Fire detection sensor data fusion method and system

Abstract

The application discloses a kind of fire detection sensor data fusion method and system, it is related to data fusion technical field, the application has significantly improved the reliability and accuracy of system, solved false alarm, report, environmental interference and sensor failure etc.Problems;By introducing detailed anomaly detection module and multistage threshold evaluation mechanism, system can accurately distinguish normal fluctuation and real fire signal, reduce false alarm and report;In addition, environmental monitoring module compares with threshold by real-time calculation environmental interference coefficient, effectively deal with the influence of environmental factors on detection accuracy, improve the reliability of detection;Safety fault-tolerant module then monitors sensor state and data transmission process in real time, ensure that data compensation mechanism is started when sensor fails or data loss, enhance the fault-tolerant capability of system;Such comprehensive measures guarantee the stability and accuracy of system under various interference and fault conditions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data fusion, in particular to a fire detection sensor data fusion method and system. BACKGROUND

[0002] Traditional fire detection systems usually rely on a single type of sensor, such as smoke, temperature, flame or carbon monoxide sensors. These sensors each have different detection capabilities and limitations. For example, smoke sensors are sensitive to dense smoke, but may not work well in smokeless fire scenarios; temperature sensors are sensitive to heat, but are slow to react to fires without obvious temperature rise. In order to improve the accuracy and response speed of fire detection, modern technology has begun to introduce multi-sensor data fusion methods, by integrating the data of multiple sensors and combining intelligent algorithms for comprehensive analysis, thereby improving the overall performance of the fire detection system.

[0003] However, the existing fire detection sensor data fusion system has the following technical defects in actual application:

[0004] 1. False alarms and missed alarms exist;

[0005] 2. Environmental interference leads to inaccurate detection;

[0006] 3. Fault tolerance is not enough, resulting in problems of sensor failure and data loss; SUMMARY

[0007] In view of the deficiencies of the prior art, the present application provides a fire detection sensor data fusion method and system, which solves the problems mentioned in the background art.

[0008] To achieve the above purpose, the present application realizes the following technical scheme: a fire detection sensor data fusion method and system, comprising an environment monitoring module, a data preprocessing module, a fusion algorithm module, an anomaly detection module, a safety fault tolerance module and a response triggering module;

[0009] The environment monitoring module is used to monitor the interference factors in the environment where the sensor is located in real time, collect the environment data set, and generate an environment interference coefficient Wd. If the environment interference coefficient Wd exceeds the preset interference threshold T1, an interference signal is transmitted to the data preprocessing module;

[0010] The data preprocessing module is used to filter and standardize the original data collected by the sensor and the environment data set transmitted by the environment monitoring module, and generate a preliminary processed data set, which is then transmitted to the fusion algorithm module;

[0011] The fusion algorithm module is configured to fuse the preliminary processed data sets based on a preset multi-sensor data fusion strategy to generate an initial fire detection coefficient Fx, and calculate a noise sensitivity Ns and a fault tolerance deviation index ε during the fusion process, and transmit the fusion result to the anomaly detection module.

[0012] The anomaly detection module is configured to detect the initial fire detection coefficient Fx output by the fusion algorithm module, generate an anomaly alarm coefficient Ax according to a preset standard curve, fit the anomaly alarm coefficient Ax with the noise sensitivity Ns to obtain the anomaly alarm coefficient Ax, evaluate the anomaly alarm coefficient Ax, and finally determine and confirm a potential false alarm or a false negative risk according to an evaluation result of the anomaly alarm coefficient Ax.

[0013] The safety fault tolerance module is configured to monitor a running state of the sensor and a data transmission process in real time, generate a sensor state stability coefficient St, evaluate the sensor state stability coefficient St, and finally start a data compensation mechanism according to an evaluation result of the sensor state stability coefficient St.

[0014] The response triggering module is configured to receive the anomaly alarm coefficient Ax generated by the anomaly detection module and the sensor state stability coefficient St generated by the safety fault tolerance module, combine the two to generate a final response coefficient Ry, evaluate the final response coefficient Ry, and finally trigger a corresponding fire warning response according to an evaluation result of the final response coefficient Ry.

[0015] In this embodiment,

[0016] Preferably, the environment monitoring module comprises an environment acquisition unit and an interference analysis unit.

[0017] The environment acquisition unit is configured to continuously monitor an environment in which the sensor is located, set a monitoring time period, use multiple types of sensors including a temperature sensor, a humidity sensor and a gas sensor to monitor environmental changes in the monitoring time period, aggregate and obtain an environment data set, extract a key environment parameter value Zmax, obtain an average environment parameter value Zavg in the set time period by a mean value algorithm in statistics, perform feature extraction on information in the environment data set, and establish an environment fluctuation model.

[0018] The interference analysis unit is configured to train and verify the environment fluctuation model, extract the environment parameter value Zmax and the average environment parameter value Zavg, perform dimensionless processing, and calculate an environment interference coefficient Wd by the following formula:

[0019]

[0020] In the formula, i=1, 2,..., n, n represents a time sequence monitored in the set time period, Zmax i represents a maximum environment parameter value at the i-th time sequence in the monitoring time period.

