Underground Pipe Gallery Warehouse Section Fire Early Warning Analysis Method and System

Abstract

The present invention relates to the field of data processing technology, and in particular to a fire warning analysis method and system for underground pipe gallery sections, the method comprising the following steps: S10, receiving temperature data collected in real time by temperature sensors respectively arranged at each measurement and control node, and drawing a temperature-distance gradient curve in the section with the temperature data as the ordinate and the distance between the temperature sensor and the wellhead as the abscissa; S20, searching for abnormally high temperature values ​​from the temperature-distance gradient curve in the section, and issuing a fire warning signal when the abnormally high temperature value reaches a set threshold. The present invention arranges a temperature sensor array in the section, collects temperature data using the temperature sensor, and analyzes the temperature data to find abnormally high temperature values. Abnormally high temperature conditions will inevitably exist on the eve of a fire, so a fire warning can be made in advance through the present invention.

Description

Technical Field

[0001] The present invention relates to the technical field of fire monitoring, and particularly to a method and system for fire early warning analysis of an underground pipe gallery bin section. Background Art

[0002] The construction of underground pipe galleries is one of the key projects in the infrastructure construction of smart cities. In urban underground pipe galleries, various pipelines such as urban water supply, drainage, gas, heat, electricity, communication, radio and television, and industry are laid. The most feared thing in underground pipe galleries is fire. At present, domestic and foreign urban underground pipe galleries are cut into different bin sections by fire doors, and a measurement and control Internet of Things is installed in each bin section. Commonly used ModBus bus protocol with RS-485 interface, ZigBee wireless transmission protocol, ring optical fiber, and 4G technology, etc. are used to build the Internet of Things network inside the pipe gallery. The latest is to adopt a highly reliable CAN Internet of Things.

[0003] For the internal fire prevention of the pipe gallery, it is mainly controlled from the material, requiring the use of fireproof and non-flammable materials, and configuring fire alarms and conducting environmental monitoring. The fire alarms are mainly smoke alarms, and the environmental monitoring is mainly the monitoring of temperature, combustible gas, oxygen, etc. In addition, there is also image monitoring by video cameras. Such measures have certain prevention and control means, but the effect is not ideal. Because the sensitivity of the smoke alarm is low, it can only be used for fire alarm, but not for fire early warning. When the fire is detected by image monitoring, it is basically a large fire and open flame. Moreover, once the smoke rises, it is impossible to distinguish the specific situation of the fire clearly. The environmental monitoring of combustible gas, temperature, and oxygen only provides the monitoring data after the fire occurs, and cannot give an early warning. This traditional Internet of Things smoke alarm and environmental detection method is effective for the fire judgment and control after the fire occurs, belonging to after-the-fact alarm, but it cannot give an early warning before the event. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for fire early warning analysis of an underground pipe gallery bin section, which can give an early warning before the fire occurs.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] In the first aspect, the present invention provides a method for fire early warning analysis of an underground pipe gallery bin section, including the following steps:

[0007] S10, receiving the temperature data collected in real time by temperature sensors respectively arranged at each measurement and control node, and taking the temperature data as the ordinate and the distance between the temperature sensor and the wellhead as the abscissa to draw a temperature-distance gradient curve in the bin section;

[0008] S20. Search for abnormally high temperature values from the temperature-distance gradient curve within the cabin section, and send a fire warning signal when the abnormally high temperature value reaches a set threshold.

[0009] In the above solution, by arranging a temperature sensor array within the cabin section, temperature data is collected using the temperature sensors, and through analysis of the temperature data, abnormally high temperature values can be discovered. There will inevitably be abnormally high temperature situations on the verge of a fire. Therefore, through the present invention, fire warnings can be given in advance.

[0010] Further optimized, in S20, the process of searching for abnormally high temperature values from the temperature-distance gradient curve within the cabin section includes: performing N times of signal superposition processing based on the temperature-distance gradient curve within the cabin section, and then performing quadratic polynomial weighted moving smoothing processing on the curve obtained after the processing, and searching for abnormally high temperature values from the curve obtained after the smoothing processing.

