Pre-disaster early warning method and system for energy storage power station

Abstract

The invention is suitable for the field of safety management of energy storage power stations, and provides a pre-disaster early warning method and system for an energy storage power station, and the method comprises the steps: collecting a historical residual current value data set, and calculating and generating a limiting judgment value; acquiring a real-time residual current value regularly; judging whether the real-time residual current value is greater than a limit judgment value or not, and generating a first modal early warning result; generating and sending an early warning signal based on the first modal early warning result; acquiring and identifying real-time environment information, and generating a second modal early warning result; acquiring and identifying a targeted real-time image, and generating a third modal early warning result; and detecting a second modal early warning result or a third modal early warning result, and generating and sending an action feedback instruction. The method and the system have the beneficial effects that the energy storage power station is monitored and analyzed by adopting multiple modals, the abnormality of the power loop is analyzed by adopting the real-time residual current value, the abnormal information is found in time, and the safety of the power loop is improved. And the early warning response speed and effectiveness are further improved.

Description

Technical Field

[0001] The present invention belongs to the field of energy storage power station safety management, and in particular relates to a pre-disaster early warning method and system for an energy storage power station. Background Art

[0002] An energy storage power station is an equipment system that stores, converts and releases cyclic electrical energy through electrochemical cells or electromagnetic energy storage media. Its core equipment includes batteries, supercapacitors, flywheels, compressed air energy storage, etc. It can store different forms of energy, such as chemical energy, mechanical energy, electrical energy, etc. It is widely used in zero-carbon smart parks, data centers, intercity rail transit, photovoltaic storage charging stations, 5G base stations, hospitals and other fields to provide stable and reliable power transmission services and achieve the goal of energy conservation and emission reduction.

[0003] Due to the large number of electrical equipment, fire accidents are very likely to occur in energy storage power stations. Fire accidents in energy storage power stations may cause damage to adjacent equipment and even cause the fire to spread to other buildings or areas, causing greater losses. Therefore, early warning of fire accidents is particularly important. The data sources of existing early warning methods are limited in comprehensiveness. In response to the above problems, it is urgent to develop a pre-disaster early warning method and system for energy storage power stations. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a pre-disaster warning method and system for an energy storage power station, aiming to solve the problems raised in the above-mentioned background technology.

[0005] The embodiment of the present invention is implemented as follows: on the one hand, a pre-disaster warning method for an energy storage power station, the method comprising: Collect historical residual current value data sets, calculate and generate limit judgment values; Get the real-time residual current value regularly; Determine whether the real-time residual current value is greater than the limit judgment value, and generate a first modal warning result; Based on the first modal warning result, generate and send a warning signal; Acquire and identify real-time environmental information and generate second-mode warning results; Acquire and identify targeted real-time images and generate third-modality warning results; Detect the second modal warning result or the third modal warning result, and generate and send an action feedback instruction.

[0006] As a further solution of the present invention, the collecting of historical residual current value data sets and the calculation and generation of limit determination values ​​specifically include: Based on the normal distribution, calculating the arithmetic mean μ of the historical residual current value data set; Based on the normal distribution, calculating the standard deviation σ of the historical residual current value data set; The limit judgment value is μ+3σ.

[0007] As a further solution of the present invention, the determining whether the real-time residual current value is greater than the limit determination value and generating the first modal warning result specifically includes: Import real-time residual current value; Determining whether the real-time residual current value is greater than a limit determination value; If the real-time residual current value is greater than the limit judgment value; Generate the first modal warning result.

[0008] As a further solution of the present invention, the acquiring and identifying real-time environmental information and generating a second modal warning result specifically includes: collecting a first real-time electrostatic voltage of a targeted device and a second real-time electrostatic voltage of a targeted device; Calculating a real-time difference between a second real-time electrostatic voltage of the targeting device and a first real-time electrostatic voltage of the targeting device; Determine whether the real-time difference is greater than the change threshold difference; If the real-time difference is greater than the change threshold difference; Generate a second modal warning result.