[0021] Preferably, the data preprocessing module comprises a filtering unit and a standardization unit;

[0022] The filtering unit is used to preliminarily screen the raw data collected by the sensor and the environmental data set transmitted by the environmental monitoring module, remove noise and abnormal data, screen out data meeting the conditions through the method of setting threshold and signal strength detection, and arrange them into a preliminary data set;

[0023] The standardization unit is used to standardize the preliminary data set screened out by the filtering unit, including unit conversion and scale adjustment of data of different sensors, so that they have unified dimensions, and through linear transformation, the data is adjusted to the same range, and finally a data set after standardization processing is generated and transmitted to the fusion algorithm module.

[0024] Preferably, the fusion algorithm module comprises a data fusion unit and a parameter calculation unit;

[0025] The data fusion unit is used to calculate the preliminary processing data set generated by the data preprocessing module based on the preset multi-sensor data fusion strategy to obtain an initial fire detection coefficient Fx, and the specific calculation formula is as follows:

[0026]

[0027] In the formula, Wd represents temperature, Ynd represents smoke concentration, Qnd represents harmful gas concentration, and Gqd represents photoelectric signal intensity.

[0028] Preferably, the parameter calculation unit is used to calculate noise sensitivity Ns and fault tolerance deviation index ε in the data fusion process; the noise sensitivity Ns is used to reflect the influence of noise in the sensor data on the fusion result, and is calculated according to the following formula

[0029]

[0030] In the formula, represents the number of sensors considered when calculating noise sensitivity, represents the noise value of the i th sensor, represents the average value of the noise value;

[0031] The fault tolerance deviation index ε is obtained by the following formula:

[0032]

[0033] In the formula, represents the number of sensors considered when calculating fault tolerance deviation, represents the measurement deviation of the ii th sensor, represents the average value of the measurement deviation.

[0034] Preferably, the anomaly detection module comprises a standard curve unit and an anomaly alarm generation unit;

[0035] The standard curve unit is configured to generate a standard curve Sx of the initial fire detection coefficient Fx according to historical data and a set detection standard; the standard curve Sx is configured to evaluate a normal range of a current fire detection coefficient and calculate a standard curve value according to the following formula:

[0036]

[0037] In the formula, a and b are coefficients obtained by regression analysis.

[0038] Preferably, the anomaly alarm generation unit is configured to compare the standard curve value Sx generated by the standard curve unit with the initial fire detection coefficient Fx output by the fusion algorithm module, calculate an anomaly alarm coefficient Ax, and according to the following formula:

[0039]

[0040] In the formula, K represents a standard deviation.

[0041] The anomaly alarm coefficient Ax is evaluated by presetting a first deviation threshold T1 and a second deviation threshold T2, and the first deviation threshold T1 > the second deviation threshold T2, and the specific content is as follows:

[0042] If the anomaly alarm coefficient Ax > the first deviation threshold T1, a first anomaly alarm is marked, indicating that there is a fire risk. At this time, the system makes corresponding alarm response measures according to the actual situation;

[0043] If the first deviation threshold T1 ≥ the anomaly alarm coefficient Ax > the second deviation threshold T2, a second anomaly alarm is marked, at this time, detailed inspection and confirmation are performed to further verify the authenticity to exclude the possibility of false alarm;

[0044] If the second deviation threshold T2 ≥ the anomaly alarm coefficient Ax, no anomaly is marked, indicating that the anomaly alarm coefficient Ax is within the preset normal range, indicating that the current fire detection coefficient Fx does not deviate from the standard curve, and no fire and anomaly occurs; at this time, subsequent data is continuously monitored.

[0045] Preferably, the safety fault-tolerant module comprises a state monitoring unit and a data compensation unit;

[0046] The state monitoring unit collects sensor state related data by monitoring the running state of the sensor in real time, obtains a sensor state value Czt and a sensor state average value And the sensor state stability coefficient St is calculated by the following formula:

[0047]

[0048] In the formula, x represents the number of sensors participating in the calculation;

[0049] The data compensation unit is used to evaluate the sensor state stability coefficient St and start the data compensation mechanism; the preset stability threshold Q is evaluated with the sensor state stability coefficient St, and the specific content is as follows:

[0050] If the stability threshold Q is less than the sensor state stability coefficient St, it indicates that the state stability of the sensor does not meet the requirements, at which time the data compensation mechanism is started, including adjusting the collected data according to the actual fluctuation of the sensor state; the unstable sensor is calibrated or replaced;

[0051] If the stability threshold Q is greater than or equal to the sensor state stability coefficient St, it indicates that the state stability of the sensor meets the requirements, at which time no data compensation is performed.

[0052] Preferably, the response triggering module obtains the final response coefficient Ry by the following formula:

[0053]

[0054] In the formula, 2 represents a constant;

[0055] The final response coefficient Ry is evaluated by the preset response threshold W, and the specific evaluation content is as follows:

[0056] If the final response coefficient Ry is greater than the response threshold W, it indicates that the current abnormal alarm and the sensor stability are abnormal; therefore, the system will trigger the fire warning response;

[0057] If the final response coefficient Ry is less than or equal to the response threshold W, it indicates that the current abnormal alarm and the sensor stability are normal; at this time, no warning is triggered, and the data continues to be monitored.

