A plant fire detection method, system, electronic device and medium

Abstract

The present application belongs to the technical field of fire detection, and aims to provide a plant fire detection method, system, electronic device and medium. The present application discloses a plant fire detection method, comprising: receiving a plurality of fire detection signals sent by a plurality of sensors in a specified area in real time; locally processing the plurality of fire detection signals respectively to obtain a plurality of locally processed data; performing fusion processing on the plurality of locally processed data to obtain an initial fire detection result; and verifying the initial fire detection result according to the plurality of locally processed data and the initial fire detection result to obtain a final fire detection result. The present application adopts a multi-sensor fusion scheme, which can effectively compensate for the limitations of single sensor functions, effectively eliminate false information, and improve the accuracy of fire detection. At the same time, the multi-sensor fusion scheme in the present application can shorten the fire detection time, which is conducive to early detection of fire.

Description

Technical Field

[0001] This invention belongs to the field of fire detection technology, specifically relating to a method, system, electronic equipment, and medium for detecting fires in factory areas. Background Technology

[0002] A factory area refers to the production site of a manufacturing enterprise, typically containing large workshops housing multiple products needed for production. Due to the high density of people and the variety of flammable and combustible materials within a factory area, a fire can spread rapidly and intensely, posing a serious threat to the personal safety of employees and the property of the company. Current technology typically uses smoke sensors for fire detection within the factory area. When the smoke level detected by the smoke detector exceeds a set threshold, an alarm signal is output to trigger a fire alarm. Simultaneously, regular manual inspections are used for supplementary fire detection.

[0003] However, in using the prior art, the inventors discovered at least the following problems:

[0004] In existing technologies, single sensors such as smoke sensors are typically used for fire alarms. However, factory detection environments are complex and diverse, and a single sensor can only describe part of the information during the fire process. This leads to a high false alarm and false negative rate when using a single sensor for fire detection. For example, smoke sensors are prone to false alarms due to kitchen fumes and water vapor, while temperature sensors are prone to false alarms due to lights, welding, etc. In addition, the high ceilings in large factories cause smoke or temperature to rise to the sensor location and be detected by the sensor in a longer time, resulting in a delay in fire detection and hindering early fire detection. Summary of the Invention

[0005] The present invention aims to solve the above-mentioned technical problems to at least a certain extent, and provides a method, system, electronic device and medium for detecting fires in factory areas.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for detecting fires in a factory area, comprising:

[0008] It can receive multiple fire detection signals from multiple sensors in a designated area in real time; among them, the multiple sensors are of different types;

[0009] Multiple fire detection signals are processed locally to obtain multiple locally processed data;

[0010] The initial fire detection results are obtained by fusing multiple locally processed data.

[0011] Based on the processed data from multiple local areas and the initial fire detection results, the initial fire detection results are verified to obtain the final fire detection results.

[0012] This invention employs a multi-sensor fusion scheme, which can effectively compensate for the limitations of a single sensor function, effectively eliminate erroneous information, and improve the accuracy of fire detection. At the same time, the multi-sensor fusion scheme in this invention can shorten the fire detection time, which is conducive to achieving early fire detection.

[0013] In one possible design, multiple sensors include a designated gas sensor, a smoke sensor, and a flame sensor; correspondingly, multiple fire detection signals include a gas detection signal, a smoke detection signal, and a flame detection signal.

[0014] In one possible design, after receiving multiple fire detection signals from multiple sensors in a designated area, the method further includes:

[0015] The gas detection signal and smoke detection signal in the fire detection signal are preprocessed using the mean filtering method to obtain the preprocessed gas detection signal and the preprocessed smoke detection signal, so as to perform local processing on the preprocessed gas detection signal and the preprocessed smoke detection signal;

[0016] A time-delay filtering method is used to preprocess the flame detection signal in the fire detection signal to obtain a preprocessed flame detection signal, which can then be used for local processing.

