CN112002095A - Fire early warning method in mine tunnel - Google Patents
Fire early warning method in mine tunnel Download PDFInfo
- Publication number
- CN112002095A CN112002095A CN202010674726.9A CN202010674726A CN112002095A CN 112002095 A CN112002095 A CN 112002095A CN 202010674726 A CN202010674726 A CN 202010674726A CN 112002095 A CN112002095 A CN 112002095A
- Authority
- CN
- China
- Prior art keywords
- early warning
- fire
- data
- model
- neural network
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
- G08B21/16—Combustible gas alarms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Analytical Chemistry (AREA)
- Combustion & Propulsion (AREA)
- Environmental & Geological Engineering (AREA)
- Toxicology (AREA)
- Alarm Systems (AREA)
- Fire Alarms (AREA)
Abstract
The invention discloses a fire early warning method in a mine tunnel, which comprises the following specific steps: s1, establishing a fire early warning training model by using a BP neural network; s2, carrying out data acquisition by using the temperature, smoke and carbon monoxide sensors, and transmitting the acquired data to a data acquisition module; s3, accurately, timely and reliably sending the smoke, CO concentration and environment temperature data to a neural network training and analyzing model from the front end; s4, inputting real-time data of smoke, CO concentration and environment temperature into the trained BP neural network model for parameter training, so that the model can finally output the probability of the occurrence of the current fire according to the three data input by the sensors, and obtain early warning grades according to the early warning probability of the fire; and S5, formulating a corresponding fire early warning response mechanism according to the early warning grades. According to the method, the in-hole site actual measurement fire data is selected as sample data, and the fire early warning model generated by training by the method is more suitable for the actual in-hole situation, so that the accuracy and the stability are further improved.
Description
Technical Field
The invention relates to the technical field of fire early warning, in particular to a fire early warning method in a mine tunnel.
Background
An early fire intelligent early warning system is an air sampling type fire early warning system. The method adopts a unique laser forward scattering technology and the most advanced artificial neural network technology of the current generation, and can accurately and reliably detect the potential fire. There are many advantages over other fire fighting systems: the sensitivity is extremely high (about 1000 times higher than the traditional one), the false alarm rate is extremely low, and the artificial intelligence technology is real.
At present, a relatively mature fire early warning system detects fire conditions through a smoke detector and carries out fire alarm when a fire disaster occurs. For mines, the mine cavity contains various harmful gases and even combustible gases. When the alarm system is started, the fire condition can not be controlled, so that the special environment of the mine cannot be applied in the mode.
Disclosure of Invention
The invention aims to provide a fire early warning method in a mine cave, which aims to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a fire early warning method in a mine cave is characterized by comprising the following specific steps:
s1, establishing a fire early warning training model by using a BP neural network;
s2, carrying out data acquisition by using the temperature, smoke and carbon monoxide sensors, and transmitting the acquired data to a data acquisition module;
s3, accurately, timely and reliably sending the smoke, CO concentration and environment temperature data to a neural network training and analyzing model from the front end;
s4, inputting real-time data of smoke, CO concentration and environment temperature into the trained BP neural network model for parameter training, so that the model can finally output the probability of the occurrence of the current fire according to the three data input by the sensors, and obtain early warning grades according to the early warning probability of the fire;
and S5, formulating a corresponding fire early warning response mechanism according to the early warning grades.
As a further scheme of the invention: in step S2, the smoke, CO concentration, and ambient temperature data are transmitted to the neural network training and analyzing model through the Zigbee wireless data transmission system, and the smoke, CO concentration, and ambient temperature data can be accurately, timely, and reliably transmitted from the front end to the neural network training and analyzing model through the wireless data transmission system, thereby avoiding the disadvantage that the data link is interrupted due to a line fault in wired data transmission.
