A smart park energy-saving fire alarm

Abstract

The present invention discloses a smart park energy-saving fire alarm, which relates to the technical field of fire alarm. The present invention comprises a detection module, a processing module, an adaptive energy-saving module and an intelligent alarm module; the detection module is used to detect smoke, temperature and combustible gas concentration in the park through sensors; various types of sensors are deployed at key positions in the park, including smoke sensors, temperature sensors and combustible gas sensors. The present invention realizes dynamic adjustment of the working state of the sensor through the adaptive energy-saving module, which significantly reduces the monitoring energy consumption. The module intelligently adjusts the sampling frequency and sensitivity of the sensor according to real-time environmental data and historical events, effectively reduces energy consumption while ensuring safe monitoring, especially at night or during unmanned periods, and further achieves energy conservation and emission reduction by reducing the operating intensity of the sensor.

Description

Technical Field

[0001] The present invention relates to the technical field of fire alarm technology, and in particular to an energy-saving fire alarm for a smart park. Background Art

[0002] In traditional fire alarm systems, fixed sensor deployment strategies are usually adopted. These systems tend to operate with the same sensitivity and sampling frequency at all times, resulting in high energy consumption. In addition, due to the lack of dynamic analysis of environmental changes and historical data, these systems may not be able to accurately judge the real fire risk and are prone to false alarms or missed alarms. False alarms will not only interfere with the normal operation of the park, but may also cause users to lose trust in the alarm system. At the same time, traditional systems still maintain a high-intensity monitoring state at night or during unmanned periods, resulting in energy waste.

[0003] With the introduction of the concepts of smart cities and smart parks, the requirements for fire alarm systems are also increasing. Modern parks not only require high-efficiency and high-accuracy fire detection, but also require the system to be able to intelligently adjust the working state according to actual usage and environmental changes to achieve energy conservation and emission reduction. The fire alarm system of a smart park needs to be able to integrate advanced sensor technology, data processing capabilities and adaptive algorithms to improve the intelligence level of fire prevention and response. At the same time, the system should also provide a variety of alarm methods to adapt to different usage scenarios and user needs.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] The purpose of the present invention is to solve the problems of high energy consumption, high false alarm and missed alarm rate, and inability to adapt to environmental changes and user needs of traditional fire alarm systems, and to propose an energy-saving fire alarm for a smart park.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A smart park energy-saving fire alarm, comprising:

[0008] Detection module, used to detect smoke, temperature and combustible gas concentration in the park through sensors;

[0009] The processing module is used to process and analyze the data obtained in the detection module to determine whether an alarm is needed;

[0010] The adaptive energy-saving module is used to dynamically adjust the working state of the sensor based on environmental changes and historical data, effectively reducing monitoring energy consumption. The specific process is as follows:

[0011] Regularly collect environmental data on temperature, humidity, and light intensity, analyze past alarm events, sensor trigger frequencies, and environmental change patterns, and evaluate sensor sensitivity, sampling frequency, and energy consumption levels;

[0012] Through algorithms, sensor parameters are dynamically adjusted according to the environment and historical data, and dynamic thresholds based on data are set for sensors, which can reduce sampling frequency during low-risk periods, increase sensitivity during high-risk periods, and reduce sensor operation intensity at night or during unmanned periods.

[0013] Monitor the environment and sensor status in real time, adjust the energy-saving strategy according to the data, and provide a user interface to allow users to customize the sensor working mode and energy-saving strategy; obtain the energy-saving judgment value through comprehensive analysis of test parameters, compare the energy-saving judgment value with the preset energy-saving judgment threshold, determine whether the energy-saving strategy meets the standard, and optimize the adaptive algorithm based on the energy-saving judgment value and user feedback;

[0014] Record the operation and effect of the energy-saving module, generate energy-saving reports, and ensure that the energy-saving module is integrated with other modules to achieve collaborative work;

[0015] The intelligent alarm module is used to provide diversified alarm methods to adapt to different usage scenarios.

