CN111486892A - Intelligent fire early warning system for lead-acid storage battery - Google Patents
Intelligent fire early warning system for lead-acid storage battery Download PDFInfo
- Publication number
- CN111486892A CN111486892A CN202010237701.2A CN202010237701A CN111486892A CN 111486892 A CN111486892 A CN 111486892A CN 202010237701 A CN202010237701 A CN 202010237701A CN 111486892 A CN111486892 A CN 111486892A
- Authority
- CN
- China
- Prior art keywords
- lead
- storage battery
- unit
- early warning
- smoke
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Abstract
The invention relates to an intelligent fire early warning system for a lead-acid storage battery, belonging to the technical field of early warning of direct-current power supplies of transformer substations; the terminal Internet of things sensing module comprises a constant current discharge voltage sensor, a floating charge current sensor, a temperature sensor, a combustible gas sensor, a smoke detector, a humidity sensor and a camera device, wherein the temperature sensor, the combustible gas sensor, the smoke detector and the humidity sensor are positioned in a lead-acid storage battery chamber, and the camera device is used for acquiring a lead-acid storage battery video; the lead-acid storage battery state identification module is connected with the terminal Internet of things sensing module and comprises an internal resistance monitoring unit, a current monitoring unit, a temperature monitoring unit, a combustible gas monitoring unit, a humidity monitoring unit and a smoke and fire video identification module; the intelligent early warning of the storage battery fire is realized.
Description
Technical Field
The invention relates to an intelligent fire early warning system for a lead-acid storage battery, and belongs to the technical field of early warning of direct-current power supplies of substations.
Background
The direct-current power supply system of the transformer substation is a source of working power supplies of relay protection, safety automatic devices, automation equipment and the like of a secondary system of the transformer substation, and is a basic guarantee for safe and reliable operation of the transformer substation. The storage battery is the most core part of the direct current power supply system, and is the only back support for the direct current power supply system to continuously provide working power supply for the load when the alternating current input is abnormal. Therefore, once the storage battery is damaged, the relay protection device loses the working power supply and the capability of rapidly cutting off the accident load, and can directly cause major equipment damage or complete stop of a transformer substation, thereby causing major loss to power grid enterprises and national economy.
The lead-acid storage battery has the advantages of low cost, high cost performance, good reliability, easily obtained raw materials and the like. Because of the full seal, no water is needed for maintenance, the valve-regulated sealed lead-acid storage battery is also called a maintenance-free storage battery. However, due to the fact that the maintenance-free property enables users to relax the routine maintenance and management of the valve-regulated lead-acid storage battery, the valve-regulated lead-acid storage battery often has the phenomena of premature failure and thermal runaway in practical use. When the battery is charged, a cumulative enhancement of the internal temperature of the battery occurs. During the temperature rise, heat is accumulated to a certain degree, the terminal voltage of the battery is suddenly reduced, the current is suddenly increased, and the storage battery is damaged, and the phenomenon is called thermal runaway. When the thermal runaway of the lead-acid storage battery is serious, the storage battery can be burnt, so that a fire disaster happens to a transformer substation or a total-station direct-current system loses voltage, and the safe operation of a power system is damaged. Based on the facts, the correlation characteristics of common faults and open fire of the lead-acid storage battery are analyzed, the key factors caused by the fire of the storage battery are searched, and the development of an intelligent fire early warning system of the lead-acid storage battery is of great importance.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the defects of the prior art are overcome, the intelligent fire early warning system for the lead-acid storage battery is provided, and the early intelligent early warning of the storage battery fire is realized.
The invention relates to an intelligent fire early warning system of a lead-acid storage battery, which comprises a terminal things-connected sensing module, a lead-acid storage battery state identification module and an alarm module which are sequentially connected, wherein the lead-acid storage battery is connected with a power supply circuit in parallel and is connected with a constant-current discharge load through a switching circuit; the lead-acid storage battery state identification module is connected with the terminal Internet of things sensing module and comprises an internal resistance monitoring unit, a current monitoring unit, a temperature monitoring unit, a combustible gas monitoring unit, a humidity monitoring unit and a smoke and fire video identification module.
