An intelligent detection method and system for indoor electrical safety hazards

Abstract

The present invention relates to the field of electrical safety monitoring technology, specifically to an intelligent detection method and system for indoor electrical safety hazards, comprising the following steps: constructing a synchronous data set based on electrical equipment and environmental data, extracting the rate of change of power and current series analysis, screening mutation signals and identifying risk segments in combination with the environment, extracting the fluctuation interval to determine the critical offset, locating the offset distance of the electrical series, and statistically marking high-incidence areas by risk frequency to generate an alarm node list. In the present invention, by collecting the environmental data of electrical connection points and unifying the time tags, high-precision synchronization of electricity consumption behavior and environmental conditions is achieved, the accuracy of abnormality identification is improved, the rate of change of power and current series is extracted, dynamic warning line offset is achieved, trajectory mapping reveals hidden abnormalities in the stable stage, frequency statistics and spatial mapping locate high-incidence areas, and closed-loop monitoring from multi-dimensional data fusion to risk area marking is achieved, significantly improving the intelligence and foresight of electrical hazard identification.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical safety monitoring, and in particular to an intelligent detection method and system for indoor electrical safety hazards. Background Art

[0002] The field of electrical safety monitoring technology involves collecting, analyzing, and providing early warnings on the real-time status of electrical equipment and wiring within buildings, aiming to reduce the incidence of safety accidents such as fires and electric shocks caused by electrical faults. The core of this technology involves collecting electrical parameters, identifying current and voltage anomalies, identifying cable overloads and short circuits, and determining residual current and ground faults. Through sensors, measurement circuits, and control centers, this technology enables continuous monitoring of indoor power usage.

[0003] The intelligent detection method for indoor electrical safety hazards targets electrical fault risks in enclosed spaces such as homes, offices, and commercial buildings. It uses information collection, data comparison, and rule-based reasoning to identify typical hazards, including wire aging, poor contact, abnormal loads, sudden changes in leakage current, and abnormal ground resistance. This detection method regularly collects multi-point data using sensors for current, voltage, temperature, and residual current. Combining pre-set hazard identification thresholds with classification logic, it compares and analyzes the collected real-time data. Furthermore, through reasoning and judgment steps, it classifies and processes data patterns that match hazard characteristics.

[0004] Existing technologies primarily rely on single-point electrical parameter collection, relying primarily on determining if indicators like voltage, current, and residual current exceed fixed thresholds. This approach presents limitations in various scenarios. For example, the impact of ambient temperature and humidity fluctuations on line performance is not effectively assessed, leading to a lack of early warning of potential hazards caused by poor contact and degraded cable insulation in high-temperature and high-humidity conditions. Static comparison logic ignores the temporal fluctuations in power usage, leading to short bursts of power or frequent switching being interpreted as normal, thus missing the early warning window. The lack of traceability analysis of historical operating trajectories makes it difficult to identify continuous abnormal trends from behavioral patterns, making it impossible to accurately locate high-risk areas. Ultimately, this results in a reactive response limited to post-fault events, failing to meet the needs of proactively addressing potential hazards in complex indoor electrical environments. For example, in office areas, periodic high load surges caused by the startup of equipment like air conditioners and electric heaters, without causing voltage drops, make it difficult to trigger existing system alarms. Over time, thermal hazards can accumulate and cause failures. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the embodiment of the present invention provides an intelligent detection method and system for indoor electrical safety hazards. The technical solution is as follows:

[0006] In one aspect, a method for intelligently detecting indoor electrical safety hazards is provided, the method comprising:

[0007] S1: Based on the data from the connection points of electrical equipment in the residence, including current, voltage, and power information, the environmental data of room temperature and humidity monitoring equipment within the same period is sorted and classified, and each value is annotated with a time tag to generate a synchronized dataset of indoor loads and environment;

[0008] S2: Based on the indoor load and environment synchronization data set, extract the time series of power and current of the power shunt terminal group, analyze the change amplitude per unit time period, and compare the change rate of the upper and lower cycles. Filter the signal sequence with excessive change rate, analyze the abnormal correlation in combination with the environmental data, and obtain the fire risk load mutation fragment;

[0009] S3: Calling the fire risk load mutation segment, extracting the current and voltage values in each segment, identifying the ratio fluctuation range within a continuous period, and marking it as a critical fluctuation when the fluctuation range exceeds the line operation reference boundary. Summarizing and outputting the voltage and current deviation abnormality segments;

[0010] S4: Based on the abnormal voltage and current offset section, identify the power, temperature and humidity time series arrangement in the corresponding time period, select high-frequency fluctuation points for behavior position mapping, determine the difference trajectory during stable operation, and mark the interval where the offset amplitude is greater than the normal section to obtain the indoor electrical sequence offset distance.

[0011] As a further solution of the present invention, the indoor load and environment synchronization data set includes electrical node numerical labels, environmental parameter timestamps, and multi-source data alignment fields; the fire risk load mutation segment includes abnormal power change values, periodic change differences, and environmental coupling indicator factors; the voltage and current offset abnormality segment includes upper and lower fluctuation limit values, ratio abnormality judgment points, and continuous abnormality identification marks; the indoor electrical sequence offset distance includes stable trajectory offset, high-frequency change position points, and operating status comparison features.

