A smart park fire alarm method, system, device and storage medium
By setting up temperature sensors in the smart park, data analysis and confidence evaluation are carried out, the fire alarm accuracy problem caused by temperature sensor data interference is solved, and high-accuracy fire alarms are achieved in an interfering environment.
Patent Information
- Application Number
- CN202411223123.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-09-03
AI Technical Summary
In the smart park, the temperature sensor data is affected by factors such as electromagnetic interference, environmental humidity, wind speed and mechanical vibration, making it difficult to ensure the accuracy and reliability of the fire alarm, thereby reducing the confidence of the fire location.
By setting a temperature sensor at the monitoring position to collect ambient temperature data, performing trusted interval extraction and information entropy analysis, determining the temperature diffusion trend and transient response volume, and then evaluating the confidence alarm value of the fire, and sending an alarm when the threshold is reached.
It improves the accuracy and reliability of fire alarms, ensures that the fire can be effectively identified in an interfering environment, and enhances the applicability of temperature sensors in real-time monitoring and alarm systems.
Smart Images

Figure CN118762491B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of fire alarm technology, and more specifically, to a smart campus fire alarm method, system, equipment and storage medium. Background Art
[0002] Fire alarm is designed to detect fire early and sound the alarm to protect the safety of people and property. It uses sensors such as smoke detectors and heat detectors to monitor environmental changes. Once smoke or abnormal temperature rise is detected, the alarm is automatically triggered. The control panel receives the signal and activates the siren, notifying residents to evacuate and contact emergency services. Modern systems also include remote monitoring and smartphone applications, allowing users to obtain alarm notifications and remotely manage system status in real time, improving response speed and system reliability. The combination of these technologies has greatly improved the efficiency of fire safety management, reduced casualties and property losses caused by fire, and has become an indispensable safety facility in modern buildings and public places.
[0003] The existing smart campus fire alarm integrates intelligent video surveillance and artificial intelligence analysis. Through high-definition cameras and artificial intelligence (AI) algorithms, it can monitor activities in various areas in real time and analyze abnormal situations, thereby providing automated fire alarms. However, there are many factors in the smart campus that interfere with the accuracy of temperature sensor data, such as electromagnetic interference, environmental humidity interference, wind speed interference, voltage interference, and mechanical vibration interference. Under the influence of these interference factors, the temperature sensor data will become more complex and uncertain, making it difficult to accurately evaluate the authenticity and reliability of the temperature sensor data, which will in turn cause the confidence of the alarmed fire location to be low. Comprehensively considering the impact of electromagnetic interference, environmental humidity, wind speed, voltage, and mechanical vibration on fire alarms, achieving confidence alarms for fires can effectively avoid the above problems, thereby improving the accuracy of fire alarms. Therefore, how to achieve confidence alarms for fires in an environment that interferes with the accuracy of temperature sensors in smart campuses, thereby improving the accuracy of fire alarms, has become a difficult problem faced by the industry. Summary of the invention
[0004] The present application provides a smart park fire alarm method, system, device and storage medium, which can realize a confident alarm for fire in an environment where there is interference with the accuracy of temperature sensors in the smart park.
[0005] In a first aspect, the present application provides a smart campus fire alarm method, comprising the following steps:
[0006] The ambient temperature data at each monitoring location is collected by temperature sensors arranged at each monitoring location in the target smart park to obtain the ambient temperature data at each monitoring location;
[0007] The credible intervals of each ambient temperature data are extracted to obtain multiple credible temperature domains. The temperature diffusion trend of each monitoring location is determined based on all credible temperature domains. Then, the critical alarm value of the ambient temperature at each monitoring location in the target smart park is determined based on all temperature diffusion trends.
[0008] Collect temperature interference data of temperature sensors at various monitoring locations in the target smart park to obtain temperature interference records, determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring location based on the information entropy of the ambient temperature fluctuation at each monitoring location combined with the temperature interference records, and then determine the transient response amount of the temperature sensors at various monitoring locations in the target smart park from all the transient fluctuation amounts;
[0009] According to all transient response quantities, confidence evaluation is performed on the critical alarm values at each monitoring location in the target smart park to obtain the confidence alarm values of fire at each monitoring location in the target smart park;
[0010] For each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park.
[0011] In some embodiments, extracting the trusted intervals of each ambient temperature data to obtain multiple trusted temperature domains specifically includes:
[0012] Obtain historical ambient temperature data and historical electromagnetic interference data at each monitoring location;
[0013] Determine the temperature interference factor of the target smart park when the electronic equipment generates electromagnetic interference based on all historical ambient temperature data and all historical electromagnetic interference data;
[0014] Determine the credible deviation value of the temperature at each monitoring location through the ambient temperature data of each monitoring location;
[0015] Determine the upper limit of the temperature credible interval and the lower limit of the temperature credible interval at each monitoring position according to the temperature interference factor and all credible deviation values;
[0016] The corresponding ambient temperature data is extracted through the upper and lower bounds of the temperature credible interval at each monitoring location to obtain multiple temperature credible domains.
[0017] In some embodiments, determining the temperature diffusion trend of each monitoring location according to all temperature credible domains specifically includes:
[0018] Standardize each temperature credible domain to obtain multiple standard temperature credible domains;
[0019] Perform linear fitting on all standard ambient temperature values in each standard temperature credible domain to obtain multiple temperature credible fitting curves;
[0020] The temperature diffusion trend of each monitoring location is determined based on all temperature credible fitting curves.
[0021] In some embodiments, determining the critical alarm value of the ambient temperature at each monitoring location in the target smart park based on all temperature diffusion trends specifically includes:
[0022] Obtaining the temperature interference factor;
[0023] Determine the abnormal temperature warning value of each monitoring location in the target smart park based on all temperature diffusion trends;
[0024] The critical alarm value of the ambient temperature at each monitoring location in the target smart park is determined by the temperature interference factor and all abnormal temperature warning values.
[0025] In some embodiments, determining the transient fluctuation amount of the ambient temperature at the corresponding monitoring location based on the information entropy of the ambient temperature fluctuation at each monitoring location in combination with the temperature disturbance record specifically includes:
[0026] Obtaining ambient temperature data at each monitoring location;
[0027] Determine the information entropy of the ambient temperature fluctuation at each monitoring location based on all ambient temperature data;
[0028] Determine the disturbance fluctuation vector space of the ambient temperature through the temperature disturbance record;
[0029] The transient fluctuation amount of the ambient temperature at the corresponding monitoring position is determined according to the information entropy of the ambient temperature fluctuation at each monitoring position and the interference fluctuation vector space.
