An intelligent flood control and early warning platform for substations

Abstract

The invention relates to an intelligent flood control and early warning platform for a substation, which comprises: an electronic water gauge, which is arranged at a location to be tested where water level monitoring is required; a piezoelectric wireless sensor, which is used to measure the weight of a single raindrop according to the received impact force, and then obtain the current rainfall; a data transmission device, which is used to receive the current water level data sent by the electronic water gauge, the current rainfall sent by the piezoelectric wireless sensor, and the current meteorological information, and send the current water level data, the current rainfall and the current meteorological information to a cloud server; the cloud server is used to calculate a water level prediction curve using a genetic algorithm and a BP neural network, and control a mobile terminal to alarm when it is determined that any value on the water level prediction curve reaches a preset water level threshold, so as to remind relevant personnel to take flood prevention measures through the flood prevention platform.

Description

Technical Field

[0001] The present invention relates to the technical field of flood prevention for substations, and in particular to an intelligent flood prevention control and early warning platform for substations. Background Art

[0002] For a long time, flood prevention has been an important aspect of the safe operation of substations. Especially in recent years, with the frequent occurrence of extreme rainstorms, the safe operation of substation equipment and its ancillary facilities has brought severe challenges. Flood backflow incidents in substations occur from time to time, and flood water will cause major losses such as forced power outages and equipment damage. With the continuous promotion of unmanned substations, improving the rapid and effective emergency response capabilities of flood prevention systems has become an urgent issue currently faced. With the continuous construction and transformation of smart substations, more and more unmanned substations have been put into operation. For important electrical equipment such as transformers and switches in unmanned substations, stable online status monitoring measures have been formed, but less investment has been made in flood prevention. Although some drainage facilities can be remotely controlled, emergency flood prevention work in response to extreme rainstorms is still slightly weak. Establishing a set of intelligent flood prevention facility platforms to achieve effective linkage of multiple systems such as waterproofing and drainage and enhance the flood prevention capabilities of substations is the focus of subsequent work.

[0003] At present, there are no perfect flood prevention facilities in substations. They mainly rely on manual sandbags for blocking and self-starting water pumps for drainage. Not only does it consume a lot of manpower and material resources, but it is also inefficient and slow to achieve the goal of timely and effective flood control and loss reduction. In addition, in the unmanned mode of substations, remote operation and maintenance personnel cannot understand the flood situation of substations in real time, and lack effective monitoring methods, which brings severe challenges to the safe operation of equipment. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an intelligent flood prevention control and early warning platform for a substation.

[0005] To solve the above problems, the technical solution adopted by the present invention is:

[0006] An intelligent flood control and early warning platform for substations, comprising:

[0007] Electronic water gauge, which is set at the place where water level monitoring is required;

[0008] Piezoelectric wireless sensor, which is used to measure the weight of a single raindrop based on the impact force received, and then obtain the current rainfall;

[0009] A data transmission device, which is used to receive the current water level data sent by the electronic water gauge, the current rainfall and the current meteorological information sent by the piezoelectric wireless sensor, and send the current water level data, the current rainfall and the current meteorological information to a cloud server;

[0010] The cloud server is used to calculate the water level prediction curve using genetic algorithm and BP neural network, and control the mobile terminal to alarm when it is determined that any value on the water level prediction curve reaches a preset water level threshold, so as to remind relevant personnel to take flood prevention measures through the flood prevention platform.

[0011] As an embodiment of the present invention, the flood control platform comprises: an underground trough, and a main water retaining plate arranged in the ground trough and capable of being raised and lowered, wherein the main water retaining plate is connected to the controller via a transmission mechanism and a power mechanism;

[0012] The controller is used to receive an opening instruction or a closing instruction sent by the main server, and control the power mechanism to open or close, so as to control the lifting of the main water baffle through the transmission mechanism.

[0013] As an implementation mode of the present invention, the control terminal is connected to the cloud server and the controller;

[0014] The control terminal is used for the staff to view the water level prediction curve and receive the alarm instruction sent by the cloud server.

[0015] As an embodiment of the present invention, the method for the cloud server to obtain a water level prediction curve includes:

[0016] Step S1, constructing a BP initial neural network model, and optimizing the BP initial neural network model using a genetic algorithm to obtain an optimized BP neural network model;

[0017] Step S2, using a verification set to verify the accuracy of the optimized BP neural network model;

[0018] Step S3, inputting the water level data, the current rainfall and the current meteorological information into the verified BP neural network model to obtain the predicted water level value at the next moment;

[0019] Step S4: obtaining the water level prediction curve based on the predicted water level values ​​at multiple moments.

