A method and system for protecting human body from electric shock based on multi-parameter fusion

Abstract

This invention belongs to the field of electrical safety technology, specifically relating to a method and system for protecting against electric shock based on multi-parameter fusion. It extracts high-frequency harmonic components, voltage jump slope, and magnetic field strength fluctuations from the residual current waveform to form multi-dimensional feature parameters. The weights of these parameters are dynamically adjusted according to their instantaneous change rates, generating a weighted feature vector. A comprehensive criterion value is then calculated using a preset rule base and compared with a dynamic threshold to determine whether to trigger the circuit breaker. This method, through the fusion analysis of multiple physical features, improves the system's recognition capability in complex electromagnetic environments, effectively reduces the probability of malfunctions caused by external interference, improves the accuracy and stability of the circuit breaker's operation, and ensures electrical safety and power supply continuity.

Description

Technical Field

[0001] This invention belongs to the field of electrical safety technology, specifically relating to a method and system for protecting human body from electric shock based on multi-parameter fusion. Background Technology

[0002] In the field of electrical safety protection, traditional residual current circuit breakers (RCCBs) mainly rely on the detection of a single parameter—residual current—to determine whether an electric shock or line leakage has occurred. When the detected residual current exceeds a set threshold, the circuit breaker is triggered to cut off the power supply, thereby preventing electric shock accidents.

[0003] However, in practical applications, especially in environments with strong electromagnetic interference (such as industrial sites with frequent start-stop cycles of variable frequency equipment and high-power motors), traditional residual current circuit breakers (RCCBs) are easily affected by external magnetic fields and high-frequency noise, leading to misjudgments of leakage current and unnecessary tripping. Such malfunctions not only affect the continuity of power supply but may also cause production interruptions and safety hazards.

[0004] While existing technologies have attempted to reduce the false alarm rate by adding filtering circuits or using fixed threshold compensation mechanisms, they rely solely on a single feature parameter and lack adaptability to complex interference environments, making it difficult to effectively improve judgment accuracy. Summary of the Invention

[0005] The purpose of this invention is to provide a human body electric shock protection method and system based on multi-parameter fusion. By fusing and analyzing multiple physical characteristics, the system's identification ability in complex electromagnetic environments is improved, effectively reducing the probability of malfunction caused by external interference, improving the accuracy and stability of circuit breaker operation, and ensuring electrical safety and power supply continuity, thereby solving the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for protecting the human body from electric shock based on multi-parameter fusion, comprising the following steps:

[0007] The high-frequency harmonic components, voltage jump slope, and magnetic field strength fluctuation value of the residual current waveform are extracted to form multi-dimensional feature parameters. According to the instantaneous change rate of the multi-dimensional feature parameters, the weight coefficients of each parameter are dynamically adjusted to generate a weighted feature vector. The weighted feature vector is input into a preset fusion rule library to calculate a comprehensive criterion value. The comprehensive criterion value is compared with a dynamic threshold range. If the threshold is exceeded, the circuit breaker is triggered to operate; otherwise, the energized state is maintained.

[0008] Preferably, the high-frequency harmonic components of the residual current waveform, the voltage jump slope, and the magnetic field strength fluctuation value are extracted to form multi-dimensional characteristic parameters, including:

[0009] The acquired current signal is bandpass filtered to separate the high-frequency part with a frequency higher than 300Hz, which is denoted as the first intermediate signal;

[0010] Perform time-domain difference operation on the first intermediate signal to obtain the sum of the absolute values ​​of the differences between adjacent periods, and mark it as the waveform change index;

[0011] The change in the spatial magnetic field is obtained by using a Hall sensor, and the ratio of the difference between adjacent time points to the waveform abrupt change index is calculated as a reference index for the intensity of magnetic field interference.

[0012] Preferably, the acquired current signal is bandpass filtered to separate the high-frequency component with a frequency higher than 300Hz, including:

[0013] The original current signal is converted into a preliminary high-frequency signal by a passive second-order high-pass filter circuit composed of inductors and capacitors. The amplitude of the preliminary high-frequency signal is then normalized to obtain the normalized high-frequency component.

