A load type identification method based on a circuit breaker intelligent algorithm

Abstract

This invention discloses a load type identification method based on a circuit breaker intelligent algorithm. The method includes collecting various electrical parameters of the load, such as transient harmonic signals and temperature drift data, through a detection unit. After denoising and normalization preprocessing, a three-level progressive feature calculation is used to obtain the transient harmonic attenuation coefficient, electromagnetic coupling interference correction coefficient, and a comprehensive load characteristic discrimination value. The result is then compared with a load type feature database. This method integrates multiple key influencing factors and uses a progressive algorithm to collaboratively eliminate interference, solving the problem of inaccurate identification in existing methods and achieving accurate load type identification. It is applicable to industrial and residential power scenarios.

Description

Technical Field

[0001] This invention relates to the field of circuit breaker control technology, and more specifically to a load type identification method based on a circuit breaker intelligent algorithm. Background Technology

[0002] In power system operation, load type identification is a core prerequisite for circuit breaker precise control, fault early warning, and optimal allocation of power resources. Existing load type identification methods largely rely on conventional static electrical parameters such as RMS voltage, RMS current, and power factor, completing identification through simple threshold comparisons or single algorithm models. However, in real-world power scenarios, transient harmonic signals are generated during load startup and operation. These signals contain information about the load's essential characteristics but are susceptible to temperature changes in the internal conductive circuit of the circuit breaker. Temperature drift distorts the amplitude and attenuation characteristics of the harmonic signals. Simultaneously, electromagnetic coupling exists between the load and the circuit breaker, and the coupling strength fluctuates with changes in the load's operating state, further interfering with the accuracy of the characteristic parameters. Existing technologies do not fully consider the mutual influence between transient harmonic signals, temperature drift, and electromagnetic coupling strength, relying solely on conventional static parameters for identification. This results in insufficient accuracy under complex operating conditions, failing to meet the high-precision load type identification requirements of power systems.

[0003] Based on the above problems, there is an urgent need for a technical solution that can integrate multiple key influencing factors, eliminate interference, and accurately identify them. Summary of the Invention

[0004] The purpose of this invention is to provide a load type identification method based on a circuit breaker intelligent algorithm, comprising: collecting electrical parameter data during load operation through the detection unit of the circuit breaker; performing feature processing on the collected electrical parameter data; and completing load type identification based on the processed feature parameters. The feature processing includes:

[0005] S1: The detection unit collects the transient harmonic signal, temperature drift data, electromagnetic coupling strength data, effective voltage value, effective current value, power factor and current distortion rate of the load.

[0006] S2: Perform preprocessing operations such as denoising and normalization on all collected data;

[0007] S3: Based on the preprocessed data, a three-level progressive feature calculation is performed to obtain the transient harmonic attenuation coefficient, electromagnetic coupling interference correction coefficient and load characteristic comprehensive discrimination value in sequence;

[0008] S4: Compare the comprehensive judgment value of the load features with the preset load type feature library, and output the load type identification result.

[0009] Preferably, the detection unit includes a harmonic sensor, a temperature sensor, an electromagnetic coupling detector, a voltage transformer, and a current transformer. The harmonic sensor is used to collect transient harmonic signals within 0.1s to 1s during the load startup phase. The temperature sensor is used to collect temperature drift data of the internal conductive circuit of the circuit breaker. The electromagnetic coupling detector is used to collect electromagnetic coupling strength data between the load and the circuit breaker.

[0010] More preferably, the preprocessing operation includes using a wavelet threshold denoising algorithm to denoise the transient harmonic signal, and using a maximum-minimum normalization method to normalize the temperature drift data, electromagnetic coupling strength data, voltage RMS value, current RMS value, power factor, and current distortion rate to the range of 0 to 1.

[0011] More preferably, in the three-level progressive feature calculation, the first level calculation is based on the transient harmonic attenuation coefficient obtained from the transient harmonic signal and temperature drift data; the second level calculation is based on the transient harmonic attenuation coefficient and electromagnetic coupling strength data to obtain the electromagnetic coupling interference correction coefficient; and the third level calculation is based on the electromagnetic coupling interference correction coefficient, voltage RMS value, current RMS value, power factor and current distortion rate to obtain the comprehensive judgment value of load characteristics.