[0030] In some embodiments, confidence evaluation is performed on the critical alarm values at each monitoring location in the target smart park based on all transient response quantities, and the confidence alarm values of fire occurring at each monitoring location in the target smart park are obtained, specifically including:
[0031] Determine the abnormal state fluctuation entropy of the temperature sensor according to all transient response quantities;
[0032] Convert all transient response quantities into transient response quantity sequences;
[0033] Determine the abnormal confidence features at each monitoring location in the target smart park through the transient response quantity sequence and the abnormal state fluctuation entropy;
[0034] The confidence alarm value of a fire at each monitoring location in the target smart park is evaluated based on all abnormal confidence features and all critical alarm values.
[0035] In some embodiments, for each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, sending the monitoring location corresponding to the confidence alarm value to the alarm center of the target smart park specifically includes:
[0036] Select a confidence alarm value;
[0037] When the confidence alarm value is less than or equal to the confidence alarm threshold, no processing is performed;
[0038] When the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park;
[0039] Repeat the above steps and compare the remaining confidence alarm values with the confidence alarm threshold. When the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park to complete the fire alarm for the target smart park.
[0040] In a second aspect, the present application provides a smart campus fire alarm system, comprising:
[0041] An acquisition module is used to collect ambient temperature data through temperature sensors arranged at various monitoring locations in the target smart park to obtain ambient temperature data at various monitoring locations;
[0042] A processing module is used to extract credible intervals of each ambient temperature data to obtain multiple credible temperature domains, determine the temperature diffusion trend of each monitoring location based on all credible temperature domains, and then determine the critical alarm value of the ambient temperature at each monitoring location in the target smart park based on all temperature diffusion trends;
[0043] The processing module is also used to collect temperature interference data of temperature sensors at various monitoring locations in the target smart park to obtain temperature interference records, and determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring location based on the information entropy of the ambient temperature fluctuation at each monitoring location combined with the temperature interference records, and then determine the transient response amount of the temperature sensor at each monitoring location in the target smart park from all the transient fluctuation amounts;
[0044] The processing module is further used to perform confidence assessment on the critical alarm value at each monitoring position in the target smart park according to all transient response quantities, and obtain the confidence alarm value of the fire at each monitoring position in the target smart park;
[0045] The execution module is used to send the monitoring location corresponding to each confidence alarm value to the alarm center of the target smart park when the confidence alarm value is greater than the confidence alarm threshold.
[0046] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned smart campus fire alarm method.
[0047] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned smart campus fire alarm method.
[0048] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:
[0049] In the smart park fire alarm method, system, device and storage medium provided by the present application, first, ambient temperature data is collected by temperature sensors arranged at various monitoring positions in the target smart park to obtain ambient temperature data at various monitoring positions; a credible interval is extracted for each ambient temperature data to obtain multiple temperature credible domains, and the temperature diffusion trend of each monitoring position is determined according to all temperature credible domains, and then the critical alarm value of the ambient temperature at each monitoring position in the target smart park is determined according to all temperature diffusion trends; the temperature interference data of the temperature sensor at each monitoring position in the target smart park is collected to obtain a temperature interference record, and the transient fluctuation amount of the ambient temperature at the corresponding monitoring position is determined based on the information entropy of the ambient temperature fluctuation at each monitoring position combined with the temperature interference record, and then the transient response amount of the temperature sensor at each monitoring position in the target smart park is determined according to all transient fluctuation amounts; a confidence assessment is performed on the critical alarm value at each monitoring position in the target smart park according to all transient response amounts to obtain a confidence alarm value of a fire at each monitoring position in the target smart park; for each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring position corresponding to the confidence alarm value is sent to the alarm center of the target smart park.
[0050] It can be seen that in the present application, confidence assessment can be performed on the critical alarm values at each monitoring location in the target smart park based on all transient response quantities, and confidence alarm values for fires at each monitoring location in the target smart park can be obtained; wherein, firstly, linear fitting is performed on each temperature credible domain to obtain a temperature diffusion trend used to reflect the temperature distribution at each monitoring location, and then the temperature interference factor is combined with each temperature diffusion trend to extract an abnormal temperature warning value used to describe the degree of deviation between the current temperature at each monitoring location and the expected temperature range, and then all abnormal temperature warning values are quantified to obtain a critical alarm value that measures the ambient temperature threshold at the monitoring location, which helps to identify abnormal conditions or potential risks of fire at the monitoring location; secondly, based on the information entropy of the ambient temperature fluctuations at each monitoring location, feature extraction is performed on the temperature interference record to obtain a transient wave describing the degree of sudden fluctuations that occur when the ambient temperature at each monitoring location in the target smart park is disturbed. Momentum, and then quantify all transient fluctuations to obtain the transient response of the temperature sensor at each monitoring position to the transient interference characteristics. The transient response can reflect the response speed and accuracy of the temperature sensor to the fire alarm under the transient condition changes, and help improve the applicability and reliability of the temperature sensor in the real-time monitoring and fire alarm system; then, according to all the transient response quantities, the critical alarm value at each monitoring position in the target smart park is confidence evaluated to obtain the confidence alarm value reflecting the degree of credibility when the alarm is issued at each monitoring position, thereby improving the accuracy of the alarm at each monitoring position; finally, for each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring position corresponding to the confidence alarm value is sent to the alarm center of the target smart park; in summary, the solution of the present application can realize the confidence alarm of fire in the environment where there is interference with the accuracy of the temperature sensor in the smart park, thereby improving the accuracy of the fire alarm. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 is an exemplary flow chart of a smart campus fire alarm method according to some embodiments of the present application;
[0052] Figure 2 is a schematic diagram of a process for determining a temperature diffusion trend in some embodiments of the present application;
[0053] Figure 3 is a schematic diagram of a process for determining transient fluctuation amount in some embodiments of the present application;
[0054] Figure 4 is a structural block diagram of a smart park fire alarm system in some embodiments of the present application;
[0055] Figure 5It is a structural diagram of a computer device for implementing a smart campus fire alarm method according to some embodiments of the present application. DETAILED DESCRIPTION
[0056] The core of this application is to collect ambient temperature data through temperature sensors arranged at various monitoring positions in the target smart park to obtain ambient temperature data at various monitoring positions; extract credible intervals for each ambient temperature data to obtain multiple temperature credible domains, determine the temperature diffusion trend of each monitoring position based on all temperature credible domains, and then determine the critical alarm value of the ambient temperature at each monitoring position in the target smart park based on all temperature diffusion trends; collect temperature interference data of temperature sensors at various monitoring positions in the target smart park to obtain temperature interference records, determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring position based on the information entropy of the ambient temperature fluctuation at each monitoring position combined with the temperature interference records, and then determine the transient response amount of the temperature sensor at each monitoring position in the target smart park based on all transient fluctuation amounts; perform confidence assessment on the critical alarm value at each monitoring position in the target smart park based on all transient response amounts to obtain the confidence alarm value of the fire at each monitoring position in the target smart park; for each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring position corresponding to the confidence alarm value is sent to the alarm center of the target smart park. The solution of the present application can realize a confident alarm for fire in an environment where there is interference with the accuracy of the temperature sensor in a smart park, thereby improving the accuracy of the fire alarm.