[0014] A fixed threshold is set, and the portion of the normalized high-frequency component whose amplitude exceeds the threshold is retained, while the rest are set to zero, thus obtaining the high-frequency harmonic components.

[0015] Preferably, performing time-domain difference operations on the first intermediate signal to obtain the sum of the absolute values ​​of the differences between adjacent periods includes:

[0016] The high-frequency harmonic components are divided according to the power frequency period, and signal segments of two consecutive period segments are extracted.

[0017] The difference between the values ​​at corresponding time points of the signal segment and the absolute value are obtained to obtain the difference sequence;

[0018] The difference sequence is summed over the period and recorded as a waveform mutation index, which is used to represent the degree of waveform mutation.

[0019] Preferably, the change in the spatial magnetic field is obtained through a Hall sensor, including:

[0020] A triaxial Hall sensor is installed inside the circuit breaker to collect magnetic field intensity components in the X, Y, and Z directions respectively. The magnetic field intensity components are then combined to obtain the total magnetic field intensity.

[0021] The total magnetic field strength is collected at fixed time intervals, and the difference between adjacent time points is calculated as the change in magnetic field at the current time.

[0022] Preferably, the weighting coefficients of each parameter are dynamically adjusted based on the instantaneous change rate of the multidimensional feature parameters to generate a weighted feature vector, including:

[0023] Calculate the differences in the high-frequency harmonic components, voltage jump slope, and magnetic field interference intensity reference values ​​at adjacent time points;

[0024] The normalized rate of change is obtained by comparing the difference in change with a set benchmark value.

[0025] The normalized rate of change is used as a weighting factor, and then multiplied by the original values ​​of the corresponding parameters in sequence to form a weighted feature vector.

[0026] Preferably, the normalized rate of change is used as a weighting factor, and multiplied sequentially by the original values ​​of the corresponding parameters to form a weighted feature vector, including:

[0027] Obtain real-time measurements of high-frequency harmonic components, voltage jump slope, and magnetic field interference intensity reference indicators at the current moment;

[0028] Multiply the weighting factor by the original value of the corresponding parameter to obtain the weighted term;

[0029] Each of the weighted items is subjected to a limit, and a maximum value is set. If an item exceeds the maximum value, it is set to the maximum value.

[0030] The weighted terms after amplitude limiting are combined into triples, which are then output as the weighted feature vector at the current time.

[0031] Preferably, the weighted feature vector is input into a preset fusion rule base to calculate a comprehensive criterion value, including:

[0032] Three sets of linear decision boundaries are defined, each corresponding to one of the three components in the weighted feature vector;

[0033] Each component of the weighted feature vector is compared with its corresponding boundary. If a component is greater than its corresponding boundary, the output flag is set to 1; otherwise, it is set to 0.

[0034] A logical code is generated based on the combination of flag bits, and the corresponding comprehensive criterion value is obtained by looking up the table based on the logical code for subsequent action judgment.

[0035] Preferably, comparing the comprehensive criterion value with the dynamic threshold range, and triggering the circuit breaker operation if the threshold is exceeded, includes:

[0036] Set a base threshold and adjust the offset according to the current environmental interference level to generate a dynamic threshold upper limit;

[0037] The comprehensive criterion value is compared with the upper limit of the dynamic threshold. If it exceeds the limit, it is determined to be an abnormal state.

[0038] If the abnormal condition is detected, the actuator will be activated after a delay to drive the circuit breaker to trip and disconnect the line.

[0039] Otherwise, maintain the existing power-on state and continue monitoring the data for the next cycle.

[0040] On the other hand, this invention proposes a human body electric shock protection system based on multi-parameter fusion, comprising:

[0041] The multidimensional feature parameter extraction module is used to extract the high-frequency harmonic components, voltage jump slope, and magnetic field strength fluctuation value of the residual current waveform to form multidimensional feature parameters.

