Automatic response system of industrial fireproof air-resistant door

Abstract

The invention relates to the technical field of automatic response, in particular to an industrial fireproof wind-resistant door automatic response system, which comprises an environment monitoring module, a door control analysis module, a door control adjustment module and an abnormity monitoring module, and is characterized in that the environment monitoring module performs data aggregation based on temperature, smoke concentration and wind speed data received in real time; and calculating an average value and a standard deviation of the data, analyzing an environment change prediction trend in a short period, and generating environment baseline data. According to the method, trend prediction and periodic analysis are performed on the environmental data by applying the ARIMA model, so that the closing speed and force of the fireproof and wind-resistant door can be adjusted according to the prediction result before a fire disaster or strong wind occurs, and the response time and efficiency of the door leaf are optimized; the isolation forest algorithm enables the system to effectively identify and analyze the abnormal mode in the sensor data flow, improves the diagnosis accuracy of the equipment fault, improves the reliability, reduces the dependence of the system on manual intervention, and effectively protects the safety and stability of industrial facilities.

Description

Technical Field

[0001] The invention relates to the field of automatic response technology, and in particular to an automatic response system for industrial fire and wind resistant doors. Background Art

[0002] Automatic response technology involves the use of sensors, control systems and actuators to implement systems that automatically perform tasks under specific conditions. It is widely used in many fields such as security, environmental monitoring, industrial automation, etc. In security applications, automatic response systems can monitor environmental changes (such as smoke, temperature, chemical leaks, etc.) in real time and take preset measures, such as activating alarms, closing imports and exports, or starting fire extinguishing systems. Its key advantage is that it can respond quickly and reduce human delays, thereby protecting life and property in emergencies.

[0003] Among them, the industrial fire and wind door automatic response system is a safety facility designed specifically for industrial buildings, mainly used for fire prevention and risk minimization. The system can be automatically activated under fire or strong wind conditions, closing the door leaves to isolate the fire source or prevent wind damage. Fire and wind doors are not limited to preventing the spread of flames and heat, but can also resist the impact from strong winds and protect the safety of people and property in the building. Through integration with fire alarms and wind speed monitoring facilities, they can automatically close when danger signals are detected. They are an indispensable part of industrial facilities.

[0004] Existing systems rely on basic trigger mechanisms and are unable to predict environmental trends and conduct in-depth analysis of complex data, resulting in overreaction or underresponse in actual processes. Traditional technologies lack analysis in the early diagnosis of sensor failures or mechanical failures, limiting the timeliness and accuracy of fault handling. This limitation causes the system to be unable to provide necessary safety guarantees in emergency situations. For example, in the event of a rapidly spreading fire or sudden strong winds, delayed response or misoperation will exacerbate losses and affect the safety of people and property in the building. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an automatic response system for industrial fire and wind resistant doors.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an automatic response system for industrial fire and wind resistance doors, the system comprising:

[0007] The environmental monitoring module aggregates data based on the real-time received temperature, smoke concentration and wind speed data, calculates the average and standard deviation of the data, analyzes the short-term environmental change forecast trend, and generates environmental baseline data;

[0008] The gating analysis module uses the ARIMA model to analyze the periodicity and trend of environmental data changes based on the environmental baseline data, determines the matching parameters of the ARIMA model, predicts short-term environmental changes, and generates gating adjustment instructions;

[0009] The door control adjustment module calculates the fire door operation parameters, including the closing speed and force of the fire door, based on the door control adjustment instruction, and adjusts the door control parameters according to the current environmental data to generate a real-time door control configuration;

[0010] The anomaly monitoring module analyzes the abnormal patterns in the sensor data stream based on the real-time gate control configuration using the isolation forest algorithm, compares the deviations of the abnormal patterns with the normal operating parameters, identifies sensor failures or mechanical failures of the door, and generates an anomaly identification record.