[0012] As a further solution of the present invention, the step of synchronizing the data set of the indoor load and the environment is specifically as follows:

[0013] S101: Based on the data of the connection points of the electrical equipment in the residence, the current value, voltage value, and power value of the socket node are extracted, the environmental parameters of the indoor temperature and humidity monitoring equipment are called, the two types of data are matched and sorted by time tags, and a corresponding set of electrical and environmental parameters is generated;

[0014] S102: Based on the corresponding set of electrical and environmental parameters, perform interval discrimination on the current value and power value under the time tag, analyze the combined fluctuation amplitude between power and humidity, and select record segments that continuously exceed the current upper limit threshold and have abnormal combined fluctuation amplitude to obtain the abnormal load fluctuation interval value;

[0015] S103: Based on the abnormal load fluctuation interval value, extract the interval voltage offset and room temperature change rate, combine the synchronization amplitude difference and duration, judge the abnormality of electrical load overload and poor contact, and generate an indoor load and environment synchronization data set.

[0016] As a further embodiment of the present invention, the fire risk load mutation fragment step is specifically as follows:

[0017] S201: Based on the indoor load and environment synchronization data set, extract the current and power series of the power shunt terminal group, identify the cycle-to-cycle change rate, filter the power and current change rate records that exceed the fluctuation threshold, and generate the load sudden change fluctuation interval;

[0018] S202: Based on the load mutation fluctuation range, call the room temperature and humidity of the corresponding time period, extract the temperature and humidity combination corresponding to the power, and determine whether the difference in the time period before the mutation exceeds the electrical safety threshold. Mark the abnormal linkage area and obtain the fire risk load mutation fragment.

[0019] As a further solution of the present invention, the steps of the abnormal voltage and current deviation section are specifically as follows:

[0020] S301: Calling the continuous current value and voltage value data in the fire risk load mutation segment, pairing them according to the same time period, calculating the ratio of each group, and generating a voltage-current ratio fluctuation sequence;

[0021] S302: Based on the voltage-current ratio fluctuation sequence, extract the upper and lower boundaries of the ratio interval of consecutive time periods, compare them with the line operation reference value, identify the section exceeding the reference value, determine the start and end time of the abnormal section and the ratio fluctuation range, mark the fluctuation period that meets the conditions as a critical section, and obtain the ratio critical fluctuation range;

[0022] S303: According to the critical fluctuation range of the ratio, extract the current value and voltage value of the corresponding period in the mutation segment, analyze the offset amplitude, summarize the offset combination of the critical section, and output the voltage and current offset abnormal section.

[0023] As a further solution of the present invention, the step of indoor electrical sequence offset distance is specifically as follows:

[0024] S401: Extracting power values, temperature, and humidity sequences within the voltage and current deviation abnormality section, analyzing the instantaneous deviation rate of power change, extracting mutation points, and recording the synchronous positions in the multi-source sequence to obtain indoor high-frequency abnormal behavior nodes;

[0025] S402: Based on the indoor high-frequency abnormal behavior nodes, the corresponding temperature and humidity value change trajectories are compared with the baseline trajectory of the steady-state segment, the range of behavior points where the continuous trajectory deviation exceeds the thermal and humidity stability threshold is identified, the deviation direction and duration characteristics are located, and the indoor thermal and humidity deviation interference segment is established;

[0026] S403: Extract the power offset trend and temperature and humidity disturbance amount during the period according to the indoor thermal and humidity offset interference section, calculate the total offset amount during the composite interference period, identify the section with low overlap rate and where the offset continuously exceeds the reference time length, and obtain the indoor electrical sequence offset distance.

[0027] As a further embodiment of the present invention, the method further comprises step S5:

[0028] S5: Based on the indoor electrical sequence offset distance, the triggering frequency of risk events in the continuous section is counted, and the high-incidence areas are located according to the cumulative frequency trend. A corresponding level label is assigned to each area, and a list of indoor electrical hidden danger alarm nodes is output;

[0029] The indoor electrical hidden danger alarm node list includes risk level partitions, event frequency thresholds, and alarm node identification numbers.

[0030] As a further solution of the present invention, the steps of the indoor electrical hidden danger alarm node list are specifically as follows:

[0031] S501: Based on the indoor electrical sequence offset distance, extract the offset event records within a continuous time period, count the number of offset event triggers in each section, and calculate the cumulative growth trend value of the event within the section, identify the continuous position intervals with continuously increasing trigger frequency, and obtain the electrical risk high-incidence section group;

[0032] S502: Based on the electrical risk high-incidence section group, combined with the event trigger frequency, duration and offset amplitude in the section, filter the sections whose trigger frequency is greater than the risk assessment classification threshold, label the corresponding time position according to the trigger level, and output the indoor electrical hazard alarm node list.

[0033] On the other hand, an electric vehicle state monitoring system is provided, wherein the electric vehicle state monitoring system is used to execute the above electric vehicle state monitoring method, and the system comprises:

[0034] The data synchronization module is based on the data of the electrical equipment connection points in the house, including the current, voltage, and power values of the socket nodes. It sorts the time series according to the cycle, extracts the room temperature and humidity values within each cycle, analyzes the mapping relationship between time tags and parameters, and forms an electrical environment correlation data set;

[0035] The hidden danger identification module extracts the power and current series of each power branch based on the electrical environment correlation data set, compares the change amplitude and increase / decrease ratio of adjacent cycles, screens the abnormal fluctuation frequency band, and identifies the room temperature and humidity values of the corresponding time period to generate an abnormal load mutation feature group;

[0036] The fluctuation discrimination module extracts the ratio of current to voltage for each set of data based on the abnormal load mutation feature group, analyzes the fluctuation range of the ratio over a continuous period of time, determines whether the operating boundary threshold is exceeded, locates the over-limit section, and obtains the critical electrical parameter abnormal section;

[0037] The trajectory analysis module matches the power sequence and temperature and humidity sequence of each time period based on the critical electrical parameter anomaly section, extracts the high-frequency point identification behavior time trajectory, compares the offset with the stable operation behavior trajectory, identifies the trajectory variation characteristics, and establishes the electrical behavior offset path group;

[0038] The node warning module is based on the electrical behavior deviation path group, counts the number of abnormal fluctuation triggers in the path, analyzes the regional mapping relationship, performs level classification on high-frequency points, locates the trigger concentration area, and outputs a list of indoor electrical hidden danger alarm nodes.

[0039] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0040] By uniformly time-labeling the current, voltage, and power values collected from electrical connection points within a residence, along with environmental information, we achieve high-precision synchronization between electricity consumption behavior and environmental conditions, enabling the precise location of abnormal events through multi-factor cross-validation. By combining time series analysis of the power and current of the power shunt terminal group, we have established a detection mechanism for short-term sudden load changes. By identifying excessive rate of change and judging environmental correlations, we can effectively identify abnormal power fluctuations caused by factors such as humidity and temperature rise. We further extract the fluctuation range of the voltage-current ratio and establish an operating boundary reference system, enabling dynamic early warning of minor deviations in circuit status. By mapping the behavioral trajectories of high-frequency fluctuation points, we break through the previous static parameter judgment method and are able to identify hidden abnormal trends during stable power consumption. The method based on risk frequency statistics and spatial mapping realizes the hierarchical positioning of risk areas and establishes a time-space chain of risk evolution, thereby outputting a warning node list with temporal characteristics and spatial accuracy, forming a full-process closed loop from data fusion, feature extraction, dynamic judgment to spatial mapping, and realizing multi-dimensional monitoring and early warning of sudden, hidden, and environmentally induced electrical hazards. Compared with the static method that only relies on threshold judgment, it enhances the intelligent recognition capability and prediction and judgment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0042] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0043] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0044] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0045] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0046] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0047] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0048] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0049] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0050] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0051] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0052] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0053] See also Figure 1 The embodiment of the present invention provides an intelligent detection method for indoor electrical safety hazards. The processing flow of the method may include the following steps:

[0054] S1: Based on the data from the connection points of electrical equipment in the residence, including the current, voltage, and power information of the socket nodes, the environmental data of the room temperature and humidity monitoring equipment in the same period are sorted and classified, and each value is annotated with a time tag to generate a synchronized dataset of indoor loads and environment;

[0055] S2: Based on the synchronized dataset of indoor loads and the environment, the power and current time series of the power shunt terminal group are extracted. The change amplitude per unit period is analyzed, and the change rate between the upper and lower periods is compared. Signal sequences with excessive change rates are screened out. The abnormal correlation is analyzed in combination with the environmental data to obtain the fire risk load mutation fragment.

[0056] S3: Call the fire risk load mutation segment, extract the current and voltage values in each segment, identify the ratio fluctuation range within the continuous time period, and mark the fluctuation range as critical when it exceeds the line operation reference boundary. Summarize and output the voltage and current deviation abnormality segments;

[0057] S4: Based on the abnormal voltage and current offset sections, identify the power, temperature and humidity time series within the corresponding period, select high-frequency fluctuation points for behavior position mapping, determine the difference trajectory during stable operation, and mark the intervals where the offset amplitude is greater than the normal section to obtain the indoor electrical sequence offset distance;

[0058] S5: Based on the indoor electrical sequence offset distance, count the triggering frequency of risk events in continuous segments, locate high-incidence areas based on the cumulative frequency trend, assign corresponding level labels to each area, and output a list of indoor electrical hidden danger alarm nodes;

[0059] The indoor load and environment synchronization data set includes electrical node numerical labels, environmental parameter timestamps, and multi-source data alignment fields. The fire risk load mutation fragment includes abnormal power change values, periodic change differences, and environmental coupling indicator factors. The voltage and current offset abnormality section includes upper and lower fluctuation limits, ratio abnormality judgment points, and continuous abnormality identification marks. The indoor electrical sequence offset distance includes stable trajectory offset, high-frequency change location points, and operating status comparison characteristics. The indoor electrical hazard alarm node list includes risk level partitions, event frequency thresholds, and alarm node identification numbers.

[0060] Specifically, if Figure 2 As shown in the figure, the steps for synchronizing the indoor load and environment datasets are as follows:

[0061] S101: Based on the data of the connection points of the electrical equipment in the residence, the current value, voltage value, and power value of the socket node are extracted, the environmental parameters of the indoor temperature and humidity monitoring equipment are called, the two types of data are matched and sorted by time tags, and a corresponding set of electrical and environmental parameters is generated;

[0062] Current, voltage, and power are common monitoring parameters in residential electrical equipment. As a key connection point for electrical equipment, outlet nodes provide real-time current, voltage, and power parameters for electrical devices. First, the current current, voltage, and power values are obtained from the outlet's electrical connection point. This can be collected in real time using a meter or sensor. Based on environmental parameters acquired by indoor temperature and humidity monitoring equipment, indoor temperature and humidity data are extracted. Environmental parameters are collected using specialized monitoring equipment, including temperature and humidity sensor data. The data is time-matched using time stamps, synchronizing the electrical and environmental data to ensure that each pair of electrical and environmental parameters corresponds to the same time period. This approach yields a complete dataset containing the timestamp, electrical data (current, voltage, power), and environmental data (temperature, humidity) at the corresponding time. For example, at a given moment, the outlet node's current is 5 amps, voltage is 220 volts, and power is 1100 watts, while the indoor temperature is 23°C and the humidity is 60%. The data will be recorded and organized into corresponding sets of electrical and environmental parameters. Through this set of data, subsequent current and power analysis, temperature and humidity fluctuations, and abnormal detection of electrical load conditions will be more accurate.

[0063] S102: Based on the corresponding set of electrical and environmental parameters, the current value and power value under the time tag are interval-determined, and the combined fluctuation amplitude between power and humidity is analyzed. Record segments that continuously exceed the current upper limit threshold and have abnormal combined fluctuation amplitude are screened out to obtain the abnormal load fluctuation interval value;

[0064] Current and power values are extracted based on the time tags. Next, interval identification is performed. This involves dividing the current and power values into intervals, setting an upper current threshold (for example, 10 amps), and then identifying the current value. If the current value exceeds this threshold, an abnormality is detected. The power value identification process is similar: a power upper threshold (for example, 1500 watts) is set. When the power value exceeds this threshold, an abnormality detection is also triggered. The combined fluctuation amplitude of the power value and humidity is analyzed by calculating the amplitude of the change in humidity and power values within a certain time interval. For example, if the humidity changes from 60% to 75%, the power value fluctuates from 1000 watts to 1300 watts. The fluctuation amplitude can be calculated and compared with the set fluctuation threshold. If it exceeds the predetermined range, it is considered an abnormal fluctuation. This method can filter out recording segments in which the current and power values exceed the upper thresholds within a continuous period of time and the fluctuation amplitude between power and humidity is abnormal, ultimately determining the abnormal load fluctuation interval value. For example, if the current value continuously exceeds 10 amps and the combined fluctuation range of humidity and power values reaches a preset abnormal range (such as humidity changes exceeding 15% and power fluctuations exceeding 300 watts), then the record will be identified as an abnormal load fluctuation range.

[0065] S103: Based on the abnormal load fluctuation interval value, extract the interval voltage offset and room temperature change rate, combine the synchronization amplitude difference and duration, determine the electrical load overload and poor contact anomalies, and generate a synchronized data set of indoor load and environment;

[0066] Based on the abnormal load fluctuation range, the voltage offset and room temperature change rate are then extracted. Voltage offset refers to the deviation of the voltage value from the normal voltage range within a specific time interval. It can be calculated by measuring the difference between the current voltage and the standard voltage (such as 220 volts). If the voltage value fluctuates significantly, exceeding the set threshold range (for example, the voltage fluctuation exceeds ±10 volts), it indicates abnormal voltage fluctuation. The room temperature change rate refers to the speed of room temperature change within a certain time period. It can be calculated by the ratio of the difference in room temperature change between two points in time to the time interval. For example, if the room temperature rises from 22°C to 28°C within an hour, with a rate of change of 6°C / hour, if the rate of change exceeds the set threshold (for example, more than 3°C / hour), it can be considered that the room temperature fluctuation within this interval is too large. Combined with the synchronization amplitude difference, that is, the difference in the change amplitude of current, voltage, temperature and humidity, by comparing the synchronous changes of different parameters, we can further judge the overload and poor contact problems of the electrical load. Overload is manifested as the current value continuously exceeding the upper limit and the power value is abnormally high, while poor contact is accompanied by the phenomenon of asynchronous voltage and current fluctuations. By combining the data, a synchronized dataset of indoor load and environment is generated, providing data support for subsequent load and environment relationship analysis.

[0067] Specifically, if Figure 3 As shown in the figure, the steps of the fire risk load mutation fragment are as follows:

[0068] S201: Based on the indoor load and environment synchronization data set, extract the current and power series of the power shunt terminal group, identify the cycle-to-cycle change rate, filter the power and current change rate records that exceed the fluctuation threshold, and generate the load sudden change fluctuation range;

[0069] The current and power series for the power distribution terminal group are extracted from the synchronized indoor load and environmental data set. This data reflects the power consumption of individual loads within the residence. By sorting the current and power values chronologically and matching them with the corresponding environmental parameters, a continuous data series is formed. The cycle-to-cycle rate of change is then identified. This involves calculating the rate of change for each current and power data point relative to the previous time point. For example, if the current changes from 5 amps to 6 amps at a given time point, the rate of change is 20%. This process requires taking the difference between each data point in the current and power series and dividing it by the value at the previous time point. After calculating the rate of change for each current and power value, the data point is filtered based on a preset fluctuation threshold. For example, if the current rate of change threshold is 10% and the power rate of change threshold is 15%, then if the current rate of change exceeds 10% or the power rate of change exceeds 15%, the data point is considered abnormally fluctuating. Records exceeding the fluctuation threshold are then filtered out. Assume that during a certain period, the current change rate reaches 12% and the power change rate reaches 18%. Both the current and power changes during this period exceed the set thresholds and are identified as a sudden load fluctuation range. For example, from 8:00 PM to 8:15 PM, the current suddenly increases from 5 amps to 6 amps, and the power value increases from 1000 watts to 1200 watts, resulting in a sudden load fluctuation range.

[0070] S202: Based on the load mutation fluctuation range, the room temperature and humidity of the corresponding time period are retrieved, the temperature and humidity combination corresponding to the power is extracted, and it is determined whether the difference in the period before the mutation exceeds the electrical safety threshold. The abnormal linkage area is marked to obtain the fire risk load mutation fragment;

[0071] Retrieve the room temperature and humidity data corresponding to the time period. By querying the indoor temperature and humidity data recorded by environmental monitoring equipment, find the environmental data that coincides with the load sudden fluctuation period. For example, assume the load sudden fluctuation period is from 8:00 PM to 8:15 PM, and the room temperature is 28°C and the humidity is 55% during this period. Next, extract the temperature and humidity combination corresponding to the power. For example, during this period, when the power value is 1200 watts, the room temperature is 28°C and the humidity is 55%. This combined data can be used to analyze the relationship between the power sudden change and environmental changes. Determine whether the difference in the period before the sudden change exceeds the electrical safety threshold. The electrical safety threshold is set based on the design standards of the electrical equipment and the actual operating environment. For example, the set safety threshold is a temperature change of more than 5°C or a humidity change of more than 10%. Suppose that 15 minutes before the load sudden change, the room temperature rose from 23°C to 28°C, a change of 5°C, which meets the safety threshold requirement. However, if the temperature change exceeds the set safety threshold (for example, more than 5°C), it will be marked as an abnormal linkage area, indicating an abnormal linkage between the load sudden change and the environmental change, posing a fire risk. For example, if the room temperature continues to rise and the humidity suddenly fluctuates significantly after a load mutation, this will affect the stability of electrical equipment, causing a short circuit or overheating, thereby creating a fire risk. In this case, the load mutation segment will be marked as a fire risk load mutation segment.

[0072] Specifically, if Figure 4 As shown in the figure, the steps for detecting abnormal voltage and current deviation in the section are as follows:

[0073] S301: Calling the continuous current value and voltage value data in the fire risk load mutation segment, pairing them according to the same time period, calculating the ratio of each group, and generating a voltage-current ratio fluctuation sequence;

[0074] Continuous current and voltage data from fire risk load mutation segments are extracted by time period. Each current and voltage data point is recorded synchronously, allowing each pair of current and voltage values to be paired based on the time stamp. For example, if the current is 5 amps and the voltage is 220 volts within the same time period, these two values are paired and their ratio is calculated. The voltage-to-current ratio is calculated using a simple division operation, such as 220V divided by 5A, which yields an impedance of 44 ohms. This calculation is repeated for each pair of current and voltage data to determine the voltage-to-current ratio for each time period. By calculating the current-to-voltage ratio for all time points, a complete voltage-to-current ratio fluctuation sequence is generated. For example, if the current is 6 amps and the voltage is 230 volts within a certain time period, the ratio is 230V / 6A = 38.33 ohms. This ratio sequence reflects the temporal changes in voltage and current and provides basic data for subsequent fluctuation analysis. By calculating and comparing each set of ratios, the fluctuations in voltage and current can be determined.

[0075] S302: Based on the voltage-current ratio fluctuation sequence, the upper and lower boundaries of the ratio interval of consecutive time periods are extracted and compared with the line operation reference value. The sections exceeding the reference value are identified, the start and end times of the abnormal sections and the ratio fluctuation range are determined, and the fluctuation periods that meet the conditions are marked as critical sections to obtain the critical fluctuation range of the ratio.

[0076] The upper and lower bounds of the ratio values for consecutive time periods are extracted by setting a maximum and minimum range in the time series. For example, if the voltage-to-current ratio fluctuates between 40 ohms and 50 ohms during a certain time period, the upper and lower bounds of this ratio range are 40 ohms and 50 ohms. The extracted ratio range is then compared with the line's operating reference value, which can be a threshold range set based on equipment standards or historical operating data. For example, a reference value of 45 ohms ± 5 ohms allows the voltage-to-current ratio to fluctuate between 40 ohms and 50 ohms. If the ratio range exceeds this range (e.g., below 40 ohms or above 50 ohms), the ratio fluctuation for that period is considered abnormal. By comparing the reference value with the ratio fluctuation range, the sections exceeding the reference value can be identified, and the start and end times of the abnormal sections, as well as the ratio fluctuation range, can be determined. For example, if the ratio drops to 35 ohms or rises to 55 ohms during a certain period, this period is marked as an abnormal fluctuation section, and its start and end times are determined. The fluctuation period that meets the conditions is marked as a critical section, which means that the voltage-current ratio fluctuation during this period exceeds the set safety threshold and poses a greater risk. The critical fluctuation range of the ratio is obtained to provide data support for subsequent abnormal analysis.

[0077] S303: Extract the current and voltage values of the corresponding time period in the mutation segment according to the critical fluctuation range of the ratio, analyze the offset amplitude, summarize the offset combination of the critical section, and output the voltage and current offset abnormal section;

[0078] Extract the current and voltage values for the corresponding time periods within the mutation segment. For each critical fluctuation interval, find the current and voltage data that overlaps with that time period. For example, if the current value is 7 amps and the voltage value is 240 volts within the critical fluctuation interval, extract the current and voltage data for that period. Then analyze the offset magnitude for that period. The offset magnitude refers to the difference between the current and voltage values in the current and previous periods. For example, if the current in the previous period was 6 amps and the voltage was 230 volts, while the current period is 7 amps and the voltage is 240 volts, the offset magnitudes are 1 amp and 10 volts, respectively. Analyzing the offset magnitude helps identify abnormal fluctuations in the electrical load. By summarizing all offset combinations within the critical interval—that is, summarizing and analyzing the current and voltage offset magnitudes that meet the critical fluctuation interval criteria—then analyze their changing patterns. If similar offset combinations occur within multiple critical intervals, such as larger current offsets and smaller voltage offsets, this indicates unstable equipment load. This offset magnitude analysis can be used for further load monitoring and fault diagnosis. For example, in a sudden change segment, the current value suddenly increases from 6 amperes to 8 amperes, while the voltage value increases from 230 volts to 240 volts. This sudden change can be marked as a voltage and current deviation abnormality segment.

[0079] Specifically, if Figure 5 As shown, the steps for indoor electrical sequence offset distance are as follows:

[0080] S401: Based on the voltage and current deviation abnormal section, extract the power value, temperature and humidity sequence within the period, analyze the instantaneous deviation rate of power change, extract the mutation point and record the synchronous position in the multi-source sequence, and obtain the indoor high-frequency abnormal behavior node;

[0081] Data is provided by the corresponding monitoring equipment and can be extracted through time synchronization. Power changes are primarily related to current and voltage fluctuations. Therefore, when voltage or current deviations are abnormal, power values also exhibit significant changes. The instantaneous deviation rate of power change is calculated. The instantaneous deviation rate refers to the rate of change of power between adjacent time periods. It can be obtained by taking the difference of the power values and dividing them by the time interval. For example, if the power is 1000 watts at one moment and 1100 watts the next, the instantaneous deviation rate is (1100 - 1000) / time interval (in seconds). This calculation helps identify sudden changes in power and, consequently, identify breakpoints. Breakpoints are moments where the power, current, or voltage values experience significant changes within a very short period of time. For example, if the power value rises sharply from 1000 watts to 1500 watts, and the rate of change far exceeds a predetermined threshold (e.g., 20%), this is a breakpoint. By marking breakpoints and recording them at synchronized locations in the multi-source sequence, nodes with high-frequency abnormal behavior can be accurately identified. For example, during a certain period of time, the power value suddenly changed at 9 o'clock in the evening, and the current and voltage also experienced large fluctuations simultaneously. This moment was considered a high-frequency abnormal behavior node and was recorded for further analysis.

[0082] S402: Based on the indoor high-frequency abnormal behavior nodes, the corresponding temperature and humidity value change trajectories are compared with the baseline trajectory of the steady-state segment. The range of behavior points where the continuous trajectory deviation exceeds the thermal and humidity stability threshold is identified. The deviation direction and duration characteristics are located, and the indoor thermal and humidity deviation interference segment is established.

[0083] The temperature and humidity trajectory for that period is compared against the baseline trajectory for the steady-state segment. The baseline trajectory refers to the stable temperature and humidity variation pattern under normal operating conditions, defined by long-term historical data or device design parameters. The temperature and humidity variations before and after the occurrence of a high-frequency abnormal behavior node are calculated and compared with the baseline trajectory. If the temperature change exceeds a set threshold (e.g., 3°C) or the humidity change exceeds a set threshold (e.g., 10%), the temperature and humidity variation for that period is considered to have significantly deviated from the normal fluctuation range. The identified behavior points where the continuous trajectory deviation exceeds the thermal and humidity stability threshold are those time periods where the temperature and humidity changes meet or exceed the set thresholds over a sustained period. For example, if the temperature increases from 23°C to 28°C and the humidity changes from 60% to 75% within an hour, the changes during this period are considered deviation points. The deviation direction and duration characteristics are identified. For example, if the temperature gradually increases and persists for more than a certain period (e.g., one hour), this deviation behavior can be considered a thermal disturbance, and an indoor thermal and humidity deviation disturbance segment can be established. This segment is characterized by sustained temperature and humidity changes that exceed the set stability range.

[0084] S403: Extract the power offset trend and temperature and humidity disturbance amount during the period based on the indoor thermal and humidity offset interference segment, calculate the total offset during the composite interference period, identify the segments with low overlap rates and where the offset lasts longer than the benchmark duration, and obtain the indoor electrical sequence offset distance;

[0085] Extract time-period power offset trends from power monitoring data. By performing time series analysis on power consumption data, we can obtain power fluctuation information for each time period. For example, if power consumption fluctuates from 0.5kW to 0.8kW during a certain time period, we need to calculate the power offset to be 0.3kW. Overlaying the power data with temperature and humidity disturbance data reveals power trends that may be related to thermal and humidity disturbances. This process involves correlating temperature fluctuations with power consumption changes to determine whether electrical equipment is experiencing offsets due to thermal and humidity disturbances. The total offset during a composite interference period is calculated by weighting the power offsets within each interference segment. For example, if the power offsets during a certain period are 0.3kW, 0.5kW, and 0.2kW, the total offset during the composite interference period is 0.3+0.5+0.2=1.0kW. This identifies segments with low overlap rates where the offsets consistently exceed a baseline duration. This operation depends on the overlap rate and baseline duration. Assuming the overlap rate is set to 10% and the reference duration is 5 minutes, when the overlapping area of two consecutive interference periods is less than 10% and the offset duration exceeds 5 minutes, the segment can be determined as the target segment. By screening segments with low overlap and offsets that continue to exceed the reference duration, the indoor electrical sequence offset distance can be effectively identified.

[0086] Specifically, if Figure 6 As shown in the figure, the steps of the indoor electrical hidden danger alarm node list are as follows:

[0087] S501: Based on the indoor electrical sequence offset distance, extract the offset event records within the continuous time period, count the number of offset event triggers in each section, and calculate the cumulative growth trend value of the events within the section. Identify the continuous location intervals with continuously increasing trigger frequency and obtain the electrical risk high-incidence section group;

[0088] Extract offset event records within consecutive time periods. Each offset event record contains offset changes in current, voltage, power, and other data for electrical equipment within a specific time period. By sequentially sorting the recorded time periods, multiple segments can be created. For example, if electrical data is analyzed over a 24-hour period, it can be divided into hourly segments. To count offset events for electrical equipment within each segment, the number of offset event triggers within each segment must be counted. Trigger counts refer to the number of times the current or voltage fluctuated significantly within a segment. For example, if the current value fluctuated by more than 10% five times within a segment, the trigger count for that segment is 5. Calculate the cumulative growth trend of the event within the segment by accumulating the trigger counts for each segment and calculating their trend. For example, if the trigger counts for three consecutive segments are 5, 7, and 9, respectively, the cumulative growth trend is (7-5)+(9-7)=4, indicating an increasing trend in trigger frequency. This analysis allows identification of consecutive intervals with a continuously increasing trigger frequency. For example, assuming that the number of triggers in certain sections has been increasing, then the sections constitute a high-risk electrical section group, which can be used as areas that require key monitoring. High-risk sections can be extracted and marked as a high-risk electrical section group for further risk assessment and monitoring.

[0089] S502: Based on the electrical risk high-incidence section group, the event trigger frequency, duration, and offset amplitude in the section are combined to select sections with a trigger frequency greater than the risk assessment classification threshold. The corresponding time position is labeled according to the trigger level, and a list of indoor electrical hazard alarm nodes is output;

[0090] Risk analysis combines the event trigger frequency, duration, and excursion within each segment. For example, a segment with a trigger frequency greater than the predetermined risk assessment classification threshold indicates that the number of event triggers within that segment exceeds the set safety threshold. For example, if the trigger frequency exceeds 10 times per hour, the segment is considered high-risk. The duration and excursion of each event also need to be considered. Duration refers to the length of time from the start to the end of the trigger event, while excursion refers to the magnitude of the change in electrical parameters (such as current and voltage). For example, if the current of a trigger event increases from 10 amps to 20 amps, the change is 10 amps, while duration refers to the length of time that the current change persists, assuming it is 5 minutes. Combining these factors, segments with a trigger frequency greater than the risk assessment classification threshold can be further identified. These segments represent unstable areas of electrical load, which can lead to equipment failure or safety hazards. The filtered segments are labeled according to their trigger levels. For example, a segment with a trigger frequency of more than 10 times per hour can be marked as "high risk," while a trigger frequency of 5 times per hour can be marked as "medium risk." In this way, the specific time location of each high-risk segment is marked, ultimately generating a list of indoor electrical hazard alarm nodes. This list can be used for further investigation and maintenance work to ensure safe equipment operation.

[0091] like Figure 7 As shown, an indoor electrical safety hazard intelligent detection system includes:

[0092] The data synchronization module is based on the data of the electrical equipment connection points in the house, including the current, voltage, and power values of the socket nodes. It sorts the time series according to the cycle, extracts the room temperature and humidity values within each cycle, analyzes the mapping relationship between time tags and parameters, and forms an electrical environment correlation data set;

[0093] Based on the electrical environment correlation data set, the hidden danger identification module extracts the power and current series of each power branch, compares the change amplitude and increase / decrease ratio of adjacent cycles, screens the abnormal fluctuation frequency band, and identifies the room temperature and humidity values in the corresponding time period to generate an abnormal load mutation feature group;

[0094] The fluctuation identification module extracts the current-to-voltage ratio of each data set based on the abnormal load mutation feature set, analyzes the fluctuation range of the ratio over a continuous period of time, determines whether it exceeds the operating boundary threshold, locates the over-limit section, and obtains the critical electrical parameter abnormal section;

[0095] The trajectory analysis module matches the power sequence and temperature and humidity sequence of each time period based on the critical electrical parameter anomaly section, extracts the high-frequency point identification behavior time trajectory, compares the offset with the stable operation behavior trajectory, identifies the trajectory variation characteristics, and establishes the electrical behavior offset path group;

[0096] The node warning module is based on the electrical behavior deviation path group, counts the number of abnormal fluctuation triggers within the path, analyzes the regional mapping relationship, performs grading on high-frequency points, locates the trigger concentration area, and outputs a list of indoor electrical hazard alarm nodes.

[0097] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An intelligent detection method for indoor electrical safety hazards, characterized in that: The following steps are involved: S1: Based on the data from the connection points of electrical equipment in the residence, including current, voltage, and power information, the environmental data of room temperature and humidity monitoring equipment within the same period is sorted and classified, and each value is annotated with a time tag to generate a synchronized dataset of indoor loads and environment; S2: Based on the indoor load and environment synchronization data set, extract the time series of power and current of the power shunt terminal group, analyze the change amplitude per unit time period, and compare the change rate of the upper and lower cycles. Filter the signal sequence with excessive change rate, analyze the abnormal correlation in combination with the environmental data, and obtain the fire risk load mutation fragment; S3: Calling the fire risk load mutation segment, extracting the current and voltage values in each segment, identifying the fluctuation range of the voltage-to-current ratio within a continuous period, marking it as a critical fluctuation when the fluctuation range exceeds the line operation reference boundary, and summarizing and outputting the voltage and current deviation abnormality segment; S4: Based on the abnormal voltage and current offset section, identify the power, temperature and humidity time series arrangement in the corresponding time period, select the high-frequency fluctuation points of power for behavior position mapping, and compare the temperature and humidity offsets with the stable operation behavior trajectory, and mark the intervals where the temperature and humidity offset amplitudes are greater than the normal section to obtain the indoor electrical sequence offset distance.

2. The intelligent detection method for indoor electrical safety hazards according to claim 1 is characterized in that: The indoor load and environment synchronization data set includes electrical node numerical labels, environmental parameter timestamps, and multi-source data alignment fields. The fire risk load mutation segment includes abnormal power change values, periodic change differences, and environmental coupling indicator factors. The voltage and current offset abnormality segment includes upper and lower fluctuation limits, ratio abnormality judgment points, and continuous abnormality identification marks. The indoor electrical sequence offset distance includes stable trajectory offset, high-frequency change location points, and operating status comparison features.

3. The intelligent detection method for indoor electrical safety hazards according to claim 1, characterized in that: The steps of synchronizing the data set between the indoor load and the environment are specifically as follows: S101: Based on the data of the connection points of the electrical equipment in the residence, the current value, voltage value, and power value of the socket node are extracted, the environmental parameters of the indoor temperature and humidity monitoring equipment are called, the two types of data are matched and sorted by time tags, and a corresponding set of electrical and environmental parameters is generated; S102: Based on the corresponding set of electrical and environmental parameters, perform interval discrimination on the current value and power value under the time tag, analyze the combined fluctuation amplitude between power and humidity, and select record segments that continuously exceed the current upper limit threshold and have abnormal combined fluctuation amplitude to obtain the abnormal load fluctuation interval value; S103: Based on the abnormal load fluctuation interval value, extract the interval voltage offset and room temperature change rate, combine the synchronization amplitude difference and duration, judge the abnormality of electrical load overload and poor contact, and generate an indoor load and environment synchronization data set.

4. The intelligent detection method for indoor electrical safety hazards according to claim 3 is characterized in that: The steps of the fire risk load mutation fragment are specifically as follows: S201: Based on the indoor load and environment synchronization data set, extract the current and power series of the power shunt terminal group, identify the cycle-to-cycle change rate, filter the power and current change rate records that exceed the fluctuation threshold, and generate the load sudden change fluctuation interval; S202: Based on the load mutation fluctuation range, call the room temperature and humidity of the corresponding time period, extract the temperature and humidity combination corresponding to the power, and determine whether the difference in the time period before the mutation exceeds the electrical safety threshold. Mark the abnormal linkage area and obtain the fire risk load mutation fragment.

5. The intelligent detection method for indoor electrical safety hazards according to claim 4 is characterized in that: The steps of the abnormal voltage and current deviation section are specifically as follows: S301: Calling the continuous current value and voltage value data in the fire risk load mutation segment, pairing them according to the same time period, calculating the ratio of each group, and generating a voltage-current ratio fluctuation sequence; S302: Based on the voltage-current ratio fluctuation sequence, extract the upper and lower boundaries of the ratio interval of consecutive time periods, compare them with the line operation reference value, identify the section exceeding the reference value, determine the start and end time of the abnormal section and the ratio fluctuation range, mark the fluctuation period that meets the conditions as a critical section, and obtain the ratio critical fluctuation range; S303: According to the critical fluctuation range of the ratio, extract the current value and voltage value of the corresponding period in the mutation segment, analyze the offset amplitude, summarize the offset combination of the critical section, and output the voltage and current offset abnormal section.

6. The intelligent detection method for indoor electrical safety hazards according to claim 5, characterized in that: The steps of indoor electrical sequence offset distance are specifically as follows: S401: Extracting power values, temperature, and humidity sequences within the voltage and current deviation abnormality section, analyzing the instantaneous deviation rate of power change, extracting mutation points, and recording the synchronous positions in the multi-source sequence to obtain indoor high-frequency abnormal behavior nodes; S402: Based on the indoor high-frequency abnormal behavior nodes, the corresponding temperature and humidity value change trajectories are compared with the baseline trajectory of the steady-state segment, the range of behavior points where the continuous trajectory deviation exceeds the thermal and humidity stability threshold is identified, the deviation direction and duration characteristics are located, and the indoor thermal and humidity deviation interference segment is established; S403: Extract the power offset trend and temperature and humidity disturbance amount during the period according to the indoor thermal and humidity offset interference section, calculate the total offset amount during the composite interference period, identify the section with low overlap rate and where the offset continuously exceeds the reference time length, and obtain the indoor electrical sequence offset distance.

7. The intelligent detection method for indoor electrical safety hazards according to claim 1, characterized in that: The method further comprises step S5: S5: Based on the indoor electrical sequence offset distance, the triggering frequency of risk events in the continuous section is counted, and the high-incidence areas are located according to the cumulative frequency trend. A corresponding level label is assigned to each area, and a list of indoor electrical hidden danger alarm nodes is output; The indoor electrical hidden danger alarm node list includes risk level partitions, event frequency thresholds, and alarm node identification numbers.

8. The intelligent detection method for indoor electrical safety hazards according to claim 7, characterized in that: The steps of the indoor electrical hidden danger alarm node list are specifically as follows: S501: Based on the indoor electrical sequence offset distance, extract the offset event records within a continuous time period, count the number of offset event triggers in each section, and calculate the cumulative growth trend value of the event within the section, identify the continuous position intervals with continuously increasing trigger frequency, and obtain the electrical risk high-incidence section group; S502: Based on the electrical risk high-incidence section group, combined with the event trigger frequency, duration and offset amplitude in the section, filter the sections whose trigger frequency is greater than the risk assessment classification threshold, label the corresponding time position according to the trigger level, and output the indoor electrical hazard alarm node list.

9. An indoor electrical safety hazard intelligent detection system, characterized in that: The system is used to implement the intelligent detection method for indoor electrical safety hazards according to any one of claims 1 to 8, and the system includes: The data synchronization module is based on the data of the electrical equipment connection points in the house, including the current, voltage, and power values of the socket nodes. It sorts the time series according to the cycle, extracts the room temperature and humidity values within each cycle, analyzes the mapping relationship between time tags and parameters, and forms an electrical environment correlation data set; The hidden danger identification module extracts the power and current series of each power branch based on the electrical environment correlation data set, compares the change amplitude and increase / decrease ratio of adjacent cycles, screens the abnormal fluctuation frequency band, and identifies the room temperature and humidity values of the corresponding time period to generate an abnormal load mutation feature group; The fluctuation discrimination module extracts the current and voltage values of each data set based on the abnormal load mutation feature group, analyzes the fluctuation range of the voltage-to-current ratio over a continuous time, determines whether it exceeds the operating boundary threshold, locates the over-limit section, and obtains the critical electrical parameter abnormal section; The trajectory analysis module matches the power sequence and temperature and humidity sequence of each time period based on the critical electrical parameter anomaly section, extracts the high-frequency power fluctuation points to identify the behavior time trajectory, and compares the temperature and humidity offsets with the stable operation behavior trajectory to identify the behavior time trajectory variation characteristics and establish the electrical behavior offset path group; The node warning module is based on the electrical behavior deviation path group, counts the number of abnormal fluctuation triggers in the path, analyzes the regional mapping relationship, performs level classification on high-frequency points, locates the trigger concentration area, and outputs a list of indoor electrical hidden danger alarm nodes.

Images