The internal resistance monitoring unit is used for monitoring the internal resistance of the lead-acid storage battery, the current monitoring unit is used for monitoring the float current of the lead-acid storage battery, the temperature monitoring unit is used for monitoring the surface temperature of the lead-acid storage battery, the combustible gas monitoring unit is used for monitoring the separation of combustible gas of the lead-acid storage battery, the humidity monitoring unit is used for monitoring the humidity condition of the lead-acid storage battery, and the picture smoke and fire video identification module is used for monitoring the smoke and fire signals of. Real-time state acquisition and monitoring are carried out on the judgment factors which are sensitive in the early stage of the failure or fire of the lead-acid storage battery, and the fire hazard of the lead-acid storage battery is found in advance. The lead-acid storage battery state identification module comprehensively considers the comprehensive judgment logic relation between the measurement results of the monitoring sensors in different states and the smoke and fire image identification results, and alarms through the alarm module, so that the early intelligent early warning of the fire of the storage battery is realized.
Preferably, the firework video identification module is connected with the camera device and comprises a preprocessing unit, a segmentation unit, an extraction unit, an identification unit, a marking unit and an output unit which are connected in sequence; the method comprises the following steps that a preprocessing unit obtains field video stream data of a storage battery of a direct-current power supply system of the transformer substation, decodes the field video stream data to obtain a single-frame picture, and preprocesses the single-frame picture to improve data quality; the segmentation unit divides the preprocessed single-frame picture into image blocks with the same size; the extraction unit carries out background image modeling based on a moving target detection method of a Gaussian mixture model to extract small image blocks containing moving object regions as recognition candidate region images; the identification unit inputs the candidate area images into the trained flame color, flame shape, flame dynamic, smoke static and smoke dynamic characteristic models for identification and classification; the marking unit marks the position of the hidden danger area confirmed by model verification in the original video frame as a firework area detected and identified; the output unit outputs the result.
Preferably, the modeling of the flame color characteristics in the identification unit uses the following rules:
rule1：R≥G≥B
rule2：R≥RT
rule3：S≥((255-R)*ST/RT)
wherein R isTIs a red component threshold, STIs a saturation threshold, the flame pixel depends mainly on the chroma and saturation of the red component (R); if the above conditions are met, the position is judged to be a flame pixel.
Preferably, the flame appearance characteristic modeling in the identification unit adopts a nested contour model, the flame dynamic characteristic modeling is based on the frequency rule of switching between the flame state and the flameless state of the pixel point, the smoke static characteristic modeling is based on an HSV color model, and the smoke dynamic characteristic modeling is based on the shape and upward movement trend of the smoke motion block.
Preferably, the internal resistance monitoring unit calculates the internal resistance according to the formula R ═ (U2-U1)/I.
Preferably, a 2000V photoelectric isolation circuit is arranged between the switching circuit and the constant current discharge load.
Preferably, the front end of the acquisition line of the constant current discharge voltage sensor is provided with a self-recovery fuse.
Compared with the prior art, the invention has the following beneficial effects:
according to the intelligent fire early warning system for the lead-acid storage battery, disclosed by the invention, the early intelligent early warning of the storage battery fire is realized by the deployment perception analysis of the terminal Internet of things sensing module and the lead-acid storage battery state identification module on the sensitive factors in the early stage of the storage battery fire.
Drawings
FIG. 1 is a block diagram of the intelligent fire early warning system for lead-acid batteries according to the present invention;
FIG. 2 is a block diagram of the pyrotechnic video identification module of the present invention;
fig. 3 is a schematic diagram of the internal resistance calculation of the internal resistance monitoring unit according to the present invention.
