Internet of Things fire-fighting electrical early warning method and early warning system

Abstract

The invention relates to the technical field of fire safety, in particular to an Internet of Things fire-fighting electrical early warning method and early warning system, and the method comprises the following steps: collecting the current and voltage data of a plurality of positions in a building in real time based on an Internet of Things sensor, recognizing abnormal fluctuation through frequency analysis, detecting the aging state of a wire, and generating a harmonic abnormality detection record. According to the invention, the current and voltage in the building are monitored in real time through the Internet of Things technology, detection and identification of wire aging and electric leakage events are realized, data support is provided for fault prevention, the early warning capability of the system is enhanced, the fire risk is identified in an early stage, and the equipment state is monitored in real time by using temperature and pressure sensors. The device performance degradation is evaluated through data analysis, timely response is made when overload, short circuit and overheating risks occur to the device, the fire risk level is calculated in combination with environment monitoring data, early warning is sent to management personnel in real time, the emergency response speed and efficiency are improved, and the fire prevention and control capacity is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire safety, and particularly to an Internet of Things (IoT) fire electrical warning method and warning system. Background Art

[0002] The technical field of fire safety focuses on preventing fire occurrence, controlling fire spread, and minimizing fire damage through the development and implementation of various methods and strategies, including fire detection and alarm systems, automatic sprinkler systems, fireproof materials and technologies, emergency evacuation procedures, and building design, to ensure the safe evacuation of personnel in case of a fire. By combining sensor technology, data analysis, communication systems, and automatic control systems, the fire prevention, fire extinguishing, and personnel evacuation capabilities of buildings and facilities are enhanced, the accuracy and response speed of fire warnings are improved, the risk of fire occurrence is reduced, the damage caused by fires is minimized, and the safety of public and private property is ensured.

[0003] Among them, the fire electrical warning method focuses on improving the prevention and early warning capabilities of electrical fires. Through sensors installed on electrical equipment, it monitors temperature, current, and various key parameters in real time, detects various abnormal states that lead to fires, including overload, short circuit, and equipment overheating, discovers fire hazards in a timely manner, sends alarms to management personnel in real time, takes response measures in the early stage of fire formation, prevents the occurrence or spread of fires, protects the safety of life and property, improves the safety protection level of buildings, and realizes an intelligent and automated fire safety system.

[0004] Traditional fire electrical warning methods focus on dealing with fires that have already occurred, including automatic sprinkler systems and emergency evacuation procedures. They are insufficient in the early prevention and real-time monitoring of fires, rely on the abnormal increase of smoke and temperature, miss the intervention opportunity in the fire formation stage, and when the abnormality is detected, the fire has developed to an uncontrollable level. There are deficiencies in integrating real-time data processing and analysis capabilities, which limit the ability to quickly respond to and handle complex situations, resulting in insufficient capabilities in fire prevention and early identification, and increasing the risk of casualties and property losses. Summary of the Invention

[0005] To solve the technical problem of the insufficient early prevention and real-time monitoring capabilities existing in the prior art, embodiments of the present invention provide an Internet of Things fire electrical warning method and warning system. The technical solutions are as follows:

[0006] On the one hand, an Internet of Things fire electrical warning method is provided, and the method includes:

[0007] S1: Based on Internet of Things sensors, collect current and voltage data at multiple locations inside the building in real time, identify abnormal fluctuations through frequency analysis, detect the wire aging state, and generate harmonic anomaly detection records;

[0008] S2: Using the harmonic anomaly detection record, detect and record leakage events by identifying short spikes and dips in the current waveform, including the power signal of the leakage and the time point information, and generate a circuit leakage diagnosis result;

[0009] S3: Based on the circuit leakage diagnosis result, use temperature and pressure sensors to monitor the operating status of multiple devices in real time. By analyzing data fluctuations and change trends, identify performance degradation and faults, and analyze the impact on fire safety, and generate a device status analysis result;

[0010] S4: Based on the device status analysis result, combined with a preset anomaly detection threshold, evaluate the overload, short - circuit, and overheat risks of the circuit and devices by real - time monitoring of abnormal power and temperature data, and generate a fault risk assessment result;

[0011] S5: Use the fault risk assessment result, combined with real - time environmental monitoring data, including environmental temperature and humidity, and smoke concentration, calculate the fire risk level of the target building in real time, and send a warning message to the management personnel to generate a fire - fighting electrical warning message.

[0012] As a further solution of the present invention, the harmonic anomaly detection record includes the amplitude of the abnormal frequency, the duration of the abnormal wavelength, and the change trend of the waveform. The circuit leakage diagnosis result includes the occurrence time of the leakage event, the leakage intensity, and the circuit segment affected. The device status analysis result includes the power consumption data of the device, the temperature change rate, and the pressure readings of key components. The fault risk assessment result includes the power signal data of the overload current, the short - circuit detection record, and the device temperature record data. The fire - fighting electrical warning message includes the fire risk level, the warning message matching result, and the risk event response record.