[0042] The dynamic weight adjustment module is used to dynamically adjust the weight coefficients of each parameter according to the instantaneous change rate of the multidimensional feature parameters, and generate a weighted feature vector.

[0043] The comprehensive criterion calculation module is used to input the weighted feature vector into a preset fusion rule base and calculate the comprehensive criterion value;

[0044] The circuit breaker action control module is used to compare the comprehensive criterion value with the dynamic threshold range. If the threshold is exceeded, the circuit breaker is triggered to operate; otherwise, the energized state is maintained.

[0045] Technical effects and advantages of the present invention: The human body electric shock protection method and system based on multi-parameter fusion proposed in this invention has the following advantages compared with the prior art:

[0046] This invention extracts high-frequency harmonic components, voltage jump slope, and magnetic field strength fluctuations from the residual current waveform to form multi-dimensional feature parameters. The weights of these parameters are dynamically adjusted based on their instantaneous change rates to generate a weighted feature vector. A comprehensive criterion value is then calculated using a preset rule base and compared with a dynamic threshold to determine whether to trigger the circuit breaker. This method, through the fusion analysis of multiple physical features, improves the system's recognition capability in complex electromagnetic environments, effectively reduces the probability of malfunctions caused by external interference, enhances the accuracy and stability of the circuit breaker's operation, and ensures electrical safety and power supply continuity. Attached Figure Description

[0047] Figure 1 This is a flowchart of the human body electric shock protection method based on multi-parameter fusion according to the present invention;

[0048] Figure 2 This is a block diagram of the human body electric shock protection system based on multi-parameter fusion according to the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] This invention provides a method for protecting human body from electric shock based on multi-parameter fusion. This method is applicable to residual current circuit breakers and miniature residual current circuit breakers, and may include products such as smart switches and smart circuit breakers. This embodiment uses a circuit breaker as an example for illustration.

[0051] This invention provides, for example Figure 1 The method for protecting human body from electric shock based on multi-parameter fusion, as shown, includes the following steps:

[0052] Step 1: Extract the high-frequency harmonic components, voltage jump slope, and magnetic field strength fluctuation values ​​of the residual current waveform to form multi-dimensional characteristic parameters; specifically including:

[0053] The acquired current signal A is bandpass filtered to separate the high-frequency component with a frequency higher than 300Hz, denoted as C. Specifically, the original current signal A is passed through a passive second-order high-pass filter circuit composed of inductor L and capacitor C to output a preliminary high-frequency signal. ;right After amplitude normalization, we obtain By setting a fixed threshold Th, the portion of C with amplitude exceeding Th is retained, while the rest is set to zero, thus obtaining the high-frequency harmonic components. .

[0054] Indicates the initial high-frequency signal Amplitude normalization is performed to eliminate the influence of differences in the original amplitude of the current signal, ensuring comparability of feature extraction under different operating conditions. Indicates taking The maximum absolute value within a period is used as the reference value for normalization to ensure that the peak value of the normalized signal is 1.

[0055] In environments with strong electromagnetic interference, the amplitude of a current signal may fluctuate significantly due to external factors. Directly using the original amplitude for subsequent analysis may lead to misjudgment. Therefore, by dividing the signal by its maximum absolute value, its dynamic range is compressed to the [-1, 1] interval, thus achieving amplitude standardization, preserving the signal waveform change trend, and removing the influence of dimensions and amplitude.

[0056] Perform time-domain difference operations on C to obtain the sum of the absolute values ​​of the differences between adjacent periods, denoted as... This is used to reflect the severity of mutations; specifically, it includes: Segment the signal according to the power frequency period T, and extract signal segments from two consecutive period segments. and ;right and The difference sequence is obtained by subtracting the values ​​at corresponding time points and taking the absolute value. This formula is used to extract the difference information between two adjacent period waveforms, and obtains the absolute value of the difference at each moment by comparing point by point.