[0009] As a further solution of the present invention, the acquisition and identification of the targeted real-time image generates a third modality warning result: Import targeted real-time images; Gray-scale processing is performed on the targeted real-time image to generate a targeted gray-scale image; Performing discrete wavelet transform processing on the target grayscale image to generate wavelet coefficients; Determine whether the wavelet coefficient is within the characteristic threshold range; If the wavelet coefficient is within the characteristic threshold range, smoke characteristic information is generated; Based on the smoke feature information, a third modal warning result is generated.

[0010] As a further solution of the present invention, on the other hand, a pre-disaster warning system for an energy storage power station is provided, the system comprising: A collection module, used for collecting historical residual current value data sets; A calculation and generation module, used for calculating and generating a limit determination value; A first acquisition module, used for periodically acquiring a real-time residual current value; A judgment module is used to judge whether the real-time residual current value is greater than the limit judgment value; A first generating module, used to generate a first modal warning result; A second generating module, used to generate and send a warning signal based on the first modal warning result; A first acquisition and identification module is used to acquire and identify real-time environmental information; The third generating module is used to generate the second modal warning result; A second acquisition and identification module is used to acquire and identify the targeted real-time image; The fourth generating module is used to generate a third modal warning result; A detection module, used to detect the second mode warning result or the third mode warning result; A fifth generating module, used for generating an action feedback instruction; The sending module is used to send action feedback instructions.

[0011] As a further solution of the present invention, the first generating module specifically includes: A first importing unit, used for importing a real-time residual current value; The first judgment unit is used to judge whether the real-time residual current value is greater than the limit judgment value.

[0012] As a further solution of the present invention, the third generation module specifically includes: A collection unit, used for collecting a first real-time electrostatic voltage of a targeting device and a second real-time electrostatic voltage of a targeting device; A calculation unit, used to calculate a real-time difference between a second real-time electrostatic voltage of the targeting device and a first real-time electrostatic voltage of the targeting device; The second judgment unit is used to judge whether the real-time difference is greater than the change threshold difference.

[0013] As a further solution of the present invention, the fourth generation module specifically includes: A second importing unit, used for importing targeted real-time images; A grayscale processing unit, used for grayscale processing of the targeted real-time image; A first generating unit, used to generate a targeted grayscale image; A discrete wavelet transform unit, used for performing discrete wavelet transform processing on the target grayscale image; A second generating unit, used for generating wavelet coefficients; A third judgment unit, used to judge whether the wavelet coefficient is within a characteristic threshold range; A third generating unit is used to generate smoke characteristic information if the wavelet coefficient is within a characteristic threshold range; The fourth generating unit is used to generate a third modal warning result based on the smoke feature information.

[0014] The embodiment of the present invention provides a pre-disaster warning method and system for an energy storage power station. The method and system use multi-modality to monitor and analyze the energy storage power station, use real-time residual current values ​​to perform abnormal analysis on the power circuit, discover abnormal information in a timely manner, and further improve the warning response speed and effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention is a main flow chart of a pre-disaster warning method for an energy storage power station.

[0016] Figure 2 The invention discloses a flow chart for collecting historical residual current value data sets in a pre-disaster warning method for an energy storage power station, calculating and generating limit judgment values.

[0017] Figure 3 The invention discloses a flow chart for generating a first modal warning result by judging whether a real-time residual current value is greater than a limit judgment value in a pre-disaster warning method of an energy storage power station.

[0018] Figure 4 The invention discloses a flow chart for obtaining and identifying real-time environmental information and generating a second modal warning result in a pre-disaster warning method for an energy storage power station.

[0019] Figure 5 The invention discloses a flow chart for obtaining and identifying targeted real-time images in a pre-disaster warning method for an energy storage power station to generate a third-modal warning result.

[0020] Figure 6 It is a main structural diagram of a pre-disaster warning system for an energy storage power station.

[0021] Figure 7 The present invention is a structural block diagram of the first generation module in a pre-disaster warning system of an energy storage power station.

[0022] Figure 8 The present invention is a structural block diagram of the third generation module in the pre-disaster warning system of an energy storage power station.

[0023] Fig. 9 The present invention is a structural block diagram of the fourth generation module in the pre-disaster warning system of an energy storage power station. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0025] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0026] The present invention provides a pre-disaster warning method and system for an energy storage power station, which solves the technical problems in the background technology.