As a still further scheme of the invention: in step S5, the fire warning response mechanisms are: level 0 (no fire hazard); level I (prompt alert, close attention video surveillance); level II (the monitoring center prompts personnel to patrol); class III (fixed point or full alarm to eliminate fire hazard).
As a still further scheme of the invention: the step S2 is performed in an in-hole environment.
According to the invention, a multi-sensor data fusion algorithm based on weighted estimation fusion is adopted to realize fire early warning, a BP neural network is utilized to establish a fire early warning training model, and then real-time data of smoke, CO concentration and ambient temperature are input into the trained BP neural network model for parameter training, so that the model can finally output the probability of the occurrence of the current fire according to three data input by sensors, and early warning grades are obtained according to the fire early warning probability. And finally, establishing a corresponding fire early warning response mechanism according to early warning grades. The fire early warning is divided into three levels in total, and a corresponding response mechanism is formulated according to the fire level. Respectively as follows: level 0 (no fire hazard); level I (prompt alert, close attention video surveillance); level II (the monitoring center prompts personnel to patrol); class III (fixed point or full alarm to eliminate fire hazard). In the invention, a Zigbee wireless data transmission system is designed for acquiring real-time data. The smoke, CO concentration and environment temperature data can be accurately, timely and reliably transmitted into the neural network training analysis model from the front end through the wireless data transmission system, and the defect that a data link is interrupted due to line faults in wired data transmission is overcome.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, through the Zigbee wireless data transmission system, the smoke, CO concentration and environment temperature data are sent to the analysis model from the front end through the wireless data transmission system, so that the reliability of data transmission is improved.
2. The method selects the in-tunnel field actual measurement fire data as sample data, the fire early warning model generated by training is more suitable for the in-tunnel actual situation, the accuracy and the stability are further improved, and the in-tunnel actual situation is combined to select the in-tunnel field actual measurement data as the fire data sample, so that the fire early warning training model of the system is established.
3. The invention can adjust the grading early warning threshold value output by the generated neural network data analysis model, so that the model can better accord with the actual situation in the hole.
The invention utilizes the change of the fire premonition to early warn the fire, establishes a data analysis model according to the environmental data template, then utilizes the wireless network data system to transmit the real-time monitored environmental data into the model for intelligent analysis, and carries out graded early warning on the fire signs according to the fire occurrence probability, thereby effectively eliminating the fire hidden danger and preventing the fire from occurring
The invention designs a fire early warning mechanism aiming at fire early warning in the environment in a tunnel. Environmental temperature, smoke and CO concentration data are acquired in real time in a Zigbee wireless data transmission mode, and then the three data are used as detection fire characteristic parameters and input into a fire early warning analysis model for analysis to obtain a fire early warning grading and early warning response mechanism. In the safe construction process, the current fire hazard degree and the current fire hazard development trend can be analyzed and judged dynamically in real time, and early warning results and processing measures of corresponding levels are given, so that the fire hazard is effectively prevented.
Drawings
Fig. 1 is a BP neural network model diagram of a fire early warning method in a mine cave.
Fig. 2 is a structural view of a fire early warning system of a fire early warning method in a mine cave.
Fig. 3 is a fire early warning model workflow of a fire early warning method in a mine cave.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 3, in an embodiment of the present invention, a method for early warning a fire in a mine cave includes the following steps: s1, establishing a fire early warning training model by using a BP neural network; s2, carrying out data acquisition by using the temperature, smoke and carbon monoxide sensors, and transmitting the acquired data to a data acquisition module; s3, accurately, timely and reliably sending the smoke, CO concentration and environment temperature data to a neural network training and analyzing model from the front end; s4, inputting real-time data of smoke, CO concentration and environment temperature into the trained BP neural network model for parameter training, so that the model can finally output the probability of the occurrence of the current fire according to the three data input by the sensors, and obtain early warning grades according to the early warning probability of the fire; and S5, formulating a corresponding fire early warning response mechanism according to the early warning grades.