[0016] Furthermore, the process of the adaptive energy-saving module monitoring the environment and sensor status in real time and adjusting the energy-saving strategy according to the data is as follows:

[0017] Define one or more low-power modes for each sensor, including reducing sampling frequency, reducing sensitivity, or entering sleep state;

[0018] Then, a schedule is established based on the working and non-working hours of the park to determine when to apply low-power mode;

[0019] Continuously monitor environmental data, including temperature, humidity, and light conditions, to assess whether environmental conditions are suitable for the sensor to operate in low-power mode;

[0020] Analyze historical data to determine the frequency and pattern of sensor triggering in different time periods to identify low-risk periods and put existing sensors into low-power mode during low-risk periods;

[0021] Analyze user behavior patterns, including working hours and rest time, to adjust energy-saving strategies;

[0022] According to preset algorithms, the working status of sensors is automatically adjusted according to schedules, environmental data and historical data;

[0023] Implement real-time monitoring, continuously adjust the sensor's operating mode and parameters according to environmental changes and sensor status, and based on real-time monitoring data.

[0024] Furthermore, the specific operation steps of the adaptive energy-saving module to obtain the energy-saving judgment value through comprehensive analysis of the test parameters are as follows:

[0025] The performance test parameters include:

[0026] Energy consumption data: Quantify the energy consumption of sensors in different time periods, including power consumption and power usage, and compare the energy consumption when no energy-saving strategy is implemented to calculate the average energy saving;

[0027] Alarm accuracy: Count the number of false alarms and missed alarms after energy-saving strategies are implemented, and calculate the average response time for each alarm. After normalization, multiply the sum of the number of false alarms and missed alarms by the average response time for each alarm to obtain the accurate judgment value;

[0028] Failure rate: Statistics on the failure rate of sensors after the implementation of energy-saving strategies, including false alarms and missed alarms;

[0029] The obtained average energy saving amount, criterion value and failure rate are normalized and then input into the following formula: To obtain the energy saving value JFZ, where ng, zm and gm are the average energy saving amount, the accurate judgment value and the failure rate, respectively. is the correction coefficient, and the obtained energy-saving value is used as the standard to measure the effect of the energy-saving strategy.

[0030] Furthermore, the processing module processes and analyzes the data obtained by the detection module to determine whether an alarm is required. The specific operation steps are as follows:

[0031] Obtain smoke density, temperature and combustible gas concentration data from the detection module in real time, and combine the real-time data with historical data and environmental parameters for comprehensive analysis;

[0032] Identify unusual patterns or threshold exceedances in data and apply statistical and machine learning algorithms to predict fire risk;

[0033] Set thresholds for smoke, temperature and combustible gases according to safety standards and revise them based on external factors when setting them;

[0034] Based on the analysis results, determine whether to trigger an alarm, determine the urgency and priority of the alarm, and work with the adaptive energy-saving module to adjust the sensor working state to optimize energy consumption;

[0035] Ensure that alarm logic is accurate, reduce false alarms, and record analysis results and decisions in the database for auditing and analysis.

[0036] Furthermore, the specific operation steps of the processing module to revise the threshold according to external factors are as follows:

[0037] External factors include:

[0038] Ambient temperature: measure the temperature around the sensor;

[0039] Humidity: measures the humidity around the sensor;

[0040] Air pressure: measures the air pressure around the sensor;

[0041] The obtained ambient temperature, humidity and air pressure are normalized and then input into the following formula: To get the shadow judgment value YPZ, where are the actual ambient temperature, humidity and air pressure, They are the preset standard temperature, humidity and air pressure. The preset weight coefficients are respectively the temperature, humidity and air pressure, and the obtained shadow judgment value is used as the standard of the influence of external factors;

[0042] The obtained shadow judgment value is compared with several preset shadow judgment value intervals. Different correction factors are set for the preset shadow judgment value intervals respectively. When the shadow judgment value interval to which the shadow judgment value belongs is determined, the corresponding correction factor is determined, and the threshold is adaptively corrected according to the correction factor to avoid the probability of false alarm of the sensor due to external factors.