[0027] like Figure 1 As shown, it is a main flow chart of a pre-disaster warning method for an energy storage power station provided by an embodiment of the present invention, and the pre-disaster warning method for an energy storage power station includes: Step S100: collecting historical residual current value data sets, calculating and generating limit determination values; Step S200: regularly obtaining the real-time residual current value; Step S300: determining whether the real-time residual current value is greater than the limit determination value, and generating a first modal warning result; Step S400: generating and sending a warning signal based on the first modal warning result; Step S500: acquiring and identifying real-time environmental information, and generating a second modal warning result; Step S600: acquiring and identifying a targeted real-time image, and generating a third modality warning result; Step S700: Detect the second modal warning result or the third modal warning result, generate and send an action feedback instruction.

[0028] When this embodiment is applied, a historical residual current value data set is first collected. The historical residual current value data set contains multiple historical residual current value data, which can be used for data reference. The residual current, i.e., leakage current, refers to the current whose current vector sum of each phase (including the neutral line) in the low-voltage distribution line is not zero, also known as leakage. When the line leaks due to reasons such as reduced insulation, the leakage will cause a grounding fault through sudden changes in voltage and current, that is, a short circuit caused by the direct connection between the phase line, the conductor and the ground. Therefore, leakage is a factor that cannot be ignored in causing electrical fires, and once leakage occurs in the line, it will continue to increase. Long-term overload and leakage will cause the distribution line to heat up and the insulation to age, thereby causing fires or electric arcs. Therefore, residual current is an important basis for early prediction of electrical fires. After collecting the historical residual current value data set, based on the normal distribution characteristics, the limit judgment value is calculated and generated, and then the real-time residual current value is obtained regularly. The real-time residual current value is compared with the limit judgment value to determine whether the real-time residual current value is greater than the limit judgment value. If the real-time residual current value is greater than the limit judgment value, the first modal warning result is generated, that is, the leakage current is too large, and there is a high possibility of electrical fire. Based on the first modal warning result, a warning signal is generated and sent. When calculating and generating the limit judgment value, μ represents the mean value, and σ represents the standard deviation. Based on the normal distribution characteristics, about 99.73% of the data values ​​fall within the range of ±3 standard deviations σ of the mean μ, that is, the limit judgment value is set to μ+3σ. When the energy storage power station is operating normally, the probability that the residual current value obtained at a certain time falls within the interval (μ-3σ, μ+3σ) is 99.73%, the probability of falling outside the interval is 0.27%, and the probability of being greater than the warning value on one side is 0.135%. According to the basic idea of ​​probability theory and hypothesis testing, a low-probability event refers to an event with a probability of less than 5%. Therefore, when the energy storage power station is operating normally, the collected residual current value is greater than the warning value, which is a low-probability event. Low-probability events are almost impossible to occur in a single test, but they are bound to occur in multiple repeated tests.Therefore, the warning value is set to μ+3σ. When the real-time residual current value obtained at regular intervals is greater than the warning value, it indicates that a low-probability event occurs during the normal operation of the electrical circuit, indicating that the real-time residual current value in the energy storage power station is abnormal. Based on the first modal warning result, a warning signal is generated and sent to timely discover the possibility of an electrical fire. After the first modal warning result is generated, the real-time environmental information is obtained and identified, that is, the temperature of the target position is monitored. If the monitoring position is abnormally heated, the static voltage is sent to change, and the second modal warning result is generated. At the same time, the target real-time image is obtained and identified, and the target real-time image is processed by discrete wavelet to determine whether smoke is generated, and the third modal warning result is generated to further improve the monitoring accuracy of electrical fires. Then, the second modal warning result or the third modal warning result is detected. If the second modal warning result or the third modal warning result exists, an action feedback instruction is generated and sent, and the relevant personnel react quickly to cut off the power and extinguish the fire in time.

[0029] like Figure 2 As shown, as a preferred embodiment of the present invention, the collecting of historical residual current value data sets and the calculation and generation of limit determination values ​​specifically include: Step S101: calculating the arithmetic mean μ of the historical residual current value data set based on normal distribution; Step S102: calculating the standard deviation σ of the historical residual current value data set based on normal distribution; Step S103: the limit determination value is μ+3σ.