[0011] In the above solution, by performing N times of signal superposition on the collected temperature data, when there are abnormally high temperature values, even if the deviation amount compared to the average temperature is very weak and not easily detectable, it can be amplified by N times after N times of superposition, and then it is easily detectable. That is to say, even the temperature data collected by temperature sensors with low precision can identify abnormally high temperature values after being processed by the above solution. Therefore, the cost of temperature sensors can be greatly reduced by adopting the above solution.

[0012] As an example of an implementable method, in S20, performing N times of signal superposition processing based on the temperature-distance gradient curve within the cabin section includes: for each temperature sensor, superimposing the temperature data collected N times by it. When there are abnormally high temperature values, the peak value of the deviation amount is △T = ∑△T i = ∑T i - NA, where △T i represents the temperature deviation value, T i represents the i-th measurement value of the temperature sensor, and A represents the average temperature.

[0013] As an example of an implementable method, in S20, performing quadratic polynomial weighted moving smoothing processing on the curve obtained after the processing includes:

[0014] Taking the j-th data point as the center point, with the data range length being m, selecting a total of 2m + 1 data points before and after the j-th data point, performing quadratic polynomial fitting on these 2m + 1 data points, and taking the calculated value as the smoothed data point;

[0015] Starting from the j ± k points, repeat the above steps in sequence to perform smoothing processing on 2m + 1 data points, where 1 ≤ k ≤ m.

[0016] Further optimized, after step S20, step S30 is further included, continuously receiving the temperature data collected by the temperature sensor, and plotting the temperature gradient-time curve in the bin section at different time points in the same curve graph, where the abscissa is the distance between the temperature sensor and the wellhead, and the ordinate is the temperature data collected by the temperature sensor in real time.

[0017] In the above solution, after the fire warning, the temperature data is continuously monitored, and the temperature gradient-time curve in the bin section at different time points is plotted. More fire information can be obtained by observing the curve, and thus more data support can be provided for the fire treatment measures.

[0018] In a second aspect, the present invention provides an underground pipe gallery bin section fire warning analysis system, including an underground pipe gallery industrial Internet control center, a co-fusion core controller, and measurement and control nodes. The underground pipe gallery industrial Internet control center is connected to the co-fusion core controller. The co-fusion core controller and the measurement and control nodes are arranged in each working bin section of the underground pipe gallery at a set distance. And one working bin section includes several measurement and control nodes, and one measurement and control node is installed with a temperature sensor; the temperature data collected by the temperature sensor in real time is transmitted to the co-fusion core controller. The temperature data of the co-fusion core controller is used as the ordinate, and the distance between the temperature sensor and the wellhead is used as the abscissa to plot the temperature-distance gradient curve in the bin section, and search for abnormally high temperature values from the temperature-distance gradient curve in the bin section, and send a fire warning signal when the abnormally high temperature value reaches a set threshold.

[0019] In a further optimized solution, when the co-fusion core controller performs the operation of searching for abnormally high temperature values from the temperature-distance gradient curve in the bin section, it first performs N times of signal superposition processing based on the temperature-distance gradient curve in the bin section, and then performs quadratic polynomial weighted moving smoothing processing on the processed curve, and searches for abnormally high temperature values from the curve obtained after the smoothing processing.

[0020] In a third aspect, the present invention provides a computer program product, including computer-readable instructions, characterized in that the computer-readable instructions, when executed by a processor, implement the steps in the underground pipe gallery bin section fire warning analysis method of the present invention.

[0021] In a fourth aspect, the present invention provides a computer-readable storage medium including computer-readable instructions, characterized in that the computer-readable instructions, when executed by a processor, implement the steps in the underground pipe gallery bin section fire warning analysis method of the present invention.

[0022] In a fifth aspect, the present invention provides an electronic device, including: a memory for storing program instructions; a processor connected to the memory for executing the program instructions in the memory to implement the steps in the underground pipe gallery bin section fire warning analysis method of the present invention.

[0023] Compared with the prior art, the present invention has the following technical advantages:

[0024] 1. Increased reliability: Changing from the data alarm of several traditional monitoring points to the big data AI analysis of a large number of temperature sensors in the blind area of a several-hundred-meter-long underground silo section (which can independently process and analyze the acquired data to obtain the temperature gradient-time curve, so as to conduct fire early warning and alarm), greatly improves the reliability of fire early warning and fire alarm information.