[0057] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a smart campus fire alarm method according to some embodiments of the present application. The smart campus fire alarm method 100 mainly includes the following steps:
[0058] In step 101, ambient temperature data is collected by temperature sensors arranged at various monitoring locations in the target smart park to obtain ambient temperature data at various monitoring locations.
[0059] In specific implementation, temperature sensors arranged at various monitoring locations in the target smart park are used to collect the ambient temperature every 30 seconds, and an ordered sequence of ambient temperature values collected every 30 seconds in the past 15 minutes is used as the ambient temperature data at each monitoring location.
[0060] In step 102, credible intervals are extracted for each ambient temperature data to obtain multiple credible temperature domains, and the temperature diffusion trend of each monitoring location is determined based on all the credible temperature domains. Then, the critical alarm value of the ambient temperature at each monitoring location in the target smart park is determined based on all the temperature diffusion trends.
[0061] In some embodiments, extracting credible intervals of various ambient temperature data to obtain multiple credible temperature domains may be achieved by using the following steps:
[0062] Obtain historical ambient temperature data and historical electromagnetic interference data at each monitoring location;
[0063] Determine the temperature interference factor of the target smart park when the electronic equipment generates electromagnetic interference based on all historical ambient temperature data and all historical electromagnetic interference data;
[0064] Determine the credible deviation value of the temperature at each monitoring location through the ambient temperature data of each monitoring location;
[0065] Determine the upper limit of the temperature credible interval and the lower limit of the temperature credible interval at each monitoring position according to the temperature interference factor and all credible deviation values;
[0066] The corresponding ambient temperature data is extracted through the upper and lower bounds of the temperature credible interval at each monitoring location to obtain multiple temperature credible domains.
[0067] It should be noted that in the present application, the smart industrial zone usually includes large-scale power equipment and power distribution systems, such as transformers, power generators, arc furnaces, etc. These devices will generate strong electromagnetic fields when running, especially when the switch is operated or the load changes, which may cause sudden electromagnetic interference. Electromagnetic interference can cause sensors to mistakenly identify non-fire signals as fire signals, such as mistaking the electromagnetic waves generated by the operation of the equipment for smoke or flames. In addition, electromagnetic interference can also cause the real fire signal to be shielded or partially shielded, making it impossible to detect the fire in a timely and accurate manner when it occurs.
[0068] In the specific implementation, the historical ambient temperature data and historical electromagnetic interference data at different monitoring locations are obtained from the database of the data management center of the target smart park. It should be noted that the historical electromagnetic interference data described in this application is a sequence consisting of electromagnetic interference information collected every 30 seconds over the past three days, wherein the electromagnetic interference information in the historical electromagnetic interference data includes electric field strength and magnetic field strength, and electromagnetic interference measurement equipment (such as a spectrum analyzer) can be used to measure the electromagnetic interference information at the monitoring location.
[0069] It should also be noted that the historical ambient temperature data described in this application is a sequence of ambient temperature values collected every 30 seconds over the past three days.
[0070] In specific implementation, the temperature interference factor of the target smart park when the electronic device generates electromagnetic interference can be determined based on all historical ambient temperature data and all historical electromagnetic interference data. The following method can be used, namely: first, the historical ambient temperature data is used as the dependent variable, and the historical electromagnetic interference data is used as the independent variable. Then, all the historical ambient temperature data and all the historical electromagnetic interference data are used to train the machine learning model (for example, support vector machine (SVM)). After the training, the weight coefficients of the machine learning model with respect to the electric field strength and the magnetic field strength can be obtained. Finally, the two weight coefficients are normalized to the minimum and maximum values, and the two normalized values are added together, and the added value is used as the temperature interference factor of the target smart park when the electronic device generates electromagnetic interference. Other methods can also be used in other embodiments, which will not be repeated here.
[0071] It should be noted that the temperature interference factor described in the present application reflects the degree of influence of the electromagnetic interference generated by the electronic equipment on the temperature at each monitoring location in the target smart park. The larger the temperature interference factor, the greater the influence of the electromagnetic interference generated by the electronic equipment on the temperature at each monitoring location in the target smart park. Conversely, the electromagnetic interference generated by the electronic equipment on the temperature at each monitoring location in the target smart park is smaller.
[0072] In specific implementation, the credible deviation value of the temperature at each monitoring location is determined by the ambient temperature data of each monitoring location, which can be implemented in the following manner, namely: first, in order to estimate a higher degree of reliability for the ambient temperature data, the confidence level of all ambient temperature data is set to 99% in this application, wherein the confidence level is a probability value used to describe the reliability of the estimation result. In other embodiments, different confidence levels can be selected according to actual needs. Secondly, the critical value under the 99% confidence level is obtained through Python, and then the total number of ambient temperature values in the ambient temperature data is squared, and the value obtained after the square root is used as the total number of square root values, and then the critical value is divided by the total number of square root values, and the value obtained by the division is used as the confidence critical value. Then, the mean of the ambient temperature data at each monitoring location is calculated, and each mean obtained is multiplied by the confidence critical value, and each value obtained by the multiplication is used as the credible deviation value at the corresponding monitoring location. In other embodiments, other methods can also be used to implement it, which are not limited here.
[0073] It should be noted that the credible deviation value described in this application represents the estimated accuracy of the mean temperature at the monitoring location at a 99% confidence level. A smaller credible deviation value means that the estimate of the mean temperature is more accurate and reliable, which can evaluate the reliability of temperature data at different locations and provide a basis for further analysis, such as providing a reference when comparing temperature change trends at different locations.
[0074] Determining the upper limit of the temperature credible interval and the lower limit of the temperature credible interval at each monitoring position according to the temperature interference factor and all credible deviation values can be achieved in the following manner, namely: selecting a monitoring position, calculating the mean and variance of the environmental data at the monitoring position, using the mean at the position to add the variance and credible deviation value of the monitoring position in turn, then adding the temperature interference factor to the summed value, and using the summed value as the upper limit of the temperature credible interval at the monitoring position, subtracting the variance and credible deviation value of the monitoring position from the mean at the position in turn, then subtracting the temperature interference factor from the mean, and using the difference value as the lower limit of the temperature credible interval at the monitoring position, repeating the above steps to obtain the upper limit of the temperature credible interval and the lower limit of the temperature credible interval at all remaining monitoring positions in turn. Other methods can also be used in other embodiments, which will not be repeated here.