[0013] As a further solution of the present invention, based on Internet of Things sensors, the steps of collecting current and voltage data at multiple locations inside the building in real time, and identifying abnormal fluctuations through frequency analysis to detect the wire aging status and generate a harmonic anomaly detection record are as follows:

[0014] S101: Based on Internet of Things sensors, deploy current and voltage sensors at multiple locations in the circuit, record the current and voltage data, and generate electrical monitoring data;

[0015] S102: Based on the electrical monitoring data, perform frequency analysis on the data, including calculating the peak - to - valley values in the time series of the current and voltage, and identifying abnormal fluctuations in the frequency, and generate a frequency analysis result;

[0016] S103: Based on the frequency analysis result, analyze the aging degree of the wire according to the correlation between various frequency fluctuation characteristics and wire aging, and generate a harmonic anomaly detection record.

[0017] As a further aspect of the present invention, the steps of using the harmonic anomaly detection record to detect and record leakage events by identifying short spikes and dips in the current waveform, including the power signal of the leakage and the time point information, and generating a circuit leakage diagnosis result are specifically as follows:

[0018] S201: Extract the harmonic anomaly detection record, analyze the power detection data, detect and mark the current waveforms with spikes and dips, analyze the occurrence frequency and duration of the target waveforms, and generate leakage waveform characteristics;

[0019] S202: Based on the leakage waveform characteristics, identify leakage events by analyzing the marked current waveforms, and generate a leakage event record;

[0020] S203: Based on the leakage event record, record the time point of the leakage occurrence and the signal characteristics of the power data, and generate a circuit leakage diagnosis result.

[0021] As a further aspect of the present invention, based on the circuit leakage diagnosis result, using temperature and pressure sensors to monitor the operating states of multiple devices in real time, identifying performance degradation and faults by analyzing data fluctuations and change trends, and analyzing the impact on fire safety, the steps of generating a device state analysis result are specifically as follows:

[0022] S301: Based on the circuit leakage diagnosis result, use temperature and pressure sensors to collect the temperature data and pressure data of multiple devices during operation in real time, and generate a real-time monitoring data set;

[0023] S302: Based on the real-time monitoring data set, analyze the temperature and pressure data, detect abnormal fluctuations, calculate the change trend of the data, identify and record abnormal events, including temperature anomalies and pressure anomalies, and generate an abnormal fluctuation analysis result;

[0024] S303: Based on the abnormal fluctuation analysis result, evaluate the safety state of the device, identify device performance degradation and faults, including increased internal resistance, circuit failure, and current fluctuation, and evaluate the impact on fire safety, and generate a device state analysis result.

[0025] As a further aspect of the present invention, the specific formula for calculating the change trend of the data is:

[0026]

[0027] where T is the trend score, used to quantify the change trend of temperature or pressure in the time series data, x i represents the temperature or pressure value of the i-th collected data point, represents the average value of the temperature or pressure of all data points in the collected data set, t irepresents the time corresponding to the i-th data point, represents the average value of the times corresponding to all data points, n represents the total number of data points, and i represents the index of the data point.

[0028] As a further solution of the present invention, based on the device status analysis result, combined with a preset anomaly detection threshold, by real-time monitoring of abnormal power and temperature data, the steps of evaluating the overload, short-circuit, and overheat risks of the circuit and the device and generating a fault risk assessment result are specifically as follows:

[0029] S401: Based on the device status analysis result, combined with a preset anomaly detection threshold, perform real-time analysis on power and temperature data, identify abnormal data points, and generate a threshold comparison result;

[0030] S402: Based on the threshold comparison result, by analyzing the change trend and periodic fluctuation of the abnormal data points, evaluate the distribution pattern of the abnormal data in time, and generate an abnormal data distribution feature;

[0031] S403: Based on the abnormal data distribution feature, by analyzing the data characteristics of the abnormal points, identify the risk events of the circuit and the device, including overload, short-circuit, and overheat, and generate a fault risk assessment result.

[0032] As a further solution of the present invention, using the fault risk assessment result, combined with real-time environmental monitoring data, including environmental temperature and humidity, and smoke concentration, the steps of calculating the fire risk level of the target building in real time and sending a warning message to the management personnel to generate a fire and electrical warning message are specifically as follows:

[0033] S501: Use the fault risk assessment result, and use a temperature and humidity sensor and a smoke sensor to collect the temperature, humidity, and smoke concentration data in the building in real time to generate a real-time environmental data set;

[0034] S502: Based on the real-time environmental data set, combined with real-time risk events, calculate a fire risk index and generate a fire risk assessment index;

[0035] S503: Based on the fire risk assessment index, evaluate the fire risk level, and send a warning message to the management personnel according to the risk level and risk type to generate a fire and electrical warning message.

[0036] As a further solution of the present invention, the specific formula for calculating the fire risk index is:

[0037] R = β0 + β1T + β2H + β3S + β4D

[0038] Among them, R represents the calculated fire risk index, β0 represents the intercept of the regression model, indicating the basic fire risk level without the influence of any environmental variables, β1 is the regression coefficient of temperature, T represents the ambient temperature monitored in real time, β2 is the regression coefficient of humidity, H represents the ambient humidity monitored in real time, β3 is the regression coefficient of smoke concentration, S represents the smoke concentration monitored in real time, β4 is the regression coefficient of the severity of real-time risk events, and D represents the severity of risk events monitored in real time.