[0011] The present invention is improved in that the steps of obtaining the environmental baseline data are specifically as follows:

[0012] Real-time data of temperature, smoke concentration, and wind speed received from multiple sensors are marked with time tags and the data are sorted according to timestamps to obtain sensor data sets;

[0013] Based on the sensor data set, the mean and standard deviation of the data are calculated using the formula:

[0014]

[0015] and

[0016]

[0017] Get the mean and standard deviation results, where x i represents the sensor data point, n is the total number of data points, MD represents the mean value of the data, and SD represents the standard deviation of the data;

[0018] Based on the mean and standard deviation results, the short-term environmental change forecast trend is analyzed to obtain an environmental baseline data set.

[0019] The present invention is improved in that the steps of analyzing the periodicity and trend are specifically as follows:

[0020] The environmental baseline data is processed for stability, and a differential method is used to reduce the seasonal and trend effects of the data to generate a stable time series data set;

[0021] Based on the stationary time series data set, the ARIMA model is used, using the formula:

[0022]

[0023] Evaluate the periodic changes and long-term trends of the data and obtain periodicity and trend analysis results, among which PF t represents the predicted value at time t, β0 is the intercept term, β1 is the coefficient at time t, t is the time variable, β2 and β3 are adjustment coefficients, T is the length of the data period, and are cosine and sine functions, which are used to model seasonal fluctuations in the data.

[0024] The present invention is improved in that the step of obtaining the gate adjustment instruction is specifically as follows:

[0025] According to the periodicity and trend, the matching parameters of the ARIMA model are determined to predict short-term environmental changes using the formula:

[0026] PR t+1 =α R ·XR t +(1-α R ) PR t

[0027] Get the gate adjustment instruction, where PR t+1 is the predicted environmental state at the next time point, XR t is the observed value at the current time t, α R is the smoothing coefficient, PR t is the predicted value at the previous time t.

[0028] The present invention is improved in that the calculation steps of the fire door operation parameters are specifically as follows:

[0029] Based on the door control adjustment instruction, physical parameters of the fire door, including weight, size and installation position, are collected to obtain basic data of the fire door;

[0030] Based on the basic data of the fire door, the formula is adopted:

[0031]

[0032] and

[0033] F opt =μmg

[0034] Calculate the closing speed and force of the fire door, where v opt Indicates closing speed, F opt is the closing force, g is the acceleration due to gravity, s is the distance the door falls, h is the height from the door frame to the ground, μ is the friction coefficient, and m is the mass of the door.

[0035] The present invention is improved in that the step of acquiring the real-time gating configuration is specifically as follows:

[0036] Analyze the currently collected real-time data, including temperature, smoke concentration and fire source distance, and integrate the data to obtain the current environmental data;

[0037] Based on the current environmental data, the formula is adopted:

[0038]

[0039] and

[0040] F adj =F base ·(1+γ c ·T amb )

[0041] Refine the gating parameters to obtain the real-time gating configuration, where v adj and F adj are the adjusted closing speed and closing force, v base and F base is the basic closing speed and closing force, β c and γ c is the adjustment factor, d fire is the distance between the fire source and the fire door, c smoke is the smoke density, T amb is the ambient temperature, α c It is the coefficient that adjusts the closing speed of the fire door according to the smoke concentration.

[0042] The present invention is improved in that the step of analyzing the abnormal pattern in the sensor data stream is specifically:

[0043] Based on the real-time door control configuration, sensor data associated with the fire door operation is collected, including the door's movement speed, opening and closing status, and continuous operation time, to obtain a continuously updated data stream;

[0044] Based on the continuously updated data stream, anomaly pattern analysis is performed using the isolation forest algorithm, using the formula:

[0045]

[0046] The anomaly detection result is obtained, where E(h(xo)) is the average path length of the data point xo in the tree, c(no) is the normalization factor, and E(xo) represents the anomaly score of the data point.

[0047] The present invention is improved in that the step of obtaining the abnormal identification record is specifically as follows:

[0048] The abnormal mode is compared with the deviation of the normal operating parameters, using the formula:

[0049]

[0050] Get the abnormal deviation value Z mod , where X Z is the currently observed data point, μ Z is the average value of historical data, σ Z is the standard deviation of historical data;

[0051] Based on the abnormal deviation value, the sensor record is compared with the fire door operation standard, sensor failure or mechanical failure is identified, and potential fault causes are analyzed to obtain an abnormal identification record.

