A method and system for improving the alarm uniformity of a rate-of-rise fire detector

Abstract

This application discloses a method and system for improving the alarm uniformity of heat-sensitive fire detectors, relating to the field of heat-sensitive detector control technology. It solves the technical problem that existing differential temperature alarm methods have poor adaptability, leading to poor fire detection and prevention effects. The method includes the following steps: Step 1: Acquire several nearby temperature detection values ​​from the temperature detection device; Step 2: Acquire a set short-term differential temperature discrimination period, acquire the detection area characteristics corresponding to the detection area, and generate a long-term differential temperature discrimination period based on the detection area characteristics; Step 3: Generate a short-term temperature difference value based on the short-term differential temperature discrimination period and the temperature detection values; generate a long-term temperature difference value based on the long-term differential temperature discrimination period and the temperature detection values; Step 4: Select a temperature warning value based on the short-term and long-term temperature difference values; Step 5: Acquire the current temperature detection value from the temperature detection device, and generate an alarm signal based on the current temperature detection value and the temperature warning value; thereby improving the effectiveness of fire detection and prevention.

Description

Technical Field

[0001] This application belongs to the field of heat detector control technology, specifically a method and system for improving the alarm uniformity of heat fire detectors. Background Technology

[0002] In automatic fire alarm systems, heat detectors are common fire triggering devices. The basic principle of a heat detector is that when a substance burns and releases a large amount of heat, the ambient temperature rises rapidly. The thermistor in the heat detector is highly sensitive to temperature changes; this physical change is processed by a microcontroller, generating an electrical signal and triggering an alarm. Heat detectors are mainly divided into two types: fixed-temperature alarm detectors and differential-temperature alarm detectors. Fixed-temperature alarm detectors activate when the temperature rises to a set value. Differential-temperature alarm detectors can also activate when the rate of temperature increase reaches a set value, even before the temperature reaches the set value.

[0003] Currently, heat detectors mainly use differential temperature alarms, which can promptly alert the system in cases of rapid temperature increases. However, this alarm mode can only detect rapid temperature rises. In cases of slow temperature increases, the short-cycle temperature difference may not trigger an alarm, resulting in delayed alerts and missed opportunities for optimal rescue, leading to poor fire monitoring and prevention effectiveness. Therefore, a method and system to improve the alarm uniformity of heat detectors is needed. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art; to this end, this application proposes a method and system for improving the alarm uniformity of heat-sensitive fire detectors, in order to solve the technical problem that the existing differential temperature alarm methods have poor adaptability, resulting in poor fire detection and prevention effects.

[0005] To achieve the above objectives, the first aspect of this application provides a method for improving the alarm uniformity of a heat-sensitive fire detector, comprising the following steps:

[0006] Step 1: Obtain several nearby temperature readings from the temperature detection device;

[0007] Step 2: Obtain the set short period for temperature difference discrimination, obtain the detection area features corresponding to the detection area, and generate a long period for temperature difference discrimination based on the detection area features;

[0008] Step 3: Generate short-cycle temperature difference value based on the temperature difference and the short-cycle temperature detection value; generate long-cycle temperature difference value based on the temperature difference and the long-cycle temperature detection value.

[0009] Step 4: Select the temperature warning value based on the short-cycle temperature difference value and the long-cycle temperature difference value;

[0010] Step 5: Obtain the current temperature detection value from the temperature detection device, and generate an alarm signal based on the current temperature detection value and the temperature warning value.

[0011] This application obtains the characteristics of the detection area corresponding to the set short-term temperature difference discrimination period, and generates a long-term temperature difference discrimination period based on the detection area characteristics; it generates a short-term temperature difference value based on the short-term temperature difference discrimination period and the temperature detection value; it generates a long-term temperature difference value based on the long-term temperature difference discrimination period and the temperature detection value; it selects a temperature warning value based on the short-term temperature difference value and the long-term temperature difference value; it obtains the temperature detection value of the current temperature detection device, and generates an alarm signal based on the current temperature detection value and the temperature warning value; by generating the length of the long-term temperature difference discrimination period specifically according to the regional characteristics of the detection area, it effectively solves the problem of untimely alarms under slow temperature rise, and at the same time, by selecting a temperature warning value based on the short-term temperature difference value and the long-term temperature difference value, it reduces the probability of false alarms; thereby improving the effectiveness of fire detection and prevention.