[0012] More preferably, the transient harmonic attenuation coefficient is obtained by the transient harmonic attenuation coefficient calculation formula, which is:

[0013]

[0014] Where λ is the transient harmonic attenuation coefficient, which is dimensionless; H n t represents the amplitude of the nth transient harmonic, in volts; N represents the total number of transient harmonics, dimensionless; n τ is the decay time of the nth harmonic, in seconds; τ is the harmonic decay time constant, in seconds; T d α represents the duration of the transient process in seconds; α is the temperature drift influence coefficient, which is dimensionless; ΔT is the temperature drift data in degrees Celsius.

[0015] More preferably, the electromagnetic coupling interference correction coefficient is obtained through an electromagnetic coupling interference correction formula, which is as follows:

[0016]

[0017] Where μ is the electromagnetic coupling interference correction coefficient, dimensionless; λ is the transient harmonic attenuation coefficient, dimensionless; β is the electromagnetic coupling influence weighting coefficient, dimensionless; C sγ represents electromagnetic coupling strength data in microtesla; D represents the installation distance between the load and the circuit breaker detection unit in meters; γ represents the frequency offset correction coefficient, dimensionless; Δf represents the offset between the load operating frequency and the rated frequency in Hertz.

[0018] More preferably, the comprehensive load characteristic discrimination value is obtained through a comprehensive load characteristic discrimination formula, which is:

[0019]

[0020] Wherein, Φ is the comprehensive judgment value of load characteristics, dimensionless; μ is the electromagnetic coupling interference correction coefficient, dimensionless; k1 is the voltage weighting coefficient, dimensionless; U is the normalized effective voltage value, dimensionless; k2 is the current weighting coefficient, dimensionless; I is the normalized effective current value, dimensionless; k3 is the power factor weighting coefficient, dimensionless; cosφ is the power factor, dimensionless; k4 is the current distortion rate weighting coefficient, dimensionless; THD is the current distortion rate, dimensionless.

[0021] More preferably, the load type feature library is constructed by collecting comprehensive discrimination values ​​of load characteristics of various standard load types under different operating conditions, and then classifying and clustering all discrimination values ​​using the K-means clustering algorithm. The standard load types include resistive loads, inductive loads, capacitive loads, and mixed loads.

[0022] More preferably, the comparison operation uses a cosine similarity algorithm to calculate the similarity between the comprehensive discriminant value of the load features and the discriminant values ​​of each category center in the load type feature library, and determines the category with the highest similarity as the final load type.

[0023] Further preferably, after outputting the load type identification result, the method further includes a step of verifying the identification result. The verification step involves collecting electrical parameter data during the load operation process again, repeating the operations from S2 to S4 to obtain a secondary load feature comprehensive discrimination value. If the deviation between the secondary load feature comprehensive discrimination value and the first obtained load feature comprehensive discrimination value is less than a preset threshold, the identification result is confirmed to be valid; otherwise, the entire identification process is re-executed.

[0024] Compared with the prior art, the present invention has the following advantages:

[0025] The core inventive technology of this invention lies in the synergistic integration of a three-level progressive feature calculation and multi-dimensional influencing factors. By collecting key parameters such as transient harmonic signals and temperature drift data, the first-level calculation eliminates the interference of temperature drift on transient harmonics; the second-level calculation corrects the deviation caused by electromagnetic coupling; and the third-level calculation integrates conventional electrical parameters to form a comprehensive discrimination value. This solution specifically addresses the core problem of existing technologies failing to consider the mutual interference of multiple factors, achieving accurate identification of load types and providing reliable support for intelligent circuit breaker control and optimized power system configuration. Attached Figure Description

[0026] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0027] Figure 1 This is a flowchart of the load type identification method based on the intelligent algorithm of circuit breakers according to the present invention. Detailed Implementation

[0028] 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. 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.

[0029] The concepts involved in this application will first be described with reference to the accompanying drawings. It should be noted that the following descriptions of various concepts are only for the purpose of making the content of this application easier to understand and do not constitute a limitation on the scope of protection of this application; furthermore, the embodiments and features in the embodiments of this application can be combined with each other unless otherwise specified. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0030] Traditional load type identification methods rely solely on conventional static electrical parameters such as RMS voltage and RMS current, without considering the mutual influence of key factors such as transient harmonic signals, temperature drift, and electromagnetic coupling strength, resulting in insufficient identification accuracy under complex operating conditions.