[0017] In one possible design, mean filtering is used to preprocess the gas detection signal and smoke detection signal in the fire detection signal, including:

[0018] Acquire all gas detection signals and all smoke detection signals within a specified time period, and use the average of all gas detection signals and the average of all smoke detection signals within the current specified time period as the gas detection signal and smoke detection signal at the current moment; wherein, the gas detection signal or smoke detection signal at the current moment is:

[0019]

[0020] In the formula, n0 is the number of gas detection signals or smoke detection signals sampled for a specified duration; d0(j) is the j-th sampled gas detection signal or smoke detection signal among the n0 sample numbers; and i0 is the starting sampling point of the specified duration interval.

[0021] In one possible design, multiple fire detection signals are processed locally to obtain multiple locally processed data, including:

[0022] Based on multiple fire detection signals and multiple prior fire detection signals corresponding to the multiple fire detection signals, multiple signal change quantities corresponding to the multiple fire detection signals are obtained; wherein, the detection time of the prior fire detection signal corresponding to any fire detection signal is earlier than the detection time of the fire detection signal.

[0023] Based on the changes in multiple signals, the membership degree of multiple fire detection signals to all preset fuzzy sets is calculated, and the multiple fire detection signals are divided into corresponding preset fuzzy sets according to the membership degree, so as to realize the fuzzification processing of multiple fire detection signals.

[0024] Obtain the fuzzy rules of all preset fuzzy sets, and perform fuzzy division on multiple fire detection signals assigned to preset fuzzy sets according to the fuzzy rules to obtain multiple fuzzy values ​​corresponding to multiple fire detection signals;

[0025] Multiple fire detection signals are clarified based on multiple ambiguities to obtain multiple locally processed data corresponding to the multiple fire detection signals; among them, the multiple locally processed data are used to characterize the fire occurrence probability corresponding to the multiple fire detection signals.

[0026] In one possible design, when performing local processing on multiple fire detection signals, an FNN neural network is used; wherein, the FNN neural network includes an input layer, a fuzzification layer, a fuzzy inference layer and a defuzzification layer connected in sequence;

[0027] When fusing multiple locally processed data, a PNN neural network is used; wherein, the PNN neural network includes an input layer, a pattern layer, a summation layer and an output layer connected in sequence.

[0028] In one possible design, based on multiple locally processed data and the initial fire detection results, the initial fire detection results are verified to obtain the final fire detection results, including:

[0029] Obtain N preceding locally processed data points corresponding to multiple locally processed data points; where N is a natural number greater than 1.

[0030] Multiple locally processed data and the detection differences between the N prior locally processed data and the initial fire detection result are obtained respectively;

[0031] Obtain the average value of the detection difference between multiple locally processed data and its N preceding locally processed data;

[0032] Based on the average value of the detection differences of multiple locally processed data and its N preceding locally processed data, the operating status of the sensors corresponding to the multiple locally processed data is verified. If the operating status of any sensor is abnormal, the initial fire detection result is determined to be abnormal, and the locally processed data corresponding to that sensor is removed from the multiple locally processed data to obtain the remaining locally processed data. Then, the final fire detection result is obtained based on the remaining locally processed data. If the operating status of all sensors is normal, the initial fire detection result is determined to be normal, and the initial fire detection result is used as the final fire detection result.

[0033] In a second aspect, the present invention provides a factory fire detection system for implementing the factory fire detection method as described in any of the preceding claims; the factory fire detection system includes:

[0034] This embodiment discloses a factory fire detection system for implementing the factory fire detection method in Embodiment 1; such as Figure 2 As shown, the factory fire detection system includes:

[0035] The signal receiving module is used to receive multiple fire detection signals sent by multiple sensors in a designated area in real time; among them, the multiple sensors are of different types;

[0036] A local processing module, which is communicatively connected to the signal receiving module, is used to perform local processing on multiple fire detection signals to obtain multiple locally processed data.