[0012] Preferably, step three specifically includes the following steps:

[0013] S31: Obtain short-cycle differential temperature judgment;

[0014] S32: Obtain several temperature detection values ​​within the short period of differential temperature discrimination, and number the several temperature detection values ​​according to the acquisition time order, and combine them into a short period array for differential temperature discrimination;

[0015] S33: Record the difference between the last temperature detection value and the first temperature detection value in the short-cycle differential temperature discrimination array as the short-cycle temperature difference value;

[0016] S34: Obtain long-cycle differential temperature judgment;

[0017] S35: Obtain several temperature detection values ​​within the long period of differential temperature discrimination, and number the several temperature detection values ​​according to the acquisition time order, and combine them into a long period array for differential temperature discrimination;

[0018] S36: The difference between the last temperature detection value and the first temperature detection value in the long-period array of the differential temperature discrimination is recorded as the long-period temperature difference value.

[0019] Preferably, the step of generating a long-term temperature difference discrimination based on the characteristics of the detection area includes:

[0020] Regional structural features and stored item features are extracted from the features of the detection area. The regional structural features are then input into the transmission influence coefficient generation model to obtain the corresponding transmission influence coefficient. The transmission influence coefficient generation model is trained using an artificial intelligence model.

[0021] Extract the combustion heat release level and combustion rate score from the characteristics of stored items; generate the item influence coefficient based on the combustion heat release level and combustion rate score;

[0022] The temperature difference is used to determine the long-term effect based on the transmission influence coefficient and the item influence coefficient.

[0023] Preferably, the transmission influence coefficient generation model is obtained through training an artificial intelligence model, including:

[0024] Acquire structural feature data for several regions, along with their corresponding transmission influence coefficients. The transmission influence coefficients are the coefficients by which experts assess the impact of regional structures on hindering temperature transmission during combustion; the greater the obstruction to temperature transmission, the higher the corresponding transmission influence score. The structural feature data includes relevant data such as the material and location of structural components within the detection range of the temperature sensor.

[0025] Several regional structural feature data and transmission influence coefficients are integrated into training data and test data. The training data is used to train the artificial intelligence model, and the test data is used to test the trained artificial intelligence model. Finally, a transmission influence coefficient generation model is obtained, in which the input is regional structural feature data and the output is the corresponding transmission influence coefficient. The artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0026] Preferably, the step of generating an article impact coefficient based on the heat release level and combustion speed score includes:

[0027] The combustion release rate score is marked as RD; the combustion speed score is marked as SD; the combustion release rate score is a score of the combustion status of the item based on the heat released by combustion per unit weight of the item, and the combustion speed score is a score of the combustion status of the item based on the time required for combustion per unit volume of the item.

[0028] The corresponding item influence coefficient is calculated using the formula WY=α1×exp(-β1×RD)+α2×exp(-β2×SD); where α1 and α2 are proportional coefficients; and β1 and β2 are adjustment coefficients.

[0029] Preferably, the step of generating a long-term temperature difference determination based on the transmission influence coefficient and the item influence coefficient includes:

[0030] Obtain the transmission influence coefficient CY and the item influence coefficient WY;

[0031] The long-period proportional coefficient K is calculated using the formula K = γ1 × CY + γ2 × WY; where γ1 and γ2 are proportional coefficients used to limit the range of the long-period proportional coefficient K.

[0032] The long period for temperature difference discrimination is calculated using the formula CZQ=K×DZQ, where DZQ is the corresponding short period for temperature difference discrimination.

