sample data to obtain lighting sample data includes: Cleaning the initial sample data to delete duplicate data in the initial sample data; The sample data is checked, and missing data in the initial sample data is supplemented to obtain the lighting sample data.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to execute the method according to any one of claims 1 to 8 when calling the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images