Wherein: 1. a terminal Internet of things sensing module; 101. a voltage sensor; 102. a float current sensor; 103. a temperature sensor; 104. a combustible gas sensor; 105. a smoke detector; 106. a humidity sensor; 107. an image pickup apparatus; 2. a lead-acid storage battery state identification module; 201. an internal resistance monitoring unit; 202. a current monitoring unit; 203. a temperature monitoring unit; 204. a combustible gas monitoring unit; 205. a humidity monitoring unit; 3. a smoke and fire video identification module; 301. a pre-processing unit; 302. a dividing unit; 303. an extraction unit; 304. an identification unit; 305. a marking unit; 306. an output unit; 4. an alarm module; 5. a power source; 6. a switching circuit; 7. and discharging the load at a constant current.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1-2, the intelligent fire early warning system for the lead-acid storage battery comprises a terminal internet of things sensing module 1, a lead-acid storage battery state identification module 2 and an alarm module 4 which are connected in sequence, wherein the lead-acid storage battery is connected with a power supply 5 in parallel and is connected with a constant current discharge load 7 through a switching circuit 6, the terminal internet of things sensing module 1 comprises a constant current discharge voltage sensor 101, a floating charge current sensor 102, a temperature sensor 103, a combustible gas sensor 104, a smoke detector 105, a humidity sensor 106 and a camera device 107, the temperature sensor 103, the combustible gas sensor 104, the smoke detector 105 and the humidity sensor 106 are positioned in a lead-acid storage battery chamber, and the camera device 107 is used for acquiring a lead-acid storage; the lead-acid storage battery state identification module 2 is connected with the terminal Internet of things sensing module 1 and comprises an internal resistance monitoring unit 201, a current monitoring unit 202, a temperature monitoring unit 203, a combustible gas monitoring unit 204, a humidity monitoring unit 205 and a smoke and fire video identification module 3.
Internal resistance monitoring unit 201 is used for monitoring lead acid battery internal resistance, current monitoring unit 202 is used for monitoring lead acid battery float current, temperature monitoring unit 203 is used for monitoring lead acid battery surface temperature, combustible gas monitoring unit 204 is used for monitoring lead acid battery combustible gas and educes, humidity monitoring unit 205 is used for monitoring lead acid battery humidity condition, picture firework video identification module 3 is used for monitoring lead acid battery firework signal according to the video. Real-time state acquisition and monitoring are carried out on the judgment factors which are sensitive in the early stage of the failure or fire of the lead-acid storage battery, and the fire hazard of the lead-acid storage battery is found in advance. The lead-acid storage battery state identification module 2 comprehensively considers the comprehensive judgment logic relation between the measurement results of the monitoring sensors in different states and the smoke and fire image identification results, and alarms through the alarm module 4, so that the very early intelligent early fire warning of the storage battery is realized.
As shown in fig. 3, the lead-acid battery pack instantly discharges to the constant-current discharge load 7, the voltage sensor 101 measures the voltage before and after the power failure, and the internal resistance calculation unit in the monitoring background calculates the internal resistance according to the formula of (U2-U1)/I. High precision, good stability and good consistency. And measuring the instantaneous power-off voltage difference after the discharge voltage is stabilized, and skipping the unstable period of initial discharge. And a special high-speed characteristic point capturing technology is adopted, so that the test result is stable and accurate, and the test process is convenient and fast. For a single group of storage batteries, a charger does not need to be disconnected, the storage battery does not need to exit the system, and the safe operation of a power supply system is not influenced during testing. The multi-loop circulating discharge avoids the influence of the whole discharge measurement internal resistance on the normal operation of the direct current system.