[0033] Preferably, the step of selecting the temperature warning value based on the short-cycle temperature difference value and the long-cycle temperature difference value includes:

[0034] S41: Obtain short-cycle temperature difference values ​​and long-cycle temperature difference values;

[0035] S42: When the short-cycle temperature difference value is greater than the set high-temperature short-cycle threshold; or, when the short-cycle temperature difference value is between the set low-temperature short-cycle threshold and the high-temperature short-cycle threshold, and the long-cycle temperature difference value is greater than the set high-temperature long-cycle threshold; set the temperature rise level to level one.

[0036] When the short-cycle temperature difference is between the set low-temperature short-cycle threshold and the high-temperature short-cycle threshold, and the long-cycle temperature difference is less than the set high-temperature long-cycle threshold; or when the short-cycle temperature difference is less than the set low-temperature short-cycle threshold, and the long-cycle temperature difference is greater than the low-temperature long-cycle threshold; the temperature level is set to level two.

[0037] When the short-cycle temperature difference is less than the set low-temperature short-cycle threshold and the long-cycle temperature difference is less than the low-temperature long-cycle threshold, the temperature rise level is set to level three; where the high-temperature long-cycle threshold is greater than the low-temperature long-cycle threshold and the high-temperature short-cycle threshold is greater than the low-temperature short-cycle threshold.

[0038] S43: When the temperature rise level is Level 1, set the temperature warning value to the high temperature rise warning threshold; when the temperature rise level is Level 2, set the temperature warning value to the medium temperature rise warning threshold; when the temperature rise level is Level 3, set the temperature warning value to the low temperature rise warning threshold.

[0039] Preferably, generating an alarm signal based on the current temperature detection value and the temperature warning value includes:

[0040] Acquire the temperature detection value and determine whether the temperature detection value is greater than the temperature warning value;

[0041] If yes, a rapid fire warning signal is generated when the temperature warning value is at the high temperature rise warning threshold; otherwise, a regular fire warning signal is generated when the temperature warning value is at the medium temperature rise warning threshold; otherwise, a slow fire warning signal is generated when the temperature warning value is at the low temperature rise warning threshold.

[0042] No, no alarm signal is generated; proceed to step three. The alarm signals include rapid fire warning signals, conventional fire warning signals, and low-speed fire warning signals.

[0043] This system classifies fires in real time, allowing for priority handling of areas with higher alarm levels when multiple fires occur and firefighters are insufficient.

[0044] Another aspect of this application provides a system for improving the alarm uniformity of a heat-sensitive fire detector, comprising: a data acquisition module, a cycle setting module, a threshold generation module, an anomaly detection module, an alarm module, and a database;

[0045] The data acquisition module acquires temperature detection values ​​in the detection area in real time through a data acquisition device connected to it, the data acquisition device including a temperature detection device;

[0046] The cycle setting module: acquires the set short cycle for temperature difference discrimination and the characteristics of the detection area corresponding to the detection area, and generates a long cycle for temperature difference discrimination based on the characteristics of the detection area;

[0047] The threshold generation module selects a temperature warning value based on the short-cycle temperature difference value and the long-cycle temperature difference value.

[0048] The anomaly detection module: acquires the current temperature detection value of the temperature detection device, and generates an alarm signal based on the current temperature detection value and the temperature warning value;

[0049] The alarm module: triggers an alarm based on the alarm signal.

[0050] Compared with the prior art, the beneficial effects of this application are:

[0051] 1. This application obtains the characteristics of the detection area corresponding to the set temperature difference discrimination short cycle, generates a temperature difference discrimination long cycle based on the detection area characteristics, generates a short cycle temperature difference value based on the short cycle temperature difference discrimination short cycle and the temperature detection value, generates a long cycle temperature difference value based on the long cycle temperature difference discrimination long cycle and the temperature detection value, selects a temperature warning value based on the short cycle temperature difference value and the long cycle temperature difference value, obtains the temperature detection value of the current temperature detection device, and generates an alarm signal based on the current temperature detection value and the temperature warning value. By generating the length of the temperature difference discrimination long cycle specifically according to the regional characteristics of the detection area, it effectively solves the problem of untimely alarms under slow temperature rise, and at the same time, by selecting the temperature warning value through the short cycle temperature difference value and the long cycle temperature difference value, it reduces the probability of false alarms by the alarm; thereby improving the effect of fire detection and prevention. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic diagram of the method steps for the alarm equalization method in this application;