In step S2, smoke, CO concentration, and ambient temperature data are sent to the neural network training and analyzing model through the Zigbee wireless data transmission system, and smoke, CO concentration, and ambient temperature data can be accurately, timely, and reliably sent to the neural network training and analyzing model from the front end through the wireless data transmission system, thereby avoiding the disadvantage that a data link is interrupted due to a line fault in wired data transmission, and in step S5, the fire warning response mechanism is: level 0 (no fire hazard); level I (prompt alert, close attention video surveillance); level II (the monitoring center prompts personnel to patrol); class III (alarm at fixed point or in whole field to eliminate fire hazard), step S2 is applied in the environment inside the hole.
The working principle of the invention is as follows:
(1) BP neural network overview
The BP neural network is a multi-layer feedforward network trained according to an error inverse propagation algorithm, and is one of the most widely applied neural network models at present. The BP network can learn and store a large number of input-output pattern mappings without prior disclosure of mathematical equations describing such mappings. And selecting a proper data set to carry out parameter training on the constructed BP neural network, so that the model can finally output the probability of the current fire according to the three data input by the sensors.
The BP neural network estimates the error of the direct leading layer of the output layer by using the output error, then estimates the error of the previous layer by using the error, obtains the error estimation of all other layers by performing reverse transmission of the layer by layer, and stops training until the error rate is lower than a certain threshold value, thereby realizing the modeling of the BP neural network, wherein the input value in the graph 1 is a feature vector with the dimension of 3, namely the temperature, smoke and CO sensor value, and is recorded as x ═ (x ═ is1,x2,x3)。
Typically, there are multiple samples in a data set, and assuming there are m samples, this data set is denoted as X ═ X (X)(1),x(2),...,x(m)). For these m samples, the set of output values is denoted as y ═ y (y)(1),y(2),...,y(m)). Here, it is agreed that the superscript (i) is the number of samples in the sample set, the superscript [ i ]]For the layer number of the neural network, the subscript [ i ]]The base of log is by default e for the sequence number of a node at a certain level in the network.
Neural networks use forward propagation for prediction. For a 3-layer neural network, the prediction values can be calculated in this way
z[1]＝xW[1]+b[1]
a[1]＝σ(z[1])
z[2]＝a[1]W[2]+b[2]
(2) Data set selection
The BP neural network is used for fire early warning, parameter training needs to be carried out on the established BP neural network model at first, and the model can finally output the probability of the occurrence of the current fire according to three data input by the sensors.
In the training and generation of the BP neural network model, while referring to the fire standard of Chinese standard test, considering the particularity of the implementation environment, the historical data in the hole is selected as a simulated fire data sample, a training model sample library is established, and the training model of the system is generated.
The model generated by the system is used for developing a simulation verification experiment and simulating the fire scene environment:
the temperature is 23 ℃ below zero, the CO content is 0ppm below zero, and the smoke is smokeless;
combustibles-plain a4 paper; the time length of single combustion is 3 minutes; experiment times-5 times.
Through experimental observation and combining with the existing theoretical knowledge, the following conclusions can be drawn: in the initial stage of paper combustion, a small amount of smoke is released, the temperature rises, and the value of CO in the air begins to be detected; smoke is reduced in the combustion process, and the temperature and the CO content are continuously increased and reach a maximum value; in the later stage of paper combustion, flame is gradually extinguished, a large amount of smoke is generated, and meanwhile, the temperature and the CO content are reduced; at the end of combustion the temperature returns to room temperature and the CO and smoke become 0. Correspondingly, sensor values corresponding to different combustion moments are recorded, and fire hazard classification is carried out on training data according to the sensor values, and the specific classification rules are as follows:
fire class
And predicting the value of the sensor by using the trained BP neural network model to obtain n x 3-dimensional fire occurrence probability value, and processing the log group to obtain the corresponding fire grade. Level 0 (no fire hazard); level I (the monitoring center prompts warnings, pays close attention to video monitoring); level II (the monitoring center prompts personnel to patrol); class III (fixed point or full alarm to eliminate fire hazard).