The switching circuit 6 comprises a plurality of relays, which are connected to the lead-acid battery pack. The switching circuit 6 is connected with the lead-acid storage battery pack and the constant-current discharge load 7, the constant-current discharge load 7 is connected into each lead-acid storage battery pack through the switching circuit 6, and the batteries in the group are subjected to discharge testing for internal resistance. Specifically, for example, 2V104 lead-acid storage batteries are divided into 11 groups by taking 10 batteries as a group, the constant-current discharge load 7 is connected to each storage battery group through a relay, and the batteries in the group are subjected to discharge test for internal resistance. A2000V photoelectric isolation circuit is arranged between the switching circuit 6 and the constant current discharge load 7, so that the insulation performance of the system is ensured. The front end of the acquisition line of the constant-current discharge voltage sensor 101 is provided with a self-recovery fuse, so that the short-circuit protection function is realized, the automatic recovery can be realized when the fault is eliminated, and the safety and convenience are realized.
The firework video recognition module 3 is connected with the image pickup device 107 and comprises a preprocessing unit 301, a dividing unit 302, an extracting unit 303, a recognition unit 304, a marking unit 305 and an output unit 306 which are connected in sequence; the preprocessing unit 301 obtains the field video stream data of the storage battery of the direct-current power supply system of the transformer substation, decodes the field video stream data to obtain a single-frame picture, and preprocesses the single-frame picture to improve the data quality; the dividing unit 302 divides the preprocessed single-frame picture into image blocks with the same size; the extraction unit 303 performs background image modeling based on a moving target detection method of a gaussian mixture model to extract a small image block including a moving object region as an identification candidate region image; the identification unit 304 inputs the candidate region images into the trained flame color, flame shape, flame dynamic, smoke static and smoke dynamic characteristic models for identification and classification; the marking unit 305 marks the position of the hidden danger area confirmed by model verification in the original video frame as a smoke and fire area detected and identified; the output unit 306 outputs the result.
Here, the firework video identification module 3 identifies the following steps:
step S1, the preprocessing unit 301 obtains the on-site video stream data of the storage battery of the direct current power supply system of the transformer substation, decodes the on-site video stream data to obtain a single-frame picture, and preprocesses the single-frame picture to improve the data quality;
step S2, the dividing unit 302 divides the preprocessed single-frame picture into image blocks with the same size;
in step S3, the extraction unit 303 performs background image modeling to extract small image blocks including a moving object region as an identification candidate region image;
step S4, the recognition unit 304 inputs the candidate region image into the trained flame color, flame shape, flame dynamics, smoke static state, smoke dynamic characteristic model for recognition and classification;
step S5, the marking unit 305 marks the position of the hidden danger area confirmed by model verification in the original video frame as a smoke and fire area detected and identified;
in step S6, the output unit 306 outputs the result.
In step S1, the preprocessing unit 301 obtains the on-site video stream data of the storage battery of the dc power supply system of the substation from the camera through Rtsp streaming media protocol.
In step S3, the method for detecting a moving object by the extraction unit 303 based on the gaussian mixture model includes the following steps:
in step S301, k gaussian distributions are selected, each gaussian distribution is called a Component (Component), and the components are linearly added to form a Probability Density Function (PDF) of the GMM, as shown in formula (1):
wherein K represents the number of Gaussian distributions, N () represents the multivariate Gaussian distribution, pikIndicating a mixed weight value, pikSatisfies the sum of 0 ≦ π k ≦ 1
Step S302, calculating the probability distribution of the GMM by using the collected pixel values of the previous N frames of images, and determining the parameters thereof by maximum likelihood estimation according to the probability density function, where the likelihood function formula (2) of the GMM is shown as follows:
step S303, calculating parameters thereof by using EM (Expectation Maximization Algorithm) Algorithm:
wherein, in formula (3), the probability that the ith data is produced by the kth component is represented;
and step S304, starting detection from the (N + 1) th frame, judging whether each pixel point in the image is matched with k established Gaussian models, if the matching is unsuccessful, judging the image as a foreground point, and if not, judging the image as a background point.