[0054] Figure 2 This is a flowchart illustrating the alarm balancing method in this application;

[0055] Figure 3 This is a schematic diagram of the alarm equalization system in this application. Detailed Implementation

[0056] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0057] Please see Figures 1-2 The first aspect of this application provides a method for improving the alarm uniformity of a heat-sensitive fire detector, comprising the following steps:

[0058] Step 1: Obtain several nearby temperature readings from the temperature detection device; the temperature readings are the values ​​detected by the temperature detection device; the temperature detection device includes a temperature sensor.

[0059] Step Two: Obtain the set short-term temperature difference discrimination period, which is a manually set detection period for rapidly heating fires; Obtain the detection area characteristics corresponding to the detection area, which are the regional characteristics of the area that the corresponding temperature detection device can detect, including the characteristics of the stored items in the area and the regional structural characteristics of the area, which need to be input in advance; for example, if the corresponding temperature detection device is installed in a warehouse with shelves and partitions for storing books or chemicals, its corresponding regional structural characteristics include the position, size, and material of the partitions in the detection area; the stored item characteristics are the relevant characteristics of books or chemicals; Generate the long-term temperature difference discrimination period based on the detection area characteristics; The long-term temperature discrimination period is the period for detecting slow-heating anomalies, and its specific setting is based on the characteristics of the stored items and the characteristics of the regional structure that affect heat transfer;

[0060] Step 3: Generate a short-cycle temperature difference value based on the short-cycle temperature difference judgment and the temperature detection value; the short-cycle temperature difference value is the temperature difference before and after the short-cycle temperature difference judgment. Generate a long-cycle temperature difference value based on the long-cycle temperature difference judgment and the temperature detection value; the long-cycle temperature difference value is the temperature difference before and after the long-cycle temperature difference judgment. The specific steps are as follows:

[0061] S31: Obtain short-cycle differential temperature judgment;

[0062] S32: Obtain several temperature detection values ​​within the short period of differential temperature discrimination, and number the several temperature detection values ​​according to the acquisition time order, and combine them into a short period array for differential temperature discrimination;

[0063] S33: Record the difference between the last temperature detection value and the first temperature detection value in the short-cycle differential temperature discrimination array as the short-cycle temperature difference value;

[0064] S34: Obtain long-cycle differential temperature judgment;

[0065] S35: Obtain several temperature detection values ​​within the long period of differential temperature discrimination, and number the several temperature detection values ​​according to the acquisition time order, and combine them into a long period array for differential temperature discrimination;

[0066] S36: The difference between the last temperature detection value and the first temperature detection value in the long-period array of the differential temperature discrimination is recorded as the long-period temperature difference value.

[0067] Step 4: Select the temperature warning value based on the short-cycle temperature difference value and the long-cycle temperature difference value; the temperature warning value is set according to the temperature rise in the short and long cycles. For example, when the temperature rises rapidly in the short cycle, setting an appropriate temperature warning value can not only provide timely alarm, but also reduce the probability of false alarms.

[0068] Step 5: Obtain the current temperature detection value from the temperature detection device, and generate an alarm signal based on the current temperature detection value and the temperature warning value.

[0069] This embodiment obtains the characteristics of the detection area corresponding to the set temperature difference discrimination short cycle, and generates a temperature difference discrimination long cycle based on the detection area characteristics; it generates a short cycle temperature difference value based on the short cycle temperature difference discrimination short cycle and the temperature detection value; it generates a long cycle temperature difference value based on the long cycle temperature difference discrimination long cycle and the temperature detection value; it selects a temperature warning value based on the short cycle temperature difference value and the long cycle temperature difference value; it obtains the temperature detection value of the current temperature detection device, and generates an alarm signal based on the current temperature detection value and the temperature warning value; by generating the length of the temperature difference discrimination long cycle specifically according to the regional characteristics of the detection area, it effectively solves the problem of untimely alarms under slow temperature rise, and at the same time, by selecting the temperature warning value by using the short cycle temperature difference value and the long cycle temperature difference value, it reduces the probability of false alarms; thereby improving the effectiveness of fire detection and prevention.