[0057] in, : The normalized high-frequency signal within the first period segment; The normalized high-frequency signal in the second period immediately following it; The absolute value of the waveform difference between two cycles at the same point in time is used to measure local waveform abrupt changes.

[0058] When a person experiences an electric shock or a circuit leaks current, the current waveform often exhibits abrupt changes or asymmetry. By comparing two consecutive power frequency cycles (e.g., 20ms at 50Hz) of high-frequency harmonic signals, the waveform distortion characteristics caused by the fault can be detected. Using absolute values ​​eliminates directional effects, focusing only on the amplitude of the change.

[0059] Sum D over the period T, denoted as... This formula is used to represent the degree of waveform abrupt change. It accumulates the difference sequence D over a complete period to obtain a comprehensive index reflecting the overall degree of waveform abrupt change. The purpose is to aggregate point-by-point difference information into a quantifiable and assessable value, facilitating subsequent comparison with a set threshold to determine whether an anomaly has occurred. A larger D... a This indicates that the current waveform is significantly different from the previous cycle, which may be due to a sudden change caused by an electric shock event or electromagnetic interference.

[0060] The change in the spatial magnetic field is obtained by using a Hall sensor. Calculate the difference between adjacent time points and The ratio of is denoted as This serves as a reference indicator for magnetic field interference intensity; specifically, it includes installing a triaxial Hall effect sensor inside the circuit breaker to collect the magnetic field intensity components in the X, Y, and Z directions, respectively. ;right Perform a synthesis operation to obtain the total magnetic field strength. This formula is used to synthesize the magnetic field component signals collected by the triaxial Hall sensor into the total magnetic field strength in space. Since the magnetic field is a vector and has directionality, the magnetic field value in a single direction alone cannot fully reflect the true strength of the magnetic field in space. By calculating the vector magnitudes of the magnetic field components in three orthogonal directions (X, Y, Z) using this formula, the total magnetic field strength of the space where the circuit breaker is located at the current moment can be obtained.

[0061] B is sampled at fixed time intervals Δt, and the difference between adjacent time intervals is calculated. This is used as the change in magnetic field at the current moment. This formula is used to extract the change in magnetic field strength between adjacent moments, i.e., the rate of change of the magnetic field over time. During the operation of electrical equipment, electromagnetic interference or sudden load changes can cause fluctuations in the spatial magnetic field. By periodically sampling and calculating the difference in magnetic field strength between adjacent moments, these transient magnetic field disturbances can be effectively captured, providing a basis for subsequent judgment on whether malfunctions are caused by external interference.

[0062] formula Vector synthesis from the three-axis magnetic field components to the total magnetic field strength was achieved, and This is used to extract the characteristics of magnetic field changes over time. Together, these two methods form the basis for sensing the external electromagnetic environment, providing key inputs for subsequent multi-parameter fusion analysis, thereby improving the stability and accuracy of the human body electric shock protection system.

[0063] Step 2: Based on the instantaneous change rate of the multidimensional feature parameters, dynamically adjust the weight coefficients of each parameter to generate a weighted feature vector; specifically including:

[0064] Calculate the high-frequency harmonic components separately Voltage jump slope Magnetic field fluctuations The difference in change between adjacent time points is denoted as ;

[0065] Will Each with the set reference value Perform a ratio calculation to obtain the normalized rate of change. By normalizing the instantaneous changes of multidimensional features, they are transformed into normalized rates of change with a uniform scale. These rates of change not only reflect the importance of each feature in the current state, but also provide a basis for subsequent weighted fusion and comprehensive criterion calculations, thereby improving the intelligent recognition capability and operational reliability of the human body electric shock protection system.

[0066] Will As weighting factors, they are successively multiplied by the original values ​​of the corresponding parameters to form a weighted feature vector. This formula is used to multiply multidimensional physical characteristics (high-frequency harmonic components, voltage jump slope, magnetic field interference index) with their corresponding normalized rates of change, forming a weighted feature vector. .