[0043] Furthermore, the specific operation steps of the detection module for detecting smoke, temperature and combustible gas concentration in the park through sensors are as follows:

[0044] Identify and locate high-risk areas in computer rooms, kitchens, and warehouses based on building layout and risk assessment reports, and optimize sensor deployment for energy saving;

[0045] Select the matching sensor type according to the detection requirements; determine the maximum effective monitoring distance of a single sensor based on the detection range provided in the sensor specification and actual testing;

[0046] Use geographic information system software to simulate sensor signal coverage to ensure that there are no blind spots in key areas; deploy smoke and temperature sensors on different floors of the building, and deploy combustible gas sensors in the basement or outdoors;

[0047] Filtering, denoising and normalization are performed on the sensor data, and the pre-processed data is transmitted to the processing module for analysis.

[0048] Furthermore, the specific operation steps of the detection module for energy-saving optimization of sensor deployment are as follows:

[0049] Risk assessment reports to identify high-risk areas;

[0050] After the high-risk areas are determined, the number of monitoring points required for all high-risk areas and the number of monitoring points expected to be deployed are determined. When the number of monitoring points required for all high-risk areas is greater than the number of monitoring points expected to be deployed, the priorities of all high-risk areas are ranked. Specifically, the risk assessment parameters of the high-risk areas are collected for comprehensive analysis, where the risk assessment parameters include:

[0051] Population density: Analyze the population density in high-risk areas during normal hours;

[0052] Complexity of electrical system: conduct a comprehensive assessment of all electrical systems in the high-risk area, determine the complexity of the electrical system, and record it as the re-evaluation value, which is used as the standard for measuring the complexity of the electrical system;

[0053] Historical fire records: obtain the number of fires that have occurred in the high-risk area in history, record it as the disaster judgment value, and use this disaster judgment value as a standard for measuring the historical fire records of the high-risk area;

[0054] Ventilation score: Score the ventilation conditions of the high-risk area and record it as the ventilation score;

[0055] After normalizing the obtained personnel density, re-evaluation value, disaster judgment value and wind assessment value, a bottom circle is established with the personnel density as the bottom circle radius, a cone model is established with the sum of the re-evaluation value and the disaster judgment value as the height, the vertex of the cone model is selected as the center of the sphere, and the wind assessment value is used as the radius to establish a spherical model, and the surface area of ​​the irregular model formed by the cone model and the spherical model is calculated and recorded as the risk assessment value. This risk assessment value is used as the risk assessment standard for measuring high-risk areas;

[0056] The risk assessment values ​​of all high-risk areas are sorted by size, and several high-risk areas at the end are eliminated. The number of high-risk areas to be eliminated is the number of monitoring points required for all high-risk areas minus the number of monitoring points expected to be deployed.

[0057] Furthermore, the intelligent alarm module provides a variety of alarm modes. The specific operation steps are as follows:

[0058] Obtain analysis results from the processing module, determine whether to trigger an alarm, and determine the urgency of the alarm based on the risk level;

[0059] Select the alarm method of sound and light, SMS, email or APP push according to the urgency and scenario, and activate the sound and light alarm system to attract attention;

[0060] Send notifications to managers via SMS, email or APP, and provide guidance on evacuation routes and emergency measures through the voice system;

[0061] Linked response with access control and lighting safety systems, receiving alarm confirmation, and tracking alarm event status;

[0062] When it is determined that the notified person has not confirmed in time, the alarm level will be automatically raised and more people will be notified. The alarm system will be tested regularly to ensure normal operation;

[0063] Allow users to set alarm methods and notification strategies according to needs, and integrate emergency services, including firefighting and medical rescue, for rapid response.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] The present invention realizes dynamic adjustment of the working state of the sensor through the adaptive energy-saving module, significantly reducing the monitoring energy consumption. The module intelligently adjusts the sampling frequency and sensitivity of the sensor according to real-time environmental data and historical events, effectively reducing energy consumption while ensuring safe monitoring, especially at night or during unmanned periods, by reducing the operating intensity of the sensor, further achieving energy conservation and emission reduction;

[0066] In the present invention, the processing module combines real-time data with historical data, and uses statistical and machine learning algorithms to improve the accuracy of fire risk prediction. The intelligent alarm module can select the most appropriate alarm method according to the risk level and usage scenario, ensuring that relevant personnel can be notified quickly and accurately when a fire occurs, thereby improving the response efficiency of the alarm system and the ability to handle emergency situations.