[0070] The method for generating a long-term temperature difference discrimination based on the characteristics of the detection area includes: extracting regional structural features and stored item features from the characteristics of the detection area, and inputting the regional structural features into the transmission influence coefficient generation model to obtain the corresponding transmission influence coefficient; the transmission influence coefficient generation model is obtained through training an artificial intelligence model.

[0071] Extract the combustion heat release level and combustion rate score from the characteristics of stored items; generate the item influence coefficient based on the combustion heat release level and combustion rate score;

[0072] The temperature difference is used to determine the long period based on the transmission influence coefficient and the item influence coefficient, including: obtaining the transmission influence coefficient CY and the item influence coefficient WY;

[0073] The long-period proportional coefficient K is calculated using the formula K = γ1 × CY + γ2 × WY; where γ1 and γ2 are proportional coefficients used to limit the range of the long-period proportional coefficient K so that K > 2.

[0074] The long period for temperature difference discrimination is calculated using the formula CZQ=K×DZQ, where DZQ is the corresponding short period for temperature difference discrimination.

[0075] This embodiment generates a long-term temperature difference discrimination period specifically by detecting the regional structural features and stored items in the detection area. This makes the long-term temperature difference discrimination period more adaptable to the current detection environment, thereby improving the accuracy of subsequent fire early warning.

[0076] The transmission influence coefficient generation model is obtained through training an artificial intelligence model, including: acquiring structural feature data of several regions and their corresponding transmission influence coefficients; the transmission influence coefficient is the influence coefficient of the regional structure on the obstruction of temperature transmission during combustion, based on experts' assessment. The greater the obstruction to temperature transmission, the greater the corresponding transmission influence score; for example, if structural objects such as walls are placed between the ignition point and the temperature detector within the detection range of the temperature detector, it will affect the speed at which the temperature at the ignition point propagates to the temperature detector; or, a digital twin model can be constructed to simulate the actual situation between the ignition point and the temperature detector, obtaining the temperature transmission time without the influence of regional structural features, and the temperature transmission time with various regional structural features, and using the ratio between the temperature transmission time with structural influence and the temperature transmission time without regional structural influence as the transmission influence coefficient; the structural feature data includes relevant data such as the material and location of structural components within the detection range of the temperature detector;

[0077] Several regional structural feature data and transmission influence coefficients are integrated into training data and test data. The training data is used to train the artificial intelligence model, and the test data is used to test the trained artificial intelligence model. Specifically, the regional structural features in the test data are input into the trained artificial intelligence model to obtain the corresponding transmission influence coefficient output. It is then determined whether the difference between the output transmission influence coefficient and the transmission influence coefficient recorded in the corresponding test data is within an acceptable range. If yes, the test data passes the test, and the next set of test data is used for testing; otherwise, the relevant parameters of the artificial intelligence model are adjusted, and the test data is used again for testing. This process continues until a set proportion of test data passes the test. Finally, a transmission influence coefficient generation model is obtained, which takes regional structural feature data as input and outputs the corresponding transmission influence coefficient. The artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0078] An item impact coefficient is generated based on the level of heat released during combustion and the rate of combustion, including:

[0079] The combustion release rate is marked as RD; the combustion speed is marked as SD; the combustion release rate is a score of the combustion of an item based on the amount of heat released per unit weight of the item. The higher the combustion release rate score, the more heat is released per unit weight; the combustion speed score is a score of the combustion of an item based on the time required for combustion per unit volume of the item. The higher the combustion speed score, the shorter the time required for combustion per unit volume.