[0067] use (i.e., the ratio of the instantaneous rate of change of each feature to the benchmark value) is used as a weighting factor; for the original features Weighted processing is performed to construct a weighted feature vector that reflects the "importance" of each feature in the current operating state. In this way, the system can dynamically highlight those features that change drastically at the current moment, thereby more accurately identifying whether it is an electric shock event or other abnormal state.

[0068] Specifically, this includes: acquiring the high-frequency harmonic components at the current moment. Voltage jump slope Magnetic field interference index Real-time measurement values; and Multiply to obtain the weighted term. Similarly, ;right Each item is subjected to a limiting process, with a maximum value E set. If any item exceeds E, it is set to E. The weighted items after limiting are then combined into triples. This is the weighted feature vector output at the current moment. This expression is a summary of the results after limiting the weighting terms obtained in the previous step, representing the final weighted feature vector output. This limiting mechanism enhances the robustness of the system and avoids individual features from having an excessive impact on the overall judgment.

[0069] Step 3: Input the weighted feature vector into a preset fusion rule base and calculate the comprehensive criterion value; specifically including:

[0070] Three sets of linear decision boundaries are defined, namely the threshold. Used to correspond to the weighted feature vector The three components; for Each component is compared with its corresponding boundary. If a component is greater than its corresponding threshold, a flag bit is output. ,otherwise ;according to Combinatorial generation logic code This serves as the discrimination mode identifier; the corresponding comprehensive criterion value J is obtained by looking up the table based on Q, and is used for subsequent action judgment. This formula is used to combine the three binary flag bits. Each value is either 0 or 1 and they are combined to form a unique logical code Q, which serves as the discrimination pattern identifier.

[0071] The first component (such as the high-frequency harmonic term) Is it greater than the decision boundary? If yes, it is 1; otherwise, it is 0. Second component (such as voltage mutation term) Is it greater than the decision boundary? If yes, it is 1; otherwise, it is 0. The third component (such as the magnetic field interference term) Is it greater than the decision boundary? If yes, it is 1; otherwise, it is 0.

[0072] This formula is a mapping from a three-bit binary number to a decimal number, where each bit represents whether a component in the weighted feature vector exceeds a set threshold. This encoding method compresses multi-dimensional feature states into a single integer value, facilitating rapid lookup of the corresponding comprehensive criterion value J.

[0073] This method has the following advantages:

[0074] The structure is clear: the three sets of comparison results correspond to three binary codes;

[0075] Unique encoding: Representable Different combinations of states;

[0076] Facilitates rule matching: Each code corresponds to a fault / interference mode, and corresponding criterion values ​​or action strategies can be preset;

[0077] Improve judgment efficiency: Avoid complex calculations and directly obtain the judgment basis by looking up the table through the code.

[0078] Step 4: Compare the comprehensive criterion value with the dynamic threshold range. If the value exceeds the threshold, trigger the circuit breaker; otherwise, maintain the energized state. Specifically, this includes:

[0079] Set a base threshold The offset G is adjusted according to the current environmental interference level to generate a dynamic threshold upper limit. ; Combine the comprehensive criterion value J with Compare, if J> This is then determined to be an abnormal state; this formula is used to generate a dynamic upper threshold. This serves as the basis for determining whether the circuit breaker has been triggered.

[0080] In electrical protection systems, using fixed threshold values ​​for judgment can easily lead to malfunctions in complex electromagnetic interference environments. To address this issue, a basic threshold value is introduced. The threshold upper limit is dynamically adjusted based on the current environmental interference level, along with the offset G, to make the system more adaptable and stable.

[0081] When an abnormal condition is detected, the actuator is activated after a delay to drive the circuit breaker to trip and disconnect the line. Specifically, this includes: when an abnormal condition is detected, starting a timer / counter and setting a delay time H; continuously monitoring the comprehensive criterion value J for subsequent cycles during period H; if J > 0.05 consecutively N times... If the tripping condition is met, a control signal is output to the electromagnetic drive device, causing the moving iron core to shift and the mechanical contacts of the circuit breaker to separate. After tripping, the actuator is locked until it is manually reset before it can be put back into operation. Otherwise, the original energized state is maintained, and data for the next cycle is monitored.