[0052] Compared with the prior art, the advantages and positive effects of the present invention are:

[0053] In the present invention, by using the ARIMA model to perform trend prediction and periodic analysis on environmental data, the fire-proof and wind-resistant doors can adjust the closing speed and force according to the prediction results before the fire or strong wind occurs, optimize the response time and efficiency of the door leaves, and the isolation forest algorithm enables the system to effectively identify and analyze abnormal patterns in the sensor data stream, thereby improving the accuracy of diagnosis of equipment failures, thereby enhancing reliability, reducing the system's dependence on manual intervention, and effectively protecting the safety and stability of industrial facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a system flow chart of the present invention;

[0055] Figure 2 This is a flow chart for obtaining environmental baseline data in the present invention;

[0056] Figure 3 It is a flow chart of periodicity and trend analysis in the present invention;

[0057] Figure 4 is a flow chart of obtaining a gate adjustment instruction in the present invention;

[0058] Figure 5 is a flow chart for calculating the operating parameters of the fire door in the present invention;

[0059] Figure 6 A flowchart for obtaining the real-time gating configuration in the present invention;

[0060] Figure 7 A flowchart of analyzing abnormal patterns in sensor data streams in the present invention;

[0061] Figure 8 The figure is a flow chart for obtaining abnormal identification records in the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0064] Example

[0065] See also Figure 1 The present invention provides a technical solution: an industrial fire and wind resistant door automatic response system comprises:

[0066] The environmental monitoring module aggregates data based on the real-time received temperature, smoke concentration and wind speed data, calculates the average and standard deviation of the data, analyzes the short-term environmental change forecast trend, and generates environmental baseline data;

[0067] The gate analysis module uses the ARIMA model to analyze the periodicity and trend of environmental data changes based on environmental baseline data, determine the matching parameters of the ARIMA model, predict short-term environmental changes, and generate gate adjustment instructions;

[0068] The door control adjustment module calculates the fire door operation parameters, including the closing speed and force of the fire door, based on the door control adjustment instructions, and adjusts the door control parameters according to the current environmental data to generate real-time door control configuration;

[0069] The anomaly monitoring module uses the isolation forest algorithm to analyze abnormal patterns in the sensor data stream based on the real-time gate control configuration, compares the deviation of the abnormal pattern with the normal operating parameters, identifies sensor failure or mechanical failure of the door, and generates anomaly identification records.

[0070] Environmental baseline data includes temperature average, smoke concentration index, and wind speed statistics. Gating adjustment instructions include operation timing, force setting, and speed configuration. Real-time gating configuration includes threshold setting, response process, and adjustment feedback information. Abnormal identification records include fault code, abnormal level, and fault source.

[0071] See also Figure 2 , the specific steps for obtaining environmental baseline data are as follows:

[0072] Real-time data of temperature, smoke concentration, and wind speed received from multiple sensors are marked with time tags and the data are sorted according to timestamps to obtain sensor data sets;

[0073] Receive real-time data from multiple sensors, including temperature, smoke concentration and wind speed. The data comes from dedicated environmental monitoring sensors set in high-risk areas. Each sensor is equipped with a timestamp function to ensure the timeliness and accuracy of data collection. The data is transmitted through a secure transmission network, and the received data is sorted in time series to ensure the consistency and logic of subsequent data processing. In this way, environmental changes can be monitored in real time and environmental hazards can be responded to quickly. This process ensures the integrity and real-time update of the data set, generating a sensor data set arranged in chronological order.