[0080] The corresponding item influence coefficient is calculated using the formula WY=α1×exp(-β1×RD)+α2×exp(-β2×SD); where α1 and α2 are proportional coefficients used to set the range of the item influence coefficient to be the same as the range of the transmission influence coefficient; β1 and β2 are adjustment coefficients.

[0081] This embodiment calculates the required detection cycle for burning items in the detection environment using the above formula. The more heat generated by the burning items, the faster the burning speed, the faster the temperature in the detection area rises, and the shorter the time it takes for the temperature to reach the temperature threshold. To ensure the sensitivity of the fire alarm, the required detection cycle is smaller, and the corresponding item influence coefficient is set smaller. Conversely, the less heat generated by the burning items, the slower the burning speed, the slower the temperature in the detection area rises, and the longer the time it takes for the temperature to reach the temperature threshold. The required detection cycle is longer, and the corresponding item influence coefficient is set larger.

[0082] Temperature warning values ​​are selected based on short-cycle and long-cycle temperature difference values, including:

[0083] S41: Obtain short-cycle temperature difference values ​​and long-cycle temperature difference values;

[0084] S42: When the short-cycle temperature difference value is greater than the set high-temperature short-cycle threshold; or, when the short-cycle temperature difference value is between the set low-temperature short-cycle threshold and the high-temperature short-cycle threshold, and the long-cycle temperature difference value is greater than the set high-temperature long-cycle threshold; set the temperature rise level to level one.

[0085] When the short-cycle temperature difference is between the set low-temperature short-cycle threshold and the high-temperature short-cycle threshold, and the long-cycle temperature difference is less than the set high-temperature long-cycle threshold; or when the short-cycle temperature difference is less than the set low-temperature short-cycle threshold, and the long-cycle temperature difference is greater than the low-temperature long-cycle threshold; the temperature level is set to level two.

[0086] When the short-cycle temperature difference is less than the set low-temperature short-cycle threshold and the long-cycle temperature difference is less than the low-temperature long-cycle threshold, the temperature rise level is set to level three; where the high-temperature long-cycle threshold is greater than the low-temperature long-cycle threshold and the high-temperature short-cycle threshold is greater than the low-temperature short-cycle threshold.

[0087] S43: When the temperature rise level is Level 1, set the temperature warning value to the high temperature rise warning threshold; when the temperature rise level is Level 2, set the temperature warning value to the medium temperature rise warning threshold; when the temperature rise level is Level 3, set the temperature warning value to the low temperature rise warning threshold.

[0088] An alarm signal is generated based on the current temperature detection value and the temperature warning value, including: acquiring the temperature detection value and determining whether the temperature detection value is greater than the temperature warning value;

[0089] If yes, a rapid fire warning signal is generated when the temperature warning value is at the high temperature rise warning threshold; otherwise, a regular fire warning signal is generated when the temperature warning value is at the medium temperature rise warning threshold; otherwise, a slow fire warning signal is generated when the temperature warning value is at the low temperature rise warning threshold.

[0090] No, no alarm signal is generated; proceed to step three. The alarm signals include rapid fire warning signals, conventional fire warning signals, and low-speed fire warning signals.

[0091] This system classifies fires in real time, allowing for priority handling of areas with higher alarm levels when multiple fires occur and firefighters are insufficient.

[0092] Please see Figure 3 Another aspect of this application provides a system for improving the alarm uniformity of a heat-sensitive fire detector, comprising: a data acquisition module, a period setting module, a threshold generation module, an anomaly detection module, an alarm module, and a database;

[0093] Data acquisition module: acquires temperature detection values ​​in the detection area in real time through a data acquisition device connected to it, the data acquisition device including a temperature detection device;

[0094] Period setting module: acquires the set short period for temperature difference discrimination and the characteristics of the detection area corresponding to the detection area, and generates a long period for temperature difference discrimination based on the characteristics of the detection area;

[0095] Threshold generation module: Selects temperature warning values ​​based on short-cycle and long-cycle temperature difference values;

[0096] Anomaly detection module: acquires the current temperature detection value of the temperature detection device, and generates an alarm signal based on the current temperature detection value and the temperature warning value;

[0097] Alarm module: Issues an alarm based on the alarm signal;

[0098] The database is used to store the short-cycle temperature difference value, long-cycle temperature difference value, short-cycle temperature difference discrimination array, and long-cycle temperature difference discrimination array for each time, so as to facilitate subsequent verification of alarm results.