[0037] The data fusion module is communicatively connected to the local processing module and is used to fuse multiple locally processed data to obtain the initial fire detection result.

[0038] The result output module is communicatively connected to the data fusion module and is used to verify the initial fire detection result based on multiple locally processed data and the initial fire detection result to obtain the final fire detection result.

[0039] Thirdly, the present invention provides an electronic device, comprising:

[0040] Memory, used to store computer program instructions; and,

[0041] A processor for executing the computer program instructions to perform the operation of the factory fire detection method as described in any of the preceding claims.

[0042] Fourthly, the present invention provides a computer-readable storage medium for storing computer-readable computer program instructions configured to perform operations of the factory fire detection method as described in any of the preceding claims when executed. Attached Figure Description

[0043] Figure 1 This is a flowchart of a factory fire detection method in one of the embodiments;

[0044] Figure 2 This is a block diagram of a factory fire detection system in one embodiment;

[0045] Figure 3 This is a block diagram of an electronic device in one embodiment. Detailed Implementation

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0047] Example 1:

[0048] This embodiment discloses a method for detecting fires in a factory area, which can be executed, but is not limited to, by a computer device or virtual machine with certain computing resources, such as a personal computer, smartphone, personal digital assistant or wearable device, or by a virtual machine.

[0049] like Figure 1 As shown, a method for detecting fires in a factory area may include, but is not limited to, the following steps:

[0050] S1. Receive multiple fire detection signals sent by multiple sensors in a designated area in real time; wherein, the multiple sensors are of different types; it should be noted that, in this embodiment, the multiple fire detection signals are sent by multiple different types of sensors, and each sensor outputs a fire detection signal to the background server at regular intervals.

[0051] Specifically, in this embodiment, the multiple sensors include a designated gas sensor, a smoke sensor, and a flame sensor; correspondingly, the multiple fire detection signals include a gas detection signal, a smoke detection signal, and a flame detection signal. For example, in this embodiment, the smoke sensor may, but is not limited to, a photoelectric smoke sensor and an ionization smoke sensor, and the corresponding fire detection signals include photoelectric smoke detection signals and ionization smoke detection signals; the designated gas sensor may, but is not limited to, a CO (carbon monoxide) detector, and the corresponding fire detection signal includes a CO detection signal.

[0052] It should be noted that the more types of sensors there are, the more complex the processing of the corresponding fire detection signals becomes, which also increases the hardware cost of fire detection. Therefore, more types and numbers of sensors are not necessarily better. In this embodiment, three types of sensors are used: smoke sensor, designated gas sensor, and flame sensor. This not only achieves good fire detection results but also avoids problems such as excessive cost and difficulty in sensor management, making it worthy of widespread application.

[0053] In this embodiment, after receiving multiple fire detection signals from multiple sensors in a designated area, the method further includes:

[0054] A1. The gas detection signal and smoke detection signal in the fire detection signal are preprocessed using the mean filtering method to obtain the preprocessed gas detection signal and the preprocessed smoke detection signal, so as to perform local processing on the preprocessed gas detection signal and the preprocessed smoke detection signal;

[0055] Specifically, in this embodiment, the mean filtering method is used to preprocess the gas detection signal and smoke detection signal in the fire detection signal, including:

[0056] Acquire all gas detection signals and all smoke detection signals within a specified time period, and use the average of all gas detection signals and the average of all smoke detection signals within the current specified time period as the gas detection signal and smoke detection signal at the current moment; wherein, the gas detection signal or smoke detection signal at the current moment is:

[0057]

[0058] In the formula, n0 is the number of gas detection signals or smoke detection signals sampled for a specified duration; d0(j) is the j-th sampled gas detection signal or smoke detection signal among the n0 sample numbers; and i0 is the starting sampling point of the specified duration interval.