[0039] On the other hand, an Internet of Things fire electrical warning system is provided. This system is applied to the Internet of Things fire electrical warning method. The system includes:

[0040] The power data acquisition module, based on Internet of Things sensors, deploys power sensors at multiple positions in the circuit to collect current and voltage data at multiple positions inside the building and generates electrical data records;

[0041] The data fluctuation analysis module, based on the electrical data records, performs frequency analysis on the power data, identifies abnormal fluctuations in the current and voltage data, detects the aging state of the wires, and generates harmonic anomaly detection records;

[0042] The real-time leakage detection module uses the harmonic anomaly detection records to analyze the short spikes and sharp drops in the current waveform, detects and identifies leakage signals, and records the time points of leakage and power signal data to generate circuit leakage diagnosis results;

[0043] The operating state monitoring module, based on the circuit leakage diagnosis results, combines the data of temperature and pressure sensors to monitor the operating states of multiple devices in real time, analyzes the fluctuations and trends of the data, identifies equipment performance degradation and potential faults, and evaluates the impact on fire safety to generate equipment state analysis results;

[0044] The risk index calculation module, based on the equipment state analysis results, combines the preset anomaly detection thresholds to evaluate the overload, short circuit, and overheat risks of the circuit and equipment in real time and generates fault risk assessment results;

[0045] The warning information sending module, based on the fault risk assessment results, detects the temperature, humidity, and smoke concentration data in the building in real time, calculates the fire risk level of the target building, and sends warning information to the management personnel to generate fire electrical warning information.

[0046] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0047] Real-time monitoring of the current and voltage in a building through Internet of Things technology enables the detection and identification of wire aging and leakage events, providing data support for fault prevention and enhancing the system's early warning ability to identify fire risks. Temperature and pressure sensors are used to monitor the device status in real time, and data analysis is utilized to evaluate the degradation of device performance. Timely responses are made when the device is at risk of overload, short circuit, or overheating. Combining environmental monitoring data to calculate the fire risk level and sending early warnings to managers in real time improves the speed and efficiency of emergency response and enhances the ability to prevent and control fires. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 It is a schematic diagram of the working process of the present invention;

[0050] Figure 2 It is a detailed flowchart of S1 of the present invention;

[0051] Figure 3 It is a detailed flowchart of S2 of the present invention;

[0052] Figure 4 It is a detailed flowchart of S3 of the present invention;

[0053] Figure 5 It is a detailed flowchart of S4 of the present invention;

[0054] Figure 6 It is a detailed flowchart of S5 of the present invention;

[0055] Figure 7 It is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] The following describes the technical solutions in the present invention with reference to the drawings.

[0057] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0058] In the embodiments of the present invention, the terms "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, they have the same meaning. The terms "of", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, they have the same meaning.

[0059] In the embodiments of the present invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, they have the same meaning.

[0060] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0061] The embodiments of the present invention provide an Internet of Things (IoT) fire electrical warning method, as shown in the flowchart of the IoT fire electrical warning method Figure 1 The processing flow of the method may include the following steps:

[0062] S1: Based on IoT sensors, collect current and voltage data at multiple locations inside the building in real time. Through frequency analysis, identify abnormal fluctuations, detect the aging state of wires, and generate harmonic anomaly detection records;

[0063] S2: Use the harmonic anomaly detection records to detect and record leakage events by identifying short spikes and dips in the current waveform, including the leakage power signal and time point information, and generate a circuit leakage diagnosis result;

[0064] S3: Based on the circuit leakage diagnosis result, use temperature and pressure sensors to monitor the operating states of multiple devices in real time. By analyzing data fluctuations and change trends, identify performance degradation and faults, and analyze the impact on fire safety, and generate a device state analysis result;

[0065] S4: Based on the device state analysis result, combined with a preset anomaly detection threshold, evaluate the overload, short circuit, and overheating risks of the circuit and devices by monitoring abnormal power and temperature data in real time, and generate a fault risk assessment result;

[0066] S5: Use the fault risk assessment result, combined with real-time environmental monitoring data, including environmental temperature and humidity, and smoke concentration, calculate the fire risk level of the target building in real time, and send a warning message to the management personnel to generate a fire electrical warning message.

[0067] The harmonic anomaly detection record includes the amplitude of the abnormal frequency, the duration of the abnormal wavelength, and the change trend of the waveform. The circuit leakage diagnosis result includes the occurrence time of the leakage event, the leakage intensity, and the affected circuit section. The equipment status analysis result includes the power consumption data of the equipment, the temperature change rate, and the pressure readings of the key components. The fault risk assessment result includes the electrical signal data of the overload current, the short-circuit detection record, and the equipment temperature record data. The fire electrical warning information includes the fire risk level, the warning information matching result, and the risk event response record.

[0068] Please refer to Figure 2 , based on the Internet of Things sensors, real-time collect the current and voltage data at multiple locations inside the building. Through frequency analysis, identify abnormal fluctuations, detect the wire aging status. The steps to generate the harmonic anomaly detection record are specifically as follows:

[0069] S101: Based on the Internet of Things sensors, deploy current and voltage sensors at multiple locations in the circuit, record the current and voltage data, and generate electrical monitoring data;

[0070] By deploying Internet of Things sensors at multiple key nodes of the circuit, the current sensor measures the current flowing through the circuit, and the voltage sensor records the voltage difference between two points of the circuit. The data sampling rate of each sensor is set to 100 times per second to ensure the real-time nature and accuracy of the data. The recorded data of current and voltage are crucial for analyzing the circuit operation status and identifying potential faults. Through the AD converter, the analog signal is converted into a digital signal for data processing and remote transmission. After the data is collected, it is stored in the cloud server for access and analysis at any time, ensuring the integrity and security of the monitoring data. The generated electrical monitoring data provides basic information for the subsequent steps and effectively supports the fault diagnosis and health assessment of the entire system.