[0025] 2. Improved safety: The underground silo section is in a closed state. During a fire, lack of oxygen will cause smoke to fill the air, and at this time, the video fire monitoring will completely fail. However, this method can still work normally and has the function of safely providing fire data.

[0026] 3. Enhanced effectiveness: Utilizing the big data AI analysis of an array composed of a large number of temperature sensors to extract useful small signals with high temperature from the clutter error interference, so as to conduct fire early warning. Through the analysis of the temperature-distance gradient curve form and data at different time sections, a large amount of information such as the ignition point, fire movement, and fire development trend can be effectively obtained.

[0027] 4. Better economy: Using inexpensive temperature sensors can achieve the discovery of abnormal high temperature values. Compared with using expensive temperature sensors or infrared imaging monitoring, it has better cost performance and economic practicality.

[0028] For other advantages of the present invention, please refer to the relevant descriptions in the embodiment part. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0030] Figure 1 It is a flowchart of the fire early warning analysis method for the underground pipe gallery silo section in the embodiment of the present invention.

[0031] Figure 2 It is an example temperature-distance gradient curve graph.

[0032] Figure 3 It is an example temperature-distance gradient curve graph obtained after signal superposition and curve smoothing processing.

[0033] Figure 4 It is an example temperature gradient-time curve graph.

[0034] Figure 5 It is a block diagram of the composition of an electronic device. Specific implementation manner

[0035] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0036] An underground pipe gallery compartment fire warning analysis system involved in this embodiment includes an underground pipe gallery industrial Internet control center, a co-fusion core controller, and measurement and control nodes. The co-fusion core controller performs underground pipe gallery compartment fire warning analysis. The underground pipe gallery industrial Internet control center is connected to the co-fusion core controller. The co-fusion core controller and the measurement and control nodes are arranged in each working compartment of the underground pipe gallery. And one working compartment includes several measurement and control nodes. The co-fusion core controller serves as the measurement and control center of each working compartment respectively, and is connected to the measurement and control nodes in the working compartment where the co-fusion core controller is located through a CAN bus. The measurement and control nodes are used to connect the measurement and control equipment in the underground pipe gallery. One measurement and control node is arranged every 10 m along the pipe gallery according to the geographical coordinates. The measurement and control equipment includes temperature and humidity sensors, infrared sensors, liquid level sensors, oxygen sensors, combustible gas sensors, etc. The measurement and control nodes and the measurement and control equipment can be respectively connected through a sensing module MCU, so as to further control devices such as lighting, manhole covers, pump machines, and fans through the sensing module MCU. For a more specific description, reference can be made to the Chinese utility model patent "Underground Pipe Gallery Safety Positioning and Monitoring System Based on CAN Bus" with the publication number CN215067841U.

[0037] Based on the system structure, it further includes a temperature sensor array. On the CAN Internet of Things in the pipe gallery compartment, one temperature sensor is installed on one measurement and control node, that is, one temperature sensor is installed every 10 meters in a superimposed manner to form a linear temperature monitoring array in the compartment. Since the position of the temperature sensor is determined, the position of the temperature sensor from the wellhead is also determined. This temperature sensor is an inexpensive temperature sensor with an accuracy of 0.1 °C and a measurement range in the room temperature range. The underground pipe gallery is usually a pipe in a closed state underground. Each pipe is separated by a firewall into approximate airtight compartments. The temperature sensor array can monitor the temperature at each point in a compartment hundreds of meters long without blind spots.

[0038] Please refer to Figure 1 , the underground pipe gallery compartment fire warning analysis method provided in this embodiment includes the following steps:

[0039] S10, taking the temperature data collected in real time by each temperature sensor as the ordinate and the distance between the temperature sensor and the wellhead as the abscissa, draw a temperature-distance gradient curve in the compartment.

[0040] for reference Figure 2 , due to systematic errors, random errors, and the consistency issues of dozens of temperature sensors, when the temperature coordinate scale is relatively large, the temperature-distance gradient curve is serrated. Figure 2 The red serrated line in Figure 2 is the measured curve. However, since the pipe gallery is several meters underground and partitioned by fire doors, the interior of the compartment is not affected by the external weather. Although the temperature-distance gradient curve is microscopically serrated, the average temperature is basically a straight line, representing the temperature baseline in this compartment, as shown by the blue solid line in

[0041] S20, based on the temperature-distance gradient curve in the compartment, perform signal superposition processing and polynomial smoothing processing, search for abnormally high temperature values, and issue a fire warning signal when the abnormally high temperature value reaches a set threshold.