[0020] As an implementation mode of the present invention, step S1 includes:

[0021] Step S101, initializing a population, which includes multiple samples;

[0022] Step S102, constructing a fitness function, iteratively calculating the fitness of each sample individual, obtaining the fitness function value of each sample individual, analyzing and judging the fitness function value, detecting whether the fitness function value has reached the expected value, and obtaining whether the number of genetic iteration operations performed is less than the preset maximum number of iterations;

[0023] Step S103: If yes, the individuals that can meet the preset requirements are used as the final weights and thresholds of the BP neural network.

[0024] As an implementation mode of the present invention, step S1 further includes:

[0025] Step S104, when it is determined that the fitness function value has not reached the expected value, and / or, when the number of genetic iteration operations performed is less than the preset maximum number of iterations, the probability of crossover and mutation is calculated based on the fitness function value generated by each individual and the operating rules in the genetic algorithm, and new individuals are derived based on the calculated probabilities.

[0026] As an implementation mode of the present invention, in step S1, the current water level data, the current rainfall and the current meteorological information are used as input data, the predicted water level data is used as output data, and Matlab is used to construct an initial BP neural network model. .

[0027] The beneficial effects of adopting the above technical solution are:

[0028] The embodiment of the present invention provides an intelligent flood control and early warning platform for substations, which can play a very positive role in flood control and drainage work in unmanned substations. Operation and maintenance personnel can remotely understand the on-site flood situation and the activation of flood control facilities in real time, and can realize remote instant remote control startup, which provides reliable technical guarantee for reducing the flood risk of substations and improving flood emergency response capabilities. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is clearly and completely described below in conjunction with specific embodiments.

[0030] The embodiment of the present invention provides a substation intelligent flood prevention control and early warning platform, which includes:

[0031] Electronic water gauge, which is set at the place where water level monitoring is required;

[0032] Piezoelectric wireless sensor, which is used to measure the weight of a single raindrop based on the impact force received, and then obtain the current rainfall;

[0033] A data transmission device, which is used to receive the current water level data sent by the electronic water gauge, the current rainfall and the current meteorological information sent by the piezoelectric wireless sensor, and send the current water level data, the current rainfall and the current meteorological information to a cloud server;

[0034] The cloud server is used to calculate the water level prediction curve using genetic algorithm and BP neural network, and control the mobile terminal to alarm when it is determined that any value on the water level prediction curve reaches a preset water level threshold, so as to remind relevant personnel to take flood prevention measures through the flood prevention platform. The control terminal is connected to the cloud server and the controller;

[0035] The control terminal is used for the staff to view the water level prediction curve and receive the alarm instruction sent by the cloud server.

[0036] Regarding the structure of the flood control platform, in a possible implementation, the flood control platform includes: an underground trough, and a main water retaining plate disposed in the ground trough and capable of being raised and lowered, wherein the main water retaining plate is connected to a controller via a transmission mechanism and a power mechanism;

[0037] The controller is used to receive an opening instruction or a closing instruction sent by the main server, and control the power mechanism to open or close, so as to control the lifting of the main water baffle through the transmission mechanism. The power mechanism can be a power source, and the transmission mechanism can be a gear rack structure, which is not specifically limited in the embodiment of the present invention.

[0038] The embodiment of the present invention provides an intelligent flood control and early warning platform for substations, which can play a very positive role in flood control and drainage work in unmanned substations. Operation and maintenance personnel can remotely understand the on-site flood situation and the activation of flood control facilities in real time, and can realize remote instant remote control startup, which provides reliable technical guarantee for reducing the flood risk of substations and improving flood emergency response capabilities.

[0039] The following describes a method for the cloud server to obtain a water level prediction curve. In a possible implementation, the method includes:

[0040] Step S1, constructing a BP initial neural network model, and optimizing the BP initial neural network model using a genetic algorithm to obtain an optimized BP neural network model;

[0041] Among them, the current water level data, current rainfall and current meteorological information can be used as input data, the predicted water level data can be used as output data, and Matlab is used to build an initial BP neural network model.