[0067] The present invention not only achieves seamless integration between modules, but also provides a user interface that allows users to customize the operating mode and energy-saving strategy of the sensor according to specific needs. At the same time, it can be integrated with third-party emergency services, such as fire departments and medical rescue, to ensure rapid response in emergency situations. By regularly evaluating the effectiveness of energy-saving strategies and optimizing them based on user feedback, long-term efficient operation and continuous performance improvement are ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0069] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0070] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0072] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0073] like Figure 1 As shown, a smart park energy-saving fire alarm includes a detection module, a processing module, an adaptive energy-saving module and an intelligent alarm module;

[0074] Detection module, used to detect smoke, temperature and combustible gas concentration in the park through sensors;

[0075] Deploy various types of sensors at key locations in the park, including smoke sensors, temperature sensors, and combustible gas sensors, to ensure that the distribution of sensors can cover all key areas to achieve comprehensive monitoring, while optimizing the energy saving of sensor deployment. The specific process is as follows:

[0076] Analyze the fire risk areas of the park and determine the key monitoring points. According to the layout of the park buildings and the fire risk assessment report, determine the high-risk areas, such as computer rooms, kitchens, warehouses, etc. After determining the high-risk areas, determine the number of monitoring points required for all high-risk areas and the number of monitoring points expected to be deployed. When the number of monitoring points required for all high-risk areas is greater than the number of monitoring points expected to be deployed, prioritize all high-risk areas. Specifically, collect the risk assessment parameters of the high-risk areas for comprehensive analysis, where the risk assessment parameters include:

[0077] Population density: Analyze the population density in high-risk areas during normal hours. Once a fire occurs in a densely populated area, evacuation is difficult and the fire risk is high. Electrical system complexity: Comprehensively evaluate all electrical systems in the high-risk area, determine the complexity score of the electrical system, and record it as the re-evaluation value. This re-evaluation value is used as a standard to measure the complexity of the electrical system. The higher the re-evaluation value, the more complex the electrical system and the higher the risk of electrical fire. Historical fire records: Obtain the number of fires that have occurred in the high-risk area in history, record it as the disaster judgment value, and use this disaster judgment value as a standard to measure the historical fire records of the high-risk area. Ventilation score: Score the ventilation conditions of the high-risk area and record it as the ventilation score.

[0078] After normalizing the obtained personnel density, re-evaluation value, disaster assessment value and wind assessment value, a bottom circle is established with the personnel density as the bottom circle radius, a cone model is established with the sum of the re-evaluation value and the disaster assessment value as the height, the vertex of the cone model is selected as the center of the sphere, and the wind assessment value is used as the radius to establish a spherical model, and the surface area of ​​the heteromorphic model formed by the cone model and the spherical model is calculated and recorded as the risk assessment value. This risk assessment value is used as the risk assessment standard for measuring high-risk areas; the risk assessment values ​​of all high-risk areas are sorted according to size, and several high-risk areas at the end are eliminated. The number of eliminated areas is the number of monitoring points required for all high-risk areas minus the number of monitoring points expected to be deployed;

[0079] Select the appropriate sensor type based on the detection requirements, and choose sensors with a wider detection angle and longer endurance, such as infrared smoke sensors, digital temperature sensors, and electrochemical combustible gas sensors; determine the maximum effective monitoring distance of a single sensor based on the detection range provided in the sensor specification and combined with actual testing; use GIS (geographic information system) software to simulate the sensor signal coverage to ensure that there are no blind spots in key areas; deploy smoke and temperature sensors on different floors of the building, and deploy combustible gas sensors in the basement or outdoors;

[0080] The deployed sensors include: smoke sensors that regularly detect the concentration of smoke particles in the air, temperature sensors that monitor the ambient temperature in real time to detect abnormal temperature increases, and combustible gas sensors that detect the concentration of specific combustible gases, such as methane and carbon monoxide. The raw data collected by the sensors is preprocessed, including filtering, denoising and normalization, to improve data quality, and the preprocessed data is synchronized to the processing module for further analysis.