[0042] Fire warning is to detect abnormally high temperature values as early as possible. And abnormally high temperature values are weak signals. To measure weak abnormally high temperatures, high-sensitivity temperature sensors can be used, but the cost is too high. That is to say, if high-sensitivity temperature sensors are used, abnormally high temperature values can be directly searched from the temperature-distance gradient curve in the compartment, but the cost of high-sensitivity temperature sensors is too high. Therefore, more preferably, in this embodiment, by combining signal superposition processing and polynomial smoothing processing, the abnormally high temperature values hidden in the measurement errors can be found, and then there is no need to use high-sensitivity temperature sensors, thereby reducing costs.

[0043] More specifically, first use the signal superposition method to process the actual measurement data of the temperature sensors, that is, after superimposing the data collected N times, then draw the temperature-distance gradient curve, and then use the curve smoothing method to smooth the temperature-distance gradient curve.

[0044] Here, the signal superposition method is to superimpose the N measurement values of each temperature sensor. When there are abnormally high temperature values, the abnormally high amount can be enlarged by N times, and then it is easy to be detected. The value of N is affected by measurement accuracy requirements, signal stability, and measurement efficiency. To use a more appropriate N value, it is preferably to conduct some experiments before actual measurement, observe the influence of different superposition times on the results, so as to determine the appropriate superposition times. At the same time, dynamic adjustment can be made according to the actual situation to achieve better measurement accuracy and efficiency.

[0045] Define the \(i\)-th measurement value of each temperature sensor as \(T_i = A+\Delta T_i\pm\sigma_i\). Then, after \(N\) superpositions, we have \(\sum_{i = 1}^{N}T_i=\sum_{i = 1}^{N}(A + \Delta T_i\pm\sigma_i)\). Here, \(T_i\) represents the \(i\)-th measurement value of the temperature sensor, \(A\) represents the average temperature of \(N\) measurements, \(\Delta T_i\) represents the high temperature deviation value, and \(\sigma_i\) represents the random error of the temperature sensor measurement. Random error is the error caused by some uncontrollable random factors during the measurement process, such as changes in environmental conditions, instability of instruments, etc. Random error is unpredictable and is manifested as random fluctuations of the measurement results around the true value. Since \(\sigma_i\) is randomly positive or negative, that is, it may be positive in this measurement and negative in the next measurement, it can be mutually offset after \(N\) iterations. Therefore, we have \(\sum_{i = 1}^{N}T_i = NA+\sum_{i = 1}^{N}(\Delta T_i)\). Therefore, when the temperature is not abnormally high, \(\sum_{i = 1}^{N}T_i = NA\); when the temperature has an abnormally high value, the peak value of the high deviation is \(\Delta T=\sum_{i = 1}^{N}\Delta T_i=\sum_{i = 1}^{N}T_i - NA\), that is, the abnormally high amount is almost enlarged by \(N\) times, so it is easy to be detected.

[0046] System error is the error caused by some inherent and determinable factors during the measurement process, such as the measurement error of the instrument itself, the limitations of the measurement method, etc. System error can be predicted and corrected. System error can be eliminated or reduced through calibration and correction, but it cannot be eliminated by repeated measurement.

[0047] After signal superposition processing, the useful signal can be enhanced and the random error can be reduced or even eliminated, making the abnormally high amount enlarged by \(N\) times and thus easy to be detected. In this embodiment, in order to further reduce the random error and system error and make the abnormal values in the curve more prominent, the curve obtained after superposition processing is also subjected to curve smoothing processing. The combination of signal superposition and curve smoothing processing can better eliminate the influence brought by the error.

