CN110711327A - Distributed modular locomotive intelligent fire prevention and control system - Google Patents
Distributed modular locomotive intelligent fire prevention and control system Download PDFInfo
- Publication number
- CN110711327A CN110711327A CN201911001746.3A CN201911001746A CN110711327A CN 110711327 A CN110711327 A CN 110711327A CN 201911001746 A CN201911001746 A CN 201911001746A CN 110711327 A CN110711327 A CN 110711327A
- Authority
- CN
- China
- Prior art keywords
- fire
- server
- parameters
- neuron
- locomotive
- 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.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C3/00—Fire prevention, containment or extinguishing specially adapted for particular objects or places
- A62C3/07—Fire prevention, containment or extinguishing specially adapted for particular objects or places in vehicles, e.g. in road vehicles
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C37/00—Control of fire-fighting equipment
-
- 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
Abstract
The invention discloses a distributed modular locomotive intelligent fire prevention and control system, which comprises: a server, a plurality of onboard processors, a plurality of sensors, and a plurality of actuators; the vehicle-mounted processor is used for receiving the environmental parameters sent by the sensors and obtaining the fire disaster grade according to the environmental parameters; receiving the weight correction value sent by the server, recalculating the fire level according to the weight correction value and the current environmental parameter, and controlling the actuator according to the fire level; and the server is used for receiving the environmental parameters and the fire grades sent by the vehicle-mounted processor, storing the environmental parameters and the fire grades, training the BP neural network according to the environmental parameters, the historical environmental parameters, the fire and fire historical data to obtain the weight correction value of the environmental parameters to the fire grades, and sending the weight correction value to the vehicle-mounted processor. The invention improves the accuracy of fire prevention and control and better ensures the operation safety of the locomotive.
Description
Technical Field
The invention relates to the technical field of locomotive fire prevention, in particular to a distributed modular locomotive intelligent fire prevention and control system.
Background
At present, although a vehicle-mounted fire prevention and control system of locomotive equipment in China can prevent and monitor locomotive fires to a certain extent, due to the lack of a special fire theory in the field of locomotives, the problems of easy false alarm, high failure rate, poor adaptability and the like exist.
Different environments can affect the judgment of the fire alarm by the locomotive fire prevention and control system, such as: with the change of altitude, the fire characteristics of locomotive electrical systems and power systems, especially diesel engine systems of diesel locomotives, can vary greatly. The difference of temperature and humidity and the harsh environmental conditions inside the locomotive can also influence the identification and judgment of the fire alarm of the fire prevention and control system. Therefore, there is a need for a system that can adapt to the specific environment of a locomotive and adjust the parameters of a fire alarm according to the change of the environment.
Disclosure of Invention
The invention provides a distributed modular locomotive intelligent fire prevention and control system, which aims to overcome the technical problems.
The invention discloses a distributed modular locomotive intelligent fire prevention and control system, which comprises:
a server, a plurality of onboard processors, a plurality of sensors, and a plurality of actuators;
the on-board processor is used for receiving the environmental parameters sent by the plurality of sensors, and the environmental parameters comprise: temperature, smoke intensity, altitude, locomotive speed and infrared parameters, and obtaining the fire disaster grade according to the environmental parameters; receiving the weight correction value sent by the server, recalculating the fire level according to the weight correction value and the current environmental parameter, and controlling the actuator according to the fire level;
and the server is used for receiving the environment parameters and the fire disaster grades sent by the vehicle-mounted processor, storing the environment parameters and the fire disaster grades, training a BP neural network according to the environment parameters, the historical environment parameters, the fire disasters and the fire disaster historical data to obtain weight correction values of the environment parameters to the fire disaster grades, and sending the weight correction values to the vehicle-mounted processor.
Further, the in-vehicle processor is specifically configured to:
the method comprises the following steps of (1) carrying out normalization processing on original environment parameters by adopting a linear function, wherein a normalization formula is as follows:
wherein Xnorm is a normalized environmental parameter, XiAs an original environment parameter, Xmax and Xmin are respectively a maximum value and a minimum value of the environment parameter.
Further, the on-board server is specifically configured to:
the neuron firing function was used as:
the neuron output is calculated, wherein,is the output of the j-layer network excitation function, Xnorm is the normalized environmental parameter, where ω isjiIs the weight of the j-layer network i neurons;
the neural network output function is:
Further, the server is specifically configured to:
the formula is adopted:
calculating an output error for each neuron, where E is the output error for each neuron, djFire risk levels set for different vehicles;
and adjusting the weight value of each neuron by a gradient descent method according to the output error.
Further, the server is specifically configured to:
the formula is adopted:
calculating the weight value of each neuron after correction, wherein eta is a correction value and is determined according to the type of the locomotive,is the difference operator.