[0099] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0100] How this application works:

[0101] This application obtains the characteristics of the detection area corresponding to the set short-term temperature difference discrimination period, and generates a long-term temperature difference discrimination period based on the detection area characteristics; it generates a short-term temperature difference value based on the short-term temperature difference discrimination period and the temperature detection value; it generates a long-term temperature difference value based on the long-term temperature difference discrimination period and the temperature detection value; it selects a temperature warning value based on the short-term temperature difference value and the long-term temperature difference value; it obtains the temperature detection value of the current temperature detection device, and generates an alarm signal based on the current temperature detection value and the temperature warning value; by generating the length of the long-term temperature difference discrimination period specifically according to the regional characteristics of the detection area, it effectively solves the problem of untimely alarms under slow temperature rise, and at the same time, by selecting a temperature warning value based on the short-term temperature difference value and the long-term temperature difference value, it reduces the probability of false alarms; thereby improving the effectiveness of fire detection and prevention.

[0102] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. A method for improving the alarm uniformity of a heat-sensitive fire detector, characterized in that, Includes the following steps: Step 1: Obtain several nearby temperature readings from the temperature detection device; Step 2: Obtain the set short period for temperature difference discrimination, obtain the detection area features corresponding to the detection area, and generate a long period for temperature difference discrimination based on the detection area features; including: extracting the regional structure features and stored item features from the detection area features, inputting the regional structure features into the transmission influence coefficient generation model to obtain the corresponding transmission influence coefficient; the transmission influence coefficient generation model is obtained through training an artificial intelligence model; Extract the combustion heat release level and combustion rate score from the characteristics of stored items; The item influence coefficient is generated based on the combustion heat release level and combustion speed score, including: marking the combustion heat release score as RD; marking the combustion speed score as SD; and calculating the corresponding item influence coefficient using the formula WY=α1×exp(-β1×RD)+α2×exp(-β2×SD); where α1 and α2 are proportional coefficients; and β1 and β2 are adjustment coefficients. The long-term temperature difference discrimination is generated based on the transmission influence coefficient and the item influence coefficient, including: obtaining the transmission influence coefficient CY and the item influence coefficient WY; calculating the long-term proportional coefficient K using the formula K=γ1×CY+γ2×WY; where γ1 and γ2 are proportional coefficients; and calculating the long-term temperature difference discrimination using the formula CZQ=K×DZQ, where DZQ is the corresponding short-term temperature difference discrimination. Step 3: Generate short-cycle temperature difference value based on the temperature difference and the short-cycle temperature detection value; generate long-cycle temperature difference value based on the temperature difference and the long-cycle temperature detection value. Step 4: Select the temperature warning value based on the short-cycle temperature difference value and the long-cycle temperature difference value; Step 5: Obtain the current temperature detection value from the temperature detection device, and generate an alarm signal based on the current temperature detection value and the temperature warning value.

2. The method for improving the alarm uniformity of a heat-sensitive fire detector according to claim 1, characterized in that, Step three includes the following steps: S31: Obtain short-cycle differential temperature judgment; S32: Obtain several temperature detection values ​​within the short period of differential temperature discrimination, and number the several temperature detection values ​​according to the acquisition time order, and combine them into a short period array for differential temperature discrimination; S33: Record the difference between the last temperature detection value and the first temperature detection value in the short-cycle differential temperature discrimination array as the short-cycle temperature difference value; S34: Obtain long-cycle differential temperature judgment; S35: Obtain several temperature detection values ​​within the long period of differential temperature discrimination, and number the several temperature detection values ​​according to the acquisition time order, and combine them into a long period array for differential temperature discrimination; S36: The difference between the last temperature detection value and the first temperature detection value in the long-period array of the differential temperature discrimination is recorded as the long-period temperature difference value.