(3) Establishment of fire early warning system
The fire early warning system is configured as shown in fig. 2, and achieves fire early warning based on a multi-sensor data fusion algorithm. The system adopts a data transmission mode of a zigbee wireless network and a wired local area network. The working principle is that the temperature, smoke and carbon monoxide sensors transmit physical quantities of environmental parameters to the data acquisition module, the data acquisition module acquires the three data, sends the three data to the wireless network through ZigBee wireless signals, transmits the data to the local area network through the wireless network, and sends the data into the neural network model through the local area network for operation, so that real-time early warning of fire conditions is realized, and a fire early warning result is displayed in a monitoring center.
The working flow of the fire early warning model based on the multi-sensor data fusion algorithm is shown in fig. 3. Firstly, data consistency check is carried out on the sensors to eliminate false data collected by a single sensor which is interfered. If the data is inconsistent, then the set of data is invalid and the next set of data continues to be checked. And after the consistency is achieved, the trained BP neural network is used for data calculation, and the probabilities of 0 level, I level, II level and III level are respectively output. And comprehensively analyzing the group of data to obtain the final early warning grade. If the fire disaster early warning level exceeds the 0 level, alarming the monitoring value according to the early warning level value, and sending a fire early warning instruction to the system; if not, the flow is continued. Meanwhile, in the design of the training model, the threshold value for generating the early warning classification of the fire early warning training model is set to be adjustable, and the threshold value can be used in combination with the environment in the hole, so that the training model can be more consistent with the actual condition of the environment in the hole, and the adaptability is higher.
The method combines the actual situation in the hole, refers to the fire standard of Chinese standard test in the training and generation of the BP neural network model, simultaneously considers the particularity of the implementation environment, selects the historical data in the hole as the simulated fire data sample, establishes the training model sample library and generates the training model of the system.
The fire early warning model of the algorithm can eliminate errors caused by noise interference or device damage to a certain extent, improve the accuracy and stability and reduce the occurrence of false alarm and missed alarm. Finally, the performance of the whole system is more accurate and stable.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes in the embodiments and/or modifications of the invention can be made, and equivalents and modifications of some features of the invention can be made without departing from the spirit and scope of the invention.
Claims (4)
1. A fire early warning method in a mine cave is characterized by comprising the following specific steps:
s1, establishing a fire early warning training model by using a BP neural network;
s2, carrying out data acquisition by using the temperature, smoke and carbon monoxide sensors, and transmitting the acquired data to a data acquisition module;
s3, accurately, timely and reliably sending the smoke, CO concentration and environment temperature data to a neural network training and analyzing model from the front end;
s4, inputting real-time data of smoke, CO concentration and environment temperature into the trained BP neural network model for parameter training, so that the model can finally output the probability of the occurrence of the current fire according to the three data input by the sensors, and obtain early warning grades according to the early warning probability of the fire;
and S5, formulating a corresponding fire early warning response mechanism according to the early warning grades.
2. The fire early warning method in a mine cavern according to claim 1, wherein: in step S2, the smoke, CO concentration, and ambient temperature data are transmitted to the neural network training and analyzing model through the Zigbee wireless data transmission system, and the smoke, CO concentration, and ambient temperature data can be accurately, timely, and reliably transmitted from the front end to the neural network training and analyzing model through the wireless data transmission system, thereby avoiding the disadvantage that the data link is interrupted due to a line fault in wired data transmission.
3. The fire early warning method in a mine cavern according to claim 1, wherein: in step S5, the fire warning response mechanisms are: level 0 (no fire hazard); level I (prompt alert, close attention video surveillance); level II (the monitoring center prompts personnel to patrol); class III (fixed point or full alarm to eliminate fire hazard).