[0071] S102: Based on the electrical monitoring data, perform frequency analysis on the data, including calculating the peak and valley values in the time series of current and voltage, identifying abnormal fluctuations in frequency, and generating the frequency analysis result;

[0072] For the collected electrical monitoring data, use the Fourier transform method to perform frequency analysis on the time series data of current and voltage, convert the time-domain signal into a frequency-domain signal, clarify the intensity of each frequency component, identify abnormal fluctuations. By calculating the amplitude of each frequency component and comparing it with the preset threshold within the normal operation range, the frequency points exceeding the threshold are regarded as abnormal. Consider the phase difference between current and voltage in the analysis to provide data support for identifying potential non-linear characteristics or asymmetric loads in the circuit. The frequency analysis result is generated in the form of charts and numerical lists, including the amplitude and phase information of each frequency. The result is crucial for diagnostic analysis and provides the necessary pre-data for the next step of harmonic anomaly detection.

[0073] S103: Based on the frequency analysis results, analyze the aging degree of the wire according to the correlation between various frequency fluctuation characteristics and wire aging, and generate a harmonic anomaly detection record;

[0074] In the above content, according to the correlation between various frequency fluctuation characteristics and wire aging, according to the formula Calculate the aging degree of the wire;

[0075] In the formula, r represents the quantitative evaluation value of the wire aging degree, f k represents the measured value of the kth frequency fluctuation characteristic, w k is the importance weight of this characteristic, m is the total number of frequency characteristics considered, and k is the index;

[0076] Detailed explanation of the formula and the derivation process of the formula calculation:

[0077] Assume that four frequency fluctuation characteristics are considered, and their measured values and importance weights are f = {0.8, 0.6, 0.9, 0.7}, w = {0.4, 0.3, 0.2, 0.1} respectively. Substitute the assumed values into the formula to calculate the aging degree:

[0078]

[0079] The result 0.75 indicates the evaluation value of the wire aging degree. The calculation process is used to analyze and predict the wire aging trend and evaluate the fire safety risk.

[0080] Please refer to Figure 3 , using the harmonic anomaly detection record, by identifying the short spikes and dips in the current waveform, detecting and recording leakage events, including the leakage power signal and time point information, the steps to generate the circuit leakage diagnosis result are specifically as follows:

[0081] S201: Extract the harmonic anomaly detection record, analyze the power detection data, detect and mark the current waveforms with spikes and dips, analyze the occurrence frequency and duration of the target waveforms, and generate leakage waveform characteristics;

[0082] Use data analysis software tools, such as MATLAB or the SciPy library in Python, to analyze the power detection data extracted from harmonic anomaly detection records. Through time series analysis methods, including peak detection algorithms, identify spikes and dips in the current waveform. Each spike and dip is automatically labeled by the algorithm, and its occurrence frequency and duration are calculated. The process includes using a sliding window method to continuously scan data points, and the window size is adjusted according to the grid frequency to adapt to different grid conditions. Whenever a current change exceeding a preset threshold is detected, the algorithm records the event and classifies it to distinguish normal load changes from potential leakage waveforms. The target analysis results will be used to generate a leakage waveform feature report, which records the characteristics of various waveforms, such as amplitude, duration, and occurrence frequency, providing key data for the next step of leakage event identification.

[0083] S202: Based on the leakage waveform characteristics, analyze the labeled current waveform to identify leakage events and generate leakage event records;

[0084] According to the previously generated leakage waveform characteristics, adopt pattern recognition techniques and use classification algorithms in machine learning, such as random forest or logistic regression, to analyze the labeled current waveform. Utilize the labeled waveform data to learn the characteristics of distinguishing normal waveforms from leakage waveforms. In practical applications, the algorithm evaluates new waveform data and determines whether it belongs to a leakage event based on the learned model. The analysis process considers factors such as the duration, shape of the waveform, and the time relationship with other events to reduce false alarms and missed detections. The analysis results are recorded in the leakage event record, which details the characteristics and confidence level of the identified leakage events, providing necessary information for further diagnosis and response.

[0085] S203: Based on the leakage event record, record the time point of leakage occurrence and the signal characteristics of the power data to generate a circuit leakage diagnosis result;

[0086] Utilize the data in the leakage event record and, through circuit analysis tools, such as circuit simulation software or dedicated diagnostic tools, record the specific time point of each leakage event occurrence and the signal characteristics of the power data. During the process, pay attention to the voltage and current changes before and after the event. Use waveform comparison and signal processing techniques, such as peak analysis and signal filtering, to describe the signal characteristics. Through target analysis, generate a circuit leakage diagnosis result. Each result includes the time of leakage, the circuit part involved, the cause, and the impact on the system. The results are crucial for maintenance personnel to locate problems and repair them in a timely manner, ensuring the safe operation and reliability of the circuit system.