[0059] It should be noted that in this embodiment, the mean filtering method is used to preprocess the gas detection signal and smoke detection signal in the fire detection signal, which can effectively eliminate electrical pulse spikes and power frequency interference, avoid instantaneous interference of the sensor, and thus help ensure the accuracy of the gas detection signal and smoke detection signal to be processed locally.

[0060] A2. A time-delay filtering method is used to preprocess the flame detection signal in the fire detection signal to obtain a preprocessed flame detection signal, which is then used for local processing. It should be noted that the time-delay filtering method avoids detection interference caused by non-flame light radiation sources. When preprocessing the flame detection signal in the fire detection signal using the time-delay filtering method, after the corresponding sensor acquires the flame detection signal, it acquires the flame detection signal again after a certain time interval before using that signal as a valid signal for subsequent local processing. In this embodiment, the time-delay filtering method can obtain an effective flame alarm pulse signal, thereby improving the accuracy of fire judgment based on the locally processed flame detection signal.

[0061] S2. Perform local processing on multiple fire detection signals to obtain multiple locally processed data.

[0062] In this embodiment, multiple fire detection signals are locally processed to obtain multiple locally processed data, including:

[0063] S201. Based on multiple fire detection signals and multiple prior fire detection signals corresponding to the multiple fire detection signals, obtain multiple signal change quantities corresponding to the multiple fire detection signals; wherein, the detection time of the prior fire detection signal corresponding to any fire detection signal is earlier than the detection time of the fire detection signal.

[0064] S202. Based on the changes in multiple signals, calculate the membership degree of each fire detection signal to all preset fuzzy sets, and assign the multiple fire detection signals to the corresponding preset fuzzy sets according to the membership degree, so as to achieve fuzzification processing of multiple fire detection signals; it should be noted that the preset fuzzy sets, such as high temperature fuzzy sets, high brightness fuzzy sets, etc., are used for subsequent fire determination; as an example, the fire detection signal sent by the i-th sensor among multiple sensors is The prior fire detection signal corresponding to this fire detection signal is: The signal change corresponding to the fire detection signal is:

[0065]

[0066] S203. Obtain the fuzzy rules of all preset fuzzy sets, and perform fuzziness division on the multiple fire detection signals assigned to the preset fuzzy sets according to the fuzzy rules to obtain multiple fuzzinesses corresponding to the multiple fire detection signals; it should be noted that in this embodiment, the fuzzy rules of the preset fuzzy sets are obtained from a preset knowledge base, which contains knowledge in the field of fire detection and the required control objectives, i.e., fuzzy rules.

[0067] S204. Based on multiple ambiguities, multiple fire detection signals are clarified to obtain multiple locally processed data corresponding to the multiple fire detection signals; wherein, the multiple locally processed data are used to characterize the fire occurrence probability corresponding to the multiple fire detection signals.

[0068] It should be noted that in this embodiment, when performing local processing on multiple fire detection signals, an FNN (Fuzzy Neural Network) is used; wherein the FNN includes an input layer, a fuzzification layer, a fuzzy inference layer and a defuzzification layer connected in sequence.

[0069] Specifically, in this embodiment, the input layer is used to receive multiple fire detection signals and obtain multiple signal change quantities corresponding to the multiple fire detection signals based on the multiple fire detection signals and the multiple prior fire detection signals corresponding to the multiple fire detection signals; wherein, the detection time of the prior fire detection signal corresponding to any fire detection signal is earlier than the detection time of the fire detection signal.

[0070] The fuzzification layer is used to calculate the membership degree of multiple fire detection signals to all preset fuzzy sets based on multiple signal changes, and to classify the multiple fire detection signals to the corresponding preset fuzzy sets according to the membership degree, so as to realize the fuzzification processing of multiple fire detection signals. It should be noted that the preset fuzzy sets, such as high temperature fuzzy sets, high brightness fuzzy sets, etc., are used for subsequent determination of whether there is a fire.