[0030] When this embodiment is applied, it is determined by two parameters of normal distribution: mean (μ) and standard deviation (σ). The mean (μ) determines the position of the normal distribution, that is, the symmetry center of the curve, and the standard deviation (σ) determines the degree of dispersion of the normal distribution, that is, the width and flatness of the curve. About 99.73% of the data values ​​fall within the range of ±3 standard deviations (σ) of the mean (μ), that is, the limit judgment value is set to μ+3σ.

[0031] like Figure 3 As shown, as a preferred embodiment of the present invention, the determining whether the real-time residual current value is greater than the limit determination value and generating the first modal warning result specifically includes: Step S301: importing real-time residual current value; Step S302: determining whether the real-time residual current value is greater than the limit determination value; Step S303: If the real-time residual current value is greater than the limit determination value; Step S304: Generate a first modal warning result.

[0032] When this embodiment is applied, the real-time residual current value is imported to determine whether the real-time residual current value is greater than the limit judgment value. If the real-time residual current value is greater than the limit judgment value, it means that there is an abnormality in the real-time residual current value, and a first modal warning result is generated. Subsequently, a warning signal can be sent according to the first modal warning result.

[0033] like Figure 4 As shown, as a preferred embodiment of the present invention, the acquisition and identification of real-time environmental information and the generation of a second modal warning result specifically include: Step S501: collecting a first real-time electrostatic voltage of a target device and a second real-time electrostatic voltage of a target device; Step S502: Calculating a real-time difference between a second real-time electrostatic voltage of the targeting device and a first real-time electrostatic voltage of the targeting device; Step S503: determine whether the real-time difference is greater than the change threshold difference; Step S504: if the real-time difference is greater than the change threshold difference; Step S505: Generate a second modal warning result.

[0034] It should be understood that when the device is abnormal, the device operating temperature may rise abnormally in a short period of time. When the device temperature rises rapidly, if the air humidity around the device is low, the electrostatic voltage may change first, because high temperature and dry environment are the main conditions for the generation and accumulation of static electricity. The first real-time electrostatic voltage of the targeted device and the second real-time electrostatic voltage of the targeted device are collected, and the real-time difference between the second real-time electrostatic voltage of the targeted device and the first real-time electrostatic voltage of the targeted device is calculated. If the real-time difference is greater than the change threshold difference, it indicates that the device temperature has increased abnormally, and a second modal warning result is generated.

[0035] like Figure 5 As shown, as a preferred embodiment of the present invention, the acquisition and identification of the target real-time image and the generation of the third modality warning result specifically include: Step S601: importing targeted real-time images; Step S602: grayscale the targeted real-time image to generate a targeted grayscale image; Step S603: performing discrete wavelet transform processing on the target grayscale image to generate wavelet coefficients; Step S604: determine whether the wavelet coefficient is within the characteristic threshold range; Step S605: if the wavelet coefficient is within the characteristic threshold range, generate smoke characteristic information; Step S606: generating a third modal warning result based on the smoke feature information; When this embodiment is applied, firstly, a target real-time image is imported, the target real-time image is grayed to generate a target gray image, the image quality is improved, the target gray image is discrete wavelet transform processed to generate wavelet coefficients, and it is determined whether the wavelet coefficients are within a characteristic threshold range. If the wavelet coefficients are within the characteristic threshold range, it means that smoke may be generated at the target position, and smoke feature information is generated in time. Based on the smoke feature information, a third modal warning result is generated.

[0036] like Figure 6 As shown, as another preferred embodiment of the present invention, on the other hand, a pre-disaster warning system for an energy storage power station, the system comprises: The acquisition module 100 is used to acquire a historical residual current value data set; A calculation and generation module 200 is used to calculate and generate a limit determination value; The first acquisition module 300 is used to periodically acquire the real-time residual current value; A judging module 400 is used to judge whether the real-time residual current value is greater than the limit judgment value; A first generating module 500 is used to generate a first modal warning result; The second generating module 600 is used to generate and send a warning signal based on the first modal warning result; A first acquisition and identification module 700 is used to acquire and identify real-time environmental information; The third generating module 800 is used to generate a second modal warning result; The second acquisition and identification module 900 is used to acquire and identify the targeted real-time image; The fourth generating module 1000 is used to generate a third modal warning result; A detection module 1100 is used to detect the second mode warning result or the third mode warning result; The fifth generating module 1200 is used to generate an action feedback instruction; The sending module 1300 is used to send an action feedback instruction.