[0074] Based on the sensor data set, calculate the mean and standard deviation of the data using the formula:

[0075]

[0076] and

[0077]

[0078] Get the mean and standard deviation results, where x i represents the sensor data point, n is the total number of data points, MD represents the mean value of the data, and SD represents the standard deviation of the data;

[0079] The following data points temperatures were collected from the sensors:

[0080] x1=15, x2=17, x3=16, x4=14, x5=15;

[0081] Total n = 5 data points;

[0082] Calculate the average:

[0083]

[0084] To calculate the standard deviation, the sum of the squares of the differences is:

[0085] (15-15.4) 2 +(17-15.4) 2 +(16-15.4) 2

[0086] +(14-15.4) 2 +(15-15.4) 2

[0087] =0.16+2.56+0.36+1.96+0.16=5.2

[0088] The standard deviation is:

[0089]

[0090] The results show that the calculated average value is 15.4℃ and the standard deviation is 1.02℃, which reflects that the temperature fluctuation of the monitored environment is small and the environment is relatively stable. This result is further used in environmental monitoring to evaluate the degree of deviation between the current environmental state and the baseline state.

[0091] Based on the mean and standard deviation results, the short-term environmental change forecast trend is analyzed to obtain the environmental baseline data set; using the mean and standard deviation calculated in the second paragraph, the data is used to create environmental baseline data. The baseline data set will include the average temperature, average smoke concentration and average wind speed of all monitoring data points in the time period, as well as the fluctuation of the data (standard deviation). It not only helps to quickly identify environmental trends, but can also be used to compare historical data and identify potential environmental changes or anomalies. By comprehensively analyzing the baseline data, a more effective response plan can be formulated.

[0092] See also Figure 3 , the specific steps for periodicity and trend analysis are:

[0093] The environmental baseline data is processed for stability, and the difference method is used to reduce the seasonal and trend effects of the data to generate a stable time series data set;

[0094] Process time series data to ensure that it is suitable for model analysis. Organize the data collected from environmental monitoring to ensure the consistency and completeness of the data in time series format, which involves removing outliers and filling missing values. The data includes parameters such as temperature, smoke concentration and wind speed. The seasonality and trend effects of the data are reduced through first-order or second-order difference methods, so that the data set reaches a stable state and generates a stable time series data set.

[0095] Based on the stationary time series data set, using the ARIMA model, the formula is:

[0096]

[0097] Evaluate the periodic changes and long-term trends of the data and obtain periodicity and trend analysis results, among which PF t represents the predicted value at time t, β0 is the intercept term, β1 is the coefficient at time t, t is the time variable, β2 and β3 are adjustment coefficients, T is the length of the data period, and are cosine and sine functions, used to model seasonal fluctuations in data;

[0098] There is a set of ambient temperature data with an observation period of one year (T=365). The specific values ​​are as follows:

[0099] On day t = 1, the temperature is 15°C, β0 = 10, β1 = 0.05, β2 = 3, β3 = 3;

[0100] Calculate the predicted temperature P1 for day t = 1:

[0101]

[0102] PF1≈10+0.05+3×1+3×0.017

[0103] PF1≈13

[0104] The results show that the model predicted a temperature of 13°C on the first day. This calculation process shows how the model calculates daily temperature forecasts based on seasonal cycles, helping to understand how to adjust the forecast values ​​based on daily cycle changes.

[0105] See also Figure 4 , the specific steps for obtaining the gate adjustment instruction are:

[0106] According to the periodicity and trend, the matching parameters of the ARIMA model are determined to predict short-term environmental changes using the formula:

[0107] PR t+1 =α R ·XR t +(1-α R ) PR t

[0108] Get the gate adjustment instruction, where PR t+1 is the predicted environmental state at the next time point, XR t is the observed value at the current time t, α R is the smoothing coefficient, between 0 and 1, PR t is the predicted value at the previous time t;

[0109] The periodicity and trend of historical environmental data were analyzed through autocorrelation and partial autocorrelation functions to identify seasonal and non-seasonal components. The Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) were used to select the optimal parameter combination from multiple models to ensure the stationarity of the time series and avoid overfitting, improve the model's prediction accuracy for future environmental changes, and optimize the model's applicability and effect in practical applications.

[0110] Monitor the current temperature XR t =22℃, previous prediction value PR t=21℃, let α R =0.5 to calculate:

[0111] PR t+1 =0.5·22+0.5·21

[0112] PR t+1 =11+10.5=21.5

[0113] The results show that based on the current and previous temperature data, the predicted temperature at the next moment is 21.5℃. The calculation process reflects the model's immediate response to environmental changes.