4. The fire early warning method in a mine cavern according to claim 1, wherein: the step S2 is performed in an in-hole environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010674726.9A CN112002095A (en) | 2020-07-14 | 2020-07-14 | Fire early warning method in mine tunnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010674726.9A CN112002095A (en) | 2020-07-14 | 2020-07-14 | Fire early warning method in mine tunnel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112002095A true CN112002095A (en) | 2020-11-27 |
Family
ID=73466997
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010674726.9A Pending CN112002095A (en) | 2020-07-14 | 2020-07-14 | Fire early warning method in mine tunnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112002095A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192282A (en) * | 2021-04-16 | 2021-07-30 | 南京玄甲物联科技有限公司 | Fire early warning system based on internet of things |
| CN113572063A (en) * | 2021-02-26 | 2021-10-29 | 河南工业职业技术学院 | Electrical cabinet system with heat dissipation and dust removal functions |
| CN113658402A (en) * | 2021-07-06 | 2021-11-16 | 上海融韵嘉丰消防装备集团有限公司 | Fire control thing networking alarm integrated system |
| CN114387755A (en) * | 2021-12-13 | 2022-04-22 | 煤炭科学技术研究院有限公司 | Mine smoke detection method, device, processor and system |
| CN114582083A (en) * | 2022-01-14 | 2022-06-03 | 西安理工大学 | Tunnel monitoring multi-sensor data fusion fire early warning method |
| CN114971409A (en) * | 2022-06-28 | 2022-08-30 | 成都秦川物联网科技股份有限公司 | Smart city fire monitoring and early warning method and system based on Internet of things |
| CN115147993A (en) * | 2022-09-05 | 2022-10-04 | 无锡卓信信息科技股份有限公司 | Fire early warning system for closed place and system data processing method thereof |
| CN117036082A (en) * | 2023-07-18 | 2023-11-10 | 湘煤立达矿山装备股份有限公司 | Intelligent mine management system and method |
| CN117975701A (en) * | 2024-03-29 | 2024-05-03 | 江苏讯汇科技股份有限公司 | Mountain fire indicating device is prevented at transmission line night |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2758671B2 (en) * | 1989-01-20 | 1998-05-28 | ホーチキ株式会社 | Fire judgment device |
| CN204833579U (en) * | 2015-08-31 | 2015-12-02 | 郭倜维 | Indoor intelligent fire alarm system based on zigBee communication |
| CN109356652A (en) * | 2018-10-12 | 2019-02-19 | 深圳市翌日科技有限公司 | Adaptive fire grading forewarning system method and system under a kind of mine |
| CN109978005A (en) * | 2019-02-25 | 2019-07-05 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire alarm method, device, storage medium and terminal device |
-
2020
- 2020-07-14 CN CN202010674726.9A patent/CN112002095A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2758671B2 (en) * | 1989-01-20 | 1998-05-28 | ホーチキ株式会社 | Fire judgment device |
| CN204833579U (en) * | 2015-08-31 | 2015-12-02 | 郭倜维 | Indoor intelligent fire alarm system based on zigBee communication |
| CN109356652A (en) * | 2018-10-12 | 2019-02-19 | 深圳市翌日科技有限公司 | Adaptive fire grading forewarning system method and system under a kind of mine |
| CN109978005A (en) * | 2019-02-25 | 2019-07-05 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire alarm method, device, storage medium and terminal device |
Non-Patent Citations (1)
| Title |
|---|
| 罗志增等: "《机器人感觉与多信息融合》", 30 June 2002, 机械工业出版社 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113572063A (en) * | 2021-02-26 | 2021-10-29 | 河南工业职业技术学院 | Electrical cabinet system with heat dissipation and dust removal functions |
| CN113192282A (en) * | 2021-04-16 | 2021-07-30 | 南京玄甲物联科技有限公司 | Fire early warning system based on internet of things |
| CN113658402A (en) * | 2021-07-06 | 2021-11-16 | 上海融韵嘉丰消防装备集团有限公司 | Fire control thing networking alarm integrated system |
| CN114387755A (en) * | 2021-12-13 | 2022-04-22 | 煤炭科学技术研究院有限公司 | Mine smoke detection method, device, processor and system |