[0071] The fuzzy inference layer is used to obtain the fuzzy rules of all preset fuzzy sets, and to perform fuzziness division on multiple fire detection signals assigned to the preset fuzzy sets according to the fuzzy rules, so as to obtain multiple fuzzinesses corresponding to multiple fire detection signals. It should be noted that the fuzzy inference layer has the reasoning ability to simulate the basic fuzzy concepts of humans, and can realize the fuzziness division of multiple fire detection signals.

[0072] The deblurring layer is used to clarify multiple fire detection signals based on multiple levels of ambiguity, resulting in multiple locally processed data corresponding to the multiple fire detection signals. It should be noted that in this embodiment, the deblurring layer can transform the ambiguity obtained from fuzzy inference into precise quantities actually used to predict the probability of fire occurrence, i.e., multiple locally processed data.

[0073] In this embodiment, the adaptive learning capability of the FNN neural network is used to select the optimal weights and parameters for layers such as fuzzification, fuzzy inference, and defuzzification, but there are no restrictions on this.

[0074] S3. The data from multiple localized processing steps are fused to obtain the initial fire detection results.

[0075] It should be noted that in this embodiment, a Product-based Neural Network (PNN) is used to fuse multiple locally processed data. The PNN includes an input layer, a pattern layer, a summation layer, and an output layer connected sequentially. It should also be noted that after fusing multiple locally processed data, the PNN achieves higher accuracy in fire detection than a single type of fire detection sensor, making it valuable for widespread application. Furthermore, the Fusion Neural Network (FNN) combines the logical reasoning ability of fuzzy systems with the self-learning ability of neural networks, giving it both powerful structural knowledge representation capabilities and the ability to optimize its own parameters.

[0076] S4. Based on the data after multiple local processing and the initial fire detection result, the initial fire detection result is verified to obtain the final fire detection result.

[0077] Specifically, in this embodiment, the initial fire detection result is verified based on multiple locally processed data and the initial fire detection result to obtain the final fire detection result, including:

[0078] S401. Obtain N prior locally processed data corresponding to multiple locally processed data; where N is a natural number greater than 1;

[0079] S402. Acquire multiple locally processed data and the detection differences between the N prior locally processed data and the initial fire detection result;

[0080] S403. Obtain the average value of the detection difference between multiple locally processed data and their N prior locally processed data;

[0081] S404. Based on the average value of the detection differences of multiple locally processed data and its N prior locally processed data, verify the operating status of the sensors corresponding to the multiple locally processed data. If the operating status of any sensor is abnormal, the initial fire detection result is determined to be abnormal, and the locally processed data corresponding to that sensor is removed from the multiple locally processed data to obtain the remaining locally processed data. Then, the final fire detection result is obtained based on the remaining locally processed data. If the operating status of all sensors is normal, the initial fire detection result is determined to be normal, and the initial fire detection result is used as the final fire detection result.

[0082] It should be noted that in this embodiment, for any locally processed data, if the average value of the detection difference between the locally processed data and its N preceding locally processed data is within a preset range, then the sensor corresponding to the locally processed data is determined to be operating normally; otherwise, the sensor corresponding to the locally processed data is determined to be operating abnormally. In this embodiment, due to the verification process of the initial fire detection result, the detection results of abnormal sensors can be promptly identified, avoiding the problem of abnormal fire detection results caused by the malfunction of a single sensor.

[0083] This embodiment employs a multi-sensor fusion scheme, which can effectively compensate for the limitations of a single sensor function, effectively eliminate erroneous information, and improve the accuracy of fire detection. At the same time, the multi-sensor fusion scheme in this embodiment can shorten the fire detection time, which is conducive to achieving early fire detection.