[0075] In specific implementation, the corresponding ambient temperature data is extracted through the upper limit of the temperature credible interval and the lower limit of the temperature credible interval at each monitoring location, and multiple temperature credible domains can be obtained in the following way, namely: select a monitoring location, and form an ordered region with ambient temperature values whose environmental data at the monitoring location is less than or equal to the upper limit of the temperature credible interval at the monitoring location and greater than or equal to the lower limit of the temperature credible interval at the monitoring location, and use the obtained region as the temperature credible domain at the monitoring location, repeat the above steps to obtain the temperature credible domains at the remaining monitoring locations.
[0076] It should be noted that the temperature credible domain described in the present application is an ordered area composed of ambient temperature values between the upper limit of the temperature credible interval and the lower limit of the temperature credible interval. The temperature credible domain represents the credible range of the temperature parameter at the monitoring location, indicating that under electromagnetic interference, there is a 99% confidence level that the actual ambient temperature value will fall within this area. The temperature credible domain is an area composed of the upper limit of the temperature credible interval and the lower limit of the temperature credible interval, wherein the upper limit of the temperature credible interval represents the maximum value of the overall temperature based on the ambient temperature data at a 99% confidence level, and the lower limit of the temperature credible interval represents the minimum value of the overall temperature based on the ambient temperature data at a 99% confidence level. In addition, it should be noted that one temperature credible domain corresponds to one monitoring location.
[0077] In some embodiments, reference Figure 2 As shown, this figure is a schematic diagram of the process of determining the temperature diffusion trend in some embodiments of the present application. In this embodiment, the temperature diffusion trend of each monitoring position can be determined according to all temperature credible domains, which can be achieved by the following steps:
[0078] First, in step 1021, each temperature credible domain is standardized to obtain a plurality of standard temperature credible domains;
[0079] Next, in step 1022, linear fitting is performed on all standard ambient temperature values in each standard temperature credible domain to obtain a plurality of temperature credible fitting curves;
[0080] Then, in step 1023, the temperature diffusion trend of each monitoring position is determined according to all the temperature credible fitting curves.
[0081] In specific implementation, the maximum absolute value normalization algorithm can be used to standardize all ambient temperature values in each temperature trusted domain, and the standardized temperature trusted domains are all used as standard temperature trusted domains. At the same time, all values in the standard temperature trusted domain are used as standard ambient temperature values, thereby obtaining multiple standard temperature trusted domains.
[0082] It should be noted that the maximum absolute value normalization algorithm used in this application will not change the distribution shape of the data in the spatial temperature distribution. At the same time, the maximum absolute value normalization is more robust in handling outliers, and outliers will not have too much impact on other data points. Other methods can also be used in other embodiments, which will not be repeated here.
[0083] In specific implementation, linear fitting is performed on all standard ambient temperature values in each standard temperature credible domain to obtain multiple temperature credible fitting curves, which can be achieved in the following manner, namely: the least squares support vector machine algorithm in the prior art is used to fit all standard ambient temperature values in the standard temperature credible domain, and the fitted curve is used as the temperature credible fitting curve of the corresponding standard temperature credible domain. Other methods can also be used in other embodiments, which are not limited here.
[0084] It should be noted that in this application, the values on each temperature credible fitting curve are used as temperature credible fitting values, and each temperature credible fitting value corresponds to a standard ambient temperature value. It should also be noted that in this application, a temperature fitting curve corresponds to a monitoring position.
[0085] In specific implementation, the temperature diffusion trend of each monitoring position can be determined based on all the temperature credible fitting curves in the following manner, namely: select a temperature credible fitting curve, select the position with the maximum derivative and the position with the minimum derivative from the temperature credible fitting curve, then calculate the slope between the position with the maximum derivative and the position with the minimum derivative, and use the slope as the temperature diffusion trend at the monitoring position corresponding to the temperature credible fitting curve, repeat the above steps to obtain the temperature diffusion trend at the monitoring position corresponding to the remaining temperature credible fitting curves. Other methods can also be used in other embodiments, which will not be repeated here.
[0086] It should be noted that the temperature diffusion trend described in the present application reflects the diffusion trend of the temperature distribution at the monitoring position. The greater the temperature diffusion trend, the more obvious the diffusion trend of the temperature distribution at the monitoring position. Conversely, the less obvious the diffusion trend of the temperature distribution at the monitoring position. The temperature diffusion trend can be used to identify monitoring positions with abnormal temperature change trends, which is helpful to identify and prevent the occurrence of fires. In addition, it should be noted that in the present application, one temperature diffusion trend corresponds to one monitoring position, and each temperature diffusion trend corresponds to a temperature fitting curve.
[0087] In some embodiments, determining the critical alarm value of the ambient temperature at each monitoring location in the target smart park based on all temperature diffusion trends can be achieved by using the following steps:
[0088] Obtaining the temperature interference factor;
[0089] Determine the abnormal temperature warning value of each monitoring location in the target smart park based on all temperature diffusion trends;
[0090] The critical alarm value of the ambient temperature at each monitoring location in the target smart park is determined by the temperature interference factor and all abnormal temperature warning values.
[0091] In specific implementation, the abnormal temperature warning value of each monitoring location in the target smart park is determined according to all temperature diffusion trends. The following method can be used, namely: select a temperature diffusion trend, subtract all the temperature credible fitting values on the temperature fitting curve corresponding to the temperature diffusion trend from the standard ambient temperature value corresponding to each temperature credible fitting value, and use the values obtained by the difference as the temperature characteristic residuals corresponding to the standard ambient temperature value, and then calculate the mean of all temperature characteristic residuals, and then multiply the obtained mean by the temperature diffusion trend, and use the multiplied value as the abnormal temperature warning value at the monitoring location in the target smart park corresponding to the temperature diffusion trend, repeat the above steps to obtain the abnormal temperature warning values at the monitoring locations in the target smart park corresponding to the remaining temperature diffusion trends. Other methods can also be used in other embodiments, which are not limited here.
[0092] It should be noted that the abnormal temperature warning value described in the present application represents a warning value of the degree of deviation between the current temperature and the expected temperature range. The abnormal temperature warning value can be used to identify potential abnormal temperature changes at the monitoring location of the target smart park, and corresponding preventive or response measures can be taken. In addition, it should be noted that one abnormal temperature warning value corresponds to one monitoring location in the target smart park.
[0093] In specific implementation, the critical alarm value of the ambient temperature at each monitoring location in the target smart park is determined by the temperature interference factor and all abnormal temperature warning values. The following method is used, namely: first, the abnormal temperature warning value with the largest value and the abnormal temperature warning value with the smallest value are selected from all the abnormal temperature warning values, the smallest abnormal temperature warning value is subtracted from the largest abnormal temperature warning value, and the subtracted value is multiplied by the temperature interference factor, and the multiplied value is used as the fire alarm interval value, and then each abnormal temperature warning value is multiplied by the fire alarm interval value, and all the multiplied values are used as the critical alarm value of the ambient temperature at the monitoring location in the target smart park corresponding to each abnormal temperature warning value. Other methods can also be used in other embodiments, which are not limited here.