[0082] On the other hand, this invention proposes a human body electric shock protection system based on multi-parameter fusion, such as... Figure 2 As shown, it includes:

[0083] The multidimensional feature parameter extraction module is used to extract the high-frequency harmonic components, voltage jump slope, and magnetic field strength fluctuation value of the residual current waveform to form multidimensional feature parameters.

[0084] The dynamic weight adjustment module is used to dynamically adjust the weight coefficients of each parameter according to the instantaneous change rate of the multidimensional feature parameters, and generate a weighted feature vector.

[0085] The comprehensive criterion calculation module is used to input the weighted feature vector into a preset fusion rule base and calculate the comprehensive criterion value;

[0086] The circuit breaker action control module is used to compare the comprehensive criterion value with the dynamic threshold range. If the threshold is exceeded, the circuit breaker is triggered to operate; otherwise, the energized state is maintained.

[0087] In addition, the modules described above are also used to implement other steps of the aforementioned multi-parameter fusion-based human body electric shock protection method, as shown below:

[0088] Suppose a distribution box is equipped with a circuit breaker with intelligent identification function to detect whether an electric shock has occurred in real time. The system continuously collects current signals, voltage changes, and spatial magnetic field information, and determines whether to trigger a tripping action through multi-parameter fusion analysis.

[0089] Step 1: Extract multidimensional feature parameters

[0090] Acquire current signal A. Assume the acquired original current signal is: A = [0.5, 0.6, 0.8, 1.2, 0.9, 0.4, 0.3, 0.2].

[0091] Bandpass filtering is used to obtain the high-frequency component C_p. A passive second-order high-pass filter circuit consisting of an inductor L and a capacitor C is used to retain components with frequencies higher than 300Hz.

[0092] Preliminary high-frequency signal obtained: =[0.2,0.3,0.5,0.7,0.6,0.2,0.1,0.05];

[0093] Normalization process: Calculate the maximum absolute value: =0.7, normalized result: C=[0.286,0.429,0.714,1.0,0.857,0.286,0.143,0.071].

[0094] Set the threshold Th=0.5 to extract high-frequency harmonic components. Set points below Th to zero: =[0,0,0.714,1.0,0.857,0,0,0].

[0095] Time-domain difference operation yields waveform abrupt change index. ,Will Divide the system into two consecutive periodic segments based on the power frequency period T: =[0,0,0.714,1.0]、 =[0.857,0,0,0];

[0096] Difference sequence D = [0.857, 0, 0.714, 1.0]; summing the results gives... :D_a=0.857+0+0.714+1.0=2.571.

[0097] Obtaining magnetic field strength fluctuations The triaxial Hall sensor measured: Total combined magnetic field strength B: =0.3.

[0098] The magnetic field at the previous moment was =0.25, then the change in magnetic field : =0.3-0.25=0.05, thus obtaining the reference index for magnetic field interference intensity. : =0.05 / 2.571=0.0194.

[0099] Step 2: Generate the weighted feature vector P_f

[0100] Obtain the feature value at the current time: ;

[0101] Calculate the instantaneous rate of change: ;

[0102] Characteristics of the previous cycle: ;

[0103] Difference in change: ;

[0104] Normalized rate of change: Set baseline value: ;

[0105] Normalization:

[0106] =0.143 / 0.2=0.715;

[0107] =0.05 / 0.1=0.5;

[0108] =0.0044 / 0.01=0.44;

[0109] Weighted combination generates a weighted feature vector P_f, with the following weighting terms:

[0110] =0.715 * 0.857 = 0.613;

[0111] =0.5 * 0.3 = 0.15;

[0112] =0.44 * 0.0194 = 0.0085;

[0113] Limiting (E=1):

[0114] =0.613 (≤1 → unchanged);

[0115] =0.15;

[0116] =0.0085;

[0117] Output weighted feature vector:

[0118] =(0.613,0.15,0.0085).