[0084] Example 2:

[0085] This embodiment discloses a factory fire detection system for implementing the factory fire detection method in Embodiment 1; such as Figure 2 As shown, the factory fire detection system includes:

[0086] The signal receiving module is used to receive multiple fire detection signals sent by multiple sensors in a designated area in real time; among them, the multiple sensors are of different types;

[0087] A local processing module, which is communicatively connected to the signal receiving module, is used to perform local processing on multiple fire detection signals to obtain multiple locally processed data.

[0088] The data fusion module is communicatively connected to the local processing module and is used to fuse multiple locally processed data to obtain the initial fire detection result.

[0089] The result output module is communicatively connected to the data fusion module and is used to verify the initial fire detection result based on multiple locally processed data and the initial fire detection result to obtain the final fire detection result.

[0090] Example 3:

[0091] Based on Embodiment 1 or 2, this embodiment discloses an electronic device, which may be a smartphone, tablet computer, laptop computer, or desktop computer, etc. The electronic device may be referred to as a terminal, portable terminal, desktop terminal, etc. Figure 3 As shown, the electronic device includes:

[0092] Memory, used to store computer program instructions; and,

[0093] A processor is used to execute the computer program instructions to perform the operation of the factory fire detection method as described in any of Embodiment 1.

[0094] Specifically, processor 301 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 301 may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). Processor 301 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 301 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen.

[0095] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 302 are used to store at least one instruction, which is executed by the processor 301 to implement the factory fire detection method provided in Embodiment 1 of this application.

[0096] In some embodiments, the terminal may also optionally include a communication interface 303 and at least one peripheral device. The processor 301, memory 302, and communication interface 303 can be connected via a bus or signal line. Each peripheral device can be connected to the communication interface 303 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 304, a display screen 305, and a power supply 306.

[0097] The communication interface 303 can be used to connect at least one I / O (Input / Output) related peripheral device to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0098] The radio frequency (RF) circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 304 communicates with communication networks and other communication devices via electromagnetic signals.

[0099] Display screen 305 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof.

[0100] Power supply 306 is used to supply power to various components in electronic devices.

[0101] Example 4:

[0102] Based on any one of the embodiments 1 to 3, this embodiment discloses a computer-readable storage medium for storing computer-readable computer program instructions configured to perform operations as described in Embodiment 1 when executed.

[0103] Obviously, those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, the present invention is not limited to any particular hardware and software combination.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of detecting a fire in a plant, characterized by: The method comprises the following steps: receiving a plurality of fire detection signals sent by a plurality of sensors in a specified area in real time; wherein the plurality of sensors are of different types; respectively processing the plurality of fire detection signals to obtain a plurality of locally processed data; fusing the plurality of locally processed data to obtain an initial fire detection result; verifying the initial fire detection result according to the plurality of locally processed data and the initial fire detection result to obtain a final fire detection result; respectively processing the plurality of fire detection signals to obtain a plurality of locally processed data, comprising: obtaining a plurality of signal change amounts corresponding to the plurality of fire detection signals according to the plurality of fire detection signals and a plurality of previous fire detection signals corresponding to the plurality of fire detection signals; wherein the detection time of any previous fire detection signal corresponding to a fire detection signal is earlier than the detection time of the fire detection signal; calculating the membership degrees of the plurality of fire detection signals belonging to all preset fuzzy sets according to the plurality of signal change amounts, and dividing the plurality of fire detection signals into corresponding preset fuzzy sets according to the membership degrees, so as to realize the fuzzy processing of the plurality of fire detection signals; obtaining fuzzy rules of all preset fuzzy sets, and dividing the plurality of fire detection signals divided into the preset fuzzy sets according to the fuzzy degrees to obtain a plurality of fuzzy degrees corresponding to the plurality of fire detection signals; clearly processing the plurality of fire detection signals according to the plurality of fuzzy degrees to obtain a plurality of locally processed data corresponding to the plurality of fire detection signals; wherein the plurality of locally processed data are used to represent the fire occurrence probability corresponding to the plurality of fire detection signals; verifying the initial fire detection result according to the plurality of locally processed data and the initial fire detection result to obtain a final fire detection result, comprising: obtaining N previous locally processed data corresponding to the plurality of locally processed data; wherein N is a natural number greater than 1; respectively obtaining the detection differences between the plurality of locally processed data and the N previous locally processed data and the initial fire detection result; respectively obtaining the average values corresponding to the detection differences of the plurality of locally processed data and the N previous locally processed data; verifying the running states of the sensors corresponding to the plurality of locally processed data according to the average values corresponding to the detection differences of the plurality of locally processed data and the N previous locally processed data, if the running state of any sensor is abnormal, determining that the initial fire detection result is abnormal, and removing the locally processed data corresponding to the sensor from the plurality of locally processed data to obtain residual locally processed data, and then obtaining the final fire detection result according to the residual locally processed data, if the running states of all sensors are normal, determining that the initial fire detection result is normal, and taking the initial fire detection result as the final fire detection result.