[0058] A fire detection sensor data fusion method, comprising the following steps:

[0059] Step one, real-time monitoring of interference factors in the environment of the sensor, collecting environmental data set, and generating environmental interference coefficient Wd, if the environmental interference coefficient Wd exceeds the preset interference threshold T1, transmitting the interference signal to the data preprocessing module;

[0060] Step two, data filtering and standardization processing of the original data collected by the sensor and the environmental data set transmitted by the environmental monitoring module, and generating a preliminary processed data set, and then transmitting it to the fusion algorithm module;

[0061] Step three, based on the preset multi-sensor data fusion strategy, the preliminary processing data set is fused to generate the initial fire detection coefficient Fx, and the noise sensitivity Ns and its fault tolerance deviation index epsilon are calculated in the fusion process, and the fusion result is transmitted to the anomaly detection module;

[0062] Step four, detecting the initial fire detection coefficient Fx output by the fusion algorithm module, and generating an abnormal alarm coefficient Ax according to the preset standard curve, fitting the abnormal alarm coefficient Ax and the noise sensitivity Ns to obtain the abnormal alarm coefficient Ax and evaluate, and finally judging and confirming the potential false alarm or false alarm risk according to the evaluation result of the abnormal alarm coefficient Ax;

[0063] Step five, real-time monitoring of the running state of the sensor and the data transmission process, generating a sensor state stability coefficient St and evaluating, and finally starting the data compensation mechanism according to the evaluation result of the state stability coefficient St;

[0064] Step six, receiving the abnormal alarm coefficient Ax generated by the anomaly detection module and the sensor state stability coefficient St generated by the safety fault tolerance module, and combining the two to generate a final response coefficient Ry and evaluate, and finally triggering the corresponding fire warning response according to the evaluation result of the final response coefficient Ry.

[0065] The present application provides a kind of fire detection sensor data fusion method and system.It has the following beneficial effects:

[0066] (1) solve the problem of false alarm and false alarm: by introducing detailed anomaly detection module and strict threshold evaluation mechanism, effectively solve the problem of false alarm and false alarm;Abnormal detection module utilizes standard curve unit and abnormal alarm generation unit to evaluate initial fire detection coefficient, and carries out multi-stage judgment through the threshold value of abnormal alarm coefficient;This method accurately distinguishes normal fluctuation and real fire signal, ensures the high accuracy of system in judging fire risk, thereby reducing the occurrence of false alarm and false alarm;This comprehensive evaluation mechanism enables the system to make more reliable response to potential fire risk, improves the overall alarm accuracy;

[0067] (2) deal with the inaccurate detection caused by environmental interference: the design of environmental monitoring module significantly improves the adaptability of the system to environmental interference;Environment acquisition unit monitors environmental changes through multiple sensors, calculates environmental interference coefficient in real time, and compares it with preset interference threshold;When interference coefficient exceeds threshold, the system will transmit and process interference signal;This method enables the system to dynamically adjust the sensitivity to environmental interference, reduces the influence of environmental factors on fire detection accuracy, thereby improving the reliability and effectiveness of detection;Through effective environmental data processing and analysis, the system can more accurately identify and distinguish fire signal and environmental interference;

[0068] (3) Enhancing fault tolerance to solve the problem of sensor failure and data loss: the safety fault tolerance module monitors the state of the sensor and the data transmission process in real time, ensuring that the system can effectively cope with the problem of sensor failure and data loss; the state monitoring unit calculates the stability coefficient of the sensor state, and based on this coefficient, the data compensation mechanism is started; when the stability does not meet the requirements, the system will adjust the data and calibrate or replace the sensor; this design enhances the fault tolerance of the system to the sensor failure, ensures the integrity and accuracy of the data, and improves the overall reliability and robustness of the system; through this fault tolerance mechanism, the system can maintain normal working state and provide stable fire detection service in the case of sensor failure or data loss. BRIEF DESCRIPTION OF DRAWINGS

[0069] Figure 1 Figure 1 is a schematic diagram of the framework structure of the fire detection sensor data fusion system of the present application;

[0070] Figure 2 Figure 2 is a schematic diagram of the step flow of the fire detection sensor data fusion method of the present application. DETAILED DESCRIPTION

[0071] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0072] Embodiment 1

[0073] Please refer to Figure 1 The present application provides a fire detection sensor data fusion method and system, which includes an environment monitoring module, a data preprocessing module, a fusion algorithm module, an anomaly detection module, a safety fault tolerance module, and a response trigger module.

[0074] The environment monitoring module is used to monitor the interference factors in the environment where the sensor is located in real time, collect the environmental data set, and generate an environmental interference coefficient Wd. If the environmental interference coefficient Wd exceeds the preset interference threshold T1, an interference signal is transmitted to the data preprocessing module.

[0075] The data preprocessing module is used to filter and standardize the original data collected by the sensor and the environmental data set transmitted by the environment monitoring module, and generate a preliminary processed data set, which is then transmitted to the fusion algorithm module.

[0076] The fusion algorithm module is configured to fuse the preliminary processed data sets based on a preset multi-sensor data fusion strategy to generate an initial fire detection coefficient Fx, and calculate a noise sensitivity Ns and a fault tolerance deviation index ε during the fusion process, and transmit the fusion result to the anomaly detection module.