[0094] It should be noted that the critical alarm value described in the present application represents the threshold value of the ambient temperature at the monitoring location. When the ambient temperature reaches or exceeds this threshold, an alarm is triggered. The critical alarm value can be used to monitor abnormal conditions or potential risks of fire at various monitoring locations in the smart park so that necessary countermeasures can be taken.
[0095] In step 103, the temperature interference data of the temperature sensors at each monitoring location in the target smart park are collected to obtain temperature interference records. The transient fluctuation amount of the ambient temperature at the corresponding monitoring location is determined based on the information entropy of the ambient temperature fluctuation at each monitoring location combined with the temperature interference records. Then, the transient response amount of the temperature sensors at each monitoring location in the target smart park is determined from all the transient fluctuation amounts.
[0096] In the specific implementation, the temperature interference data of the temperature sensors at each monitoring location in the interference target smart park are collected, and the set of all temperature sensor data is recorded as humidity interference.
[0097] It should be noted that the humidity at the monitoring location in the present application will affect the performance of the temperature sensor (such as the resistance temperature detector), resulting in inaccurate readings; the stability of the power supply voltage connected to the temperature sensor at the monitoring location will affect the working state of the electronic components of the temperature sensor, resulting in measurement errors or temporary failure of the sensor; the wind speed at the monitoring location will affect the air flow around the temperature sensor, causing the temperature measured by the temperature sensor to deviate from the actual ambient temperature. For example, strong winds may take away heat and cause the temperature sensor reading to be low; the vibration and impact generated by mechanical equipment near the monitoring location during operation will affect the installation stability of the temperature sensor, resulting in instantaneous fluctuations or errors in the readings.
[0098] It should be noted that the temperature interference data in the present application is composed of humidity data, wind speed data, voltage data and mechanical vibration data, and the humidity data, wind speed data, voltage data and mechanical vibration data are all used as temperature interference component data, and all values in the temperature interference component data are used as temperature interference component values, wherein, a humidity sensor is used at the monitoring position to collect humidity once every 30 seconds, and an ordered sequence of humidity values collected every 30 seconds in the past 15 minutes is used as humidity data at the monitoring position; a hot wire anemometer is used at the monitoring position to collect wind speed once every 30 seconds, and an ordered sequence of wind speed values collected every 30 seconds in the past 15 minutes is used as wind speed data at the monitoring position; a voltage sensor is used at the monitoring position to collect voltage once every 30 seconds, and an ordered sequence of voltage values collected every 30 seconds in the past 15 minutes is used as voltage data at the monitoring position; a vibration sensor is used at the monitoring position to collect vibration amplitude once every 30 seconds, and an ordered sequence of vibration amplitude values collected every 30 seconds in the past 15 minutes is used as mechanical vibration data at the monitoring position.
[0099] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of the process of determining the transient fluctuation amount in some embodiments of the present application. In this embodiment, the transient fluctuation amount of the ambient temperature at the corresponding monitoring position is determined based on the information entropy of the ambient temperature fluctuation at each monitoring position combined with the temperature interference record, which can be implemented by the following steps:
[0100] First, in step 1031, the ambient temperature data at each monitoring location is obtained;
[0101] Secondly, in step 1032, the information entropy of the ambient temperature fluctuation at each monitoring location is determined based on all the ambient temperature data;
[0102] Then, in step 1033, the interference fluctuation vector space of the ambient temperature is determined through the temperature interference record;
[0103] Finally, in step 1034, the transient fluctuation amount of the ambient temperature at the corresponding monitoring position is determined according to the information entropy of the ambient temperature fluctuation at each monitoring position and the interference fluctuation vector space.
[0104] It should be noted that the information entropy of ambient temperature fluctuations in the present application is an indicator for measuring the uncertainty and complexity in ambient temperature data, which quantifies the randomness and distribution characteristics of ambient temperature data. The higher the information entropy value, the more abnormal conditions there are in the smart industrial park. For example, sudden temperature changes indicate equipment failure or local high temperature events. As a preferred embodiment, the information entropy of ambient temperature fluctuations at each monitoring location is determined based on all ambient temperature data. This can be achieved in the following way, namely: for each monitoring location, kernel density estimation (such as Gaussian kernel density estimation) is used to calculate the probability distribution of temperature values in the ambient data at each monitoring location, and then the information entropy in the prior art is used to perform entropy feature description on the probability distribution obtained at each monitoring location, and the value obtained after the entropy feature description is used as the information entropy of the ambient temperature fluctuation at the corresponding monitoring location.
[0105] In specific implementation, the interference fluctuation vector space of the ambient temperature determined by the temperature interference record can be implemented in the following manner, namely: first, create a sliding window, use the total number of temperature interference components in the temperature interference data of the temperature interference record as the window step, and set the length of the sliding window to a value of the same size as the window step; then, select a temperature interference data from the temperature interference record, and then select a temperature interference component data from the temperature interference data, align the sliding window with the first temperature interference component value in the temperature interference component data, select the largest temperature interference component value from the temperature interference component values covered by the sliding window, and use the largest temperature interference component value as the maximum temperature interference component value; then move the sliding window to align the sliding window with the second temperature interference component value in the temperature interference component data. Temperature interference component value, select the largest temperature interference component value from the temperature interference component values covered by the sliding window, and use the largest temperature interference component value as the maximum temperature interference component value, repeat the above steps, move the sliding window in sequence until the first position of the sliding window is aligned with the last temperature interference component value in the temperature interference component data, and stop moving, and form all the obtained maximum temperature interference component values into a vector according to the sliding window movement order, and use the vector as the interference fluctuation vector of the ambient temperature, repeat the above steps, perform the same processing on the temperature interference component data of all the temperature interference data in the temperature interference record, obtain the remaining interference fluctuation vectors, and use the set composed of all the interference fluctuation vectors as the interference fluctuation vector space. In other embodiments, other methods can also be used for implementation, which is not limited here.
[0106] It should be noted that the interference fluctuation vector space described in the present application is a set composed of multiple interference fluctuation vectors, wherein the interference fluctuation vectors in the interference fluctuation vector space represent abnormal fluctuation sequences generated by different types of data of the ambient temperature at the interference monitoring location. The interference fluctuation vectors can be used to quickly monitor the abnormal conditions of the sensor equipment, and then extract the trend characteristics of the interference from the interference fluctuation vectors.