[0048] For the curve smoothing method, here the quadratic polynomial weighted moving smoothing method is used to smooth the temperature-distance gradient measurement curve after \(N\) times of signal superposition processing. Specifically, the \(j\)-th data point is selected as the center point, and the data range length is \(m\). By selecting the data points within the data range length (including the \(j\)-th data point and its front and back data points), a total of \(2m + 1\) data points are obtained. Perform quadratic polynomial fitting on these \(2m+1\) data points (the quadratic polynomial fitting formula is: \(y = ax\) 2+(bx + c), and use the calculated value as the smoothed data point. Starting from the points j ± k (1 ≤ k ≤ m), repeat the above steps in sequence to smooth 2m + 1 data points. Among them, the least squares method is used to fit the quadratic polynomial to obtain the coefficients a, b, and c of the fitting curve (when calculating the coefficients of the fitting curve, the weighted least squares method is used to assign different weights to each data point to reflect its importance in the fitting curve. Generally speaking, the data points closer to the current data point have larger weights, and the data points farther away have smaller weights).

[0049] The curve smoothing method can effectively eliminate the systematic errors of different temperature sensors. For the systematic errors with an average value of zero for different temperature sensors, the more smoothing points (M = 2m + 1), the better the error suppression effect (its variance is reduced by M times); however, increasing M will cause distortion of the useful signal, especially the peak part of the high-frequency component of the useful signal. For the selection of the smoothing point number M, the following aspects can be considered:

[0050] 1) Periodicity of data: If the data has obvious periodicity, then select the smoothing point number corresponding to the data period to ensure capturing the periodic changes. 2) Purpose of smoothing: If you want to smooth the noise in the data, then select a larger smoothing point number; if you want to retain the detailed information of the data, then select a smaller smoothing point number. 3) Change speed of data: If the data changes rapidly, then select a larger smoothing point number to smooth the data to reduce the impact of mutations; conversely, if the data changes slowly, then select a smaller smoothing point number.

[0051] The quadratic polynomial weighted moving smoothing algorithm is a weighted function calculated by the measured values of 2m + 1 data points centered on the data point j according to the polynomial formula to obtain the smoothed value of the data point j. Table 1 shows the quadratic polynomial weighted coefficients and cubic polynomial weighted coefficients obtained by Savitzky and Golay using the least squares method.

[0052] Table 1: Quadratic and Cubic Polynomial Weighted Coefficients

[0053]

[0054]

[0055] Table 1 shows the weighted coefficients of some discrete points at a distance from the center point 0 obtained through a large amount of data analysis. These weighted coefficients are affected by factors such as the actual environment and need to be analyzed specifically for specific situations. Moreover, the specific formula for obtaining the smoothed data point is as follows: In the formula, W(k) is the weighted function, W is the sum of the weighted coefficients, X(k) is the actual measured value at the kth point, and Y(j) is the smoothed value at the jth point.

[0056] The quadratic polynomial weighted moving smoothing method described in this article combines the moving smoothing method and the polynomial smoothing method. In the moving smoothing method, the data at each point (j) is obtained by weighting the data of several adjacent points (2m + 1 points). The weighting function usually uses a simple rectangular function or a triangular function. The polynomial smoothing method calculates the weighting function according to the polynomial formula using the measured values of 2m + 1 points centered on j, and obtains the smoothed value at point j. Table 1 shows the weighting coefficients required for the polynomial smoothing algorithm. The numbers 15, 13, 11, 9, 7, 5 in the first row of Table 1 all represent the value of the smoothing point M (2m + 1).

[0057] Figure 3 It is the temperature-distance gradient curve graph in the bin section for example. The black serrated line is the connection of the actual measured values of the temperature sensors at each measurement and control node. The red thin curve is the bin section fire warning curve obtained by using the signal superposition method and the curve smoothing method to eliminate the measurement random error of each measurement and control node and the system error of each temperature sensor when there is a fire warning. Figure 3 A thick red straight line is also given in it. This thick red straight line represents that when there is no fire, the measured curve after smoothing is a straight line with basically constant temperature.

[0058] When there is a fire warning, the red thin curve is not a straight line. As Figure 3 shown, it reflects that the temperature of the measurement and control node L1 is higher than the normal value, so it indicates that there is a hidden danger at the measurement and control node L1, and a fire warning can be issued to start the fire warning plan. In order to ensure the timeliness of the fire warning, as long as it is higher than the normal value in the curve, a fire warning is issued.