[0087] Please refer to Figure 4, based on the circuit leakage diagnosis results, using temperature and pressure sensors, to monitor the operating status of multiple devices in real time. By analyzing data fluctuations and change trends, identify performance degradation and faults, and analyze the impact on fire safety. The specific steps to generate the device status analysis results are as follows:

[0088] S301: Based on the circuit leakage diagnosis results, using temperature and pressure sensors, collect the temperature data and pressure data of multiple devices during operation in real time, and generate a real-time monitoring data set;

[0089] Using temperature and pressure sensors deployed on key devices to continuously monitor the operating status of the devices. The data collected by the sensors includes the surface temperature and internal pressure of the devices. The target data is updated once per second to capture the immediate operating conditions. Use wireless network technology to transmit the collected data to the central data processing center. The data integration system forms a real-time monitoring data set by integrating data from various sources. The data processing center uses data normalization and cleaning algorithms to ensure the accuracy and availability of the data. Combining trend analysis helps to identify changes in device operation. The generated data set provides a basis for subsequent analysis and supports more complex data processing and anomaly detection tasks.

[0090] S302: Based on the real-time monitoring data set, analyze the temperature and pressure data, detect abnormal fluctuations, and calculate the change trend of the data. Identify and record abnormal events, including temperature anomalies and pressure anomalies, and generate the abnormal fluctuation analysis result; The specific formula for calculating the change trend of the data is: Among them, is the trend score, used to quantify the change trend of temperature or pressure in time series data, represents the temperature or pressure value of the th collected data point, represents the average value of the temperature or pressure of all data points in the collected data set, represents the time corresponding to the th data point, represents the average value of the times corresponding to all data points, represents the total number of data points, represents the index of the data point.

[0091] Formula: ; Detailed explanation of the formula and the derivation process of the formula calculation: 2]The formula is used to calculate the correlation between temperature or pressure data and the time series, and the result is used to judge the consistency and trend of data changes; Parameter meaning and setting value: : The total number of data points, assuming ; is the timestamp of the th data point, assumed to be , is the average value of all time points, ; is the temperature or pressure value of the th data point. Assuming the factor considered is the pressure value, the corresponding numerical values of the data points are , is the average temperature or pressure value of all data points, ; Substitute the parameters into the formula for calculation: ; ; ; ; The result indicates that the correlation between the change in temperature or pressure data and time is low, indicating that there is no obvious trend in the data change. The calculation process is used to identify the randomness or abnormal behavior in the data fluctuation and take corresponding preventive measures.

[0106] S303: Based on the results of the abnormal fluctuation analysis, evaluate the safety status of the device, identify the degradation and faults of the device performance, including increased internal resistance, circuit failure, current fluctuation, and evaluate the impact on fire safety, and generate the device status analysis result;

[0107] Comprehensively utilize the results of anomaly fluctuation analysis, and through machine learning techniques such as decision trees and clustering analysis, evaluate the safety status and performance degradation of the equipment. The target algorithm is used to learn the differences between the normal and abnormal states of the equipment from historical data and apply it to real-time data to identify potential failures or performance degradation. During the evaluation process, detect the increase in the internal resistance of the equipment, potential failures of the circuit, and current fluctuation conditions. The identified problems are recorded in the equipment status analysis results, including the specific type, cause, and predicted impact of the failure. By evaluating the potential impact of the target problem on fire safety, ensure that measures are taken before major risks occur. The analysis is crucial for ensuring the safe operation of the facility and preventing disasters from occurring.

[0108] Please refer to Figure 5 , based on the equipment status analysis results, combined with the preset anomaly detection threshold, evaluate the overload, short circuit, and overheat risks of the circuit and equipment by real-time monitoring of abnormal power and temperature data. The specific steps for generating the fault risk assessment results are as follows:

[0109] S401: Based on the equipment status analysis results, combined with the preset anomaly detection threshold, perform real-time analysis on the power and temperature data, identify abnormal data points, and generate a threshold comparison result;

[0110] Adopt threshold analysis technology, combined with the previously set anomaly detection criteria, perform real-time monitoring on the collected power and temperature data, and use numerical analysis software, such as the NumPy library in Python, to achieve rapid data processing and threshold comparison. The threshold is set based on the statistical analysis results of the equipment's historical operation data, including the calculation of the average value and standard deviation, to determine the upper and lower limits of anomaly detection. Through real-time analysis, the system automatically marks the data points that exceed the target threshold as abnormal. The marked abnormal data points are recorded in real-time, and the timestamp and specific value of each data point are recorded in detail to assist in subsequent trend analysis and fault diagnosis. The generated threshold comparison result will be used to initially identify potential performance problems of the equipment, such as overheating or voltage instability, providing a basis for subsequent analysis.

[0111] S402: Based on the threshold comparison result, evaluate the distribution pattern of abnormal data over time by analyzing the change trend and periodic fluctuation of abnormal data points, and generate the distribution characteristics of abnormal data;

[0112] Based on the threshold comparison results, the time series analysis method is used to study the changing trends and periodic fluctuations of the marked abnormal data points. The autoregressive moving average model and periodic analysis techniques are adopted to reveal the time dependence and periodic patterns of the data. Statistical calculations are performed through MATLAB. Each abnormal point is analyzed for its position, frequency, and influence intensity in the time series. By examining the duration and repeating patterns of abnormal events, the potential system impacts are evaluated. The generated report on the distribution characteristics of abnormal data describes the time distribution patterns of all abnormal data, providing valuable insights for predicting possible future equipment failures and performing preventive maintenance.