[0107] In specific implementation, the following method can be used to determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring position based on the information entropy of the ambient temperature fluctuation at each monitoring position and the interference fluctuation vector space, namely: first, use a clustering algorithm (such as k-means clustering, which is not limited here) to extract outliers from each interference fluctuation vector in the interference fluctuation vector space, where the outliers represent the maximum temperature interference component value, and then calculate the mean of the outliers of each interference fluctuation vector, and use the obtained means as the outlier means of the corresponding interference fluctuation vector, select a monitoring position, multiply the information entropy of the ambient temperature fluctuation at the monitoring position by the outlier means of each interference fluctuation vector, and then add the values obtained after the multiplication, and use the value obtained after the addition as the transient fluctuation amount of the ambient temperature at the monitoring position, repeat the above steps to obtain the transient fluctuation amount of the ambient temperature at the remaining monitoring positions. In other embodiments, other methods can also be used for implementation, which will not be repeated here.
[0108] It should be noted that the transient fluctuation amount described in the present application represents the degree of sudden fluctuation that occurs when the ambient temperature at the monitoring location is disturbed. The larger the transient fluctuation amount, the higher the degree of sudden fluctuation that occurs when the ambient temperature at the monitoring location is disturbed, and vice versa. It should be noted that each transient fluctuation amount in the present application corresponds to a monitoring location.
[0109] In some embodiments, determining the transient response of the temperature sensor at each monitoring location in the target smart park from all transient fluctuations can be achieved by the following steps:
[0110] Obtaining the temperature interference factor;
[0111] Determine a transient interference characteristic sequence of the temperature sensor according to the temperature interference factor and all transient fluctuation quantities;
[0112] The transient interference feature sequence is used to determine the transient response of the temperature sensor at each monitoring location in the target smart park.
[0113] In specific implementation, determining the transient interference characteristic sequence of the temperature sensor according to the temperature interference factor and all transient fluctuation quantities can be implemented in the following manner, namely: sorting all transient fluctuation quantities in ascending order, taking the sequence obtained after sorting as the transient fluctuation sequence, selecting the first transient fluctuation quantity from the transient fluctuation sequence, subtracting the first transient fluctuation quantity from the second transient fluctuation quantity, and then dividing the subtracted value by the temperature interference factor, and taking the divided value as the transient interference characteristic value of the first transient fluctuation quantity, and then selecting the second transient fluctuation quantity from the transient fluctuation sequence. Momentum, subtract the second transient fluctuation amount from the third transient fluctuation amount, divide the subtracted value by the temperature interference factor, and use the divided value as the transient interference characteristic value of the second transient fluctuation amount, repeat the above steps until the penultimate transient fluctuation amount in the transient fluctuation sequence, subtract the mean of the transient fluctuation sequence from the penultimate transient fluctuation amount, divide the subtracted value by the temperature interference factor, and use the divided value as the transient interference characteristic value of the penultimate transient fluctuation amount. Other methods can also be used in other embodiments, which are not limited here.
[0114] It should be noted that the transient interference feature sequence described in the present application is an ordered sequence composed of multiple transient interference feature values. The transient interference feature values in the transient interference feature sequence are used to identify the abnormal behavior of the temperature sensor when it is subjected to sudden interference, thereby helping to quickly locate the monitoring position. It should also be noted that each transient interference feature value in the present application corresponds to a monitoring position.
[0115] In specific implementation, the transient response amount of the temperature sensor at each monitoring position in the target smart park can be determined by the transient interference feature sequence in the following manner, namely: select the first transient interference feature value from the transient interference feature sequence, calculate the straight-line distance between the monitoring position corresponding to the first transient interference feature value and the monitoring position corresponding to the second transient interference feature value, then divide the first transient interference feature value by the straight-line distance between the two, and use the value obtained by the division as the transient response amount of the temperature sensor at the monitoring position corresponding to the first transient interference feature value, then select the second transient interference feature value from the transient interference feature sequence, calculate the straight-line distance between the monitoring position corresponding to the second transient interference feature value and the third transient interference feature value. The straight-line distance between the monitoring positions corresponding to the characteristic values, and then divide the second transient interference characteristic value by the straight-line distance between the two, and use the value obtained by division as the transient response of the temperature sensor at the monitoring position corresponding to the second transient interference characteristic value, repeat the above steps until the penultimate transient interference characteristic value, calculate the straight-line distance between the monitoring position corresponding to the penultimate transient interference characteristic value and the monitoring position corresponding to the first transient interference characteristic value, and then divide the penultimate transient interference characteristic value by the straight-line distance between the two, and use the value obtained by division as the transient response of the temperature sensor at the monitoring position corresponding to the penultimate transient interference characteristic value. Other methods can also be used in other embodiments, which are not limited here.
[0116] It should be noted that the transient response quantity described in this application refers to a quantitative description of the response degree of the temperature sensor at the monitoring position to the transient interference characteristics. The transient response quantity can reflect the response speed and accuracy of the temperature sensor to the fire alarm under the instantaneous condition changes, and help improve the applicability and reliability of the temperature sensor in the real-time monitoring and fire alarm system.
[0117] In step 104, a confidence assessment is performed on the critical alarm value at each monitoring location in the target smart park based on all transient response quantities to obtain a confidence alarm value of a fire at each monitoring location in the target smart park.
[0118] In some embodiments, confidence evaluation is performed on the critical alarm values at each monitoring location in the target smart park based on all transient response quantities, and the confidence alarm values of fires at each monitoring location in the target smart park can be obtained by the following steps, namely:
[0119] Determine the abnormal state fluctuation entropy of the temperature sensor according to all transient response quantities;
[0120] Convert all transient response quantities into transient response quantity sequences;
[0121] Determine the abnormal confidence features at each monitoring location in the target smart park through the transient response quantity sequence and the abnormal state fluctuation entropy;
[0122] The confidence alarm value of a fire at each monitoring location in the target smart park is evaluated based on all abnormal confidence features and all critical alarm values.
[0123] It should be noted that the abnormal state fluctuation entropy of the temperature sensor in the present application refers to a measure of the intensity of the abnormal fluctuation in the output data of the temperature sensor. The greater the intensity of the abnormal fluctuation in the output data of the temperature sensor, the greater the abnormal state fluctuation entropy, and vice versa. As a preferred embodiment, determining the abnormal state fluctuation entropy of the temperature sensor based on all transient response quantities can be achieved in the following manner, namely: performing entropy feature description on all transient response quantities through the information entropy in the prior art, and using the value obtained after the entropy feature description as the abnormal state fluctuation entropy of the temperature sensor.
[0124] In specific implementation, converting all transient response quantities into a transient response quantity sequence can be achieved in the following manner, namely: sorting all transient response quantities in ascending order, and using the sequence obtained after sorting as the transient response quantity sequence.