According to the invention, the weight correction value of the environmental parameter of the locomotive to the fire level is obtained by training the BP neural network on the fire history data, so that the accuracy of fire prevention and control is improved, and the operation safety of the locomotive is better ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a distributed modular locomotive intelligent fire prevention and control system of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. 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.
Fig. 1 is a schematic structural diagram of a distributed modular locomotive intelligent fire prevention and control system of the present invention, and as shown in fig. 1, the system of the present embodiment may include:
a server 101, a plurality of on-board processors 102, a plurality of sensors 103, and a plurality of actuators 104;
the on-board processor is used for receiving the environmental parameters sent by the plurality of sensors, and the environmental parameters comprise: temperature, smoke intensity, altitude, locomotive speed and infrared parameters, and obtaining the fire disaster grade according to the environmental parameters; receiving the weight correction value sent by the server, recalculating the fire level according to the weight correction value and the current environmental parameter, and controlling the actuator according to the fire level;
and the server is used for receiving the environment parameters and the fire disaster grades sent by the vehicle-mounted processor, storing the environment parameters and the fire disaster grades, training a BP neural network according to the environment parameters, the historical environment parameters, the fire disasters and the fire disaster historical data to obtain weight correction values of the environment parameters to the fire disaster grades, and sending the weight correction values to the vehicle-mounted processor.
Further, the in-vehicle processor is specifically configured to:
the method comprises the following steps of (1) carrying out normalization processing on original environment parameters by adopting a linear function, wherein a normalization formula is as follows:
wherein Xnorm is a normalized environmental parameter, XiAs an original environment parameter, Xmax and Xmin are respectively a maximum value and a minimum value of the environment parameter.
Specifically, the present embodiment employs a linear function to linearize and convert the raw data to [ 01 ]]Range, environment parameter of normalization process is neural network input matrix, environment parameter matrix is [ x1、x2、x3、x4、x5]Wherein x is1、x2、x3、x4、x5Respectively representing temperature, smoke, altitude, locomotive speed and infrared parameters.
Wherein, when i is 1,2,5, the environmental parameter corresponds to temperature, smoke intensity and infrared ray, and the analog-to-digital conversion chip that this embodiment chose for use is 12 bits, and the normalization formula that temperature, smoke intensity and infrared ray correspond is:
when i is 3, the environmental parameter corresponds to the altitude, and the sea wave height corresponds two kinds of motorcycle types: non-plateau vehicle type and plateau vehicle type. The normalization formula corresponding to the non-plateau vehicle type is as follows:
the normalization formula corresponding to the plateau vehicle type is as follows:
when i is 3, the environmental parameter corresponds to the locomotive speed, and is divided into: common locomotives, high-speed locomotives, 200 kilometers standard motor train units and 300 kilometers standard motor train units. The corresponding normalization formula of the common locomotive is as follows:
the corresponding normalization formula of the high-speed locomotive is as follows:
the corresponding normalization formula of the 200 km standard motor train unit is as follows:
the corresponding normalization formula of the 300 kilometer standard motor train unit is as follows:
for example, the locomotive with model HXN3 operates with the following environmental parameters: the sea wave height is 100 meters, the speed per hour is 80 kilometers per hour, and the analog-to-digital conversion of the temperature, smoke intensity and infrared parameter sensors is as follows: 4000. 3010, 4005. The environmental parameters are normalized as follows:
X1=4000/4096=0.97
X2=3010/4096=0.73
X3=100/2500=0.04
X4=80/120=0.66
X5=4005/4096=0.98
further, the on-board server is specifically configured to:
the neuron firing function was used as:
the neuron output is calculated, wherein,is the output of the j-layer network excitation function, Xnorm is the normalized environmental parameter, where ω isjiIs the weight of the j-layer network i neurons;
the above-mentioned environmental parameters are used as input matrices [0.97, 0.73, 0.04, 0.66, 0.98] of formula (9).
Specifically, the present embodiment designs a three-layer artificial neural network algorithm, a weight matrix, and the weight matrix determines the output of each level of node in the network and further affects the final output of the artificial neural network, as follows:
calculating the output value of the neuron excitation function as
[0.9778,0.9835,0.53,0.9533,0.6921]
The neural network output function is:
And taking the output value of the neuron excitation function as the input of the output function of the neural network, and calculating to obtain a matrix [0.87, 0.7654, 0.3217, 0.2819 and 0.69], wherein the matrix is multiplied by an influence matrix [0.3, 0.2, 0.1, 0.3 and 0.1] to obtain the fire grade of 0.87. Table 1 shows the fire risk level as a risk level table, which may determine that the current locomotive has a fire and the sensor is about to fail.