[0077] The anomaly detection module is configured to detect the initial fire detection coefficient Fx output by the fusion algorithm module, generate an anomaly alarm coefficient Ax according to a preset standard curve, fit the anomaly alarm coefficient Ax with the noise sensitivity Ns to obtain the anomaly alarm coefficient Ax and evaluate the anomaly alarm coefficient Ax, and finally determine and confirm a potential false alarm or missed alarm risk according to an evaluation result of the anomaly alarm coefficient Ax.

[0078] The safety fault tolerance module is configured to monitor a running state of the sensor and a data transmission process in real time, generate a sensor state stability coefficient St and evaluate the sensor state stability coefficient St, and finally start a data compensation mechanism according to an evaluation result of the sensor state stability coefficient St.

[0079] The response triggering module is configured to receive the anomaly alarm coefficient Ax generated by the anomaly detection module and the sensor state stability coefficient St generated by the safety fault tolerance module, combine the two to generate a final response coefficient Ry and evaluate the final response coefficient Ry, and finally trigger a corresponding fire warning response according to an evaluation result of the final response coefficient Ry.

[0080] In this embodiment, the environment monitoring module identifies environmental interference factors in time and transmits the interference factors to the data preprocessing module through real-time monitoring and calculation of interference coefficients, effectively reducing the influence of environmental interference on detection accuracy; the data preprocessing module filters and standardizes the collected raw data, ensuring the consistency and accuracy of the data and providing a high-quality data basis for the subsequent fusion algorithm module; the fusion algorithm module generates an initial fire detection coefficient Fx in combination with a multi-sensor data fusion strategy, and calculates a noise sensitivity Ns and a fault tolerance deviation index ε during the fusion process, improving the accuracy of fire detection and the fault tolerance capability of the system; the anomaly detection module generates and evaluates an anomaly alarm coefficient Ax through a standard curve, effectively distinguishing normal fluctuations from fire signals and reducing the risk of false alarms and missed alarms; the safety fault tolerance module monitors the state of the sensor in real time, generates a stability coefficient and starts a data compensation mechanism, enhancing the stability and reliability of the system; and the response triggering module generates a response coefficient Ry finally by comprehensively considering the anomaly alarm coefficient Ax and the sensor state stability coefficient St, ensuring that the system can trigger a warning response quickly when a fire occurs and improving the response efficiency of the system.

[0081] Embodiment 2

[0082] The environment monitoring module includes an environment acquisition unit and an interference analysis unit.

[0083] The environment acquisition unit is used for continuously monitoring the environment where the sensor is located, setting a monitoring time period, using multiple types of sensors including temperature sensors, humidity sensors and gas sensors to monitor the environmental changes in the monitoring time period, collecting the environmental data set and extracting the key environmental parameter value Zmax, obtaining the average environmental parameter value Zavg in the set time period through the mean value algorithm in statistics, and performing feature extraction on the information in the environmental data set to establish an environmental fluctuation model;

[0084] The interference analysis unit is used for training and verifying the environmental fluctuation model, extracting the environmental parameter value Zmax and the average environmental parameter value Zavg, performing dimensionless processing, and calculating the environmental interference coefficient Wd through the following formula:

[0085]

[0086] In the formula, i=1, 2,..., n, n represents the time sequence monitored in the set time period, Zmax i represents the maximum environmental parameter value of the i-th time sequence in the monitoring time period.

[0087] In the embodiment, the environment acquisition unit continuously monitors the environment where the sensor is located, uses multiple types of sensors to comprehensively and meticulously collect environmental data, and the use of multiple types of sensors improves the detection capability of environmental interference factors. In addition, the environment acquisition unit extracts the key environmental parameter value Zmax and calculates the average environmental parameter value Zavg to establish an environmental fluctuation model, which realizes accurate evaluation and modeling of environmental fluctuations. The interference analysis unit trains and verifies the environmental fluctuation model, performs dimensionless processing on the environmental parameter value Zmax and Zavg, and calculates the environmental interference coefficient Wd, thereby providing quantitative analysis of the influence of environmental interference, so that the system can more accurately identify interference signals and take corresponding measures, and the reliability and accuracy of data processing are optimized.

[0088] Embodiment 3

[0089] The data preprocessing module includes a filtering unit and a standardization unit;

[0090] The filtering unit is used for preliminarily screening the original data collected by the sensor and the environmental data set transmitted by the environmental monitoring module, removing noise and abnormal data, screening out data meeting the conditions through the method of setting threshold and signal strength detection, and arranging the data into a preliminary data set;

[0091] The standardization unit is used for standardizing the preliminary data set screened by the filtering unit, including unit conversion and scale adjustment of data of different sensors to make them have unified dimension, and adjusting the data to the same range through linear transformation, and finally generating a data set after standardization processing and transmitting it to the fusion algorithm module.

[0092] In this embodiment, the filtering unit removes noise and abnormal data through preliminary screening of the original data collected by the sensor and the environmental data set transmitted by the environmental monitoring module, improves the quality and accuracy of the data, and ensures that only data meeting the conditions are retained through the method of setting threshold and signal strength detection, thereby reducing errors and interference in the data and improving the reliability of data processing. The standardization unit standardizes the filtered data, including unit conversion and scale adjustment, so that the data of different sensors have unified dimension and range, which can effectively eliminate the deviation between different data sources and ensure the consistency and comparability of the data. The generated standardized data set provides high-quality input data for the fusion algorithm module, improves the accuracy of fire detection and the overall performance of the system.