[0113] S403: Based on the distribution characteristics of abnormal data, by analyzing the data characteristics of abnormal points, risk events of circuits and equipment are identified, including overload, short circuit, and overheating, to generate the fault risk assessment results.

[0114] Based on the distribution characteristics of abnormal data, data mining and machine learning techniques such as decision tree analysis are applied to deeply analyze the data characteristics of abnormal points. The analysis involves evaluating specific parameters of each abnormal point, such as the degree of mutation of current, voltage, and temperature and their correlations with equipment failures. Through target analysis, risk events related to circuits and equipment are identified, including overload, short circuit, and overheating, etc. Each identified risk event is recorded in the fault risk assessment results, which details the type of the event, the occurrence time, the affected scope, and its specific impact on the equipment safety. The target results are crucial for operators, helping to take necessary maintenance measures in a timely manner, avoiding equipment damage and potential safety accidents, and ensuring the safety of equipment and personnel.

[0115] Please refer to Figure 6 , using the fault risk assessment results and combining with real-time environmental monitoring data, including environmental temperature and humidity, and smoke concentration, the fire risk level of the target building is calculated in real time, and warning information is sent to the management personnel. The steps to generate the fire and electrical warning information are specifically as follows:

[0116] S501: Using the fault risk assessment results, temperature and humidity sensors and smoke sensors are used to collect the temperature, humidity, and smoke concentration data in the building in real time to generate a real-time environmental data set.

[0117] By configuring temperature and humidity sensors and smoke sensors in key areas, the data captured by the temperature and humidity sensors includes air temperature and relative humidity, while the smoke sensors measure the concentration of smoke particles in the air. The target sensors send data to the central monitoring system every second, using wireless communication technology to ensure the real-time and reliability of data transmission. The data processing system aggregates and preliminarily analyzes the target real-time data to generate a real-time environmental data set, including the timestamp, measurement value, and measurement location information of the data. The data set provides a basis for subsequent risk assessment and helps to quickly respond to potential environmental changes and emergencies.

[0118] S502: Based on the real-time environmental data set and combined with real-time risk events, calculate the fire risk index and generate the fire risk assessment index;

[0119] The specific formula for calculating the fire risk index is:

[0120] R = β0 + β1T + β2H + β3S + β4D

[0121] Where, R represents the calculated fire risk index, β0 represents the intercept of the regression model, indicating the basic fire risk level without the influence of any environmental variables, β1 is the regression coefficient of temperature, T represents the real-time monitored environmental temperature, β2 is the regression coefficient of humidity, H represents the real-time monitored environmental humidity, β3 is the regression coefficient of smoke concentration, S represents the real-time monitored smoke concentration, β4 is the regression coefficient of the severity of real-time risk events, and D represents the severity of real-time monitored risk events.

[0122] Formula:

[0123] R = β0 + β1T + β2H + β3S + β4D;

[0124] Detailed explanation of the formula and the derivation process of formula calculation:

[0125] The formula is used to comprehensively evaluate the fire risk index, and the result is used to analyze the fire risk level of the target building;

[0126] Meaning and setting values of parameters:

[0127] β0: Intercept, assumed to be 0.5, representing the basic fire risk index and the lowest risk without external influence;

[0128] β1: Regression coefficient of temperature, assumed to be 0.1, indicating that for every 1°C increase in temperature, the fire risk index increases by 0.1;

[0129] β2: Regression coefficient of humidity, assumed to be -0.05, indicating that for every 1% decrease in humidity, the fire risk index increases by 0.05;

[0130] β3: The regression coefficient of the smoke concentration, assumed to be 0.2, indicating that for every 1-unit increase in the smoke concentration, the fire risk index increases by 0.2;

[0131] β4: The regression coefficient of the severity of the risk event, assumed to be 0.3, indicating that for every 1-level increase in the risk event, the fire risk index increases by 0.3;

[0132] T: The ambient temperature measured, assumed to be 30°C, which is collected in real time by the temperature sensor;

[0133] H: The ambient humidity measured, assumed to be 40%, which is collected in real time by the humidity sensor and quantified as a percentage;

[0134] S: The smoke concentration measured, assumed to be 5 units, which is output as a concentration value by the smoke sensor;

[0135] D: The severity of the risk event measured, assumed to be level 2, and the comprehensive impact of the event is quantified as a severity level by the risk event assessment system;

[0136] Substitute the parameters into the formula for calculation:

[0137] Substitute the specific values of the above parameters:

[0138] R = 0.5 + (0.1 × 30) + (-0.05 × 40) + (0.2 × 5) + (0.3 × 2);

[0139] R = 0.5 + 3 - 2 + 1 + 0.6;

[0140] R = 3.1;

[0141] The calculated fire risk index R = 3.1 indicates a relatively high fire risk in the current environment. Measures need to be taken to prevent and control the occurrence of fires. The data reflects the potential threat level of fire occurrence, and the calculation results are used for real-time decision-making to improve the accuracy and response efficiency of fire prevention and control.

[0142] S503: Based on the fire risk assessment index, evaluate the fire risk level, and send warning information to the management personnel according to the risk level and risk type, and generate fire and electrical warning information;

[0143] Compare the risk index with the preset risk level threshold. If the risk index exceeds the threshold, it will be identified as a high risk. According to different risk levels and types, the warning mechanism will be automatically triggered to send warning messages to the mobile devices or emails of the management personnel. The warning messages include the risk level, recommended response measures, and emergency contact information. The process includes data communication, an automatic alarm system, and user interface design to ensure the accurate transmission and timely response of information. The generated fire electrical warning information helps the management personnel take necessary preventive or response measures to reduce the potential damage caused by fires.