TABLE 1
To ensure the accuracy of the fire classification.
Further, the server is specifically configured to:
the formula is adopted:
calculating an output error for each neuron, where E is the output error for each neuron, djFire risk levels set for different vehicles;
specifically, this embodiment djThe corresponding matrix is [0.765, 0.6541, 0.2187, 0.3819, 0.597 ]]And calculating to obtain output errors of the neurons as [0.0012, 0.003, 0.0021, 0.0015, 0.00197 ]]。
And adjusting the weight value of each neuron by a gradient descent method according to the output error.
Further, the server is specifically configured to:
the formula is adopted:
calculating the weight value of each neuron after correction, wherein eta is a correction value and is determined according to the type of the locomotive,is the difference operator.
Specifically, the output error is substituted into the equation (12), η is a correction value, and is determined according to the type of the locomotive, where η is 0.45 for the internal combustion locomotive, 0.324 for the electric locomotive, 0.142 for the 200 km standard motor train unit, and 0.112 for the 300 km standard motor train unit. Get the corrected weight of
The corrected weight is used to calculate the fire level for the next cycle. Through the correction of the weighted value, the accuracy of the fire level is improved.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (5)
1. The utility model provides a distributed module ization locomotive intelligence fire prevention control system which characterized in that includes:
a server, a plurality of onboard processors, a plurality of sensors, and a plurality of actuators;
the on-board processor is used for receiving the environmental parameters sent by the plurality of sensors, and the environmental parameters comprise: temperature, smoke intensity, altitude, locomotive speed and infrared parameters, and obtaining the fire disaster grade according to the environmental parameters; receiving the weight correction value sent by the server, recalculating the fire level according to the weight correction value and the current environmental parameter, and controlling the actuator according to the fire level;
and the server is used for receiving the environment parameters and the fire disaster grades sent by the vehicle-mounted processor, storing the environment parameters and the fire disaster grades, training a BP neural network according to the environment parameters, the historical environment parameters, the fire disasters and the fire disaster historical data to obtain weight correction values of the environment parameters to the fire disaster grades, and sending the weight correction values to the vehicle-mounted processor.
2. The system of claim 1, wherein the in-vehicle processor is specifically configured to:
the method comprises the following steps of (1) carrying out normalization processing on original environment parameters by adopting a linear function, wherein a normalization formula is as follows:
wherein Xnorm is a normalized environmental parameter, XiAs an original environment parameter, Xmax and Xmin are respectively a maximum value and a minimum value of the environment parameter.
3. The system of claim 2, wherein the in-vehicle server is specifically configured to:
the neuron firing function was used as:
the neuron output is calculated, wherein,is the output of the j-layer network excitation function, Xnorm is the normalized environmental parameter, where ω isjiIs the weight of the j-layer network i neurons;
the neural network output function is:
a fire risk rating is calculated, wherein,is a risk classification.
4. The system of claim 1, wherein the server is specifically configured to:
the formula is adopted:
calculating an output error for each neuron, where E is the output error for each neuron, djFire risk levels set for different vehicles;
and adjusting the weight value of each neuron by a gradient descent method according to the output error.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911001746.3A CN110711327B (en) | 2019-10-21 | 2019-10-21 | Distributed modular locomotive intelligent fire prevention and control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911001746.3A CN110711327B (en) | 2019-10-21 | 2019-10-21 | Distributed modular locomotive intelligent fire prevention and control system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110711327A true CN110711327A (en) | 2020-01-21 |
CN110711327B CN110711327B (en) | 2021-01-05 |
Family
ID=69213944
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911001746.3A Active CN110711327B (en) | 2019-10-21 | 2019-10-21 | Distributed modular locomotive intelligent fire prevention and control system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110711327B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111420334A (en) * | 2020-04-03 | 2020-07-17 | 西华大学 | Internet-based household intelligent mobile fire-fighting measurement and control system and use method |
WO2024067143A1 (en) * | 2022-09-26 | 2024-04-04 | 华为技术有限公司 | Information transmission method, apparatus and system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2840215Y (en) * | 2005-10-31 | 2006-11-22 | 四川威龙消防设备有限公司 | Locomotive fire composite detecting device |