[0125] In specific implementation, the abnormal confidence features at each monitoring position in the target smart park are determined by the transient response quantity sequence and the abnormal state fluctuation entropy, which can be achieved in the following manner, namely: first, all transient response quantities in the transient response quantity sequence are divided by the abnormal state fluctuation entropy, and the transient response quantity sequence after dividing by the abnormal state fluctuation entropy is used as a state response sequence, and each value in the state response sequence is used as a state response value, wherein each state response value corresponds to a monitoring position, and then, the first state response value is selected from the state response sequence, and then the state response values that are closest to the first state response value and have the same number as the window step value are selected from the state response sequence. , thereby forming an ordered sequence, and using the ordered sequence as the abnormal confidence feature at the monitoring position in the target smart park corresponding to the first state response value, and then selecting the second state response value from the state response sequence, and then selecting the state response value closest to the second state response value and the same number as the window step value from the state response sequence, thereby forming an ordered sequence, and using the ordered sequence as the abnormal confidence feature at the monitoring position in the target smart park corresponding to the second state response value, repeating the above steps, and obtaining the abnormal confidence features at the monitoring position in the target smart park corresponding to the remaining state response values in turn. Other methods can also be used in other embodiments, which are not limited here.
[0126] It should be noted that the abnormal confidence feature described in the present application reflects the sequence of the degree of credibility when an abnormal state occurs between monitoring positions within a certain range. The abnormal confidence feature can be used to determine the effective range of abnormalities at different monitoring positions, and potential abnormal states in ambient temperature data can be quickly identified. It should also be noted that each abnormal confidence feature in the present application corresponds to a monitoring position.
[0127] It should be noted that the confidence alarm value described in the present application reflects the parameter value of the degree of credibility when an alarm is issued at the monitoring location. The larger the confidence alarm value, the greater the degree of credibility when an alarm is issued at the monitoring location of the target smart park, that is, the higher the accuracy of the alarm at the monitoring location of the target smart park. As a preferred embodiment, the confidence alarm value of a fire at each monitoring location of the target smart park is evaluated based on all abnormal confidence features and all critical alarm values. The following method can be used, namely: select an abnormal confidence feature, calculate the variance of all remaining abnormal confidence features, and use the abnormal confidence feature with the largest variance value as the target abnormal setting Confidence feature, then, all the state response values in the abnormal confidence feature are multiplied by the critical alarm value at the monitoring position corresponding to the abnormal confidence feature, and then all the multiplied values are summed up, and the summed value is divided by the maximum state response value in the target abnormal confidence feature, and then the divided value is used as the confidence alarm value at the monitoring position in the target smart park corresponding to the abnormal confidence feature, and the above steps are repeated to obtain the confidence alarm values of the remaining abnormal confidence features corresponding to the monitoring positions in the target smart park. It should be noted that each confidence alarm value in the present application corresponds to a monitoring position, and other methods can also be used to achieve it in other embodiments, which will not be repeated here.
[0128] In step 105, for each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park.
[0129] In some embodiments, for each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park, which can be implemented by the following steps:
[0130] Select a confidence alarm value;
[0131] When the confidence alarm value is less than or equal to the confidence alarm threshold, no processing is performed;
[0132] When the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park;
[0133] Repeat the above steps and compare the remaining confidence alarm values with the confidence alarm threshold. When the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park, and finally a fire alarm is realized for the target smart park.
[0134] In specific implementation, when the confidence alarm value is greater than the confidence alarm threshold, the sensor at the monitoring position corresponding to the confidence alarm value is used to send its own position coordinates to the alarm center of the target smart park.
[0135] It should be noted that the confidence alarm threshold described in the present application can be determined by the percentile method. For example: first, the 90th percentile is used as the confidence alarm threshold, and all confidence alarm values are sorted to obtain a sequence, for example, X=[2, 3, 4, 5, 6, 9, 11, 13, 20, 25, 30]. Secondly, the 90th percentile position 0.9×(10+1)=9.9 is calculated, and then the weighted average of the 9th and 10th confidence alarm values is taken, that is, the confidence alarm threshold=25+0.9×(30-25)=29.5. In other embodiments, the confidence alarm threshold can be determined according to actual needs, and is not limited here.
[0136] In addition, in another aspect of the present application, in some embodiments, the present application provides a smart campus fire alarm system, referring to Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a smart campus fire alarm system according to some embodiments of the present application. The smart campus fire alarm system 400 includes: an acquisition module 401, a processing module 402 and an execution module 403, which are described as follows:
[0137] Acquisition module 401, in this application, acquisition module 401 is mainly used to collect ambient temperature data through temperature sensors arranged at various monitoring locations in the target smart park, and obtain ambient temperature data at various monitoring locations;
[0138] Processing module 402, in this application, is used to extract credible intervals of each ambient temperature data to obtain multiple credible temperature domains, determine the temperature diffusion trend of each monitoring location based on all credible temperature domains, and then determine the critical alarm value of the ambient temperature at each monitoring location in the target smart park based on all temperature diffusion trends;
[0139] It should be noted that the processing module 402 described in the present application is also used to collect temperature interference data of temperature sensors at various monitoring locations in the target smart park to obtain temperature interference records, and determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring location based on the information entropy of the ambient temperature fluctuation at each monitoring location combined with the temperature interference record, and then determine the transient response amount of the temperature sensor at each monitoring location in the target smart park from all the transient fluctuation amounts;
[0140] In addition, the processing module 402 described in the present application is also used to perform confidence assessment on the critical alarm value at each monitoring position in the target smart park according to all transient response quantities, and obtain the confidence alarm value of the fire at each monitoring position in the target smart park;
[0141] Execution module 403. In the present application, execution module 403 is mainly used for each confidence alarm value. When the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park.
[0142] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned smart campus fire alarm method.
[0143] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device using a smart campus fire alarm method according to some embodiments of the present application. The smart campus fire alarm method in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.
[0144] Processor 501 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the smart campus fire alarm method in the present application.
[0145] The communication bus 502 may be used to transmit information between the above-mentioned components.
[0146] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.
[0147] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The method described in the above method embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.
[0148] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.
[0149] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).
[0150] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.
[0151] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned smart campus fire alarm method.
[0152] In summary, in the smart park fire alarm method, system, device and storage medium disclosed in the embodiments of the present application, ambient temperature data is collected by temperature sensors arranged at various monitoring locations in the target smart park to obtain ambient temperature data at each monitoring location; a credible interval is extracted for each ambient temperature data to obtain multiple temperature credible domains, and the temperature diffusion trend of each monitoring location is determined based on all the temperature credible domains, and then the critical alarm value of the ambient temperature at each monitoring location in the target smart park is determined based on all the temperature diffusion trends; the temperature interference data of the temperature sensors at each monitoring location in the target smart park are collected to obtain the temperature Interference records, based on the information entropy of the ambient temperature fluctuations at each monitoring location combined with the temperature interference records, determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring location, and then determine the transient response amount of the temperature sensor at each monitoring location in the target smart park from all the transient fluctuation amounts; perform confidence assessment on the critical alarm value at each monitoring location in the target smart park based on all the transient response amounts, and obtain the confidence alarm value of the fire at each monitoring location in the target smart park; for each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park. The solution of the present application can realize the confidence alarm of fire in an environment where there is interference with the accuracy of the temperature sensor in the smart park, thereby improving the accuracy of the fire alarm.