[0114] See also Figure 5 , the calculation steps of the fire door operating parameters are as follows:

[0115] Based on the door control adjustment instructions, the physical parameters of the fire door, including weight, size and installation location, are collected to obtain the basic data of the fire door;

[0116] In the process of adjusting the fire door parameters, the real-time monitoring system is used to obtain the response data of the fire door in different environments, including temperature and smoke concentration, etc. The initial response setting of the fire door is evaluated based on the data, and the data is analyzed to determine the basic operating parameters of the fire door, including the starting force and initial closing speed. The performance of the fire door in actual fire conditions is evaluated through basic data, and the operating parameters of the fire door are adjusted according to the analysis results to adapt to environmental changes.

[0117] Based on the basic data of fire doors, the formula is used:

[0118]

[0119] and

[0120] F opt =μmg

[0121] Calculate the closing speed and force of the fire door, where v opt Indicates closing speed, F opt is the closing force, g is the acceleration due to gravity, s is the distance the door falls, h is the height from the door frame to the ground, μ is the friction coefficient, and m is the mass of the door;

[0122] There are the following data:

[0123] The weight of the fire door is m = 60kg;

[0124] The height from the door frame to the ground is h = 3m;

[0125] The door's descent distance s = 3.5 m;

[0126] Gravitational acceleration g = 9.8 m / s2 ;

[0127] Friction coefficient μ = 0.15;

[0128] Calculate the optimal closing speed v opt :

[0129]

[0130] Calculate the required closing force F opt :

[0131] F opt =0.15×60×9.8

[0132] F opt =0.15×588

[0133] F opt =88.2N

[0134] The results show that under the adjusted parameters, the optimal closing speed of the fire door should be 1.67m / s, and the required closing force is 88.2N, ensuring that the door can complete the closing operation in a timely and safe manner in a fire emergency.

[0135] See also Figure 6 , the specific steps for obtaining the real-time gating configuration are:

[0136] Analyze the currently collected real-time data, including temperature, smoke concentration and fire source distance, and integrate the data to obtain the current environmental data;

[0137] Based on real-time environmental monitoring data, the necessity of evaluating and updating fire door operating parameters is evaluated. Data on temperature, smoke concentration and distance to the fire source are collected to determine the initial adjustment requirements for fire door operation. Real-time data is analyzed to calculate the door control parameters that need to be adjusted, including the adjusted closing speed and force, to ensure that the operation of the fire door is synchronized with the current environmental conditions. The adjusted operating parameters are generated and applied to the door control system to optimize the response and performance of the fire door in an emergency.

[0138] Based on current environmental data, the formula is adopted:

[0139]

[0140] and

[0141] F adj =F base ·(1+γ c ·T amb )

[0142] Refine the gating parameters to obtain the real-time gating configuration, where vadj and F adj are the adjusted closing speed and closing force, v base and F base is the basic closing speed and closing force, β c and γ c is the adjustment factor, d fire is the distance between the fire source and the fire door, c smoke is the smoke density, T amb is the ambient temperature, α c It is the coefficient of smoke density adjusting the closing speed of fire doors;

[0143] There are the following data:

[0144] Basic closing speed v base 0.5m / s;

[0145] Basic closing force F base 2kN;

[0146] Distance from fire source d fire 10m;

[0147] Smoke density c smoke is 0.2;

[0148] Ambient temperature T amb 300K;

[0149] β c , α c and γ c They are 0.05, 0.1 and 0.01 respectively;

[0150] Substitute into the formula to calculate:

[0151]

[0152] F adj =2·(1+0.01·300)=8

[0153] The results show that based on the current fire source distance and smoke concentration, the adjusted closing speed is 0.980m / s, while the adjusted closing force factor is 8kN, showing how the operation of the fire door can be adjusted through specific environmental data to maximize its performance and safety in a fire.