[0144] Please refer to Figure 7 , an Internet of Things (IoT) fire electrical warning system. The IoT fire electrical warning system is used to execute the above-mentioned IoT fire electrical warning method. The system includes:

[0145] The power data acquisition module, based on IoT sensors, deploys power sensors at multiple locations in the circuit to collect current and voltage data at multiple locations inside the building and generates electrical data records.

[0146] The data fluctuation analysis module, based on the electrical data records, performs frequency analysis on the power data to identify abnormal fluctuations in the current and voltage data, detects the aging state of the wires, and generates harmonic anomaly detection records.

[0147] The real-time leakage detection module uses the harmonic anomaly detection records to analyze the short spikes and sharp drops in the current waveform, detects and identifies leakage signals, and records the time points of leakage and power signal data to generate circuit leakage diagnosis results.

[0148] The operating state monitoring module, based on the circuit leakage diagnosis results, combines the data of temperature and pressure sensors to monitor the operating states of multiple devices in real time, analyzes the fluctuations and trends of the data, identifies equipment performance degradation and potential faults, and evaluates the impact on fire safety to generate equipment state analysis results.

[0149] The risk index calculation module, based on the equipment state analysis results, combines the preset anomaly detection threshold to evaluate the overload, short-circuit, and overheat risks of the circuit and equipment in real time and generates fault risk assessment results.

[0150] The warning message sending module, based on the fault risk assessment results, detects the temperature, humidity, and smoke concentration data inside the building in real time, calculates the fire risk level of the target building, and sends warning messages to the management personnel to generate fire electrical warning information.

[0151] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0152] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0153] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0154] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0155] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0156] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0157] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. [[ID=I0]]

[0159] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0160] When the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0161] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An Internet of Things fire electrical warning method, characterized in that The method includes: Based on Internet of Things sensors, collect current and voltage data at multiple locations inside the building in real time. Through frequency analysis, identify abnormal fluctuations, detect the aging status of wires, and generate harmonic anomaly detection records. Using the harmonic anomaly detection records, detect and record leakage events by identifying short spikes and dips in the current waveform, including the power signal of the leakage and time point information, and generate a circuit leakage diagnosis result. Based on the circuit leakage diagnosis result, use temperature and pressure sensors to monitor the operating status of multiple devices in real time. By analyzing data fluctuations and change trends, identify performance degradation and faults, and analyze the impact on fire safety, and generate a device status analysis result. Based on the device status analysis result, combined with preset abnormal detection thresholds, evaluate the overload, short - circuit, and overheat risks of circuits and devices by monitoring abnormal power and temperature data in real time, and generate a fault risk assessment result. Using the fault risk assessment result, combined with real - time environmental monitoring data, including environmental temperature and humidity, and smoke concentration, calculate the fire risk level of the target building in real time, and send a warning message to the management personnel, and generate a fire and electrical warning message.

2. The method for early warning of Internet of Things fire protection electrical equipment according to claim 1, wherein, The harmonic anomaly detection records include the amplitude of the abnormal frequency, the duration of the abnormal wavelength, and the change trend of the waveform. The circuit leakage diagnosis result includes the occurrence time of the leakage event, the leakage intensity, and the affected circuit section. The device status analysis result includes the power consumption data of the device, the temperature change rate, and the pressure readings of key components. The fault risk assessment result includes the power signal data of the overload current, the short - circuit detection record, and the device temperature record data. The fire and electrical warning message includes the fire risk level, the warning message matching result, and the risk event response record.

3. The Internet of Things fire electrical warning method according to claim 1, characterized in that The steps of collecting current and voltage data at multiple locations inside the building in real time based on Internet of Things sensors, through frequency analysis, identifying abnormal fluctuations, detecting the aging status of wires, and generating harmonic anomaly detection records are specifically as follows: Based on Internet of Things sensors, deploy current and voltage sensors at multiple locations in the circuit, record current and voltage data, and generate electrical monitoring data. Based on the electrical monitoring data, perform frequency analysis on the data, including calculating the peak - to - valley values in the time series of current and voltage, identifying abnormal fluctuations in frequency, and generating a frequency analysis result. Based on the frequency analysis result, analyze the aging degree of the wires according to the correlation between various frequency fluctuation characteristics and wire aging, and generate harmonic anomaly detection records.

4. The method for early warning of Internet of Things fire protection electrical equipment according to claim 1, wherein, The steps of using the harmonic anomaly detection records, detecting and recording leakage events by identifying short spikes and dips in the current waveform, including the power signal of the leakage and time point information, and generating a circuit leakage diagnosis result are specifically as follows: Extract the harmonic anomaly detection records, analyze the power detection data, detect and mark the current waveforms with spikes and dips, analyze the occurrence frequency and duration of the target waveform, and generate leakage waveform characteristics. Based on the leakage waveform characteristics, identify leakage events by analyzing the marked current waveforms, and generate a leakage event record. Based on the recorded leakage events, record the time point of leakage occurrence and the signal characteristics of power data, and generate a circuit leakage diagnosis result.