[0042] This step includes:

[0043] Step S101, initializing a population, which includes multiple samples;

[0044] Step S102, constructing a fitness function, iteratively calculating the fitness of each sample individual, obtaining the fitness function value of each sample individual, analyzing and judging the fitness function value, detecting whether the fitness function value has reached the expected value, and obtaining whether the number of genetic iteration operations performed is less than the preset maximum number of iterations;

[0045] Step S103: If yes, the individuals that can meet the preset requirements are used as the final weights and thresholds of the BP neural network.

[0046] Of course, it also includes:

[0047] Step S104, when it is determined that the fitness function value has not reached the expected value, and / or, when the number of genetic iteration operations performed is less than the preset maximum number of iterations, the probability of crossover and mutation is calculated based on the fitness function value generated by each individual and the operating rules in the genetic algorithm, and new individuals are derived based on the calculated probabilities.

[0048] Step S2, using a verification set to verify the accuracy of the optimized BP neural network model;

[0049] Step S3, inputting the water level data, the current rainfall and the current meteorological information into the verified BP neural network model to obtain the predicted water level value at the next moment;

[0050] Step S4: obtaining the water level prediction curve based on the predicted water level values ​​at multiple moments.

[0051] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent flood control and early warning platform for substations, characterized in that: It includes: Electronic water gauge, which is set at the place where water level monitoring is required; Piezoelectric wireless sensor, which is used to measure the weight of a single raindrop based on the impact force received, and then obtain the current rainfall; A data transmission device, which is used to receive the current water level data sent by the electronic water gauge, the current rainfall and the current meteorological information sent by the piezoelectric wireless sensor, and send the current water level data, the current rainfall and the current meteorological information to a cloud server; The cloud server is used to calculate the water level prediction curve using genetic algorithm and BP neural network, and control the mobile terminal to alarm when it is determined that any value on the water level prediction curve reaches a preset water level threshold, so as to remind relevant personnel to take flood prevention measures through the flood prevention platform.

2. The intelligent flood control and early warning platform for substations according to claim 1 is characterized in that: The flood control platform comprises: an underground trough, and a main water retaining plate arranged in the ground trough and capable of being raised and lowered, wherein the main water retaining plate is connected to a controller via a transmission mechanism and a power mechanism; The controller is used to receive an opening instruction or a closing instruction sent by the main server, and control the power mechanism to open or close, so as to control the lifting of the main water baffle through the transmission mechanism.

3. The intelligent flood control and early warning platform for substations according to claim 1 is characterized in that: The control terminal is connected to the cloud server and the controller; The control terminal is used for the staff to view the water level prediction curve and receive the alarm instruction sent by the cloud server.

4. The intelligent flood control and early warning platform for substations according to claim 1 is characterized in that: The method for the cloud server to obtain a water level prediction curve includes: Step S1, constructing a BP initial neural network model, and optimizing the BP initial neural network model using a genetic algorithm to obtain an optimized BP neural network model; Step S2, using a verification set to verify the accuracy of the optimized BP neural network model; Step S3, inputting the water level data, the current rainfall and the current meteorological information into the verified BP neural network model to obtain the predicted water level value at the next moment; Step S4: obtaining the water level prediction curve based on the predicted water level values ​​at multiple moments.

5. The intelligent flood control and early warning platform for substations according to claim 1 is characterized in that: Step S1 includes: Step S101, initializing a population, which includes multiple samples; Step S102, constructing a fitness function, iteratively calculating the fitness of each sample individual, obtaining the fitness function value of each sample individual, analyzing and judging the fitness function value, detecting whether the fitness function value has reached the expected value, and obtaining whether the number of genetic iteration operations performed is less than the preset maximum number of iterations; Step S103: If yes, the individuals that can meet the preset requirements are used as the final weights and thresholds of the BP neural network.

6. The intelligent flood control and early warning platform for substations according to claim 1 is characterized in that: Step S1 also includes: Step S104, when it is determined that the fitness function value has not reached the expected value, and / or, when the number of genetic iteration operations performed is less than the preset maximum number of iterations, the probability of crossover and mutation is calculated based on the fitness function value generated by each individual and the operating rules in the genetic algorithm, and new individuals are derived based on the calculated probabilities.

7. The intelligent flood control and early warning platform for substations according to claim 1 is characterized in that: In step S1, the current water level data, the current rainfall and the current meteorological information are used as input data, and the predicted water level data is used as output data, and Matlab is used to build an initial BP neural network model.