[0081] The processing module is used to process and analyze the data obtained from the detection module to determine whether an alarm is needed;

[0082] Receive real-time data from the detection modules, including smoke concentration, temperature, and combustible gas concentration, and integrate the received data with historical data and environmental parameters for comprehensive analysis; analyze the data to identify any abnormal patterns or threshold exceedances, such as a sudden increase in smoke concentration or an abnormal increase in temperature, and use statistical and machine learning algorithms to analyze data trends and predict potential fire risks; set thresholds for smoke, temperature, and combustible gas based on the specific needs and safety standards of the park, and verify the detected abnormal data to eliminate the possibility of false alarms;

[0083] When setting the threshold, the threshold is revised based on external factors, including:

[0084] Ambient temperature: measures the temperature around the sensor. The ambient temperature may change in different seasons or at different times of the day, affecting the threshold of the temperature sensor. Humidity: measures the humidity around the sensor. High humidity may affect the reading of the smoke sensor, and moisture may be mistaken for smoke. Air pressure: measures the air pressure around the sensor. Changes in air pressure may affect the diffusion rate of combustible gases and the reading of the sensor.

[0085] The obtained ambient temperature, humidity and air pressure are normalized and then input into the following formula: To get the shadow judgment value YPZ, where are the actual ambient temperature, humidity and air pressure, They are the preset standard temperature, humidity and air pressure. The preset weight coefficients are respectively the temperature, humidity and air pressure, and the obtained shadow judgment value is used as the standard for the influence of external factors; the obtained shadow judgment value is compared with several preset shadow judgment value intervals, and different correction factors are set corresponding to the preset shadow judgment value intervals. When the shadow judgment value interval to which the shadow judgment value belongs is determined, the corresponding correction factor is judged, and the threshold is adaptively corrected according to the correction factor to avoid the possibility of false alarm of the sensor due to external factors.

[0086] Based on the analysis results, make decisions on whether to trigger an alarm, evaluate the urgency of the alarm, and determine the priority of the alarm. Work with the adaptive energy-saving module to adjust the working state of the sensor according to the analysis results to optimize energy consumption; set the alarm logic to ensure that the alarm is triggered only when specific conditions are met to reduce false alarms. Record the analysis results and decisions in the database for auditing and subsequent analysis.

[0087] The adaptive energy-saving module is used to dynamically adjust the working state of the sensor based on environmental changes and historical data, effectively reducing monitoring energy consumption;

[0088] Collect environmental data related to sensors, such as temperature, humidity, light intensity, etc., which may affect the working efficiency of sensors, and analyze historical data, including past alarm events, sensor triggering frequency, and environmental change patterns; evaluate the current working status of sensors, including their sensitivity settings, sampling frequency, and energy consumption levels, analyze the energy consumption patterns of sensors, and determine which sensors can reduce their operating frequency or enter low-power mode during specific time periods;

[0089] Design an adaptive algorithm to dynamically adjust the working parameters of the sensor according to environmental data and historical data, set dynamic thresholds for the sensor, and these thresholds will be automatically adjusted according to environmental changes and historical data; adjust the working mode of the sensor according to the results of the adaptive algorithm, such as reducing the sampling frequency during low-risk periods or increasing the sensitivity during high-risk periods; implement energy-saving strategies, such as reducing the operating intensity of the sensor at night or during unmanned periods, monitor environmental changes and sensor status in real time, and continuously adjust the energy-saving strategy according to real-time data. The specific process is as follows:

[0090] Define one or more low-power modes for each sensor, including reducing sampling frequency, reducing sensitivity, or entering a sleep state; then establish a schedule based on the park's working and non-working hours to determine when to apply the low-power mode;

[0091] Continuously monitor environmental data, including temperature, humidity, and light conditions, to assess whether environmental conditions are suitable for sensors to operate in low-power mode; analyze historical data to determine the frequency and pattern of sensor triggering within a specific time period to identify low-risk periods and put existing sensors into low-power mode during low-risk periods; analyze user behavior patterns, such as working hours, rest time, etc., to adjust energy-saving strategies; automatically adjust the working status of sensors according to schedules, environmental data, and historical data based on preset algorithms; implement real-time monitoring, and dynamically adjust the working mode and parameters of sensors based on environmental changes and sensor status, and based on real-time monitoring data.