[0093] Embodiment 4

[0094] The fusion algorithm module includes a data fusion unit and a parameter calculation unit.

[0095] The data fusion unit is used for calculating the initial fire detection coefficient Fx based on the preset multi-sensor data fusion strategy, and the preliminary processing data set generated by the data preprocessing module, and the specific calculation formula is as follows:

[0096]

[0097] In the formula, Wd represents temperature, Ynd represents smoke concentration, Qnd represents harmful gas concentration, and Gqd represents photoelectric signal intensity.

[0098] The parameter calculation unit is used for calculating noise sensitivity Ns and fault tolerance deviation index ε in the data fusion process. The noise sensitivity Ns is used to reflect the influence of noise in the sensor data on the fusion result, and is calculated according to the following formula

[0099]

[0100] In the formula, represents the number of sensors considered when calculating noise sensitivity, represents the noise value of the i th sensor, represents the average value of the noise value;

[0101] The fault tolerance deviation index ε is obtained by the following formula:

[0102]

[0103] wherein, represents the number of sensors considered when calculating the fault tolerance deviation, represents the measurement deviation of the i-th sensor, represents the average value of the measurement deviation.

[0104] In this embodiment, the data fusion unit calculates the preliminary processing data set based on the multi-sensor data fusion strategy to generate the initial fire detection coefficient Fx, thereby integrating data from different sources to provide comprehensive fire detection results and improve the accuracy and reliability of the system. The parameter calculation unit calculates the noise sensitivity Ns and the fault tolerance deviation index ε during the data fusion process to reflect the influence of noise in the sensor data on the fusion results and evaluate the fault tolerance capability of the data. The noise sensitivity Ns reveals how noise in the data affects the final results by considering the number of sensors and their noise values, ensuring the stability of data fusion. The fault tolerance deviation index ε evaluates the fault tolerance capability of the system when facing sensor failures by considering the number of sensors and their measurement deviations, thereby improving the robustness and reliability of the system and reducing fire detection errors caused by sensor problems.

[0105] Embodiment 5

[0106] The anomaly detection module includes a standard curve unit and an anomaly alarm generation unit.

[0107] The standard curve unit is used to generate a standard curve Sx of the initial fire detection coefficient Fx according to historical data and set detection standards. The standard curve Sx is used to evaluate the normal range of the current fire detection coefficient, and the standard curve value is calculated by the following formula:

[0108]

[0109] wherein a and b are coefficients obtained by regression analysis.

[0110] The anomaly alarm generation unit compares the standard curve value Sx generated by the standard curve unit with the initial fire detection coefficient Fx output by the fusion algorithm module, calculates the anomaly alarm coefficient Ax, and according to the following formula:

[0111]

[0112] wherein K represents the standard deviation.

[0113] The anomaly alarm coefficient Ax is evaluated by presetting a first deviation threshold T1 and a second deviation threshold T2, and the first deviation threshold T1 is greater than the second deviation threshold T2. The specific content is as follows:

[0114] If the abnormal alarm coefficient Ax is greater than the first deviation threshold T1, it is marked as a first abnormal alarm, indicating that there is a fire risk. At this time, the system makes corresponding alarm response measures according to the actual situation;

[0115] If the first deviation threshold T1 is greater than the abnormal alarm coefficient Ax is greater than the second deviation threshold T2, it is marked as a second abnormal alarm, at which time detailed inspection and confirmation are carried out to further verify its authenticity to exclude the possibility of false alarm;

[0116] If the second deviation threshold T2 is greater than the abnormal alarm coefficient Ax, no abnormality is marked, indicating that the abnormal alarm coefficient Ax is within the preset normal range, indicating that the current fire detection coefficient Fx does not deviate from the standard curve and no fire and abnormal situation occurs; At this time, the subsequent data is continuously monitored.

[0117] In the embodiment, the standard curve unit generates the standard curve Sx of the initial fire detection coefficient Fx through historical data and set detection standards. This process enables the normal range of the current fire detection coefficient to be accurately evaluated, thereby improving the accuracy of fire detection. The abnormal alarm generation unit compares the standard curve value Sx with the initial fire detection coefficient Fx, calculates the abnormal alarm coefficient Ax, and evaluates it through the set deviation thresholds T1 and T2, so as to accurately distinguish different levels of fire risk. If Ax exceeds the first deviation threshold T1, it is marked as a first abnormal alarm, indicating that there is a higher fire risk, and the system will take corresponding alarm response measures. If Ax is between T1 and T2, it is marked as a second abnormal alarm, which needs to be further checked and confirmed to exclude false alarm. If Ax is lower than the second deviation threshold T2, it indicates that the detection result is within the normal range, the system continues to monitor, avoids false alarm and ensures stable operation of the system.