[0037] When this embodiment is applied, the acquisition module 100 acquires a historical residual current value data set, the calculation and generation module 200 calculates and generates a limit judgment value, the first acquisition module 300 periodically acquires a real-time residual current value, the judgment module 400 judges whether the real-time residual current value is greater than the limit judgment value, the first generation module 500 generates a first modal warning result, the second generation module 600 generates and sends a warning signal based on the first modal warning result, the first acquisition and identification module 700 acquires and identifies real-time environmental information, the third generation module 800 generates a second modal warning result, the second acquisition and identification module 900 acquires and identifies the targeted real-time image, the fourth generation module 1000 generates a third modal warning result, the detection module 1100 detects the second modal warning result or the third modal warning result, the fifth generation module 1200 generates an action feedback instruction, and the sending module 1300 sends the action feedback instruction.

[0038] like Figure 7 As shown, as another preferred embodiment of the present invention, the first generating module 500 specifically includes: A first importing unit 501 is used to import a real-time residual current value; The first judging unit 502 is used to judge whether the real-time residual current value is greater than the limit judgment value.

[0039] When this embodiment is applied, the first import unit 501 imports the real-time residual current value, and the first judgment unit 502 judges whether the real-time residual current value is greater than the limit judgment value. If the real-time residual current value is greater than the limit judgment value, a first modal warning result is generated.

[0040] like Figure 8 As shown, as another preferred embodiment of the present invention, the third generating module 800 specifically includes: A collection unit 801 is used to collect a first real-time electrostatic voltage of a target device and a second real-time electrostatic voltage of a target device; A calculation unit 802, used to calculate a real-time difference between a second real-time electrostatic voltage of the target device and a first real-time electrostatic voltage of the target device; The second judgment unit 803 is used to judge whether the real-time difference is greater than the change threshold difference.

[0041] When this embodiment is applied, the acquisition unit 801 acquires the first real-time electrostatic voltage of the targeting device and the second real-time electrostatic voltage of the targeting device, the calculation unit 802 calculates the real-time difference between the second real-time electrostatic voltage of the targeting device and the first real-time electrostatic voltage of the targeting device, and the second judgment unit 803 judges whether the real-time difference is greater than the change threshold difference. If the real-time difference is greater than the change threshold difference, a second modal warning result is generated.

[0042] like Fig. 9As shown, as another preferred embodiment of the present invention, the fourth generating module 1000 specifically includes: The second importing unit 1001 is used to import the targeted real-time image; A grayscale processing unit 1002 is used to perform grayscale processing on the targeted real-time image; A first generating unit 1003 is used to generate a targeted grayscale image; A discrete wavelet transform unit 1004 is used to perform discrete wavelet transform processing on the target grayscale image; The second generating unit 1005 is used to generate wavelet coefficients; The third judging unit 1006 is used to judge whether the wavelet coefficient is within the characteristic threshold range; The third generating unit 1007 is used to generate smoke characteristic information if the wavelet coefficient is within the characteristic threshold range; The fourth generating unit 1008 is used to generate a third modal warning result based on the smoke feature information.

[0043] When this embodiment is applied, the second import unit 1001 is used to import the targeted real-time image, the grayscale processing unit 1002 performs grayscale processing on the targeted real-time image, the first generation unit 1003 generates a targeted grayscale image, the discrete wavelet transform unit 1004 performs discrete wavelet transform processing on the targeted grayscale image, the second generation unit 1005 generates wavelet coefficients, and the third judgment unit 1006 judges whether the wavelet coefficients are within the characteristic threshold range. If the wavelet coefficients are within the characteristic threshold range, the third generation unit 1007 generates smoke feature information, and based on the smoke feature information, the fourth generation unit 1008 generates a third modal warning result.