CN104894335A (en) * | 2015-06-25 | 2015-09-09 | 长春工业大学 | Method for fusing information of spatter predictive analyzers for AOD (argon oxygen decarburization) furnaces |
RU2582461C1 (en) * | 2015-06-08 | 2016-04-27 | Закрытое Акционерное Общество "Нпг Гранит-Саламандра" | Multi-channel system for fire extinguishing in cars and traction rolling stock |
CN205486611U (en) * | 2016-03-01 | 2016-08-17 | 天津航联迪克科技有限公司 | Distributing type motor car fire alarm system |
CN108538013A (en) * | 2018-04-04 | 2018-09-14 | 浙江工贸职业技术学院 | A kind of motor-car emergency service robot with detection function |
CN109767652A (en) * | 2019-02-27 | 2019-05-17 | 株洲太昌电子信息技术股份有限公司 | A kind of the security system and control method of railway locomotive rescue |
CN109993938A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团辽宁有限公司 | Fire monitoring method, apparatus, equipment and medium |
CN110135266A (en) * | 2019-04-17 | 2019-08-16 | 浙江理工大学 | A kind of dual camera electrical fire preventing control method and system based on deep learning |
-
2019
- 2019-10-21 CN CN201911001746.3A patent/CN110711327B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2840215Y (en) * | 2005-10-31 | 2006-11-22 | 四川威龙消防设备有限公司 | Locomotive fire composite detecting device |
RU2582461C1 (en) * | 2015-06-08 | 2016-04-27 | Закрытое Акционерное Общество "Нпг Гранит-Саламандра" | Multi-channel system for fire extinguishing in cars and traction rolling stock |
CN104894335A (en) * | 2015-06-25 | 2015-09-09 | 长春工业大学 | Method for fusing information of spatter predictive analyzers for AOD (argon oxygen decarburization) furnaces |
CN205486611U (en) * | 2016-03-01 | 2016-08-17 | 天津航联迪克科技有限公司 | Distributing type motor car fire alarm system |
CN109993938A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团辽宁有限公司 | Fire monitoring method, apparatus, equipment and medium |
CN108538013A (en) * | 2018-04-04 | 2018-09-14 | 浙江工贸职业技术学院 | A kind of motor-car emergency service robot with detection function |
CN109767652A (en) * | 2019-02-27 | 2019-05-17 | 株洲太昌电子信息技术股份有限公司 | A kind of the security system and control method of railway locomotive rescue |
CN110135266A (en) * | 2019-04-17 | 2019-08-16 | 浙江理工大学 | A kind of dual camera electrical fire preventing control method and system based on deep learning |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111420334A (en) * | 2020-04-03 | 2020-07-17 | 西华大学 | Internet-based household intelligent mobile fire-fighting measurement and control system and use method |
WO2024067143A1 (en) * | 2022-09-26 | 2024-04-04 | 华为技术有限公司 | Information transmission method, apparatus and system |
Also Published As
Publication number | Publication date |
---|---|
CN110711327B (en) | 2021-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11232655B2 (en) | System and method for interfacing with a vehicular controller area network | |
CN110711327B (en) | Distributed modular locomotive intelligent fire prevention and control system | |
CN105389863B (en) | A kind of vehicle condition index calculation method assessed vehicle condition | |
US9836894B2 (en) | Distributed vehicle health management systems | |
CN106219342B (en) | Elevator self diagnosis and pre- diagnostic system and method based on time-frequency convert algorithm | |
CN102753395B (en) | Vehicle sensor node | |
CN109163913A (en) | A kind of Diagnosis method of automobile faults and relevant device | |
CN108881497B (en) | Remote intelligent diagnosis system for automobile detection line | |
CN111555716A (en) | Method, device and equipment for determining working state of photovoltaic array and storage medium | |
US20060112119A1 (en) | System, method and computer program product for real-time event indentification and course of action interpretation | |
CN104318347A (en) | Power transmission line icing state assessment method based on information fusion of multiple sensors | |
US20200066062A1 (en) | Method and system for vehicle analysis | |
CN102801767A (en) | Prognostics and health management (PHM) system for single-level aircraft structure and implementation method | |
CN110826054A (en) | Vehicle-mounted CAN bus intrusion detection method based on message data field characteristics | |
CN113419226A (en) | Radar troubleshooting system | |
CN116304942A (en) | Neural network-based automatic driving vehicle abnormality management method and system | |
CN109572692A (en) | A kind of electric-controlled vehicle Anti-knocking system and its control method | |
WO2022049135A1 (en) | Electronic system for executing a critical function, and associated method | |
US20220266883A1 (en) | Monitoring system for axles of a vehicle | |
CN113108949B (en) | Model fusion-based sonde temperature sensor error prediction method | |
CN115238574A (en) | Digital twin-based power transmission line data management method | |
CN104101419B (en) | A kind of deviation of weight warning system being applied to Automobile Digital weighbridge and method | |
CN109946096B (en) | High-speed train air pipe fault diagnosis method based on model space | |
CN110531163B (en) | Bus capacitance state monitoring method for suspension chopper of maglev train | |
CN113344719A (en) | Insurance user risk early warning monitoring system and monitoring method thereof |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |