Fire-fighting electrical early warning method and system based on Internet of Things

Abstract

The invention discloses a fire-fighting electrical early warning method and system based on the Internet of Things, and relates to the technical field of fire-fighting early warning. According to the fire-fighting electrical early warning method based on the Internet of Things, operation time sequence data of a plurality of electrical devices of a to-be-early-warned power station are continuously obtained, a comprehensive fire risk assessment index of each electrical device of the to-be-early-warned power station is analyzed, judgment and analysis are carried out on the comprehensive fire risk assessment index and a preset comprehensive fire risk assessment interval, and whether abnormity occurs or not is analyzed according to a judgment result; through real-time data acquisition of the Internet of Things technology, multi-dimensional operation data of the electrical equipment can be obtained, the data are used for analyzing the thermal fluctuation index, the current impact index, the voltage fluctuation sensitive index and the like of each piece of equipment, so that more accurate fire risk assessment is provided, and through integration of a plurality of equipment parameters, the fire risk assessment accuracy is improved. And comprehensive analysis is carried out in combination with various indexes, and potential fire risks in equipment operation are comprehensively reflected.

Description

Technical Field

[0001] The present invention relates to the technical field of fire warning, and particularly to a fire electrical warning method and system based on the Internet of Things. Background Art

[0002] With the acceleration of the urbanization process and the wide application of electrical equipment in various fields such as various buildings, industrial facilities, and public facilities, the hidden dangers of electrical fires have attracted more and more attention. During the operation of electrical equipment, due to factors such as overload, short circuit, and aging of electrical components, fires may be triggered. According to statistical data, electrical fires account for a relatively large proportion among fire types. Therefore, it is crucial to take effective warning and prevention measures.

[0003] At present, most traditional fire electrical warning systems rely on manual inspections or regular detections of the operating status of electrical equipment. However, this method has problems such as untimely detection, low efficiency, and difficulty in real-time response. In addition, with the increasing variety and quantity of electrical equipment, the traditional manual inspection mode has been difficult to meet the requirements of modern power systems.

[0004] The prior art, such as a fire electrical warning method and system based on the Internet of Things disclosed in the invention patent application with publication number: CN118692201A, includes obtaining a power station distribution map of a target power station and setting fire warning points of the target power station; obtaining warning point data of the fire warning points; analyzing the warning point environment data of the fire warning points to obtain an environmental abnormality degree; analyzing the warning point equipment data of the fire warning points to obtain an equipment abnormality degree; analyzing the warning point signal data of the fire warning points to obtain a signal transmission abnormality degree; judging the environmental safety, equipment safety, and signal transmission safety of the fire warning points and obtaining the warning point warning degree of the fire warning points and the fire warning degree of the target power station; and obtaining the fire warning result of the target site based on the fire warning degree of the target power station. This application has the effects of more targeted and comprehensive warning monitoring of the fire scene, and more accurate fire warning results.

[0005] Based on the above solutions, it is found that the limitations of the prior art at least include the following problems. First, the prior art is usually limited to monitoring and judging through the operating data of a single device, lacking comprehensive analysis of multiple electrical devices. In this case, abnormal parameters of individual devices are easily ignored, and real-time fire risk assessment cannot be carried out from a global perspective, easily resulting in the failure to timely identify the fire hazards of some devices. Second, the fire warning systems in the prior art mostly focus on the judgment of a single parameter, without introducing a comprehensive evaluation of multiple dimensions of the device, and lacking modeling of the interaction between these parameters, easily resulting in a relatively simple warning function of the system and being difficult to effectively cope with the changing operating states of electrical devices. Summary of the Invention

[0006] In view of the deficiencies of the prior art, the present invention provides a fire electrical warning method and system based on the Internet of Things, which solves the problems in the prior art such as relying only on single equipment parameter monitoring, lacking comprehensive evaluation of equipment in multiple dimensions, and setting static warning intervals.

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions: A fire electrical warning method based on the Internet of Things includes the following steps: Continuously obtain the operation time series data of several electrical equipment in the power station to be warned, and analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, heat conduction sensitivity index, isolation decay index, and electric field disturbance index of each electrical equipment in the power station to be warned, and conduct comprehensive analysis to obtain the comprehensive fire risk assessment index of each electrical equipment in the power station to be warned; respectively judge and analyze the comprehensive fire risk assessment index of each electrical equipment in the power station to be warned with the preset comprehensive fire risk assessment interval, and regard the electrical equipment whose comprehensive fire risk assessment index is outside the preset comprehensive fire risk assessment interval as abnormal, and send an abnormal alarm to relevant staff.

[0008] Among them, the specific formula for calculating the comprehensive fire risk assessment index of each electrical equipment in the power station to be warned is as follows: Among them, HzF i is the comprehensive fire risk assessment index of the i-th electrical equipment in the power station to be warned, RbD i is the thermal fluctuation index of the i-th electrical equipment in the power station to be warned, DcJ i is the current impact index of the i-th electrical equipment in the power station to be warned, YbD i is the voltage fluctuation sensitivity index of the i-th electrical equipment in the power station to be warned, RcM i is the heat conduction sensitivity index of the i-th electrical equipment in the power station to be warned, GsT i is the isolation decay index of the i-th electrical equipment in the power station to be warned, GsT i is the electric field disturbance index of the i-th electrical equipment in the power station to be warned, ξ 1 is the thermoelectric coupling influence coefficient stored in the database, ξ 2 is the insulation degradation influence coefficient stored in the database, ξ 3 are the electric field smoothing influence coefficients stored in the database in turn, i = 1, 2, 3,..., i 0 i 0 is the number of electrical equipment in the power station to be warned.

[0009] Furthermore, the operation time series data includes operation temperature values, operation current values, operation voltage values, surface thermal radiation values, insulation resistance values, and electric field strength values within a set range at several time points.

[0010] Further, the specific steps for analyzing the thermal fluctuation index of each electrical equipment in the power station to be warned are as follows: Read the operating temperature values of each electrical equipment in the power station to be warned at several time points, and conduct comprehensive analysis to obtain the average operating temperature and the operating temperature change index of each electrical equipment in the power station to be warned; Conduct comprehensive analysis on the average operating temperature and the operating temperature change index of each electrical equipment in the power station to be warned to obtain the thermal fluctuation index of each electrical equipment in the power station to be warned.

[0011] Further, the specific formula for calculating the thermal fluctuation index of each electrical equipment in the power station to be warned is as follows: Among them, RbD i is the thermal fluctuation index of the i-th electrical equipment in the power station to be warned, YxJ i is the average operating temperature of the i-th electrical equipment in the power station to be warned, e is the natural constant, WbH i is the operating temperature change index of the i-th electrical equipment in the power station to be warned, α is the temperature change influence coefficient stored in the database, i = 1, 2, 3,..., i 0 ,i 0 is the number of electrical equipment in the power station to be warned.

[0012] Further, the specific steps for analyzing the current impact index of each electrical equipment in the power station to be warned are as follows: Read the operating current values of each electrical equipment in the power station to be warned at several time points, and conduct comparative analysis to obtain the maximum operating current of each electrical equipment in the power station to be warned; Conduct comprehensive analysis on the operating current values of each electrical equipment in the power station to be warned at several time points to obtain the operating current change index of each electrical equipment in the power station to be warned; Obtain the maximum reference value of the operating current of each electrical equipment in the power station to be warned, and conduct comprehensive analysis in combination with the maximum operating current and the operating current change index of each electrical equipment in the power station to be warned to obtain the current impact index of each electrical equipment in the power station to be warned.

[0013] Further, the specific steps for analyzing the voltage fluctuation sensitivity index of each electrical equipment in the power station to be warned are as follows: Read the operating voltage values of each electrical equipment in the power station to be warned at several time points, and conduct comparative analysis to obtain the maximum operating voltage of each electrical equipment in the power station to be warned; Conduct comprehensive analysis on the operating voltage values of each electrical equipment in the power station to be warned at several time points to obtain the operating voltage change index of each electrical equipment in the power station to be warned; Obtain the maximum reference value of the operating voltage of each electrical equipment in the power station to be warned, and conduct comprehensive analysis in combination with the maximum operating voltage and the operating voltage change index of each electrical equipment in the power station to be warned to obtain the voltage fluctuation sensitivity index of each electrical equipment in the power station to be warned; Among them, the specific formulas for calculating the operating voltage change index and the voltage fluctuation sensitivity index of each electrical equipment in the power station to be warned are as follows: Among them, YbH i is the operating voltage change index of the i-th electrical equipment of the power station to be warned, YxY i(u+1) is the operating voltage value of the i-th electrical equipment of the power station to be warned at the (u + 1)-th time point, YxY iu is the operating voltage value of the i-th electrical equipment of the power station to be warned at the u-th time point, YbD i is the voltage fluctuation sensitivity index of the i-th electrical equipment of the power station to be warned, is the maximum operating voltage of the i-th electrical equipment of the power station to be warned, DyC i is the maximum reference value of the operating voltage of the i-th electrical equipment of the power station to be warned, δ is the voltage regulation coefficient stored in the database, μ is the voltage change influence coefficient stored in the database, i = 1, 2, 3, …, i 0 i 0 is the number of electrical equipment of the power station to be warned, u = 1, 2, 3, …, u 0 u 0 is the number of time points

[0014] Furthermore, the specific steps for analyzing the heat conduction sensitivity index of each electrical equipment of the power station to be warned are as follows: Read the surface heat radiation values of each electrical equipment of the power station to be warned at several time points, and conduct comprehensive analysis to obtain the surface heat radiation mean value and surface heat radiation change index of each electrical equipment of the power station to be warned; Obtain the surface heat radiation reference value of each electrical equipment of the power station to be warned, and conduct comprehensive analysis in combination with the surface heat radiation mean value and surface heat radiation change index of each electrical equipment of the power station to be warned to obtain the heat conduction sensitivity index of each electrical equipment of the power station to be warned; Among them, the specific formula for calculating the heat conduction sensitivity index of each electrical equipment of the power station to be warned is as follows: Among them, RcM i is the heat conduction sensitivity index of the i-th electrical equipment of the power station to be warned, BmJ i is the surface heat radiation mean value of the i-th electrical equipment of the power station to be warned, BmC i is the surface heat radiation reference value of the i-th electrical equipment of the power station to be warned, BmH i is the surface heat radiation change index of the i-th electrical equipment of the power station to be warned, θ is the surface heat radiation change influence coefficient stored in the database, i = 1, 2, 3, …, i 0 i 0 is the number of electrical equipment of the power station to be warned.

[0015] Further, the specific steps for analyzing the isolation decay index of each electrical device in the power station to be warned are as follows: Read the insulation resistance values of each electrical device in the power station to be warned at several time points, and conduct comparative analysis to obtain the minimum insulation resistance value of each electrical device in the power station to be warned; Conduct comprehensive analysis on the insulation resistance values of each electrical device in the power station to be warned at several time points to obtain the insulation resistance change index of each electrical device in the power station to be warned; Obtain the minimum reference value of the insulation resistance of each electrical device in the power station to be warned, and conduct comprehensive analysis in combination with the insulation resistance change index of each electrical device in the power station to be warned to obtain the isolation decay index of each electrical device in the power station to be warned; Among them, the specific formulas for calculating the insulation resistance change index and isolation decay index of each electrical device in the power station to be warned are as follows: Among them, JbH i is the insulation resistance change index of the i-th electrical device in the power station to be warned, JyD i(u+1) is the insulation resistance value of the i-th electrical device in the power station to be warned at the (u + 1)-th time point, JyD iu is the insulation resistance value of the i-th electrical device in the power station to be warned at the u-th time point, GsT i is the isolation decay index of the i-th electrical device in the power station to be warned, is the minimum insulation resistance value of the i-th electrical device in the power station to be warned, JyC i is the minimum reference value of the insulation resistance of the i-th electrical device in the power station to be warned, σ is the insulation resistance change influence coefficient stored in the database, i = 1, 2, 3,..., i 0 , i 0 is the number of electrical devices in the power station to be warned, u = 1, 2, 3,..., u 0 , u 0 is the number of time points.

[0016] Further, the specific steps for analyzing the electric field disturbance index of each electrical device in the power station to be warned are as follows: Read the electric field strength values within the set range of each electrical device in the power station to be warned at several time points, and conduct comprehensive analysis to obtain the average electric field strength and electric field strength change index within the set range of each electrical device in the power station to be warned; Conduct comprehensive analysis on the average electric field strength and electric field strength change index within the set range of each electrical device in the power station to be warned to obtain the electric field disturbance index of each electrical device in the power station to be warned.

[0017] A fire electrical warning system based on the Internet of Things, comprising: a data acquisition module, an index analysis module, a comprehensive evaluation module, and a judgment and warning module; the data acquisition module is used to continuously acquire the operation time series data of a plurality of electrical devices in the power station to be warned; the index analysis module is used to analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, heat conduction sensitivity index, isolation decay index, and electric field disturbance index of each electrical device in the power station to be warned based on the operation time series data of the plurality of electrical devices in the power station to be warned; the comprehensive evaluation module is used to comprehensively analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, heat conduction sensitivity index, isolation decay index, and electric field disturbance index of each electrical device in the power station to be warned to obtain the comprehensive fire risk assessment index of each electrical device in the power station to be warned; the judgment and warning module is used to respectively judge and analyze the comprehensive fire risk assessment index of each electrical device in the power station to be warned with a preset comprehensive fire risk assessment interval, and regard the electrical devices whose comprehensive fire risk assessment index is outside the preset comprehensive fire risk assessment interval as abnormal, and send an abnormal alarm to relevant staff.

[0018] The present invention has the following beneficial effects:

[0019] (1) The fire electrical warning method based on the Internet of Things can obtain multi-dimensional operation data of electrical devices, such as key parameters like temperature, current, voltage, thermal radiation, insulation resistance, etc., through real-time data collection of the Internet of Things technology. These data are used to analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, etc. of each device, so as to provide a more accurate fire risk assessment. By comprehensively considering multiple device parameters and combining various indices for comprehensive analysis, it can comprehensively reflect the potential fire risks during the operation of the device. This comprehensive evaluation avoids the blind spots of single-parameter analysis, can timely detect abnormal states in the device, significantly improves the accuracy of fire prediction, and reduces the risks of false alarms and missed alarms.

[0020] (2) The fire electrical warning method based on the Internet of Things can dynamically adjust the preset fire risk assessment interval and update the risk assessment in real time according to the actual operation state of the device and environmental changes. Traditional fire risk assessments usually rely on static threshold settings and cannot effectively cope with the changes of devices under different workloads or environmental conditions. However, this method triggers an alarm when the comprehensive fire risk assessment index of the device exceeds the preset safety interval by comparing it with the preset interval in real time. This dynamic adjustment mechanism enables the fire warning system to flexibly respond to the actual changes of the device, more accurately reflect the risk status of the device, avoids the limitations of traditional static assessments, and improves the response speed and reliability of the warning.

[0021] (3) The fire electrical warning method based on the Internet of Things can monitor various abnormal indicators of devices in real time, such as thermal fluctuations, current surges, voltage fluctuations, insulation degradation, etc. When the comprehensive fire risk assessment index of the device exceeds the preset safety range, it is automatically identified as an abnormal device, and relevant staff are notified through an alarm. This timely warning mechanism can greatly reduce the occurrence probability of equipment failures or fires. Especially when the device is in a high-risk state, the staff can quickly take measures according to the alarm information, such as adjusting the load, stopping operation, or performing maintenance, thus effectively avoiding potential hidden dangers that may lead to fires and significantly improving the safety of the power station and the service life of the equipment.

[0022] (4) The fire electrical warning system based on the Internet of Things adopts a modular design, including a data acquisition module, an index analysis module, a comprehensive evaluation module, and a judgment and warning module, to ensure the flexibility and scalability of the system in different scenarios. Each module operates independently and can be upgraded or replaced according to requirements, greatly improving the adaptability of the system. For example, the data acquisition module can support the access of different types of devices and sensors, the index analysis module can adjust the analysis method according to the working conditions of different devices, and the independence of the comprehensive evaluation module and the judgment and warning module ensures the stable operation of the system in complex environments. Through this modular design, the system can adapt to the expansion of the power station scale and the change of device types, while facilitating later maintenance and optimization, reducing the maintenance cost, and improving the long-term stability of the system.

[0023] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flowchart of a fire electrical warning method based on the Internet of Things according to the present invention.

[0025] Figure 2 It is a block diagram of a fire electrical warning system based on the Internet of Things according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The general idea for the problems in the embodiments of the present application is as follows:

[0027] First, through Internet of Things technology, continuously obtain the operation time-series data of each electrical device in the power station to be warned, including key parameters such as temperature, current, voltage, surface thermal radiation, insulation resistance, and electric field strength. Then, conduct a detailed analysis of these data, calculate various indexes of each electrical device (such as thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, etc.). Next, utilize the above analysis results, based on the different indexes of each electrical device, conduct a comprehensive analysis and obtain the comprehensive fire risk assessment index of each device. This index reflects the overall fire risk of the device and can comprehensively consider the interaction between various parameters. Finally, compare the comprehensive fire risk assessment index of each electrical device with the preset risk interval. If the assessment index of a certain device exceeds the preset interval, the system marks it as abnormal and sends an abnormal alarm to relevant staff to achieve timely risk prevention and control.

[0028] Please refer to Figure 1 , an embodiment of the present invention provides a technical solution: a fire electrical warning method based on the Internet of Things, including the following steps: continuously obtain the operation time-series data of several electrical devices in the power station to be warned, and analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, heat conduction sensitivity index, isolation decay index, and electric field disturbance index of each electrical device in the power station to be warned, and conduct a comprehensive analysis to obtain the comprehensive fire risk assessment index of each electrical device in the power station to be warned; respectively judge and analyze the comprehensive fire risk assessment index of each electrical device in the power station to be warned with the preset comprehensive fire risk assessment interval, and regard the electrical devices whose comprehensive fire risk assessment index is outside the preset comprehensive fire risk assessment interval as abnormal, and send an abnormal alarm to relevant staff.

[0029] Among them, the specific formula for calculating the comprehensive fire risk assessment index of each electrical device in the power station to be warned is as follows: Among them, HzF i is the comprehensive fire risk assessment index of the i-th electrical device in the power station to be warned, RbD i is the thermal fluctuation index of the i-th electrical device in the power station to be warned, DcJ i is the current impact index of the i-th electrical device in the power station to be warned, YbD i is the voltage fluctuation sensitivity index of the i-th electrical device in the power station to be warned, RcM i is the heat conduction sensitivity index of the i-th electrical device in the power station to be warned, GsT i is the isolation decay index of the i-th electrical device in the power station to be warned, DrD i is the electric field disturbance index of the i-th electrical device in the power station to be warned, ξ 1 is the thermoelectric coupling influence coefficient stored in the database, ξ 2The insulation degradation influence coefficient stored in the database, ξ 3 The electric field smoothing influence coefficients stored in the database in sequence, i = 1, 2, 3, …, i 0 , i 0 is the number of electrical equipment in the power station to be pre-warned.

[0030] It should be explained that ξ 1 is used to measure the influence of the thermal effect generated by temperature changes on the working state of electrical equipment during operation. This coefficient determines the potential risk of the thermal effect on the equipment within different temperature fluctuation ranges by analyzing the thermal dynamic characteristics of the electrical equipment, combining historical operation data and equipment design parameters. Specifically, the thermoelectric coupling influence coefficient can monitor the working temperature change of the electrical equipment in real time through a temperature sensor, and calculate it by combining parameters such as the heat capacity and heat dissipation capacity of the equipment. Experimental and simulation analysis can also help optimize the setting of the coefficient, so as to more accurately evaluate the fire risk of the equipment.

[0031] ξ 2 reflects the trend of the gradual decline of the insulation performance of the equipment insulation material during long-term operation due to factors such as current load and voltage fluctuation. This coefficient is obtained by monitoring the change of the insulation resistance value of the equipment. By installing an insulation resistance sensor, regularly measuring the insulation resistance of the electrical equipment, and combining factors such as the service life and working environment of the equipment, the degradation degree of the insulation material is evaluated. Experimental data and historical fault analysis can further determine the specific impact of the degradation on the fire risk, so as to provide a basis for the setting of the coefficient.

[0032] ξ 3 is used to evaluate the influence of electric field changes on the operation stability and safety of electrical equipment during operation. This coefficient usually monitors the electric field intensity fluctuation around the equipment in real time through an electric field sensor, and analyzes it by combining the electrical structure and material characteristics of the equipment. Through multiple tests and data accumulation, the potential threat of electric field changes to the equipment is studied, and the relationship between electric field fluctuation and the fire risk of the equipment is determined. This coefficient can also be determined by laboratory simulation to measure the response of the equipment under different electric field intensities, which helps to determine the specific value of the electric field smoothing influence coefficient.

[0033] The operation time series data includes the operation temperature values, operation current values, operation voltage values, surface thermal radiation values, insulation resistance values, and electric field intensity values within a set range at several time points.

[0034] The operation temperature value can be collected through a temperature sensor (such as: thermocouple, RTD temperature sensor), which is used to reflect the heat generated by the equipment during operation. If the temperature is too high, it means that the equipment is under a large thermal load, which may be caused by overload, high ambient temperature or poor heat dissipation, etc.

[0035] The operating current value can be collected by current sensors (such as Hall sensors, shunt resistors), which is used to reflect the change of device load. Overload or sudden increase in current is one of the main causes of electrical fires. Continuous high current or instantaneous overload current may cause device overheating or electrical faults.

[0036] The operating voltage value can be obtained by voltage sensors, usually through voltage transformers (VT) or digital voltage sensors for real-time monitoring, which is used to reflect the stability of the power supply system and power quality. For example, too high voltage may cause damage to device insulation, while too low voltage may cause the device to fail to operate properly.

[0037] The surface thermal radiation value can be collected by infrared temperature sensors (such as infrared thermal imagers). This device can detect the thermal radiation emitted by the device surface and provide the surface temperature distribution through thermal maps or temperature readings, which is used to reflect the surface temperature distribution of the device. Local overheating or heat accumulation may lead to fires. Thermal radiation monitoring helps to detect hot spots with abnormal surface temperatures of devices. Usually, this situation indicates device overload, failure or aging. By monitoring thermal radiation, the overheating risk of the device can be detected in real time.

[0038] The insulation resistance value can be collected by insulation resistance testers (such as megohmmeters). These testers can periodically detect the resistance of the device insulation system, especially in high-voltage devices, to detect whether there is electrical leakage or poor electrical contact. It is used to reflect the condition of the device insulation layer. Under normal circumstances, the insulation resistance should be maintained within a certain range. A lower resistance value indicates that there may be problems with the insulation layer, which may lead to electrical leakage, grounding faults or short circuits.

[0039] The electric field strength value within a set range can be monitored by electric field sensors or using electrometers. These devices can detect the change of electric field strength in the device or electrical environment in real time, especially in high-voltage areas. It is used to reflect the electrical contact or insulation state of electrical devices. When the electric field strength increases abnormally, it may mean that the insulation of the electrical device is damaged or the contact is poor, increasing the risk of electrical faults and fires. By monitoring the electric field strength, potential electrical contact problems of the device can be detected in time.

[0040] Specifically, the specific steps for analyzing the thermal fluctuation index of each electrical device in the power station to be warned are as follows: Read the operating temperature values of each electrical device in the power station to be warned at several time points and conduct comprehensive analysis to obtain the average operating temperature and operating temperature change index of each electrical device in the power station to be warned; Conduct comprehensive analysis on the average operating temperature and operating temperature change index of each electrical device in the power station to be warned to obtain the thermal fluctuation index of each electrical device in the power station to be warned.

[0041] Among them, the specific formulas for calculating the average operating temperature and the operating temperature change index of each electrical device in the power station to be warned are as follows: Among them, YxJ i is the average operating temperature of the i-th electrical device in the power station to be warned, and YxW iu is the operating temperature value of the i-th electrical device in the power station to be warned at the u-th time point, and WbH i is the operating temperature change index of the i-th electrical device in the power station to be warned, and YxW i(u+1) is the operating temperature value of the i-th electrical device in the power station to be warned at the (u + 1)-th time point, where i = 1, 2, 3, …, i 0 i 0 is the number of electrical devices in the power station to be warned, and u = 1, 2, 3, …, u 0 u 0 is the number of time points.

[0042] The specific formula for calculating the thermal fluctuation index of each electrical device in the power station to be warned is as follows: Among them, RbD i is the thermal fluctuation index of the i-th electrical device in the power station to be warned, and YxJ i is the average operating temperature of the i-th electrical device in the power station to be warned, e is the natural constant, and its value is 2.718 in this embodiment, and WbH i is the operating temperature change index of the i-th electrical device in the power station to be warned, α is the temperature change influence coefficient stored in the database, and i = 1, 2, 3, …, i 0 i 0 is the number of electrical devices in the power station to be warned.

[0043] It should be noted that α is used to reflect the relationship between the operating stability and the fire risk of electrical devices under different temperature change conditions. This coefficient is obtained by studying the temperature change law of electrical devices and the relationship between them and device performance and failure rate. Specifically, the temperature change influence coefficient can be obtained through the following steps:

[0044] Under actual operating conditions, install temperature sensors and continuously monitor the temperature changes of electrical devices, and record the temperature fluctuation data of the devices under different loads, environmental conditions, and working states.

[0045] Combined with the design parameters of electrical devices (such as temperature tolerance range, heat dissipation capacity, insulation material characteristics, etc.) for analysis, evaluate the impact of temperature fluctuations on the long-term stable operation of the devices, and analyze the failure rate of the devices under temperature fluctuations through historical failure data, and further obtain the correlation between temperature changes and the fire risk of the devices.

[0046] Through simulation experiments, the performance changes of the device under different temperature change ranges are tested, the thermal response characteristics of the device are measured, and then the influence degree of temperature change on the device is verified. The simulation experiments can help calculate a reasonable temperature change influence coefficient according to the influence of different ambient temperature changes on the device.

[0047] Based on the experimental data and fault analysis, a database between temperature change and the fire risk of the device is established, storing the influence coefficients of different devices under different temperature fluctuation ranges, and adjusted according to factors such as device type and operating environment.

[0048] In this implementation plan, by performing time-series data analysis on the operating temperature values of each electrical device, first calculating the average operating temperature, and then further calculating the temperature change index, it is possible to more accurately capture the temperature fluctuations of the device at different time points. Compared with traditional methods, this method can effectively identify the subtle fluctuations of the device temperature, avoid ignoring abnormal temperature rises in the short term, and improve the sensitivity to the operating state of the device. Calculating the temperature change index and combining it with the average temperature for comprehensive analysis can reflect the speed and amplitude of the device temperature change in real time, thereby determining whether the device is within the normal temperature fluctuation range. In this way, the temperature fluctuations of the device can be dynamically monitored, and the possible overheating risks of the device can be detected in a timely manner. Especially when the load of the electrical device changes greatly, the temperature changes violently. This method can quickly respond and issue a warning to avoid faults or fires caused by device overheating. By introducing the temperature change influence coefficient (the coefficient stored in the database), the system can quantify the influence of temperature change according to the device type, working environment, and historical data. This can not only improve the personalization and accuracy of temperature fluctuation analysis, but also be optimized according to the historical operation data of the device, adapt to temperature changes in different environments, and ensure that the risk assessment is more in line with the actual operating conditions, avoiding misjudgments or missed judgments caused by a unified threshold. The calculated thermal fluctuation index is an important part of the comprehensive fire risk assessment. Through detailed analysis of temperature fluctuations, it can accurately reflect the thermal load and heat dissipation status of the device, providing important data support for the assessment of fire risk. Combining the analysis of other parameters (such as current, temperature, insulation resistance, etc.) can more comprehensively evaluate the comprehensive fire risk of the device, thus effectively preventing the occurrence of fires.

[0049] Specifically, the specific steps for analyzing the current impact index of each electrical device in the power station to be warned are as follows: Read the operating current values of each electrical device in the power station to be warned at several time points, and conduct a comparative analysis to obtain the maximum operating current of each electrical device in the power station to be warned; conduct a comprehensive analysis of the operating current values of each electrical device in the power station to be warned at several time points to obtain the operating current change index of each electrical device in the power station to be warned; obtain the maximum reference value of the operating current of each electrical device in the power station to be warned, and conduct a comprehensive analysis in combination with the maximum operating current and the operating current change index of each electrical device in the power station to be warned to obtain the current impact index of each electrical device in the power station to be warned.

[0050] Among them, the specific formulas for calculating the operating current change index and the current impact index of each electrical device in the power station to be warned are as follows: Among them, DbH i is the operating current change index of the i-th electrical device in the power station to be warned, and YxD i(u+1) is the operating current value of the i-th electrical device in the power station to be warned at the (u + 1)-th time point, and YxD iu is the operating current value of the i-th electrical device in the power station to be warned at the u-th time point, and DcJ i is the current impact index of the i-th electrical device in the power station to be warned, and YxD i Max is the maximum operating current of the i-th electrical device in the power station to be warned, and YxC i is the maximum reference value of the operating current of the i-th electrical device in the power station to be warned, ω is the current change influence coefficient stored in the database, i = 1, 2, 3,..., i 0 i 0 is the number of electrical devices in the power station to be warned, u = 1, 2, 3,..., u 0 u 0 is the number of time points.

[0051] It should be noted that ω is used to measure the impact of current fluctuations and changes on the device performance and fire risk during the operation of the electrical device. This coefficient is determined by analyzing the relationship between current changes and device stability and failure modes. The specific acquisition process is as follows:

[0052] Install current sensors in the electrical device to collect current data of the device in different operating states in real time. By monitoring the current fluctuations of the device under different loads, working environments, and time periods, record the change amplitude and frequency of the current.

[0053] Combined with the electrical characteristics of the equipment (such as rated current, maximum carrying current, shock resistance, etc.), evaluate the potential impact of current fluctuations on the equipment. For example, excessive current fluctuations may accelerate the aging of the equipment or cause failures, especially imposing additional burdens on components such as insulation materials and contact points.

[0054] By collecting the historical operation data and fault records of the equipment, analyze the relationship between current fluctuations and the occurrence of faults, and count the frequency of faults in equipment with large current changes, so as to determine the degree of influence of current changes on the fire risk of the equipment.

[0055] Through laboratory tests and on-site verification, evaluate the operating status of the equipment under different current fluctuation conditions, measure the impact of current changes on the equipment performance, temperature rise, and the potential to cause fires. Based on these experimental data, determine the current change influence coefficient.

[0056] Based on the above data, establish a database for the influence of equipment current changes, record the influence coefficients of different equipment under different current fluctuation conditions, and adjust the coefficient values according to the equipment type, application scenario, and operating conditions.

[0057] In this implementation scheme, through the comprehensive analysis of the maximum current value and the current change index, the current impact situation of the device during operation can be accurately identified. The current impact index combines the maximum current value and the current change index, and can capture whether the device has experienced sudden current fluctuations or overload conditions. This is of great significance for judging whether the electrical device is in a safe operating state and avoiding equipment damage or fire risks caused by current impacts. By calculating the current change index, this method can reflect the current fluctuation amplitude of the electrical device at different time periods. Different from traditional current monitoring, this method not only monitors the current value at a single moment, but also through the comprehensive analysis of data at multiple time points, can identify the abnormal fluctuation trend of the current within a certain time period, avoiding the problem that the potential risk of short-term current fluctuations to the device is not identified. By combining the maximum current value and the current change index, this method calculates the current impact index of the device, which makes the impact of current fluctuations not only consider the instantaneous maximum current value, but also comprehensively consider the change rate. Through this comprehensive analysis, the impact risk of the device during current mutation can be evaluated, and those situations where the current changes too much and may cause device instability or failure can be identified in time. This is crucial for the long-term stable operation of the power station. Combining the current change impact coefficient of each electrical device, this method can be dynamically adjusted according to historical data and actual operating conditions, improving the flexibility and accuracy of the early warning system. By continuously updating the current impact assessment of the device, the electrical health status of the device can be monitored in real time, and potential fire hazards caused by load changes or current overload can be discovered in time. The calculation of the current impact index can effectively identify the situation of excessive load during the operation of the device by capturing abnormal current fluctuations, and timely discovery of abnormal current helps to take measures in advance, such as reducing the load or performing maintenance, thereby reducing the failures caused by overload of the device. This can not only extend the service life of the device, but also effectively reduce safety hazards such as device damage and fire caused by current impacts.

[0058] Specifically, the specific steps for analyzing the voltage fluctuation sensitivity index of each electrical device in the power station to be warned are as follows: Read the operating voltage values of each electrical device in the power station to be warned at several time points and conduct a comparative analysis to obtain the maximum operating voltage of each electrical device in the power station to be warned; Conduct a comprehensive analysis of the operating voltage values of each electrical device in the power station to be warned at several time points to obtain the operating voltage change index of each electrical device in the power station to be warned; Obtain the maximum reference value of the operating voltage of each electrical device in the power station to be warned, and conduct a comprehensive analysis in combination with the maximum operating voltage and the operating voltage change index of each electrical device in the power station to be warned to obtain the voltage fluctuation sensitivity index of each electrical device in the power station to be warned.

[0059] Among them, the specific formulas for calculating the operating voltage change index and the voltage fluctuation sensitivity index of each electrical device in the power station to be warned are as follows: Among them, YbH i is the operating voltage change index of the i-th electrical equipment in the power station to be pre-warned, and YxY i(u+1) is the operating voltage value of the i-th electrical equipment at the (u + 1)-th time point in the power station to be pre-warned, and YxY iu is the operating voltage value of the i-th electrical equipment at the u-th time point in the power station to be pre-warned, and YbD i is the voltage fluctuation sensitivity index of the i-th electrical equipment in the power station to be pre-warned, is the maximum operating voltage of the i-th electrical equipment in the power station to be pre-warned, and DyC i is the maximum reference value of the operating voltage of the i-th electrical equipment in the power station to be pre-warned. δ is the voltage regulation coefficient stored in the database, and μ is the voltage change influence coefficient stored in the database. i = 1, 2, 3, …, i 0 i 0 is the number of electrical equipment in the power station to be pre-warned, and u = 1, 2, 3, …, u 0 u 0 is the number of time points.

[0060] It should be noted that δ is used to measure the adaptability of the internal adjustment mechanism of the electrical equipment to voltage changes during voltage fluctuations, as well as its impact on the stability and fire risk of the equipment. This coefficient is determined by analyzing the voltage regulation function, response speed, voltage stabilization range and design characteristics of the equipment. The specific acquisition process is as follows:

[0061] First, analyze the voltage regulation system of the electrical equipment, including voltage stabilizing equipment, automatic voltage regulating devices, compensation equipment, etc., and evaluate the response ability of these regulation systems under voltage fluctuations, especially the regulation effect under extreme conditions such as overvoltage and undervoltage. The voltage regulation ability of the equipment will directly affect the impact degree of voltage fluctuations on the equipment performance.

[0062] During the operation of the equipment, the voltage value of the electrical equipment is monitored in real time through voltage sensors, the amplitude and frequency of voltage changes are analyzed, and combined with the voltage regulation system of the equipment, the impact of voltage fluctuations on the equipment stability is evaluated. For example, if the equipment can quickly adjust to a stable voltage, the regulation coefficient will be lower; if the regulation system responds slowly, the coefficient will be higher.

[0063] By studying the fault history of the equipment under different voltage fluctuations, especially the fault data related to voltage regulation failure, the impact of voltage fluctuations on the equipment operation risk is evaluated. The failure or insufficiency of the voltage regulation system will lead to premature damage of the equipment and even cause a fire.

[0064] Through experimental tests, the response of the device voltage regulation system and the changes in device performance under different voltage fluctuation conditions are examined. By simulating different voltage fluctuation scenarios, the effectiveness of the voltage regulation system and its role in the occurrence of device failures or fire risks are evaluated.

[0065] Based on the experimental data and historical operation data, a database of voltage regulation coefficients is established, and the values of the voltage regulation coefficients are adjusted according to the regulation capabilities, operating environments, and failure modes of different electrical devices.

[0066] μ is used to measure the impact of voltage changes on the performance and stability of electrical devices during voltage fluctuations. It reflects the potential risks of voltage changes to the devices, especially problems such as failures, overheating, or performance degradation that may be caused by voltage fluctuations. The process of obtaining this coefficient generally includes the following steps:

[0067] For each electrical device, evaluate its sensitivity to voltage changes according to its design and operating principle. For example, some devices (such as high-precision instruments or microprocessors) may be very sensitive to voltage fluctuations, and even slight voltage changes may cause device failures; while other devices (such as large motors or transformers) may have a stronger ability to adapt to voltage fluctuations. During the actual operation of the device, monitor the amplitude and frequency of voltage fluctuations and evaluate how these changes affect the operating state of the device. Excessive voltage fluctuations may lead to a decrease in device operating efficiency, or cause the device to overheat and be damaged. For example, frequent voltage fluctuations may cause the electrical components inside the device (such as capacitors and inductors) to enter an unstable state, affecting the long-term operation and safety of the device. By reviewing the historical data of the device, analyze the relationship between voltage fluctuations and device failures or performance degradation. Collect records of device failures or abnormalities during periods of large voltage fluctuations and establish a statistical relationship between voltage fluctuations and device failures. If a device is prone to failure under certain specific voltage fluctuation conditions, it indicates that the device is sensitive to voltage fluctuations, and a higher influence coefficient should be set for it. Under experimental conditions, by simulating different voltage fluctuation amplitudes (such as +10%, -10%, etc.) and frequencies, test the performance of the device under these fluctuation conditions and evaluate the operating stability and risks of the device under voltage fluctuations. Through the experimental results, the impact of voltage fluctuations on device performance can be quantified and the voltage change influence coefficient can be obtained. Different types of devices have different sensitivities to voltage fluctuations. For example, devices with a large load (such as large generators or transformers) have less impact on voltage fluctuations, while devices with a small load and high precision requirements (such as electronic control systems or microcomputers) are more sensitive to voltage fluctuations. According to factors such as device type, usage environment, and rated voltage, adjust the value of the voltage change influence coefficient to ensure that it reflects the actual impact of voltage changes on different devices. Based on the experimental data of the voltage change impact on the device, historical failure records, and the design characteristics of different devices, establish a database of voltage change influence coefficients. As the device operation progresses, adjust this coefficient to more accurately reflect the actual impact of voltage changes on the device. For example, if some devices show a higher failure rate or temperature rise phenomenon under frequent voltage fluctuations, the voltage change influence coefficient should be appropriately increased to reflect the higher risk.

[0068] In this implementation plan, by comprehensively analyzing the maximum voltage value and voltage change index of each electrical device, it is possible to more accurately capture the voltage fluctuations during the operation of the device, and identify severe voltage fluctuations or instantaneous anomalies. Compared with the traditional method of only monitoring the instantaneous voltage value, this method can accurately reflect the voltage stability of the device, and timely detect the risks that voltage fluctuations may pose to the device, especially the potential faults, damages or fire hazards that may be caused by excessive or low voltage. By calculating the voltage change index, this method not only considers the instantaneous maximum voltage, but also comprehensively takes into account the rate and amplitude of voltage change. This means that when the voltage fluctuates severely, the system can respond in a timely manner through the change index, not only reflecting the amplitude of voltage fluctuation, but also capturing the speed of voltage fluctuation, further improving the evaluation accuracy of the impact of voltage fluctuations on the device. This comprehensive analysis helps to avoid potential device failures caused by voltage fluctuations. By introducing voltage fluctuation sensitivity coefficients (including voltage regulation coefficient and voltage change impact coefficient), this method can quantify and adjust voltage fluctuations according to the specific operating environment and historical data of the device. According to the working conditions of different devices, the impact of voltage fluctuations will vary. Using the stored voltage change impact coefficient for personalized adjustment can be flexibly applied in different industries and devices, improving the accuracy of risk assessment. By calculating the voltage fluctuation sensitivity index in real time, this method can timely detect the fault risks that electrical devices may face due to voltage fluctuations during operation, and take preventive measures, including reducing the device load, adjusting the operating conditions or immediately shutting down for maintenance, etc., thus reducing the risks of device damage and fire. Timely warnings can protect the device and ensure the safe and stable operation of the electrical system. Combining with Internet of Things technology, this method automatically obtains the operating voltage data of electrical devices and conducts real-time analysis, which not only reduces the need for manual intervention, but also improves the intelligent level of device management. The automatic monitoring and risk assessment of the device operating status can more quickly reflect the abnormal conditions of the device, improving the management efficiency and response speed.

[0069] Specifically, the specific steps for analyzing the heat conduction sensitivity index of each electrical device in the power station to be warned are as follows: Read the surface heat radiation values of each electrical device in the power station to be warned at several time points and conduct comprehensive analysis to obtain the surface heat radiation mean value and surface heat radiation change index of each electrical device in the power station to be warned; Obtain the surface heat radiation reference value of each electrical device in the power station to be warned, and conduct comprehensive analysis in combination with the surface heat radiation mean value and surface heat radiation change index of each electrical device in the power station to be warned to obtain the heat conduction sensitivity index of each electrical device in the power station to be warned.

[0070] Among them, the specific formulas for calculating the surface heat radiation mean value and surface heat radiation change index of each electrical device in the power station to be warned are as follows: Among them, BmJi is the average surface thermal radiation of the i-th electrical equipment in the power station to be warned, BmF iu is the surface thermal radiation value of the i-th electrical equipment in the power station to be warned at the u-th time point, BmH i is the surface thermal radiation change index of the i-th electrical equipment in the power station to be warned, BmF i(u+1) is the surface thermal radiation value of the i-th electrical equipment in the power station to be warned at the (u + 1)-th time point, i = 1, 2, 3,..., i 0 i 0 is the number of electrical equipment in the power station to be warned, u = 1, 2, 3,..., u 0 u 0 is the number of time points.

[0071] Among them, the specific formula for calculating the heat conduction sensitivity index of each electrical equipment in the power station to be warned is as follows: Among them, RcM i is the heat conduction sensitivity index of the i-th electrical equipment in the power station to be warned, BmJ i is the average surface thermal radiation of the i-th electrical equipment in the power station to be warned, BmC i is the reference value of the surface thermal radiation of the i-th electrical equipment in the power station to be warned, BmH i is the surface thermal radiation change index of the i-th electrical equipment in the power station to be warned, θ is the surface thermal radiation change influence coefficient stored in the database, i = 1, 2, 3,..., i 0 i 0 is the number of electrical equipment in the power station to be warned.

[0072] It should be explained that θ is used to describe the influence of the change of the surface thermal radiation of the equipment on the performance and stability of the electrical equipment. It reflects the influence of the fluctuation of the surface thermal radiation of the equipment on the internal temperature distribution and heat conduction of the equipment. The process of obtaining this coefficient usually includes the following steps:

[0073] By analyzing the surface material, shape and structure of the electrical equipment, evaluate its surface's response ability to thermal radiation. Different materials (such as metals, plastics, ceramics, etc.) have different absorption and emission characteristics of thermal radiation, thus affecting the heat conduction performance of the equipment. For example, some materials may have a high ability to absorb thermal radiation and are prone to heat accumulation; while other materials may have a strong ability to emit thermal radiation and help the equipment dissipate heat better.

[0074] Monitor the change of the surface temperature of electrical equipment over time, especially during the operation of the equipment. Due to internal heat generation or external environmental temperature fluctuations, the surface thermal radiation changes. The change of thermal radiation may affect the temperature distribution on the equipment surface, and further affect the working temperature and stability of internal components. Through an infrared temperature detector or thermal imaging technology, obtain the temperature data of the equipment surface in real time, and calculate its change trend to evaluate the impact of surface thermal radiation on the equipment.

[0075] Under laboratory conditions, simulate the thermal radiation fluctuations in different environments and measure the impact of the change of the equipment surface thermal radiation on the internal heat distribution of the equipment. Through experimental data, the relationship between the change of thermal radiation and equipment failure or performance change can be quantitatively analyzed. For example, by adjusting the change of the equipment surface temperature, analyze the impact of thermal radiation fluctuations during the equipment operation on the temperature rise, aging, etc. of electrical components (such as capacitors, resistors, connection points, etc.).

[0076] Analyze the change of thermal radiation during the historical operation of the equipment and its correlation with the occurrence of failures. By collecting the failure data of the equipment in a high-temperature environment or when there are large fluctuations in surface thermal radiation, study the long-term impact of thermal radiation on the equipment performance. For example, equipment overheating may lead to problems such as insulation aging and component failure. According to the correlation between equipment failures and surface thermal radiation fluctuations, determine the degree of impact of surface thermal radiation changes on the equipment, so as to adjust the surface thermal radiation change impact coefficient.

[0077] Different types of electrical equipment have different sensitivities to thermal radiation. For example, precision instruments or high-power equipment may be more easily affected by thermal radiation changes, while some large motors or power equipment may have strong heat dissipation capabilities and are less affected by surface thermal radiation. Combine the actual application environment of the equipment (such as indoor or outdoor, temperature fluctuation range, etc.) to appropriately adjust the surface thermal radiation change impact coefficient to reflect the thermal conduction sensitivity of the equipment under different conditions.

[0078] Based on the test data, historical failure records and simulation analysis of the equipment, establish a database of surface thermal radiation change impact coefficients. As the equipment operation and monitoring data accumulate, this coefficient can be continuously adjusted to improve the accurate assessment of the impact of thermal radiation fluctuations on the equipment in the actual environment.

[0079] In this implementation plan, by reading the surface thermal radiation value in real time and calculating the average surface thermal radiation value and the change index, the thermal radiation situation of the device can be accurately monitored. Surface thermal radiation is an important indicator reflecting the thermal load of the device. Especially for high-power devices, excessive temperature can cause device aging or damage. Through comprehensive analysis of these data, it is possible to timely detect whether there is a problem of local overheating in the device, avoiding the fire risk caused by heat accumulation. By calculating the heat conduction sensitivity index, this method combines the average thermal radiation value and the thermal radiation change index of the device, comprehensively evaluating the heat conduction ability of the device and its sensitivity to temperature changes. Electrical devices usually have local temperature increases due to poor heat dissipation or overload. If the heat conduction performance is poor, it may cause device damage or fire. This method can effectively identify this potential risk, so as to take cooling or maintenance measures in advance. By introducing the influence coefficient of thermal radiation change, this method can make personalized adjustments to the influence of thermal radiation change according to the working characteristics of different devices. The heat conduction performance of each electrical device is different. By combining the reference value of the surface thermal radiation of the device, the heat conduction ability of the device under different working conditions can be accurately quantified. This personalized evaluation not only improves the accuracy of the heat conduction sensitivity index, but also provides optimization suggestions according to the actual situation of the device to ensure the safe operation of the device.

[0080] Specifically, the specific steps for analyzing the isolation decay index of each electrical device in the power station to be warned are as follows: Read the insulation resistance values of each electrical device in the power station to be warned at several time points and conduct comparative analysis to obtain the minimum insulation resistance value of each electrical device in the power station to be warned; Conduct comprehensive analysis on the insulation resistance values of each electrical device in the power station to be warned at several time points to obtain the insulation resistance change index of each electrical device in the power station to be warned; Obtain the minimum reference value of the insulation resistance of each electrical device in the power station to be warned, and conduct comprehensive analysis in combination with the insulation resistance change index of each electrical device in the power station to be warned to obtain the isolation decay index of each electrical device in the power station to be warned.

[0081] Among them, the specific formulas for calculating the insulation resistance change index and the isolation decay index of each electrical device in the power station to be warned are as follows: Among them, JbH i is the insulation resistance change index of the i-th electrical device in the power station to be warned, and JyD i(u+1) is the insulation resistance value of the i-th electrical device in the power station to be warned at the (u + 1)-th time point, and JyD iu is the insulation resistance value of the i-th electrical device in the power station to be warned at the u-th time point, and GsT i is the isolation decay index of the i-th electrical device in the power station to be warned, and JyD i Min is the minimum insulation resistance value of the i-th electrical device in the power station to be warned, and JyCi is the minimum reference value of the insulation resistance of the i-th electrical equipment in the power station to be pre-warned, σ is the influence coefficient of the insulation resistance change stored in the database, and i = 1, 2, 3, …, i 0 , i 0 is the number of electrical equipment in the power station to be pre-warned, and u = 1, 2, 3, …, u 0 , u 0 is the number of time points.

[0082] It should be explained that σ is used to describe the influence of the insulation resistance change on the isolation degradation degree of electrical equipment. It reflects how the change of insulation resistance accelerates or slows down the process of isolation degradation under different operating conditions of the equipment. The process of obtaining this coefficient usually includes the following steps:

[0083] By collecting the insulation resistance data of electrical equipment in different time periods, analyzing the change trend of the insulation resistance during the long-term operation of the equipment. These data are usually obtained by regularly detecting the insulation resistance value of the equipment, reflecting the aging situation of the equipment in actual operation, comparing the insulation resistance changes of different electrical equipment in similar environments, and classifying them according to the aging degree of the equipment to evaluate its influence on isolation degradation.

[0084] The change of insulation resistance is not only affected by the aging of the equipment's own materials, but also by external environmental factors such as temperature, humidity, and pollutants. Therefore, it is necessary to analyze the insulation resistance changes of electrical equipment under different environmental conditions. For example, in a high-temperature or humid environment, the resistance of the insulation material may drop rapidly, thus accelerating the isolation degradation of the equipment. Through the correlation analysis of environmental changes and equipment resistance changes, the influence degree of external factors on insulation resistance changes can be determined, so as to set the influence coefficient.

[0085] Under laboratory conditions, simulate the insulation resistance changes of electrical equipment under different environments and operating states. For example, by means of heating, humidifying, polluting, etc., simulate the usage scenarios of the equipment in extreme environments, measure the changes of the equipment's insulation resistance. The insulation resistance change data obtained through experimental tests can provide a theoretical basis for the calculation of the coefficient and help evaluate the degradation risk of the equipment under different environmental conditions.

[0086] Different types of electrical equipment and the insulation materials they use have different resistance characteristics. Some equipment uses insulation materials with higher stability, while other materials may be more sensitive to environmental changes. Conduct a detailed analysis of the insulation materials of the equipment, and determine the influence degree of different materials on the insulation resistance change according to the aging resistance ability and electrical performance of the materials, combined with the test data.

[0087] Analyze the historical fault records of the equipment, especially the types of faults related to the decrease in insulation resistance. Through fault mode analysis, identify which factors are most likely to cause the decrease in the insulation resistance of the equipment and the degree of the decrease. Based on this retrospective data, set different influence coefficients for the change in insulation resistance to more accurately evaluate the isolation degradation risk of electrical equipment in subsequent early warnings.

[0088] During the long-term operation of electrical equipment, as the detection data accumulates continuously, regularly update and optimize the influence coefficients for the change in insulation resistance. Through repeated analysis of historical data, adjust the influence coefficients to make them more in line with the actual operating conditions of the current electrical equipment.

[0089] In this implementation plan, by reading and analyzing the change in insulation resistance of each electrical equipment in real time, the dynamic monitoring of the status of power station equipment can be achieved. This real-time nature can help detect potential electrical equipment failures or isolation degradation problems early, avoid the occurrence of sudden failures. By comparing the historical data of the equipment with the minimum reference value and combining the calculation of the insulation resistance change index, the health status and isolation degradation degree of the equipment can be evaluated more accurately. Such analysis can timely detect whether the equipment enters the risk area, so as to carry out targeted maintenance and intervention. Combining the insulation resistance values measured multiple times, comprehensive analysis is carried out to obtain a more comprehensive change trend and evaluation index, avoiding the deviation at a single time point and improving the early warning accuracy. By calculating the isolation degradation index, the possible failures of electrical equipment can be predicted more scientifically, and the maintenance or replacement work of the equipment can be planned in advance, thereby optimizing the allocation of maintenance resources, improving the overall operation efficiency and reliability of the power station. Systematically obtaining the key indicators of each equipment can help the power station manager make more scientific decisions, plan the maintenance cycle, and effectively allocate maintenance and replacement resources, reducing the downtime and maintenance costs.

[0090] Specifically, the specific steps for analyzing the electric field disturbance index of each electrical equipment in the power station to be warned are as follows: Read the electric field intensity values within the set range at several time points of each electrical equipment in the power station to be warned, and conduct comprehensive analysis to obtain the average electric field intensity and the electric field intensity change index within the set range of each electrical equipment in the power station to be warned; Conduct comprehensive analysis on the average electric field intensity and the electric field intensity change index within the set range of each electrical equipment in the power station to be warned to obtain the electric field disturbance index of each electrical equipment in the power station to be warned.

[0091] Among them, the specific formulas for calculating the average electric field intensity and the electric field intensity change index within the set range of each electrical equipment in the power station to be warned are as follows: Among them, DqJ i is the average electric field intensity within the set range of the i-th electrical equipment in the power station to be warned, DqZ iuis the electric field strength value within the set range at the u-th time point of the i-th electrical equipment of the power station to be pre-warned, DqH i is the electric field strength change index within the set range of the i-th electrical equipment of the power station to be pre-warned, DqZ i(u+1) is the electric field strength value within the set range at the (u + 1)-th time point of the i-th electrical equipment of the power station to be pre-warned, i = 1, 2, 3, …, i 0 , i 0 is the number of electrical equipment in the power station to be pre-warned, u = 1, 2, 3, …, u 0 , u 0 is the number of time points.

[0092] Among them, the specific formula for calculating the electric field disturbance index of each electrical equipment in the power station to be pre-warned is as follows: DrD i = DqJ i *(1 + DqH i *λ); where, DrD i is the electric field disturbance index of the i-th electrical equipment in the power station to be pre-warned, DqJ i is the average value of the electric field strength within the set range of the i-th electrical equipment in the power station to be pre-warned, DqH i is the electric field strength change index within the set range of the i-th electrical equipment in the power station to be pre-warned, λ is the influence coefficient of electric field strength change stored in the database, i = 1, 2, 3, …, i 0 , i 0 is the number of electrical equipment in the power station to be pre-warned.

[0093] It should be explained that λ is used to measure the influence of the change in electric field strength on the degree of electric field disturbance of electrical equipment, and it can be obtained through the following methods:

[0094] By monitoring the electric field strength data of electrical equipment in the power station to be pre-warned at different time periods, obtain the electric field change situation of the equipment under various operating conditions, focus on analyzing the fluctuation range of the electric field strength and its change rate, evaluate the possible influence of the change in electric field strength on the equipment, classify the influence of electric field disturbance of electrical equipment according to the fluctuation amplitude and frequency of the electric field strength, and find out the sensitivity of the change in electric field strength under different conditions.

[0095] The electric field strength is affected by external environments (such as temperature, humidity, pollution and other factors), so it is necessary to analyze the influence of different working environments on the change in electric field strength. For example, high-voltage equipment usually generates a strong electric field, and factors such as surrounding electrical interference and equipment aging may cause electric field fluctuations. For the influence of different environmental factors on the change in electric field strength, combined with the equipment operation data, set the influence coefficient of electric field strength change.

[0096] Different types of electrical equipment have different electric field characteristics. Some equipment may be designed with strong electric field shielding capabilities during design, while other equipment may be vulnerable to interference under large electric field changes. The material and insulation design of the equipment all affect the sensitivity to changes in electric field strength. By analyzing the electric field shielding design and material characteristics of the equipment and combining the test data on the changes in electric field strength during the operation of the equipment, the influence coefficient of electric field strength changes can be obtained.

[0097] In a laboratory or on-site environment, by simulating changes in electric field strength, the performance of electrical equipment under different electric field fluctuations can be tested. For example, by applying electric field interference with different frequencies and amplitudes, observing the response of the equipment, and measuring the degree of electric field disturbance of the equipment, the experimental results can provide a basis for the influence coefficient of electric field strength changes and help determine the influence intensity of different electric field changes on electrical equipment.

[0098] Analyze the historical faults of electrical equipment, especially the fault types related to electric field disturbance. By tracing back the fault data, identify which electrical equipment is more likely to fail under large electric field fluctuations, further verify the influence of changes in electric field strength. Combining with fault cases, the specific influence of electric field changes on equipment performance can be determined, so as to set the influence coefficients suitable for different equipment types.

[0099] In this implementation scheme, by reading the electric field intensity value of the electrical equipment and conducting real-time monitoring, it is possible to promptly capture the electric field disturbances that may occur during the operation of the equipment. This helps to detect early the risks of unstable operation or potential faults in the electrical equipment, avoiding greater problems caused by electric field disturbances. The calculation of the average electric field intensity and the electric field intensity change index provides a quantitative analysis of the equipment operation. Through this comprehensive analysis, it can accurately reflect whether the equipment is within the normal working range and whether there are abnormal fluctuations, thus enhancing the early warning ability. The calculation of the electric field disturbance index combines the change of the electric field intensity with the health status of the equipment, which can help managers formulate more scientific equipment protection and maintenance strategies, avoid damage to the equipment due to abnormal electric fields, and improve the safety of the equipment. The change of the electric field intensity and the disturbance index can reflect the change of the internal electrical activities of the equipment. By continuously tracking these changes, potential electrical faults or equipment failures can be predicted in advance, repaired in a timely manner, and the equipment downtime and sudden failures can be reduced. By combining the change of the electric field intensity with the influence coefficient, more accurate clues about the source of the fault can be provided. The electric field disturbance indices of different equipment can effectively distinguish the working state and the fault state of the equipment, helping technicians to conduct more accurate fault location and diagnosis. Through the dynamic evaluation of the electric field disturbance index, the health management of the equipment can be realized, reducing the power station shutdown or other safety problems caused by abnormal electrical equipment, and improving the overall stability and reliability of the power station. Combining the electric field disturbance data, the power station managers can better plan the maintenance and repair tasks, ensure that the high-risk equipment is processed in a timely manner, optimize the resource allocation, thereby reducing the operation cost and improving the efficiency.

[0100] Please refer to Figure 2 , an embodiment of the present invention provides a technical solution: a fire electrical early warning system based on the Internet of Things, including: a data acquisition module, an index analysis module, a comprehensive evaluation module, and a judgment and early warning module; the data acquisition module is used to continuously acquire the operation timing data of a plurality of electrical equipment in the power station to be warned; the index analysis module is used to analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, heat conduction sensitivity index, isolation decay index, and electric field disturbance index of each electrical equipment in the power station to be warned based on the operation timing data of a plurality of electrical equipment in the power station to be warned; the comprehensive evaluation module is used to comprehensively analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, heat conduction sensitivity index, isolation decay index, and electric field disturbance index of each electrical equipment in the power station to be warned to obtain the comprehensive fire risk assessment index of each electrical equipment in the power station to be warned; the judgment and early warning module is used to respectively judge and analyze the comprehensive fire risk assessment index of each electrical equipment in the power station to be warned with a preset comprehensive fire risk assessment interval, and regard the electrical equipment whose comprehensive fire risk assessment index is outside the preset comprehensive fire risk assessment interval as abnormal, and send an abnormal alarm to the relevant staff.

[0101] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic creative concept. Therefore, the appended claims are intended to be interpreted to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0102] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A fire electrical early warning method based on the Internet of Things, characterized in that: The following steps are involved: Continuously obtain the operation sequence data of several electrical equipment of the power station to be warned, and analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, thermal conductivity sensitivity index, isolation decay index, electric field disturbance index of each electrical equipment of the power station to be warned, and conduct comprehensive analysis to obtain the comprehensive fire risk assessment index of each electrical equipment of the power station to be warned; The comprehensive fire risk assessment index of each electrical equipment in the power station to be warned is judged and analyzed with the preset comprehensive fire risk assessment interval, and the electrical equipment whose comprehensive fire risk assessment index is outside the preset comprehensive fire risk assessment interval is regarded as abnormal, and an abnormal alarm is sent; The specific formula for calculating the comprehensive fire risk assessment index of each electrical equipment in the power station to be warned is as follows: Among them, HzF i is the comprehensive fire risk assessment index of the i-th electrical equipment in the power station to be warned, RbD i 、DcJ i , YbD i , RcM i , GsT i 、DrD i They are the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, thermal conduction sensitivity index, isolation decay index and electric field disturbance index of the i-th electrical equipment in the power station to be warned. ξ1, ξ2 and ξ3 are the thermal-electric linkage influence coefficient, insulation degradation influence coefficient and electric field smoothing influence coefficient stored in the database respectively. i=1, 2, 3, …, i0, where i0 is the number of electrical equipment in the power station to be warned.

2. The fire electrical early warning method based on the Internet of Things according to claim 1 is characterized in that: The operating sequence data includes operating temperature values, operating current values, operating voltage values, surface heat radiation values, insulation resistance values, and electric field strength values ​​within a set range at several time points.

3. The fire electrical early warning method based on the Internet of Things according to claim 2 is characterized in that: The specific steps for analyzing the thermal fluctuation index of each electrical equipment in the power station to be warned are as follows: Read the operating temperature values ​​of each electrical equipment of the power station to be warned at several time points, and conduct a comprehensive analysis to obtain the operating temperature average and operating temperature variation index of each electrical equipment of the power station to be warned; A comprehensive analysis is performed on the operating temperature mean and operating temperature variation index of each electrical equipment in the power station to be warned, and a thermal fluctuation index of each electrical equipment in the power station to be warned is obtained.

4. The fire electrical early warning method based on the Internet of Things according to claim 3 is characterized in that: The specific formula for calculating the thermal fluctuation index of each electrical equipment in the power station to be warned is as follows: Among them, RbD i is the thermal fluctuation index of the ith electrical equipment of the power station to be warned, YxJ i is the mean operating temperature of the ith electrical equipment in the power station to be warned, e is a natural constant, WbH i is the operating temperature change index of the i-th electrical equipment in the power station to be warned, α is the temperature change influence coefficient stored in the database, i=1, 2, 3, ..., i0, i0 is the number of electrical equipment in the power station to be warned.

5. The fire electrical early warning method based on the Internet of Things according to claim 2 is characterized in that: The specific steps for analyzing the current impact index of each electrical equipment in the power station to be warned are as follows: Read the operating current values ​​of each electrical device of the power station to be warned at several time points, and perform comparative analysis to obtain the maximum operating current value of each electrical device of the power station to be warned; The operating current values ​​of each electrical equipment of the power station to be warned at several time points are analyzed comprehensively to obtain the operating current change index of each electrical equipment of the power station to be warned; The maximum parameter value of the operating current of each electrical equipment in the power station to be warned is obtained, and a comprehensive analysis is performed based on the maximum operating current and the operating current change index of each electrical equipment in the power station to be warned, so as to obtain the current impact index of each electrical equipment in the power station to be warned.

6. The fire electrical early warning method based on the Internet of Things according to claim 2 is characterized in that: The specific steps for analyzing the voltage fluctuation sensitivity index of each electrical equipment in the power station to be warned are as follows: Read the operating voltage values ​​of each electrical equipment of the power station to be warned at several time points, and compare and analyze them to obtain the maximum operating voltage value of each electrical equipment of the power station to be warned; The operating voltage values ​​of each electrical equipment of the power station to be warned at several time points are analyzed comprehensively to obtain the operating voltage change index of each electrical equipment of the power station to be warned; The maximum parameter value of the operating voltage of each electrical equipment in the power station to be warned is obtained, and a comprehensive analysis is performed on the maximum operating voltage and the operating voltage variation index of each electrical equipment in the power station to be warned, so as to obtain the voltage fluctuation sensitivity index of each electrical equipment in the power station to be warned; The specific formula for calculating the operating voltage variation index and voltage fluctuation sensitivity index of each electrical equipment in the power station to be warned is as follows: Among them, YbH i is the operating voltage variation index of the i-th electrical equipment in the power station to be warned, YxY i(u+1) is the operating voltage value of the i-th electrical equipment of the power station to be warned at the u+1th time point, YxY iu is the operating voltage value of the i-th electrical equipment of the power station to be warned at the u-th time point, YbD i is the voltage fluctuation sensitivity index of the i-th electrical equipment in the power station to be warned, YxY i Max is the maximum operating voltage of the ith electrical equipment in the power station to be warned, DyC i is the maximum parameter value of the operating voltage of the i-th electrical equipment in the power station to be warned, δ is the voltage regulation coefficient stored in the database, μ is the voltage change influence coefficient stored in the database, i=1, 2, 3, …, i0, i0 is the number of electrical equipment in the power station to be warned, u=1, 2, 3, …, u0, u0 is the number of time points.

7. The fire electrical early warning method based on the Internet of Things according to claim 2 is characterized in that: The specific steps for analyzing the thermal conductivity sensitivity index of each electrical equipment in the power station to be warned are as follows: Read the surface thermal radiation values ​​of each electrical equipment of the power station to be warned at several time points, and conduct a comprehensive analysis to obtain the surface thermal radiation mean value and surface thermal radiation variation index of each electrical equipment of the power station to be warned; Obtain the surface thermal radiation parameter value of each electrical equipment in the power station to be warned, and conduct a comprehensive analysis based on the surface thermal radiation mean value and surface thermal radiation variation index of each electrical equipment in the power station to be warned, so as to obtain the thermal conduction sensitivity index of each electrical equipment in the power station to be warned; The specific formula for calculating the thermal conductivity sensitivity index of each electrical equipment in the power station to be warned is as follows: Among them, RcM i is the thermal conductivity sensitivity index of the ith electrical equipment of the power station to be warned, BmJ i is the mean surface thermal radiation value of the i-th electrical equipment in the power station to be warned, BmC i BmH is the surface thermal radiation parameter value of the i-th electrical equipment in the power station to be warned, i is the surface thermal radiation variation index of the i-th electrical equipment in the power station to be warned, θ is the surface thermal radiation variation influence coefficient stored in the database, i=1, 2, 3, …, i0, i0 is the number of electrical equipment in the power station to be warned.

8. The fire electrical early warning method based on the Internet of Things according to claim 2 is characterized in that: The specific steps for analyzing the isolation degradation index of each electrical equipment in the power station to be warned are as follows: Read the insulation resistance values ​​of each electrical equipment of the power station to be warned at several time points, and compare and analyze them to obtain the minimum insulation resistance value of each electrical equipment of the power station to be warned; The insulation resistance values ​​of each electrical equipment of the power station to be warned at several time points are analyzed comprehensively to obtain the insulation resistance change index of each electrical equipment of the power station to be warned; The minimum parameter value of the insulation resistance of each electrical equipment of the power station to be warned is obtained, and a comprehensive analysis is performed in combination with the insulation resistance variation index of each electrical equipment of the power station to be warned, so as to obtain the isolation decay index of each electrical equipment of the power station to be warned; The specific formula for calculating the insulation resistance change index and isolation decay index of each electrical equipment in the power station to be warned is as follows: Among them, JbH i is the insulation resistance variation index of the ith electrical equipment in the power station to be warned, JyD i(u+1) is the insulation resistance value of the ith electrical equipment of the power station to be warned at the u+1th time point, JyD iu is the insulation resistance value of the i-th electrical equipment of the power station to be warned at the u-th time point, GsT i is the isolation degradation index of the i-th electrical equipment of the power station to be warned, is the minimum insulation resistance of the ith electrical equipment in the power station to be warned, JyC i is the minimum parameter value of the insulation resistance of the i-th electrical equipment in the power station to be warned, σ is the insulation resistance change influence coefficient stored in the database, i = 1, 2, 3, ..., i0, i0 is the number of electrical equipment in the power station to be warned, u = 1, 2, 3, ..., u0, u0 is the number of time points.

9. The fire electrical early warning method based on the Internet of Things according to claim 2 is characterized in that: The specific steps for analyzing the electric field disturbance index of each electrical equipment in the power station to be warned are as follows: Read the electric field strength values ​​within the set range of each electrical equipment of the power station to be warned at several time points, and conduct a comprehensive analysis to obtain the electric field strength mean value and electric field strength variation index within the set range of each electrical equipment of the power station to be warned; A comprehensive analysis is performed on the electric field intensity mean value and electric field intensity variation index within a set range of each electrical device in the power station to be warned, and the electric field disturbance index of each electrical device in the power station to be warned is obtained.

10. A fire electrical early warning system based on the Internet of Things, applying the fire electrical early warning method based on the Internet of Things according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, index analysis module, comprehensive evaluation module, judgment and early warning module; The data acquisition module is used to continuously acquire the operation sequence data of several electrical equipments of the power station to be warned; The index analysis module is used to analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, thermal conduction sensitivity index, isolation decay index, and electric field disturbance index of each electrical equipment in the power station to be warned based on the operation sequence data of several electrical equipment in the power station to be warned; The comprehensive assessment module is used to comprehensively analyze the thermal fluctuation index, current impact index, voltage fluctuation sensitivity index, thermal conductivity sensitivity index, isolation decay index, and electric field disturbance index of each electrical equipment in the power station to be warned, and obtain a comprehensive fire risk assessment index for each electrical equipment in the power station to be warned; The judgment and warning module is used to judge and analyze the comprehensive fire risk assessment index of each electrical equipment in the power station to be warned with the preset comprehensive fire risk assessment interval, and regard the electrical equipment whose comprehensive fire risk assessment index is outside the preset comprehensive fire risk assessment interval as abnormal, and send an abnormal alarm.

Images