[0118] Embodiment 6

[0119] The safety fault-tolerant module comprises a state monitoring unit and a data compensation unit;

[0120] The state monitoring unit collects sensor state related data by monitoring the state of the sensor in real time, acquires the sensor state value Czt and the sensor state average value , and calculates the sensor state stability coefficient St through the following formula:

[0121]

[0122] In the formula, x represents the number of sensors participating in the calculation;

[0123] The data compensation unit is used to evaluate the sensor state stability coefficient St to start the data compensation mechanism; the sensor state stability coefficient St is evaluated by the preset stability threshold Q, and the specific content is as follows:

[0124] If the stability threshold Q is less than the sensor state stability coefficient St, it indicates that the sensor state stability does not meet the requirements, at this time the data compensation mechanism is started, including adjusting the collected data according to the actual fluctuation of the sensor state; the unstable sensor is calibrated or replaced;

[0125] If the stability threshold Q is greater than or equal to the sensor state stability coefficient St, it indicates that the sensor state stability meets the requirements, at this time no data compensation is performed.

[0126] In this embodiment, the state monitoring unit monitors the running state of the sensor in real time, calculates the sensor state stability coefficient St by collecting the sensor state value Czt and the average value, which can identify the running stability of the sensor in time, thereby ensuring the reliability and accuracy of the data; the data compensation unit evaluates the sensor state stability coefficient St and the preset stability threshold Q to determine whether to start the data compensation mechanism; if St is lower than the threshold Q, it indicates that the sensor state is unstable, the system will start the data compensation mechanism to adjust the data, and the unstable sensor is calibrated or replaced, thereby effectively solving the problems of sensor failure and data loss; if St is higher than the threshold Q, the system considers that the sensor state is stable, and no compensation is needed, which not only reduces unnecessary maintenance work, but also maintains the normal operation of the system.

[0127] Embodiment 7

[0128] The response triggering module obtains the final response coefficient Ry by the following formula:

[0129]

[0130] In the formula, 2 represents a constant;

[0131] The final response coefficient Ry is evaluated by the preset response threshold W, and the specific evaluation content is as follows:

[0132] If the final response coefficient Ry is greater than the response threshold W, it indicates that the current abnormal alarm and sensor stability are abnormal; therefore, the system triggers the fire warning response;

[0133] If the final response coefficient Ry is less than or equal to the response threshold W, it indicates that the current abnormal alarm and sensor stability are normal; at this time, no warning is triggered, and the data continues to be monitored.

[0134] In this embodiment, the intelligent triggering of fire warning is realized by calculating the final response coefficient Ry and comparing it with the preset response threshold W. When the final response coefficient Ry is higher than the response threshold W, the system identifies that there is a problem with the current abnormal alarm and sensor stability, and then triggers the fire warning response, which can effectively deal with potential fire risks. If the final response coefficient Ry is lower than or equal to the response threshold W, it means that the current abnormal alarm and sensor state are normal, and the system will continue to monitor the data to avoid unnecessary warnings, which can reduce false positives and ensure the efficient operation of the system.

[0135] Embodiment 8

[0136] Please refer to Figure 2 A fire detection sensor data fusion method, comprising the following steps:

[0137] Step one, real-time monitoring of interference factors in the environment where the sensor is located, collecting environmental data sets, and generating an environmental interference coefficient Wd. If the environmental interference coefficient Wd exceeds the preset interference threshold T1, an interference signal is transmitted to the data preprocessing module;

[0138] Step two, data filtering and standardization processing of the original data collected by the sensor and the environmental data set transmitted by the environmental monitoring module, and generating a preliminary processed data set, and then transmitting it to the fusion algorithm module;

[0139] Step three, based on the preset multi-sensor data fusion strategy, the preliminary processed data set is fused to generate an initial fire detection coefficient Fx, and the noise sensitivity Ns and its fault tolerance deviation index ε are calculated during the fusion process. The fusion result is transmitted to the anomaly detection module;

[0140] Step four, detecting the initial fire detection coefficient Fx output by the fusion algorithm module, and generating an abnormal alarm coefficient Ax according to the preset standard curve, fitting the abnormal alarm coefficient Ax and the noise sensitivity Ns to obtain the abnormal alarm coefficient Ax and evaluate it. Finally, according to the evaluation result of the abnormal alarm coefficient Ax, the potential false alarm or missed alarm risk is judged and confirmed;

[0141] Step five, real-time monitoring of the running state and data transmission process of the sensor, generating a sensor state stability coefficient St and evaluating it, and finally starting the data compensation mechanism according to the evaluation result of the state stability coefficient St;

[0142] Step six, receiving the abnormal alarm coefficient Ax generated by the anomaly detection module and the sensor state stability coefficient St generated by the safety fault tolerance module, and combining the two to generate a final response coefficient Ry and evaluate it. Finally, according to the evaluation result of the final response coefficient Ry, the corresponding fire warning response is triggered.