Wherein, the flame color feature modeling in the identification unit (304) of the step S4 adopts the following rule:
rule1：R≥G≥B
rule2：R≥RT
rule3：S≥((255-R)*ST/RT)
wherein R isTIs a red component threshold, STIs a saturation threshold, the flame pixel depends mainly on the chroma and saturation of the red component (R); if the above conditions are met, the position is judged to be a flame pixel and is displayed as white, otherwise, the position is displayed as black. The selection of the threshold value in the criterion is crucial to flame detection, in order to obtain the best effect of flame identification, two sliding bars are arranged, the sizes of the threshold values RT and ST are changed, and the most appropriate value is selected.
The flame appearance characteristic modeling adopts nested profile model, the flame dynamic characteristic modeling is based on the frequency rule that the pixel has two kinds of states of flame and no flame to switch, the smog static characteristic modeling is based on HSV color model, wherein: h represents hue, color of the reaction image, S represents saturation, vividness of the color of the reaction image, and V represents brightness and brightness of the reaction image; the smoke dynamic feature modeling is based on the shape and upward movement trend of the smoke motion block, and comprises the following steps:
step a, dividing the motion trend of a motion block into eight directions, wherein the horizontal right direction is a 0-degree direction, the motion trend is in a counterclockwise sequence, and the interval of each direction is 45 degrees;
b, numbering each direction in sequence counterclockwise by taking the right direction as the No. 1 direction, wherein the No. 3 direction represents the right upper direction, and the No. 7 direction represents the right lower direction;
step c, respectively calculating the difference size of eight neighborhood images at corresponding positions in the central image and the next frame image;
and d, selecting the position with the minimum difference value, namely the movement trend of the central image, wherein the central image is the smoke movement block.
Claims (7)
1. The intelligent fire early warning system for the lead-acid storage battery is characterized by comprising a terminal Internet of things sensing module (1), a lead-acid storage battery state identification module (2) and an alarm module (4) which are sequentially connected, wherein the lead-acid storage battery is connected with a power supply (5) in parallel, and is connected with a constant-current discharge load (7) through a switching circuit (6), the terminal Internet of things sensing module (1) comprises a voltage sensor (101), a floating charge current sensor (102), a temperature sensor (103), a combustible gas sensor (104), a smoke detector (105), a humidity sensor (106) and a camera device (107), the temperature sensor (103), the combustible gas sensor (104), the smoke detector (105) and the humidity sensor (106) are positioned in a lead-acid storage battery chamber, and the camera device (107) is used for acquiring a lead-; the lead-acid storage battery state identification module (2) is connected with the terminal Internet of things sensing module (1) and comprises an internal resistance monitoring unit (201), a current monitoring unit (202), a temperature monitoring unit (203), a combustible gas monitoring unit (204), a humidity monitoring unit (205) and a smoke and fire video identification module (3).
2. The lead-acid battery intelligent fire early warning system according to claim 1, wherein the smoke and fire video identification module (3) is connected with the camera device (107) and comprises a preprocessing unit (301), a segmentation unit (302), an extraction unit (303), an identification unit (304), a marking unit (305) and an output unit (306) which are sequentially connected, wherein the preprocessing unit (301) acquires field video stream data of a storage battery of a direct current power supply system of a transformer substation, decodes the field video stream data to obtain a single-frame picture, and preprocesses the single-frame picture to improve data quality; the segmentation unit (302) segments the preprocessed single-frame picture into image blocks with the same size; an extraction unit (303) performs background image modeling based on a moving target detection method of a Gaussian mixture model to extract small image blocks containing moving object regions as recognition candidate region images; the identification unit (304) inputs the candidate area image into a trained flame color, flame shape, flame dynamic, smoke static and smoke dynamic characteristic model for identification and classification; the marking unit (305) marks the positions of the hidden danger areas confirmed by model verification in the original video frame as firework areas detected and identified; an output unit (306) outputs the result.