| CN114582083A (en) * | 2022-01-14 | 2022-06-03 | 西安理工大学 | Tunnel monitoring multi-sensor data fusion fire early warning method |
| CN114582083B (en) * | 2022-01-14 | 2023-06-30 | 西安理工大学 | Tunnel monitoring multi-sensor data fusion fire disaster early warning method |
| CN114971409A (en) * | 2022-06-28 | 2022-08-30 | 成都秦川物联网科技股份有限公司 | Smart city fire monitoring and early warning method and system based on Internet of things |
| CN114971409B (en) * | 2022-06-28 | 2024-06-21 | 成都秦川物联网科技股份有限公司 | Smart city fire monitoring and early warning method and system based on Internet of things |
| CN115147993A (en) * | 2022-09-05 | 2022-10-04 | 无锡卓信信息科技股份有限公司 | Fire early warning system for closed place and system data processing method thereof |
| CN117036082A (en) * | 2023-07-18 | 2023-11-10 | 湘煤立达矿山装备股份有限公司 | Intelligent mine management system and method |
| CN117036082B (en) * | 2023-07-18 | 2024-05-10 | 湘煤立达矿山装备股份有限公司 | Intelligent mine management system and method |
| CN117975701A (en) * | 2024-03-29 | 2024-05-03 | 江苏讯汇科技股份有限公司 | Mountain fire indicating device is prevented at transmission line night |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112002095A (en) | Fire early warning method in mine tunnel | |
| CN101251942B (en) | Underground space fire intelligent detection early alarming and forecasting method and apparatus | |
| Wu et al. | An intelligent tunnel firefighting system and small-scale demonstration | |
| CN104933841A (en) | Fire prediction method based on self-organizing neural network | |
| CN107240216A (en) | Based on 3DGIS+BIM technologies and artificial intelligence O＆M emergent alarm and fast response method | |
| CN113223264B (en) | Fire disaster intelligent early warning system and method based on QPSO-BP neural network | |
| CN103325205B (en) | Based on inside fire Forecasting Methodology and the system of radial base neural net | |
| CN105185022A (en) | Transformer substation fire detection system based on multi-sensor information combination and detection information combination method | |
| CN113920673B (en) | Indoor fire intelligent monitoring method and system | |
| CN111986436B (en) | Comprehensive flame detection method based on ultraviolet and deep neural networks | |
| CN113192283B (en) | Wireless fire early warning system with multi-sensor information fusion | |
| CN105975991B (en) | A kind of improved extreme learning machine fire kind recognition methods | |
| CN1963878A (en) | Intelligence inspection prewarning forecasting apparatus for fire of high-rise building | |
| CN117319451B (en) | Urban fire-fighting Internet of things supervision system based on multi-mode big data and method thereof | |
| CN116052360B (en) | Fire alarm system | |
| CN207895646U (en) | Intelligent building automatic fire alarm system | |
| CN201445722U (en) | Automatic alarming and extinguishing system for fire disaster of large building | |
| CN112885021B (en) | Multi-sensor fire prediction method and system based on composite algorithm | |
| CN117406137B (en) | Method and system for monitoring lightning leakage current of power transmission line | |
| CN1115448A (en) | Early stage fire detecting apparatus | |
| CN108759920B (en) | Warehouse safety monitoring system based on thing networking | |
| Wang et al. | Forest fire detection system based on Fuzzy Kalman filter | |
| CN116938683A (en) | Network path analysis system and method based on network security anomaly detection | |
| CN117054967A (en) | Positioning method based on intelligent positioning of mining safety helmet and product structure | |
| CN109345754A (en) | A kind of mine fire warning monitoring system and method based on BP neural network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201127 |