[0143] In this embodiment, step one generates an environmental disturbance coefficient Wd by monitoring environmental disturbances in real-time, ensuring that the impact of environmental disturbances on data is identified and addressed in a timely manner, thereby reducing the risk of false positives caused by disturbances; step two filters and standardizes sensor data, optimizing data quality and consistency to ensure that the underlying data for subsequent fusion and analysis is accurate and reliable; step three generates an initial fire detection coefficient Fx through a multi-sensor data fusion strategy, calculates noise sensitivity Ns and fault tolerance deviation index ε, enhancing the system's adaptability to noise and deviation and improving the accuracy of fire detection; step four further reduces the likelihood of false positives and false negatives through the generation of a standard curve by the anomaly detection module and the evaluation of an anomaly alarm coefficient Ax, ensuring the reliability of fire alarms; step five generates a sensor state stability coefficient St by monitoring sensor status and data transmission processes, and initiates a data compensation mechanism when necessary, enhancing the system's fault tolerance capability in the event of sensor failure; step six generates a final response coefficient Ry by combining the anomaly alarm coefficient Ax and the sensor state stability coefficient St, and triggers a fire warning response based on the evaluation results, thereby ensuring safety while reducing unnecessary warnings. This method effectively solves the problems of false positives and false negatives in traditional fire detection systems through multi-level and multi-dimensional detection and optimization, improving the overall performance of the fire warning system.

[0144] While embodiments of the present application have been shown and described, it is to be understood that the embodiments described are merely divergences, modifications, replacements and variations of the embodiments, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A fire detection sensor data fusion system, characterized by: The system comprises an environment monitoring module, a data preprocessing module, a fusion algorithm module, an anomaly detection module, a security fault-tolerant module, and a response triggering module. The environment monitoring module is configured to monitor interference factors in an environment in which the sensor is located in real time, collect an environment data set, and generate an environment interference coefficient Wd. The data preprocessing module is configured to perform data filtering and standardization processing on the original data collected by the sensor and the environment data set transmitted by the environment monitoring module, and generate a preliminary processed data set, which is then transmitted to the fusion algorithm module. The fusion algorithm module is configured to fuse the preliminary processed data set based on a preset multi-sensor data fusion strategy, generate an initial fire detection coefficient Fx, and calculate a noise sensitivity Ns and a fault-tolerant deviation index ε during the fusion process. The anomaly detection module is configured to detect the initial fire detection coefficient Fx output by the fusion algorithm module, generate an abnormal alarm coefficient Ax according to a preset standard curve, fit the abnormal alarm coefficient Ax and the noise sensitivity Ns to obtain the abnormal alarm coefficient Ax, and evaluate the abnormal alarm coefficient Ax. The security fault-tolerant module is configured to monitor the running state of the sensor and the data transmission process in real time, generate a sensor state stability coefficient St, and evaluate the sensor state stability coefficient St. The response triggering module is configured to receive the abnormal alarm coefficient Ax generated by the anomaly detection module and the sensor state stability coefficient St generated by the security fault-tolerant module, combine the two to generate a final response coefficient Ry, and evaluate the final response coefficient Ry.

2. The fire detection sensor data fusion system of claim 1, wherein: The environment monitoring module comprises an environment collection unit and an interference analysis unit. The environment collection unit is configured to continuously monitor the environment in which the sensor is located, set a monitoring time period, use multiple types of sensors, including temperature sensors, humidity sensors, and gas sensors, to monitor environmental changes during the monitoring time period, collect an environment data set, extract key environment parameter values Zmax, obtain average environment parameter values Zavg in the set time period through a mean value algorithm in statistics, and perform feature extraction on information in the environment data set to establish an environment fluctuation model. The interference analysis unit is configured to train and verify the environment fluctuation model, extract environment parameter values Zmax and average environment parameter values Zavg, perform dimensionless processing, and calculate the environment interference coefficient Wd through the following formula: ； where i=1, 2,..., n, n represents the time sequence monitored in the set time period, and Zmaxi represents the maximum environment parameter value at the ith time sequence in the monitoring time period.

3. The fire detection sensor data fusion system of claim 1, wherein: The data preprocessing module comprises a filtering unit and a standardization unit. The filtering unit is used for preliminary screening of raw data collected by sensors and environmental data sets transmitted by the environmental monitoring module, removing noise and abnormal data, screening data meeting the conditions through a threshold setting and signal strength detection method, and arranging the data into a preliminary data set; The standardization unit is used for standardization processing of the preliminary data set screened by the filtering unit, including unit conversion and scale adjustment of data from different sensors to make them have a unified dimension, and adjusting the data to the same range through linear transformation, to finally generate a data set after standardization processing and transmit it to the fusion algorithm module.

4. The fire detection sensor data fusion system of claim 1, wherein: The fusion algorithm module includes a data fusion unit and a parameter calculation unit. The data fusion unit is used for calculating the initial fire detection coefficient Fx based on a preset multi-sensor data fusion strategy, and the specific calculation formula is as follows: ； In the formula, Wd represents temperature, Ynd represents smoke concentration, Qnd represents harmful gas concentration, and Gqd represents photoelectric signal intensity.

5. The fire detection sensor data fusion system of claim 4, wherein: The parameter calculation unit is used for calculating noise sensitivity Ns and fault tolerance deviation index ε in the data fusion process; noise sensitivity Ns is used to reflect the influence of noise in the sensor data on the fusion result, and is calculated according to the following formula ； In the formula, represents the number of sensors considered when calculating the noise sensitivity, represents the noise value of the i-th sensor, represents the average value of the noise values; The fault tolerance deviation index ε is obtained by the following formula: ； wherein denotes the number of sensors considered when calculating the fault-tolerant bias, denotes the measurement bias of the i-th sensor, denotes the average value of the measurement bias.