2. The method of claim 1, wherein: The plurality of sensors comprise gas sensors, smoke sensors and flame sensors; correspondingly, the plurality of fire detection signals comprise gas detection signals, smoke detection signals and flame detection signals.

3. The method of claim 2, wherein: After receiving the plurality of fire detection signals sent by the plurality of sensors in the specified area, the method further comprises: The mean filtering method is used to pre-process the gas detection signal and the smoke detection signal in the fire detection signal, to obtain a pre-processed gas detection signal and a pre-processed smoke detection signal, so as to locally process the pre-processed gas detection signal and the pre-processed smoke detection signal. The delay filtering method is used to pre-process the flame detection signal in the fire detection signal, to obtain a pre-processed flame detection signal, so as to locally process the pre-processed flame detection signal.

4. The method of claim 3, wherein: The mean filtering method is used to pre-process the gas detection signal and the smoke detection signal in the fire detection signal, including: All gas detection signals and all smoke detection signals within a specified time length are obtained, and the mean value of all gas detection signals within the current specified time length and the mean value of all smoke detection signals are taken as the gas detection signal and the smoke detection signal at the current time; wherein the gas detection signal or the smoke detection signal at the current time is: In the formula, n0 is the sampling number of the gas detection signal or the smoke detection signal in the specified time length; d0(j) is the gas detection signal or the smoke detection signal of the jth sample in the n0 sampling number; i0 is the starting sampling point of the specified time length interval.

5. The method of claim 1, wherein: When the multiple fire detection signals are locally processed respectively, the FNN neural network is used to realize; wherein the FNN neural network includes an input layer, a fuzzification layer, a fuzzy inference layer and a defuzzification layer connected in turn; When the multiple locally processed data are fused, the PNN neural network is used to realize; wherein the PNN neural network includes an input layer, a mode layer, a summation layer and an output layer connected in turn.

6. A plant fire detection system characterized by: The plant fire detection method as claimed in any one of claims 1 to 5 is used to realize; The plant fire detection system includes: A signal receiving module is used to receive multiple fire detection signals sent by multiple sensors in a specified area in real time; wherein the types of multiple sensors are different; A local processing module is in communication connection with the signal receiving module, and is used to locally process multiple fire detection signals respectively to obtain multiple locally processed data; A data fusion module is in communication connection with the local processing module, and is used to fuse multiple locally processed data to obtain an initial fire detection result; A result output module is in communication connection with the data fusion module, and is used to verify the initial fire detection result according to multiple locally processed data and the initial fire detection result, to obtain a final fire detection result.

7. An electronic device, comprising: including: A memory is used to store computer program instructions; and A processor is used to execute the computer program instructions to complete the operation of the plant fire detection method as claimed in any one of claims 1 to 5.

8. A computer readable storage medium for storing computer readable computer program instructions, characterized in that: The computer program instructions are configured to execute the operation of the plant fire detection method as claimed in any one of claims 1 to 5 when running.

Images