5. The method for early warning of Internet of Things fire protection electrical equipment according to claim 1, wherein, Based on the circuit leakage diagnosis result, use temperature and pressure sensors to monitor the operating status of multiple devices in real time. By analyzing data fluctuations and change trends, identify performance degradation and faults, and analyze the impact on fire safety. The specific steps for generating a device status analysis result are as follows: Based on the circuit leakage diagnosis result, use temperature and pressure sensors to collect temperature data and pressure data of multiple devices during operation in real time, and generate a real-time monitoring data set. Based on the real-time monitoring data set, analyze temperature and pressure data, detect abnormal fluctuations, and calculate the change trend of the data. Identify and record abnormal events, including temperature anomalies and pressure anomalies, and generate an abnormal fluctuation analysis result. Based on the abnormal fluctuation analysis result, evaluate the safety status of the device, identify device performance degradation and faults, including increased internal resistance, circuit failure, and current fluctuation, and evaluate the impact on fire safety, and generate a device status analysis result.

6. The method for early warning of Internet of Things fire protection electrical equipment according to claim 5, wherein, The specific formula for calculating the change trend of the data is: Among them, T is the trend score, which is used to quantify the change trend of temperature or pressure in time series data, and x i represents the temperature or pressure value of the i-th collected data point, represents the average value of the temperature or pressure of all data points in the collected data set, and t i represents the time corresponding to the i-th data point, represents the average value of the time corresponding to all data points, n represents the total number of data points, and i represents the index of the data point.

7. The method for early warning of fire-fighting electrical equipment in the Internet of Things according to claim 1, characterized in that, Based on the device status analysis result, combined with a preset abnormal detection threshold, by monitoring abnormal power and temperature data in real time, evaluate the overload, short-circuit, and overheat risks of the circuit and the device, and the specific steps for generating a fault risk assessment result are as follows: Based on the device status analysis result, combined with a preset abnormal detection threshold, perform real-time analysis on power and temperature data, identify abnormal data points, and generate a threshold comparison result. Based on the threshold comparison result, by analyzing the change trend and periodic fluctuations of abnormal data points, evaluate the distribution pattern of abnormal data in time, and generate the distribution characteristics of abnormal data. Based on the distribution characteristics of abnormal data, by analyzing the data characteristics of abnormal points, identify risk events of the circuit and the device, including overload, short-circuit, and overheat, and generate a fault risk assessment result.

8. The Internet of Things fire electrical warning method according to claim 1, characterized in that Using the fault risk assessment result, combined with real-time environmental monitoring data, including environmental temperature and humidity, and smoke concentration, calculate the fire risk level of the target building in real time, and send a warning message to the management personnel. The specific steps for generating a fire and electrical warning message are as follows: Using the fault risk assessment result, use temperature and humidity sensors and smoke sensors to collect temperature, humidity, and smoke concentration data in the building in real time, and generate a real-time environmental data set. Based on the real-time environmental data set, combined with real-time risk events, calculate the fire risk index, and generate a fire risk assessment index. Based on the fire risk assessment index, evaluate the fire risk level, and send a warning message to the management personnel according to the risk level and risk type, and generate a fire and electrical warning message.

9. The method for early warning of Internet of Things fire protection electrical equipment according to claim 8, characterized in that, The specific formula for calculating the fire risk index is: R = β0 + β1T + β2H + β3S + β4D Among them, R represents the calculated fire risk index, β0 represents the intercept of the regression model, indicating the basic fire risk level without the influence of any environmental variables, β1 is the regression coefficient of temperature, T represents the ambient temperature monitored in real time, β2 is the regression coefficient of humidity, H represents the ambient humidity monitored in real time, β3 is the regression coefficient of smoke concentration, S represents the smoke concentration monitored in real time, β4 is the regression coefficient of the severity of real-time risk events, and D represents the severity of risk events monitored in real time.

10. An Internet of Things fire electrical warning system, characterized in that, The Internet of Things fire and electrical warning method according to any one of claims 1-9, the system comprising: The power data acquisition module, based on Internet of Things sensors, deploys power sensors at multiple positions in the circuit to collect current and voltage data at multiple positions inside the building, and generates electrical data records; The data fluctuation analysis module, based on the electrical data records, performs frequency analysis on the power data, identifies abnormal fluctuations in the current and voltage data, detects the aging state of the wires, and generates harmonic anomaly detection records; The real-time leakage detection module uses the harmonic anomaly detection records to analyze the short spikes and sharp drops in the current waveform, detects and identifies leakage signals, and records the time points of leakage and power signal data, generating a circuit leakage diagnosis result; The operating state monitoring module, based on the circuit leakage diagnosis result, combines the data of temperature and pressure sensors to monitor the operating states of multiple devices in real time, analyzes the fluctuations and trends of the data, identifies device performance degradation and potential faults, and evaluates the impact on fire safety, generating a device state analysis result; The risk index calculation module, based on the device state analysis result, combines the preset anomaly detection thresholds to evaluate the overload, short circuit, and overheat risks of the circuit and devices in real time, generating a fault risk assessment result; The warning information sending module, based on the fault risk assessment result, detects the temperature, humidity, and smoke concentration data in the building in real time, calculates the fire risk level of the target building, and sends a warning message to the management personnel, generating a fire and electrical warning message.

Images