[0153] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0154] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A smart park fire alarm method, characterized in that: The steps include: The ambient temperature data at each monitoring location is collected by temperature sensors arranged at each monitoring location in the target smart park to obtain the ambient temperature data at each monitoring location; The trusted intervals of each ambient temperature data are extracted to obtain multiple trusted temperature domains. The temperature diffusion trend of each monitoring location is determined based on all the trusted temperature domains. The temperature diffusion trend reflects the diffusion trend of the temperature distribution at the monitoring location. Then, the critical alarm value of the ambient temperature at each monitoring location in the target smart park is determined based on all the temperature diffusion trends. Collect temperature disturbance data of temperature sensors at various monitoring locations in the target smart park to obtain temperature disturbance records, and determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring location based on the information entropy of the ambient temperature fluctuation at each monitoring location combined with the temperature disturbance records. The information entropy of the ambient temperature fluctuation is an indicator for measuring uncertainty and complexity in ambient temperature data, and then determine the transient response amount of the temperature sensors at various monitoring locations in the target smart park from all transient fluctuation amounts; According to all transient response quantities, confidence evaluation is performed on the critical alarm values at each monitoring location in the target smart park, and confidence alarm values of fires at each monitoring location in the target smart park are obtained, wherein the confidence alarm values reflect the parameter values of the credibility of the alarm at the monitoring location; For each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park; Among them, the trusted intervals of each ambient temperature data are extracted to obtain multiple temperature trusted domains, including: Obtain historical ambient temperature data and historical electromagnetic interference data at each monitoring location; Determine the temperature interference factor of the target smart park when the electronic equipment generates electromagnetic interference based on all historical ambient temperature data and all historical electromagnetic interference data; Determine the credible deviation value of the temperature at each monitoring location through the ambient temperature data of each monitoring location; Determine the upper limit of the temperature credible interval and the lower limit of the temperature credible interval at each monitoring position according to the temperature interference factor and all credible deviation values; The corresponding ambient temperature data is extracted through the upper bound and lower bound of the temperature credible interval of each monitoring location to obtain multiple temperature credible domains; Among them, determining the temperature diffusion trend of each monitoring location based on all temperature credible domains specifically includes: Standardize each temperature credible domain to obtain multiple standard temperature credible domains; Perform linear fitting on all standard ambient temperature values in each standard temperature credible domain to obtain multiple temperature credible fitting curves; Determine the temperature diffusion trend of each monitoring location based on all temperature credible fitting curves; Among them, determining the transient fluctuation amount of the ambient temperature at the corresponding monitoring position based on the information entropy of the ambient temperature fluctuation at each monitoring position in combination with the temperature interference record specifically includes: Obtaining ambient temperature data at each monitoring location; Determine the information entropy of the ambient temperature fluctuation at each monitoring location based on all ambient temperature data; Determine the disturbance fluctuation vector space of the ambient temperature through the temperature disturbance record; Determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring position according to the information entropy of the ambient temperature fluctuation at each monitoring position and the interference fluctuation vector space; Among them, confidence evaluation is performed on the critical alarm values at each monitoring location in the target smart park according to all transient response quantities, and the confidence alarm values of fires at each monitoring location in the target smart park are obtained, which specifically include: Determine the abnormal state fluctuation entropy of the temperature sensor according to all transient response quantities; Convert all transient response quantities into transient response quantity sequences; Determine the abnormal confidence features at each monitoring location in the target smart park through the transient response quantity sequence and the abnormal state fluctuation entropy; The confidence alarm value of a fire at each monitoring location in the target smart park is evaluated based on all abnormal confidence features and all critical alarm values.
2. The method according to claim 1, characterized in that The critical alarm values of the ambient temperature at each monitoring location in the target smart park are determined by all temperature diffusion trends, including: Obtaining the temperature interference factor; Determine the abnormal temperature warning value of each monitoring location in the target smart park based on all temperature diffusion trends; The critical alarm value of the ambient temperature at each monitoring location in the target smart park is determined by the temperature interference factor and all abnormal temperature warning values.
3. The method according to claim 1, characterized in that For each confidence alarm value, when the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park, specifically including: Select a confidence alarm value; When the confidence alarm value is less than or equal to the confidence alarm threshold, no processing is performed; When the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park; Repeat the above steps and compare the remaining confidence alarm values with the confidence alarm threshold. When the confidence alarm value is greater than the confidence alarm threshold, the monitoring location corresponding to the confidence alarm value is sent to the alarm center of the target smart park to complete the fire alarm for the target smart park.
4. A smart park fire alarm system, characterized in that: The method described in any one of claims 1 to 3 is used for fire alarm, and the smart park fire alarm system comprises: An acquisition module is used to collect ambient temperature data through temperature sensors arranged at various monitoring locations in the target smart park to obtain ambient temperature data at various monitoring locations; A processing module is used to extract credible intervals of each ambient temperature data to obtain multiple credible temperature domains, determine the temperature diffusion trend of each monitoring location based on all credible temperature domains, and then determine the critical alarm value of the ambient temperature at each monitoring location in the target smart park based on all temperature diffusion trends; The processing module is also used to collect temperature interference data of temperature sensors at various monitoring locations in the target smart park to obtain temperature interference records, and determine the transient fluctuation amount of the ambient temperature at the corresponding monitoring location based on the information entropy of the ambient temperature fluctuation at each monitoring location combined with the temperature interference records, and then determine the transient response amount of the temperature sensor at each monitoring location in the target smart park from all the transient fluctuation amounts; The processing module is further used to perform confidence assessment on the critical alarm value at each monitoring position in the target smart park according to all transient response quantities, and obtain the confidence alarm value of the fire at each monitoring position in the target smart park; The execution module is used to send the monitoring location corresponding to each confidence alarm value to the alarm center of the target smart park when the confidence alarm value is greater than the confidence alarm threshold.
5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the smart park fire alarm method described in any one of claims 1 to 3 is implemented.
6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the smart park fire alarm method according to any one of claims 1 to 3 is implemented.
Citation Information
Patent Citations
Intelligent fire risk early warning method and system based on multi-source data fusion
CN117746602A
Fiber optic temperature sensors in a distributed smoke detection system
US20200370969A1
Fire detector
US6064064A