[0154] See also Figure 7 ,The steps to analyze abnormal patterns in sensor data streams are as follows:

[0155] Based on real-time door control configuration, sensor data related to fire door operation is collected, including door movement speed, open and closed status, and continuous operation time, to obtain a continuously updated data stream;

[0156] Under the real-time door control configuration, data is collected on the movement speed, opening and closing status, and operation duration of the fire door. The data is captured in real time by the sensors of the door control system and then transmitted through a wireless or wired network to form a continuously updated data stream. The data stream not only includes the movement parameters of each door, but also records the timestamp of each door operation, thereby providing a complete operation log. The log can be used for subsequent data analysis and maintenance operations. This method ensures the integrity and real-time nature of the data, and at the same time provides the necessary prerequisites for anomaly detection, so that the door control system can respond quickly when a fault or abnormal operation mode occurs, ensuring the safety and reliability of the door control system.

[0157] Based on the continuously updated data stream, the isolation forest algorithm is used for abnormal pattern analysis, using the formula:

[0158]

[0159] Get the anomaly detection result, where E(h(xo)) is the average path length of the data point xo in the tree, c(no) is the normalization factor used to adjust the impact of the data set size, and E(xo) represents the anomaly score of the data point;

[0160] 100 data points were collected, and E(h(xo))=10, c(no)=5;

[0161] Substitute the data and calculate:

[0162]

[0163] If the judgment standard for normal data is 0, and the anomaly score of xo is 0.25, then the result indicates that xo is abnormal relative to other data points and needs further analysis.

[0164] See also Figure 8 ,The specific steps for obtaining abnormal identification records are:

[0165] Compare the deviation of abnormal mode to normal operating parameters using the formula:

[0166]

[0167] Get the abnormal deviation value Z mod , where X Z is the currently observed data point, μ Z is the average value of historical data, σ Z is the standard deviation of historical data;

[0168] The following data was collected:

[0169] X Z =10,μZ =8,σ Z =1.5;

[0170] The calculation steps are as follows:

[0171] |X Z -μ Z |=|10-8|=2

[0172]

[0173] Substituting the above results into the formula, we get:

[0174]

[0175] This result shows that if the anomaly threshold is 1, then 0 is less than 1, indicating that the current data point X=10 is not considered an anomaly under this setting.

[0176] Based on the abnormal deviation value, the sensor record is compared with the fire door operation standard to identify sensor failure or mechanical failure, and the potential cause of the failure is analyzed to obtain the abnormal identification record;

[0177] Sensors are used to continuously collect data on the movement speed, opening and closing status, and duration of operation of fire doors. The collected data is stored and preliminarily cleaned and formatted for subsequent processing. Data processing includes filtering out noise, correcting deviations, and making preliminary judgments on anomalies or trends in the data. It involves the use of statistical analysis and time series analysis techniques to determine the normal fluctuation range of the data and capture prominent abnormal patterns. The processed data stream will be used for further analysis and decision support, such as predicting door maintenance needs and optimizing the service life of doors.

[0178] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. Industrial fire and wind resistant door automatic response system, characterized by: The system comprises: The environmental monitoring module aggregates data based on the real-time received temperature, smoke concentration and wind speed data, calculates the average and standard deviation of the data, analyzes the short-term environmental change forecast trend, and generates environmental baseline data; The gating analysis module uses the ARIMA model to analyze the periodicity and trend of environmental data changes based on the environmental baseline data, determines the matching parameters of the ARIMA model, predicts short-term environmental changes, and generates gating adjustment instructions; The door control adjustment module calculates the fire door operation parameters, including the closing speed and force of the fire door, based on the door control adjustment instruction, and adjusts the door control parameters according to the current environmental data to generate a real-time door control configuration; The anomaly monitoring module analyzes the abnormal patterns in the sensor data stream based on the real-time gate control configuration using the isolation forest algorithm, compares the deviations of the abnormal patterns with the normal operating parameters, identifies sensor failures or mechanical failures of the door, and generates an anomaly identification record.

2. The automatic response system for industrial fire and wind resistant doors according to claim 1 is characterized in that: The steps for obtaining the environmental baseline data are specifically as follows: Real-time data of temperature, smoke concentration, and wind speed received from multiple sensors are marked with time tags and the data are sorted according to timestamps to obtain sensor data sets; Based on the sensor data set, the mean and standard deviation of the data are calculated using the formula: and Get the mean and standard deviation results, where x i represents the sensor data point, n is the total number of data points, MD represents the mean value of the data, and SD represents the standard deviation of the data; Based on the mean and standard deviation results, the short-term environmental change forecast trend is analyzed to obtain an environmental baseline data set.