[0044] The above embodiment of the present invention provides a pre-disaster warning method for an energy storage power station, and provides a pre-disaster warning system for an energy storage power station. First, a historical residual current value data set is collected. The historical residual current value data set contains multiple historical residual current value data, which can be used for data reference. The residual current, i.e., leakage current, refers to the current whose current vector sum of each phase (including the neutral line) in the low-voltage distribution line is not zero, also known as leakage. When the line leaks due to reasons such as reduced insulation, the leakage will cause a grounding fault through sudden changes in voltage and current, that is, a short circuit caused by the direct connection between the phase line, the conductor and the ground. Therefore, leakage is a factor that cannot be ignored in causing electrical fires, and once leakage occurs in the line, it will continue to increase. Long-term overload and leakage will cause the distribution line to heat up and the insulation to age, thereby causing fires or arcs. Therefore, residual current is an important basis for early prediction of electrical fires. After collecting the historical residual current value data set, based on the normal distribution characteristics, the limit judgment value is calculated and generated, and then the real-time residual current value is obtained regularly. The real-time residual current value is compared with the limit judgment value to determine whether the real-time residual current value is greater than the limit judgment value. If the real-time residual current value is greater than the limit judgment value, the first modal warning result is generated, that is, the leakage current is too large, and there is a high possibility of electrical fire. Based on the first modal warning result, a warning signal is generated and sent. When calculating and generating the limit judgment value, μ represents the mean value, and σ represents the standard deviation. Based on the normal distribution characteristics, about 99.73% of the data values ​​fall within the range of ±3 standard deviations σ of the mean μ, that is, the limit judgment value is set to μ+3σ. When the energy storage power station is operating normally, the probability that the residual current value obtained at a certain time falls within the interval (μ-3σ, μ+3σ) is 99.73%, the probability of falling outside the interval is 0.27%, and the probability of being greater than the warning value on one side is 0.135%. According to the basic idea of ​​probability theory and hypothesis testing, a low-probability event refers to an event with a probability of less than 5%. Therefore, when the energy storage power station is operating normally, the collected residual current value is greater than the warning value, which is a low-probability event. Low-probability events are almost impossible to occur in a single test, but they are bound to occur in multiple repeated tests.Therefore, the warning value is set to μ+3σ. When the real-time residual current value obtained at regular intervals is greater than the warning value, it indicates that a low-probability event occurs during the normal operation of the electrical circuit, indicating that the real-time residual current value in the energy storage power station is abnormal. Based on the first modal warning result, a warning signal is generated and sent to timely discover the possibility of electrical fires. After the first modal warning result is generated, the real-time environmental information is obtained and identified, that is, the temperature of the target position is monitored. If the monitoring position is abnormally heated, resulting in a change in the electrostatic voltage, the second modal warning result is generated. At the same time, the target real-time image is obtained and identified, and the target is detected. Discrete wavelet processing is performed on the real-time image to determine whether smoke is generated, and the third modal warning result is generated to further improve the monitoring accuracy of electrical fires. Then the second modal warning result or the third modal warning result is detected. If the second modal warning result or the third modal warning result exists, an action feedback instruction is generated and sent, and relevant personnel quickly respond to power off and extinguish the fire in time. The method and system use multi-modality to monitor and analyze the energy storage power station, use real-time residual current value to perform abnormal analysis on the power circuit, and detect abnormal information in time, further improving the warning response speed and effectiveness.

[0045] In order to load the above-mentioned method and system and enable it to run smoothly, the system, in addition to the various modules mentioned above, may also include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, processors and memories, etc.

[0046] The processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the system, and various interfaces and lines are used to connect various parts.

[0047] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0048] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A pre-disaster warning method for an energy storage power station, characterized in that: The method comprises: Collect historical residual current value data sets, calculate and generate limit judgment values; Get the real-time residual current value regularly; Determine whether the real-time residual current value is greater than the limit judgment value, and generate a first modal warning result; Based on the first modal warning result, generate and send a warning signal; Acquire and identify real-time environmental information and generate second-mode warning results; Acquire and identify targeted real-time images and generate third-modality warning results; Detect the second modal warning result or the third modal warning result, and generate and send an action feedback instruction.