3. The method for improving the alarm uniformity of a heat-sensitive fire detector according to claim 1, characterized in that, The transmission influence coefficient generation model is obtained through training an artificial intelligence model, including: Acquire several regional structural feature data and their corresponding transmission influence coefficients; integrate the regional structural feature data and transmission influence coefficients into training data and test data; train the artificial intelligence model using the training data and test the trained artificial intelligence model using the test data, and finally obtain a transmission influence coefficient generation model with regional structural feature data as input and corresponding transmission influence coefficients as output. The artificial intelligence model includes a BP neural network model and an RBF neural network model.

4. The method for improving the alarm uniformity of a heat-sensitive fire detector according to claim 1, characterized in that, The selection of temperature warning values ​​based on short-cycle and long-cycle temperature difference values ​​includes: S41: Obtain short-cycle temperature difference values ​​and long-cycle temperature difference values; S42: When the short-cycle temperature difference value is greater than the set high-temperature short-cycle threshold; or, when the short-cycle temperature difference value is between the set low-temperature short-cycle threshold and the high-temperature short-cycle threshold, and the long-cycle temperature difference value is greater than the set high-temperature long-cycle threshold; set the temperature rise level to level one. When the short-cycle temperature difference is between the set low-temperature short-cycle threshold and the high-temperature short-cycle threshold, and the long-cycle temperature difference is less than the set high-temperature long-cycle threshold; or when the short-cycle temperature difference is less than the set low-temperature short-cycle threshold, and the long-cycle temperature difference is greater than the low-temperature long-cycle threshold; the temperature level is set to level two. When the short-cycle temperature difference is less than the set low-temperature short-cycle threshold and the long-cycle temperature difference is less than the low-temperature long-cycle threshold, the temperature rise level is set to level three; where the high-temperature long-cycle threshold is greater than the low-temperature long-cycle threshold and the high-temperature short-cycle threshold is greater than the low-temperature short-cycle threshold. S43: When the temperature rise level is Level 1, set the temperature warning value to the high temperature rise warning threshold; when the temperature rise level is Level 2, set the temperature warning value to the medium temperature rise warning threshold; when the temperature rise level is Level 3, set the temperature warning value to the low temperature rise warning threshold.

5. A method for improving the alarm uniformity of a heat-sensitive fire detector according to claim 1, characterized in that, The process of generating an alarm signal based on the current temperature detection value and the temperature warning value includes: Acquire the temperature detection value and determine whether the temperature detection value is greater than the temperature warning value; If yes, a rapid fire warning signal is generated when the temperature warning value is at the high temperature rise warning threshold; otherwise, a regular fire warning signal is generated when the temperature warning value is at the medium temperature rise warning threshold; otherwise, a slow fire warning signal is generated when the temperature warning value is at the low temperature rise warning threshold. No, no alarm signal is generated; proceed to step three. The alarm signals include rapid fire warning signals, conventional fire warning signals, and low-speed fire warning signals.

6. A system for improving the alarm uniformity of heat-sensitive fire detectors, used to implement the method for improving the alarm uniformity of heat-sensitive fire detectors as described in any one of claims 1-5; characterized in that, include: The system includes a data acquisition module, a period setting module, a threshold generation module, an anomaly detection module, an alarm module, and a database. The data acquisition module acquires the temperature detection value within the detection area in real time through the data acquisition device connected to it; The cycle setting module: acquires the set short cycle for temperature difference discrimination and the characteristics of the detection area corresponding to the detection area, and generates a long cycle for temperature difference discrimination based on the characteristics of the detection area; The threshold generation module selects a temperature warning value based on the short-cycle temperature difference value and the long-cycle temperature difference value. The anomaly detection module: acquires the current temperature detection value of the temperature detection device, and generates an alarm signal based on the current temperature detection value and the temperature warning value; The alarm module: triggers an alarm based on the alarm signal.

Images