[0119] Step 3: Calculate the comprehensive criterion value J

[0120] Set decision boundaries: ;

[0121] Compare whether each component exceeds the limit:

[0122] ;

[0123] ;

[0124] ;

[0125] Generate logical code Q: ;

[0126] To obtain the comprehensive criterion value J, refer to the preset rule table. Q=6 corresponds to J=0.82.

[0127] Step 4: Dynamic Threshold Comparison and Action Control

[0128] Set the base threshold and offset: =0.75, G=0.05 (based on the current environmental interference level);

[0129] Calculate the upper limit of the dynamic threshold : =0.75 + 0.05 = 0.80;

[0130] Compare J with J=0.82> =0.80 → This is considered an abnormal state;

[0131] Activate the delay confirmation mechanism: Set the delay time H = 3 cycles, and N = 2 consecutive exceedances;

[0132] The current cycle meets the conditions; continue monitoring the next cycle.

[0133] If J> appears again in subsequent cycles If the number of trips reaches N, then the tripping action will be executed.

[0134] Output control signals to the electromagnetic drive device to push the iron core to move and disconnect the mechanical contacts;

[0135] After the trip is completed, the actuator is locked and manual reset is required to restore power.

[0136] This embodiment fully simulates an electric shock protection process in a real-world application scenario, including: signal acquisition and filtering, feature extraction and normalization, dynamic weight adjustment and weighted fusion, logical encoding and rule matching, dynamic threshold comparison and delayed confirmation. The entire process demonstrates the advantages of multi-parameter fusion judgment, improving the system's stability and accuracy in complex electromagnetic interference environments, effectively preventing malfunctions, and ensuring electrical safety.

[0137] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A human body electric shock protection method based on multi-parameter fusion, characterized in that, The method comprises the following steps: extracting high-frequency harmonic components, voltage mutation slope and magnetic field intensity fluctuation value of the residual current waveform to form multi-dimensional characteristic parameters; dynamically adjusting weight coefficients of each parameter according to instantaneous change rates of the multi-dimensional characteristic parameters to generate a weighted characteristic vector; inputting the weighted characteristic vector into a preset fusion rule library to calculate a comprehensive criterion value; comparing the comprehensive criterion value with a dynamic threshold range, triggering a circuit breaker action if the threshold is exceeded, otherwise maintaining a power-on state.

2. The multi-parameter fusion based human body electric shock protection method according to claim 1, characterized in that, extracting high-frequency harmonic components, voltage mutation slope and magnetic field intensity fluctuation value of the residual current waveform to form multi-dimensional characteristic parameters, comprising: band-pass filtering the collected current signal to separate the high-frequency part with a frequency higher than 300Hz, marked as a first intermediate signal; performing time domain difference operation on the first intermediate signal to obtain the sum of absolute values of adjacent period difference values, marked as a waveform mutation index; acquiring the spatial magnetic field change amount through a Hall sensor, and calculating the ratio of the adjacent time difference value and the waveform mutation index as a magnetic field interference intensity reference index.

3. The multi-parameter fusion based human touch protection method according to claim 2, characterized in that, band-pass filtering the collected current signal to separate the high-frequency part with a frequency higher than 300Hz, comprising: converting the original current signal into a preliminary high-frequency signal through a passive second-order high-pass filter circuit composed of inductance and capacitance, and performing amplitude normalization processing on the preliminary high-frequency signal to obtain a normalized high-frequency component; setting a fixed threshold, retaining the part of the normalized high-frequency component with an amplitude exceeding the threshold, and setting the rest to zero to obtain the high-frequency harmonic component.

4. The multi-parameter fusion based human body electric shock protection method according to claim 2, characterized in that, performing time domain difference operation on the first intermediate signal to obtain the sum of absolute values of adjacent period difference values, comprising: dividing the high-frequency harmonic component by power frequency period to extract signal segments of two continuous period segments; differencing the values of the signal segments at corresponding time points and taking absolute values to obtain a difference sequence; cumulatively summing the difference sequence within the period to obtain the waveform mutation index for representing the waveform mutation degree.