6. The fire detection sensor data fusion system of claim 1, wherein: The anomaly detection module includes a standard curve unit and an abnormal alarm generation unit. The standard curve unit is used to generate a standard curve Sx of the initial fire detection coefficient Fx according to historical data and a set detection standard; the standard curve Sx is used to evaluate the normal range of the current fire detection coefficient, and the standard curve value is calculated according to the following formula: ； In the formula, a and b are coefficients obtained by regression analysis.

7. The fire detection sensor data fusion system of claim 1, wherein: The abnormal alarm generation unit is used to compare the standard curve value Sx generated by the standard curve unit with the initial fire detection coefficient Fx output by the fusion algorithm module, calculate the abnormal alarm coefficient Ax, and according to the following formula: ； In the formula, K represents the standard deviation; The abnormal alarm coefficient Ax is evaluated by presetting a first deviation threshold T1 and a second deviation threshold T2, and the first deviation threshold T1 > the second deviation threshold T2, and the specific content is as follows: If the abnormal alarm coefficient Ax > the first deviation threshold T1, it is marked as the first abnormal alarm, indicating that there is a fire risk; at this time, the system makes corresponding alarm response measures according to the actual situation; If the first deviation threshold T1 ≥ the abnormal alarm coefficient Ax > the second deviation threshold T2, it is marked as the second abnormal alarm, at this time, detailed inspection and confirmation are carried out to further verify its authenticity to exclude the possibility of false alarm; If the second deviation threshold T2 ≥ the abnormal alarm coefficient Ax, no abnormal mark is made, indicating that the abnormal alarm coefficient Ax is within the preset normal range, indicating that the current fire detection coefficient Fx does not deviate from the standard curve and no fire and abnormal situation occurs; at this time, the subsequent data is continuously monitored.

8. The fire detection sensor data fusion system of claim 1, wherein: The safety fault tolerance module includes a state monitoring unit and a data compensation unit; The state monitoring unit collects sensor state related data by monitoring the running state of the sensor in real time, obtains the sensor state value Czt and the sensor state average value and obtains the sensor state stability coefficient St through the following formula: ； In the formula, x represents the number of sensors participating in the calculation; The data compensation unit is used to evaluate the sensor state stability coefficient St and start the data compensation mechanism; the preset stability threshold Q is evaluated with the sensor state stability coefficient St, and the specific content is as follows: If the stability threshold Q is less than the sensor state stability coefficient St, it indicates that the state stability of the sensor does not meet the requirements, at this time the data compensation mechanism is started, including adjusting the collected data according to the actual fluctuation of the sensor state; the unstable sensor is calibrated or replaced; If the stability threshold Q is greater than or equal to the sensor state stability coefficient St, it indicates that the state stability of the sensor meets the requirements, at this time no data compensation is performed.

9. The fire detection sensor data fusion system of claim 1, wherein: The response triggering module obtains the final response coefficient Ry through the following formula: ； In the formula, 2 represents a constant; The preset response threshold W is evaluated with the final response coefficient Ry, and the specific evaluation content is as follows: If the final response coefficient Ry is greater than the response threshold W, it indicates that the current abnormal alarm and sensor stability are abnormal; therefore, the system will trigger the fire warning response; If the final response coefficient Ry is less than or equal to the response threshold W, it indicates that the current abnormal alarm and sensor stability are normal; At this time, the pre-warning is not triggered, and the data continues to be monitored.

10. A method of fusing data from fire detection sensors, according to the system for fusing data from fire detection sensors as defined in claim 1, characterized in that: The steps include: Step one, real-time monitoring of interference factors in the environment of the sensor, collecting environmental data sets, and generating an environmental interference coefficient Wd, if the environmental interference coefficient Wd exceeds the preset interference threshold T1, an interference signal is transmitted to the data preprocessing module; Step two, data filtering and standardization processing are performed on the original data collected by the sensor and the environmental data set transmitted by the environmental monitoring module, and a preliminary processed data set is generated, which is then transmitted to the fusion algorithm module; Step three, based on the preset multi-sensor data fusion strategy, the preliminary processed data set is fused to generate an initial fire detection coefficient Fx, and the noise sensitivity Ns and the fault tolerance deviation index ε are calculated during the fusion process, and the fusion result is transmitted to the anomaly detection module; Step four, the initial fire detection coefficient Fx output by the fusion algorithm module is detected, and an abnormal alarm coefficient Ax is generated according to the preset standard curve, and the abnormal alarm coefficient Ax and the noise sensitivity Ns are fitted to obtain the abnormal alarm coefficient Ax and evaluate it, finally, according to the evaluation result of the abnormal alarm coefficient Ax, the potential false alarm or missed alarm risk is judged and confirmed; Step five, real-time monitoring of the running state of the sensor and the data transmission process, the sensor state stability coefficient St is generated and evaluated, and finally the data compensation mechanism is started according to the evaluation result of the state stability coefficient St; Step six, the abnormal alarm coefficient Ax generated by the anomaly detection module and the sensor state stability coefficient St generated by the safety fault tolerance module are received, and the final response coefficient Ry is generated and evaluated by combining the two, and finally the corresponding fire warning response is triggered according to the evaluation result of the final response coefficient Ry.

Images