[0092] Provide a user interface to allow users to customize the sensor's operating mode and energy-saving strategy according to specific needs; regularly evaluate the effectiveness of energy-saving strategies and conduct comprehensive analysis through effect test parameters, where the effect test parameters include:

[0093] Energy consumption data: quantify the energy consumption of sensors in different time periods, including power consumption and power usage, and compare the energy consumption when no energy-saving strategy is made to calculate the average energy saving amount; Alarm accuracy: count the number of false alarms and missed alarms after the energy-saving strategy is implemented, and calculate the average response time for each alarm. After normalization, the sum of the number of false alarms and missed alarms is multiplied by the average response time for each alarm to obtain the accurate judgment value; Failure rate: count the failure rate of sensors after the implementation of the energy-saving strategy, including false alarms and missed alarms;

[0094] The obtained average energy saving amount, criterion value and failure rate are normalized and then input into the following formula: To obtain the energy saving value JFZ, where ng, zm and gm are the average energy saving amount, the accurate judgment value and the failure rate, respectively. is the correction coefficient, the value is set between 0.96 and 1.21, and the obtained energy-saving judgment value is used as a standard to measure the effect of the energy-saving strategy;

[0095] The obtained energy-saving value JFZ is compared with the preset energy-saving threshold. When the energy-saving value JFZ is greater than the preset energy-saving threshold, it is judged that the energy-saving strategy effect has reached the expected standard. Otherwise, it is judged that the energy-saving strategy effect has not reached the standard. The energy-saving effect and user feedback are incorporated into the adaptive algorithm to continuously optimize the energy-saving strategy so that the final energy-saving strategy effect reaches the expected standard. The operation and effect of the adaptive energy-saving module are recorded, and an energy-saving report is generated for reference by users and maintenance personnel to ensure that the adaptive energy-saving module is seamlessly integrated with the detection module, processing module and intelligent alarm module to achieve the coordinated work of the overall system.

[0096] The intelligent alarm module is used to provide diversified alarm modes to adapt to different usage scenarios;

[0097] Receive the analysis results of the processing module, determine whether the alarm conditions are met, and evaluate the urgency of the alarm based on the detected risk level; select the appropriate alarm method based on the alarm level and usage scenario, such as sound and light alarm, SMS notification, APP push, etc. When a fire occurs, sound and light alarms are issued to attract the attention of people in the park; send notifications to park managers or security teams via SMS, email or dedicated APP, and use voice prompts to provide additional guidance information, such as evacuation routes or emergency measures;

[0098] Linked with other security systems in the park (such as access control system and lighting system) to provide a more comprehensive security response, allowing personnel receiving alarms to confirm receipt of alarms for easy tracking and management; recording detailed information of all alarm events, including time, location, alarm level and response; automatically upgrading the alarm level to notify more personnel or initiate additional emergency procedures if no confirmation or response is received within the preset time; regularly conducting alarm tests to ensure the normal operation of the alarm system, allowing users to customize alarm methods and notification strategies according to specific needs; integrating third-party emergency services, such as fire departments, medical rescue, etc., to provide faster response.