5. The multi-parameter fusion based human body electric shock protection method according to claim 2, characterized in that, acquiring the spatial magnetic field change amount through a Hall sensor, comprising: installing a three-axis Hall induction element inside the circuit breaker to collect X, Y and Z direction magnetic field intensity components respectively, performing synthetic operation on the magnetic field intensity components to obtain the total magnetic field intensity; collecting the total magnetic field intensity every fixed time interval to calculate the adjacent time difference value as the current time magnetic field change amount.

6. The multi-parameter fusion based human touch protection method according to claim 1, wherein, dynamically adjusting weight coefficients of each parameter according to instantaneous change rates of the multi-dimensional characteristic parameters to generate a weighted characteristic vector, comprising: calculating the change difference values of the high-frequency harmonic component, the voltage mutation slope and the magnetic field interference intensity reference index at adjacent time points respectively; performing ratio operation on the change difference values and a set reference value to obtain a normalized change rate; multiplying the normalized change rate by the original values of the corresponding parameters in turn as weight factors to combine into a weighted characteristic vector.

7. The multi-parameter fusion based human touch protection method according to claim 6, characterized in that, multiplying the normalized change rate by the original values of the corresponding parameters in turn as weight factors to combine into a weighted characteristic vector, comprising: obtaining real-time measurement values of the high-frequency harmonic component, the voltage mutation slope and the magnetic field interference intensity reference index at the current time; multiplying the weight factors by the original values of the corresponding parameters to obtain weighted items; The weighted items are respectively subjected to amplitude limiting processing, and a maximum value is set, and if an item exceeds the maximum value, the maximum value is set; The amplitude-limited weighted items are combined into a triple, which is output as a weighted feature vector at the current time.

8. The multi-parameter fusion based human touch protection method according to claim 1, wherein, The weighted feature vector is input into a preset fusion rule library to calculate a comprehensive criterion value, including: Three sets of linear decision boundaries are set, respectively corresponding to the three components in the weighted feature vector; The components of the weighted feature vector are respectively compared with the corresponding boundaries, and if a component is greater than the corresponding boundary, the flag bit is output as 1, otherwise as 0; According to the flag bit combination, a logic code is generated, and according to the logic code, a corresponding comprehensive criterion value is obtained from a table, which is used for subsequent action judgment.

9. The multi-parameter fusion based human touch protection method according to claim 1, wherein, The comprehensive criterion value is compared with a dynamic threshold range, and if it exceeds the threshold, a circuit breaker action is triggered, including: A basic threshold is set, and an offset is adjusted according to the current environmental interference level to generate a dynamic threshold upper limit; The comprehensive criterion value is compared with the dynamic threshold upper limit, and if it exceeds, it is determined as an abnormal state; In the abnormal state, a time delay is started to execute an actuator to drive the circuit breaker to trip and cut off the circuit; Otherwise, the original power-on state is maintained, and the next cycle of data is continuously monitored.

10. A multi-parameter fusion based human body electric shock protection system for implementing the method of any one of claims 1-9, characterized by, Including: A multi-dimensional feature parameter extraction module is used to extract high-frequency harmonic components, voltage mutation slopes and magnetic field intensity fluctuation values of the residual current waveform to form multi-dimensional feature parameters; A dynamic weight adjustment module is used to dynamically adjust the weight coefficients of each parameter according to the instantaneous change rate of the multi-dimensional feature parameters to generate a weighted feature vector; A comprehensive criterion calculation module is used to input the weighted feature vector into a preset fusion rule library to calculate a comprehensive criterion value; A circuit breaker action control module is used to compare the comprehensive criterion value with a dynamic threshold range, and if it exceeds the threshold, a circuit breaker action is triggered, otherwise the power-on state is maintained.

Images