[0059] S30. Draw the temperature gradient-time curve in the bin section at different time points in the same curve graph. The abscissa is the distance between the temperature sensor and the wellhead, and the ordinate is the temperature data collected by the temperature sensor in real time.

[0060] After processing and analyzing the data values collected by the temperature sensor through steps S10 - S20, a fire warning can be realized. After the warning, the temperature change can be continuously observed. If the temperature continues to increase and reaches an abnormal value (for example, if the smoothed temperature curve is significantly higher than the normal value by more than 10°C after data processing, it is regarded as an abnormal value), a fire temperature alarm is issued at this time. Because the fire signal is already a strong signal at this time, there is no need to perform the aforementioned weak signal processing, and the temperature gradient-time curve graph is directly drawn to provide data for fire analysis.

[0061] The temperature gradient-time curve graph is as Figure 4 shown. The abscissa is the distance from the wellhead, the ordinate is the temperature, and the time gradient in the bin section at different time periods is drawn on the graph. Figure 4In the figure, the blue curve is the fire warning curve. At 10 o'clock, a temperature anomaly was found at L1 in the warehouse section, and a fire warning was issued. At 12:30, a fire alarm sounded at L1. The fire gradient curve is asymmetric. The negative temperature gradient of the warehouse section is large, and the fire did not develop negatively in the warehouse section; the positive temperature gradient of the warehouse section is small, and the fire developed positively in the warehouse section. At 12:32, the fire temperature gradient curve is purple. At LI, the temperature gradient slows down and the temperature value decreases, indicating that the fire at L1 is being extinguished and getting smaller. A new temperature anomaly appears at L2 in the warehouse section, which is suspected to be a new fire point. However, the positive temperature gradient of L2 is large, and it seems that the fire did not continue to develop positively in the warehouse section. This provides a lot of useful information for fire alarm analysis and processing when the video surveillance fails in the underground warehouse section filled with smoke.

[0062] like Figure 5 As shown, this embodiment also provides an electronic device, which may include a processor 41 and a memory 42, wherein the memory 42 is coupled to the processor 41. It is worth noting that this figure is exemplary, and other types of structures may be used to supplement or replace this structure to achieve data extraction, report generation, communication or other functions.

[0063] like Figure 5 As shown, the electronic device may further include: an input unit 43, a display unit 44 and a power supply 45. It is worth noting that the electronic device does not necessarily have to include Figure 5 In addition, electronic devices may also include Figure 5 For components not shown, reference may be made to the prior art.

[0064] The processor 41 is sometimes also called a controller or an operation control, and may include a microprocessor or other processor devices and / or logic devices. The processor 41 receives inputs and controls the operations of various components of the electronic device.

[0065] The memory 42 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices, and may store information such as configuration information of the processor 41 and instructions executed by the processor 41. The processor 41 may execute the program stored in the memory 42 to implement information storage or processing. In one embodiment, the memory 42 also includes a buffer memory, i.e., a buffer, to store intermediate information.

[0066] An embodiment of the present invention further provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed in an electronic device, the program product enables the electronic device to execute the operation steps included in the method of the present invention.

[0067] An embodiment of the present invention also provides a storage medium storing computer-readable instructions, and the computer-readable instructions enable an electronic device to execute the operation steps included in the method of the present invention.

[0068] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0069] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0070] The above-described embodiments are only specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications, substitutions, and improvements, etc. These modifications, substitutions, and improvements should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A fire early warning analysis method for underground pipe gallery section, characterized in that: The following steps are involved: S10, receiving temperature data collected in real time by temperature sensors respectively arranged at each measurement and control node, and drawing a temperature-distance gradient curve in the compartment with the temperature data as the ordinate and the distance between the temperature sensor and the wellhead as the abscissa; S20, searching for an abnormally high temperature value from the temperature-distance gradient curve in the compartment, and issuing a fire warning signal when the abnormally high temperature value reaches a set threshold; The process of searching for abnormally high temperature values ​​from the temperature-distance gradient curve in the cabin section comprises: performing N times of signal superposition processing based on the temperature-distance gradient curve in the cabin section, and then performing quadratic polynomial weighted moving smoothing processing on the processed curve, and searching for abnormally high temperature values ​​from the smoothed curve; Based on the temperature-distance gradient curve in the cabin, N signal superposition processing is performed, including: conducting an experiment before actual measurement to observe the influence of different superposition times on the result, so as to determine the value of N; for each temperature sensor, superimposing the temperature data collected N times, when there is an abnormally high temperature value, the peak value of the high value is △T=∑△Ti=∑Ti-NA, △Ti represents the high temperature value, Ti represents the i-th measurement value of the temperature sensor, and A represents the average temperature value; The processed curve is subjected to quadratic polynomial weighted moving smoothing processing, including: Take the jth data point as the center point, the data range length is m, select 2m+1 data points before and after the jth data point, perform quadratic polynomial fitting on these 2m+1 data points, and use the calculated value as the smoothed data point; Starting from point j±k, repeat the above steps in sequence to smooth 2m+1 data points, 1≤k≤m; the specific formula of the smoothed data point is: Where W(k) is the weighted function, W is the sum of weighted coefficients, X(k) is the actual measured value at point k, and Y(j) is the smoothed value at point j.