[0099] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart park energy-saving fire alarm, characterized in that: include: Detection module, used to detect smoke, temperature and combustible gas concentration in the park through sensors; The processing module is used to process and analyze the data obtained in the detection module to determine whether an alarm is needed; The adaptive energy-saving module is used to dynamically adjust the working state of the sensor based on environmental changes and historical data, effectively reducing monitoring energy consumption. The specific process is as follows: Regularly collect environmental data on temperature, humidity, and light intensity, analyze past alarm events, sensor trigger frequencies, and environmental change patterns, and evaluate sensor sensitivity, sampling frequency, and energy consumption levels; Through algorithms, sensor parameters are dynamically adjusted according to the environment and historical data, and dynamic thresholds based on data are set for sensors, which can reduce sampling frequency during low-risk periods, increase sensitivity during high-risk periods, and reduce sensor operation intensity at night or during unmanned periods. Monitor the environment and sensor status in real time, adjust energy-saving strategies based on data, and provide a user interface that allows users to customize sensor working modes and energy-saving strategies; The energy-saving judgment value is obtained through comprehensive analysis of test parameters, and the energy-saving judgment value is compared with the preset energy-saving judgment threshold to determine whether the energy-saving strategy meets the standard, and the adaptive algorithm is optimized according to the energy-saving judgment value and user feedback; Record the operation and effect of the energy-saving module, generate energy-saving reports, and ensure that the energy-saving module is integrated with other modules to achieve collaborative work; The process of real-time monitoring of the environment and sensor status and adjusting the energy-saving strategy based on the data is as follows: Define one or more low-power modes for each sensor, including reducing sampling frequency, reducing sensitivity, or entering sleep state; Then, a schedule is established based on the working and non-working hours of the park to determine when to apply low-power mode; Continuously monitor environmental data, including temperature, humidity, and light conditions, to assess whether environmental conditions are suitable for the sensor to operate in low-power mode; Analyze historical data to determine the frequency and pattern of sensor triggering in different time periods to identify low-risk periods and put existing sensors into low-power mode during low-risk periods; Analyze user behavior patterns, including working hours and rest time, to adjust energy-saving strategies; According to preset algorithms, the working status of sensors is automatically adjusted according to schedules, environmental data and historical data; Implement real-time monitoring, continuously adjust the sensor's operating mode and parameters according to environmental changes and sensor status, and based on real-time monitoring data; The specific steps for obtaining the node judgment value through comprehensive analysis of the test parameters are as follows: The performance test parameters include: Energy consumption data: Quantify the energy consumption of sensors in different time periods, including power consumption and power usage, and compare the energy consumption when no energy-saving strategy is implemented to calculate the average energy saving; Alarm accuracy: Count the number of false alarms and missed alarms after energy-saving strategies are implemented, and calculate the average response time for each alarm. After normalization, multiply the sum of the number of false alarms and missed alarms by the average response time for each alarm to obtain the accurate judgment value; Failure rate: Statistics on the failure rate of sensors after the implementation of energy-saving strategies, including false alarms and missed alarms; The obtained average energy saving amount, criterion value and failure rate are normalized and then input into the following formula: To obtain the energy saving value JFZ, where ng, zm and gm are the average energy saving amount, the accurate judgment value and the failure rate respectively. is the correction coefficient, and the obtained energy-saving value is used as the standard to measure the effect of energy-saving strategy; The intelligent alarm module is used to provide diversified alarm methods to adapt to different usage scenarios.

2. According to claim 1, the smart park energy-saving fire alarm is characterized in that: The processing module processes and analyzes the data obtained by the detection module to determine whether an alarm is needed. The specific operation steps are as follows: Obtain smoke density, temperature and combustible gas concentration data from the detection module in real time, and combine the real-time data with historical data and environmental parameters for comprehensive analysis; Identify unusual patterns or threshold exceedances in data and apply statistical and machine learning algorithms to predict fire risk; Set thresholds for smoke, temperature and combustible gases according to safety standards and revise them based on external factors when setting them; Based on the analysis results, determine whether to trigger an alarm, determine the urgency and priority of the alarm, and work with the adaptive energy-saving module to adjust the sensor working state to optimize energy consumption; Ensure that alarm logic is accurate, reduce false alarms, and record analysis results and decisions in the database for auditing and analysis.

3. The smart park energy-saving fire alarm according to claim 2 is characterized in that: The specific operation steps of the processing module to revise the threshold according to external factors are as follows: External factors include: Ambient temperature: measure the temperature around the sensor; Humidity: measures the humidity around the sensor; Air pressure: measures the air pressure around the sensor; The obtained ambient temperature, humidity and air pressure are normalized and then input into the following formula: To get the shadow judgment value YPZ, where are the actual ambient temperature, humidity and air pressure, They are the preset standard temperature, humidity and air pressure. The preset weight coefficients are respectively the temperature, humidity and air pressure, and the obtained shadow judgment value is used as the standard of the influence of external factors; The obtained shadow judgment value is compared with several preset shadow judgment value intervals. Different correction factors are set for the preset shadow judgment value intervals respectively. When the shadow judgment value interval to which the shadow judgment value belongs is determined, the corresponding correction factor is determined, and the threshold is adaptively corrected according to the correction factor to avoid the probability of false alarm of the sensor due to external factors.