2. The pre-disaster warning method for energy storage power station according to claim 1 is characterized in that: The collecting of historical residual current value data sets and the calculation and generation of limit determination values ​​specifically include: Based on the normal distribution, calculating the arithmetic mean μ of the historical residual current value data set; Based on the normal distribution, calculating the standard deviation σ of the historical residual current value data set; The limit judgment value is μ+3σ.

3. The pre-disaster warning method for energy storage power station according to claim 1 is characterized in that: The determining whether the real-time residual current value is greater than the limit determination value and generating the first modal warning result specifically includes: Import real-time residual current value; Determining whether the real-time residual current value is greater than a limit determination value; If the real-time residual current value is greater than the limit judgment value; Generate the first modal warning result.

4. The pre-disaster warning method for energy storage power station according to claim 1 is characterized in that: The acquiring and identifying real-time environmental information and generating a second modal warning result specifically includes: collecting a first real-time electrostatic voltage of a targeted device and a second real-time electrostatic voltage of a targeted device; Calculating a real-time difference between a second real-time electrostatic voltage of the targeting device and a first real-time electrostatic voltage of the targeting device; Determine whether the real-time difference is greater than the change threshold difference; If the real-time difference is greater than the change threshold difference; Generate a second modal warning result.

5. The pre-disaster warning method for energy storage power station according to claim 1 is characterized in that: The acquisition and identification of the targeted real-time image generates a third modality warning result: Import targeted real-time images; Gray-scale processing is performed on the targeted real-time image to generate a targeted gray-scale image; Performing discrete wavelet transform processing on the target grayscale image to generate wavelet coefficients; Determine whether the wavelet coefficient is within the characteristic threshold range; If the wavelet coefficient is within the characteristic threshold range, smoke characteristic information is generated; Based on the smoke feature information, a third modal warning result is generated.

6. A pre-disaster warning system for an energy storage power station, characterized in that: The system comprises: A collection module, used for collecting historical residual current value data sets; A calculation and generation module, used for calculating and generating a limit determination value; A first acquisition module, used for periodically acquiring a real-time residual current value; A judgment module is used to judge whether the real-time residual current value is greater than the limit judgment value; A first generating module, used to generate a first modal warning result; A second generating module, used to generate and send a warning signal based on the first modal warning result; A first acquisition and identification module is used to acquire and identify real-time environmental information; The third generating module is used to generate the second modal warning result; A second acquisition and identification module is used to acquire and identify the targeted real-time image; The fourth generating module is used to generate a third modal warning result; A detection module, used to detect the second mode warning result or the third mode warning result; A fifth generating module, used for generating an action feedback instruction; The sending module is used to send action feedback instructions.

7. The pre-disaster warning system for energy storage power station according to claim 6 is characterized in that: The first generation module specifically includes: A first importing unit, used for importing a real-time residual current value; The first judgment unit is used to judge whether the real-time residual current value is greater than the limit judgment value.

8. The pre-disaster warning system for energy storage power station according to claim 6 is characterized in that: The third generation module specifically includes: A collection unit, used for collecting a first real-time electrostatic voltage of a targeting device and a second real-time electrostatic voltage of a targeting device; A calculation unit, used to calculate a real-time difference between a second real-time electrostatic voltage of the targeting device and a first real-time electrostatic voltage of the targeting device; The second judgment unit is used to judge whether the real-time difference is greater than the change threshold difference.

9. The energy storage power station pre-disaster warning system according to claim 6, characterized in that: The fourth generation module specifically includes: A second importing unit, used for importing targeted real-time images; A grayscale processing unit, used for grayscale processing of the targeted real-time image; A first generating unit, used to generate a targeted grayscale image; A discrete wavelet transform unit, used for performing discrete wavelet transform processing on the target grayscale image; A second generating unit, used for generating wavelet coefficients; A third judgment unit, used to judge whether the wavelet coefficient is within a characteristic threshold range; A third generating unit is used to generate smoke characteristic information if the wavelet coefficient is within a characteristic threshold range; The fourth generating unit is used to generate a third modal warning result based on the smoke feature information.

Images