3. The automatic response system for industrial fire and wind resistant doors according to claim 1 is characterized in that: The specific steps of the periodicity and trend analysis are as follows: The environmental baseline data is processed for stability, and a differential method is used to reduce the seasonal and trend effects of the data to generate a stable time series data set; Based on the stationary time series data set, the ARIMA model is used, using the formula: Evaluate the periodic changes and long-term trends of the data and obtain periodicity and trend analysis results, among which PF t represents the predicted value at time t, β0 is the intercept term, β1 is the coefficient at time t, t is the time variable, β2 and β3 are adjustment coefficients, T is the length of the data period, and are cosine and sine functions, which are used to model seasonal fluctuations in the data.

4. The automatic response system for industrial fire and wind resistant doors according to claim 1 is characterized in that: The steps for obtaining the gate adjustment instruction are specifically as follows: According to the periodicity and trend, the matching parameters of the ARIMA model are determined to predict short-term environmental changes using the formula: PR t+1 =α R ·XR t +(1-α R )·PR t Get the gate adjustment instruction, where PR t+1 is the predicted environmental state at the next time point, XR t is the observed value at the current time t, α R is the smoothing coefficient, PR t is the predicted value at the previous time t.

5. The automatic response system for industrial fire and wind resistant doors according to claim 1 is characterized in that: The calculation steps of the fire door operating parameters are specifically as follows: Based on the door control adjustment instruction, physical parameters of the fire door, including weight, size and installation position, are collected to obtain basic data of the fire door; Based on the basic data of the fire door, the formula is adopted: and F opt =μmg Calculate the closing speed and force of the fire door, where v opt Indicates closing speed, F opt is the closing force, g is the acceleration due to gravity, s is the distance the door falls, h is the height from the door frame to the ground, μ is the friction coefficient, and m is the mass of the door.

6. The automatic response system for industrial fire and wind resistant doors according to claim 1, characterized in that: The steps for obtaining the real-time gating configuration are specifically as follows: Analyze the currently collected real-time data, including temperature, smoke concentration and fire source distance, and integrate the data to obtain the current environmental data; Based on the current environmental data, the formula is adopted: and F adj =F base ·(1+γ c ·T amb ) Refine the gating parameters to obtain the real-time gating configuration, where v adj and F adj are the adjusted closing speed and closing force, v base and F base is the basic closing speed and closing force, β c and γ c is the adjustment factor, d fire is the distance between the fire source and the fire door, c smoke is the smoke density, T amb is the ambient temperature, α c It is the coefficient that adjusts the closing speed of the fire door according to the smoke concentration.

7. The automatic response system for industrial fire and wind resistant doors according to claim 1 is characterized in that: The steps of analyzing abnormal patterns in the sensor data stream are specifically: Based on the real-time door control configuration, sensor data associated with the fire door operation is collected, including the door's movement speed, opening and closing status, and continuous operation time, to obtain a continuously updated data stream; Based on the continuously updated data stream, anomaly pattern analysis is performed using the isolation forest algorithm, using the formula: The anomaly detection result is obtained, where E(h(xo)) is the average path length of the data point xo in the tree, c(no) is the normalization factor, and E(xo) represents the anomaly score of the data point.

8. The automatic response system for industrial fire and wind resistant doors according to claim 1 is characterized in that: The steps for obtaining the abnormal identification record are specifically as follows: The abnormal mode is compared with the deviation of the normal operating parameters, using the formula: Get the abnormal deviation value Z mod , where X Z is the currently observed data point, μ Z is the average value of historical data, σ Z is the standard deviation of historical data; Based on the abnormal deviation value, the sensor record is compared with the fire door operation standard, sensor failure or mechanical failure is identified, and potential fault causes are analyzed to obtain an abnormal identification record.

Images