3. The lead-acid battery intelligent fire early warning system according to claim 2, characterized in that the flame color feature modeling in the identification unit (304) adopts the following rule:
rule1：R≥G≥B
rule2：R≥RT
rule3：S≥((255-R)*ST/RT)
wherein R isTIs a red component threshold, STIs a saturation threshold, the flame pixel depends mainly on the chroma and saturation of the red component (R); if the above conditions are met, the position is judged to be a flame pixel.
4. The lead-acid battery intelligent fire early warning system according to claim 2, wherein the flame appearance characteristic modeling in the identification unit (304) adopts a nested contour model, the flame dynamic characteristic modeling is based on the frequency rule of switching between the flame state and the flameless state of a pixel point, the smoke static characteristic modeling is based on an HSV color model, and the smoke dynamic characteristic modeling is based on the shape and the upward movement trend of a smoke motion block.
5. The lead-acid battery intelligent fire early warning system according to any one of claims 1-4, wherein the internal resistance monitoring unit (201) calculates the internal resistance according to the formula R ═ U2-U1)/I.
6. The lead-acid battery intelligent fire early warning system according to claim 5, wherein a 2000V photoelectric isolation circuit is arranged between the switching circuit (6) and the constant current discharge load (7).
7. The lead-acid battery intelligent fire early warning system according to claim 6, wherein a self-recovery fuse is arranged at the front end of the acquisition line of the constant-current discharge voltage sensor (101).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010237701.2A CN111486892A (en) | 2020-03-30 | 2020-03-30 | Intelligent fire early warning system for lead-acid storage battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010237701.2A CN111486892A (en) | 2020-03-30 | 2020-03-30 | Intelligent fire early warning system for lead-acid storage battery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111486892A true CN111486892A (en) | 2020-08-04 |
Family
ID=71812480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010237701.2A Pending CN111486892A (en) | 2020-03-30 | 2020-03-30 | Intelligent fire early warning system for lead-acid storage battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111486892A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111460973A (en) * | 2020-03-30 | 2020-07-28 | 国网山西省电力公司电力科学研究院 | Smoke and fire signal detection and image visualization automatic identification method |
| CN112488340A (en) * | 2020-12-18 | 2021-03-12 | 无锡挚达物联科技有限公司 | Intelligent energy storage control method and device based on deep learning and storage medium |
| CN115548900A (en) * | 2022-10-21 | 2022-12-30 | 上海蓝箭电控设备南通有限公司 | Outdoor power distribution cabinet with high-temperature fire extinguishing function |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090060260A1 (en) * | 2007-08-29 | 2009-03-05 | Billy Hou | Intelligent image smoke/flame sensor and detection system |
| CN102707238A (en) * | 2012-06-01 | 2012-10-03 | 江苏省电力公司检修分公司 | Storage battery performance on-line monitoring system and monitoring method |
| CN107656216A (en) * | 2017-11-15 | 2018-02-02 | 国网辽宁省电力有限公司鞍山供电公司 | A kind of lead-acid accumulator on-line monitoring is safeguarded and early warning system and performance estimating method |
| CN109637068A (en) * | 2018-11-23 | 2019-04-16 | 山东智洋电气股份有限公司 | Intelligent pyrotechnics identifying system |
| CN110882504A (en) * | 2019-11-22 | 2020-03-17 | 国网河北省电力有限公司电力科学研究院 | Direct-current power supply system storage battery pack fire pre-judging and fire extinguishing system and method |
-
2020
- 2020-03-30 CN CN202010237701.2A patent/CN111486892A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090060260A1 (en) * | 2007-08-29 | 2009-03-05 | Billy Hou | Intelligent image smoke/flame sensor and detection system |
| CN102707238A (en) * | 2012-06-01 | 2012-10-03 | 江苏省电力公司检修分公司 | Storage battery performance on-line monitoring system and monitoring method |