4. The smart park energy-saving fire alarm according to claim 1 is characterized in that: The specific operation steps of the detection module to detect smoke, temperature and combustible gas concentration in the park through sensors are as follows: Identify and locate high-risk areas in computer rooms, kitchens, and warehouses based on building layout and risk assessment reports, and optimize sensor deployment for energy saving; Select the matching sensor type according to the detection requirements; According to the detection range provided in the sensor specification and combined with actual testing, determine the maximum effective monitoring distance of a single sensor; Use geographic information system software to simulate sensor signal coverage to ensure there are no blind spots in key areas; Deploy smoke and temperature sensors on different floors of a building, and deploy combustible gas sensors in basements or outdoors; Filtering, denoising and normalization are performed on the sensor data, and the pre-processed data is transmitted to the processing module for analysis.

5. The smart park energy-saving fire alarm according to claim 4 is characterized in that: The specific operation steps of the detection module to perform energy-saving optimization on sensor deployment are as follows: Analyze the fire risk areas in the park, identify key monitoring points, and determine high-risk areas based on the park's building layout and fire risk assessment report; After the high-risk areas are determined, the number of monitoring points required for all high-risk areas and the number of monitoring points expected to be deployed are determined. When the number of monitoring points required for all high-risk areas is greater than the number of monitoring points expected to be deployed, the priorities of all high-risk areas are ranked. Specifically, the risk assessment parameters of the high-risk areas are collected for comprehensive analysis, where the risk assessment parameters include: Population density: Analyze the population density in high-risk areas during normal hours; Complexity of electrical system: conduct a comprehensive assessment of all electrical systems in the high-risk area, determine the complexity of the electrical system, and record it as the re-evaluation value, which is used as the standard for measuring the complexity of the electrical system; Historical fire records: obtain the number of fires that have occurred in the high-risk area in history, record it as the disaster judgment value, and use this disaster judgment value as a standard for measuring the historical fire records of the high-risk area; Ventilation score: Score the ventilation conditions of the high-risk area and record it as the ventilation score; After normalizing the obtained personnel density, re-evaluation value, disaster judgment value and wind assessment value, a bottom circle is established with the personnel density as the bottom circle radius, a cone model is established with the sum of the re-evaluation value and the disaster judgment value as the height, the vertex of the cone model is selected as the center of the sphere, and the wind assessment value is used as the radius to establish a spherical model, and the surface area of ​​the irregular model formed by the cone model and the spherical model is calculated and recorded as the risk assessment value. This risk assessment value is used as the risk assessment standard for measuring high-risk areas; The risk assessment values ​​of all high-risk areas are sorted by size, and several high-risk areas at the end are eliminated. The number of high-risk areas to be eliminated is the number of monitoring points required for all high-risk areas minus the number of monitoring points expected to be deployed.

6. The smart park energy-saving fire alarm according to claim 1 is characterized in that: The intelligent alarm module provides a variety of alarm modes. The specific operation steps are as follows: Obtain analysis results from the processing module, determine whether to trigger an alarm, and determine the urgency of the alarm based on the risk level; Select the alarm method of sound and light, SMS, email or APP push according to the urgency and scenario, and activate the sound and light alarm system to attract attention; Send notifications to managers via SMS, email or APP, and provide guidance on evacuation routes and emergency measures through the voice system; Linked response with access control and lighting safety systems, receiving alarm confirmation, and tracking alarm event status; When it is determined that the notified person has not confirmed in time, the alarm level will be automatically raised and more people will be notified. The alarm system will be tested regularly to ensure normal operation; Allow users to set alarm methods and notification strategies according to needs, and integrate emergency services, including firefighting and medical rescue, for rapid response.

Images