2. The underground pipe gallery section fire early warning analysis method according to claim 1 is characterized in that: After step S20, the method also includes S30, which continues to receive the temperature data collected by the temperature sensor, and draws the temperature gradient-time curve in the bin segment at different time points in the same graph, where the horizontal axis is the distance between the temperature sensor and the wellhead, and the vertical axis is the temperature data collected by the temperature sensor in real time.

3. An underground pipe gallery section fire early warning analysis system, characterized in that: It includes an underground pipe gallery industrial Internet control center, a symbiotic core controller and measurement and control nodes. The underground pipe gallery industrial Internet control center is connected to the symbiotic core controller. The symbiotic core controller and the measurement and control nodes are arranged in each working compartment of the underground pipe gallery according to a set distance, and one working compartment includes several measurement and control nodes. One measurement and control node is equipped with a temperature sensor. The temperature data collected by the temperature sensor in real time is transmitted to the symbiotic core controller. The temperature data of the symbiotic core controller is the ordinate, and the distance between the temperature sensor and the wellhead is the abscissa. The temperature-distance gradient curve in the compartment is drawn, and the abnormally high temperature value is searched from the temperature-distance gradient curve in the compartment, and a fire warning signal is issued when the abnormally high temperature value reaches the set threshold. When the symbiotic core controller performs the operation of searching for abnormally high temperature values ​​from the temperature-distance gradient curve in the compartment, it first performs N signal superposition processing based on the temperature-distance gradient curve in the compartment, and then performs quadratic polynomial weighted moving smoothing processing on the processed curve, and searches for abnormally high temperature values ​​from the smoothed curve; Based on the temperature-distance gradient curve in the cabin, N signal superposition processing is performed, including: conducting an experiment before actual measurement to observe the influence of different superposition times on the result, so as to determine the value of N; for each temperature sensor, superimposing the temperature data collected N times, when there is an abnormally high temperature value, the peak value of the high value is △T=∑△Ti=∑Ti-NA, △Ti represents the high temperature value, Ti represents the i-th measurement value of the temperature sensor, and A represents the average temperature value; The processed curve is subjected to quadratic polynomial weighted moving smoothing, including: taking the jth data point as the center point, the data range length is m, selecting a total of 2m+1 data points before and after the jth data point, performing quadratic polynomial fitting on these 2m+1 data points, and taking the calculated value as the smoothed data point; starting from the j±k point, repeating the above steps in sequence, smoothing the 2m+1 data points, 1≤k≤m; the specific formula of the smoothed data point is: Where W(k) is the weighted function, W is the sum of weighted coefficients, X(k) is the actual measured value at point k, and Y(j) is the smoothed value at point j.

4. A computer program product comprising computer readable instructions, characterized in that: When executed by a processor, the computer-readable instructions implement the steps in the underground pipe gallery section fire warning analysis method described in any one of claims 1-2.

5. A computer-readable storage medium comprising computer-readable instructions, characterized in that: When executed by a processor, the computer-readable instructions implement the steps in the underground pipe gallery section fire warning analysis method described in any one of claims 1-2.

6. An electronic device, characterized in that: include: Memory, which stores program instructions; A processor is connected to the memory and executes program instructions in the memory to implement the steps in the underground pipe gallery section fire warning analysis method described in any one of claims 1-2.

Images