| CN107656216A (en) * | 2017-11-15 | 2018-02-02 | 国网辽宁省电力有限公司鞍山供电公司 | A kind of lead-acid accumulator on-line monitoring is safeguarded and early warning system and performance estimating method |
| CN109637068A (en) * | 2018-11-23 | 2019-04-16 | 山东智洋电气股份有限公司 | Intelligent pyrotechnics identifying system |
| CN110882504A (en) * | 2019-11-22 | 2020-03-17 | 国网河北省电力有限公司电力科学研究院 | Direct-current power supply system storage battery pack fire pre-judging and fire extinguishing system and method |
Non-Patent Citations (1)
| Title |
|---|
| 敖非 等: "直流电源预警及灭火系统的设计与实现", 《电器安全》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111460973A (en) * | 2020-03-30 | 2020-07-28 | 国网山西省电力公司电力科学研究院 | Smoke and fire signal detection and image visualization automatic identification method |
| CN112488340A (en) * | 2020-12-18 | 2021-03-12 | 无锡挚达物联科技有限公司 | Intelligent energy storage control method and device based on deep learning and storage medium |
| CN115548900A (en) * | 2022-10-21 | 2022-12-30 | 上海蓝箭电控设备南通有限公司 | Outdoor power distribution cabinet with high-temperature fire extinguishing function |
| CN115548900B (en) * | 2022-10-21 | 2023-12-22 | 上海蓝箭电控设备南通有限公司 | Outdoor switch board with high temperature function of putting out a fire |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111486892A (en) | Intelligent fire early warning system for lead-acid storage battery | |
| CN106238350B (en) | A kind of solar battery sheet method for separating and system based on machine vision | |
| CN110266268B (en) | Photovoltaic module fault detection method based on image fusion recognition | |
| CN103490511A (en) | Power distribution network communication terminal detection system and method | |
| CN110889441B (en) | Power transformation equipment data anomaly identification method based on distance and point density | |
| CN116189103B (en) | Equipment monitoring automatic control method and control system based on visual image analysis | |
| CN110240036A (en) | It is a kind of to detect the device and method for seeking entry into the electric bicycle of elevator | |
| CN112083000B (en) | Intelligent identification method and system for appearance defects of substation equipment | |
| CN111445462A (en) | Storage battery leakage detection method based on neural network and thermography | |
| CN106887105A (en) | A kind of advance notice of novel road tunnel fire hazard and warning system based on disaster-stricken people's feature | |
| CN105894015A (en) | Gate state analyzing method and system | |
| CN109163811A (en) | A kind of real-time intelligent analysis is portable to wear infrared radiation detection apparatus | |
| CN116740654B (en) | Substation operation prevention and control method based on image recognition technology | |
| CN111899210A (en) | Arc detection method based on image recognition | |
| CN111460973A (en) | Smoke and fire signal detection and image visualization automatic identification method | |
| CN113567845A (en) | High-voltage circuit breaker life cycle intelligent evaluation method based on deep belief network | |
| Zhang et al. | Intelligent detection technology of infrared image of substation equipment based on deep learning algorithm | |
| CN109961428B (en) | Manifold-based non-negative matrix factorization electric smelting magnesium oxide industrial fault detection method | |
| CN215416884U (en) | Power transformer state identification and safety prevention and control system | |
| KR20160048240A (en) | Smoke detection method using density distribution characteristics of smoke | |
| CN111127433B (en) | Method and device for detecting flame | |
| Changfu et al. | Research of substation equipment abnormity identification based on image processing | |
| CN206594784U (en) | A kind of advance notice of novel road tunnel fire hazard and warning system based on disaster-stricken people's feature | |
| CN113920535A (en) | Electronic region detection method based on YOLOv5 | |
| CN111766537A (en) | Insulation trend analysis method for direct current system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200804 |
|
| RJ01 | Rejection of invention patent application after publication |