[0031] Based on this, please refer to Figure 1This embodiment provides a load type identification method based on a circuit breaker intelligent algorithm. The method involves collecting electrical parameter data during load operation via the circuit breaker's detection unit, performing feature processing on the collected electrical parameter data, and identifying the load type based on the processed feature parameters. The feature processing includes four steps, S1 to S4: S1: Collecting transient harmonic signals, temperature drift data, electromagnetic coupling strength data, effective voltage value, effective current value, power factor, and current distortion rate of the load via the detection unit; S2: Preprocessing all collected data by denoising and normalization; S3: Performing a three-level progressive feature calculation based on the preprocessed data to sequentially obtain the transient harmonic attenuation coefficient, electromagnetic coupling interference correction coefficient, and comprehensive load feature discrimination value; S4: Comparing the comprehensive load feature discrimination value with a preset load type feature library and outputting the load type identification result.

[0032] The core of this technical solution lies in constructing a complete logic for multi-dimensional data acquisition and three-level progressive feature calculation. Step S1 comprehensively collects key parameters during load operation: transient harmonic signals reflect the essential characteristics of the load startup phase; temperature drift data reflects the impact of the circuit breaker's internal environment on the signal; electromagnetic coupling strength data characterizes the interaction between the load and the circuit breaker; and conventional electrical parameters provide basic operational information. Step S2 eliminates noise interference in the original data and unifies the data scale through denoising and normalization, laying the foundation for subsequent calculations. Step S3's three-level progressive feature calculation is the core innovation. The first-level calculation combines transient harmonic signals and temperature drift data to eliminate temperature interference with harmonic characteristics; the second-level calculation incorporates electromagnetic coupling strength data based on the previous step's results to correct coupling interference; and the third-level calculation integrates all effective parameters to form a comprehensive discrimination value that fully reflects the load type. Step S4 achieves accurate load type identification through comparison with a feature database. This solution systematically addresses the shortcomings of existing technologies through multi-parameter collaboration and progressive calculation, achieving accurate load type identification.

[0033] Traditional detection units often use a single or a few types of sensors, which cannot comprehensively collect multi-dimensional data such as transient harmonics, temperature drift, and electromagnetic coupling strength, resulting in a lack of effective data support for subsequent feature calculations.

[0034] Based on this, the detection unit includes a harmonic sensor, a temperature sensor, an electromagnetic coupling detector, a voltage transformer, and a current transformer. The harmonic sensor is used to collect transient harmonic signals within 0.1s to 1s during the load startup phase. The temperature sensor is used to collect temperature drift data of the internal conductive circuit of the circuit breaker. The electromagnetic coupling detector is used to collect electromagnetic coupling strength data between the load and the circuit breaker.

[0035] This technical solution achieves accurate acquisition of multi-dimensional key data through targeted configuration of sensor types. Harmonic sensors specifically collect transient harmonic signals during the load startup phase. These signals are unaffected by steady-state operation and more accurately reflect the load's inherent characteristics. The acquisition time window is set within 0.1s to 1s, ensuring complete capture of the transient process while avoiding redundant data. Temperature sensors focus on temperature drift data within the circuit breaker's internal conductive loops. Temperature changes at this location directly affect the transmission and detection accuracy of harmonic signals, making it a crucial data point for identifying interference factors. Electromagnetic coupling detectors specifically collect electromagnetic coupling strength data between the load and the circuit breaker, accurately characterizing the degree of electromagnetic interaction between them. Voltage transformers and current transformers collect RMS voltage and current values, respectively, providing data for conventional electrical parameter analysis. These sensors, each performing its specific function and working in concert, comprehensively cover the key data dimensions required for load identification, providing ample data support for subsequent three-level progressive feature calculations.

[0036] The collected raw data contains problems such as environmental noise and inconsistent data scales, which directly affect the accuracy and effectiveness of feature calculation. Traditional preprocessing methods can only solve a single problem and cannot meet the dual requirements of noise reduction and normalization.

[0037] Based on this, the preprocessing operation includes using a wavelet threshold denoising algorithm to denoise the transient harmonic signal, and using a maximum-minimum normalization method to normalize the temperature drift data, electromagnetic coupling strength data, voltage RMS value, current RMS value, power factor and current distortion rate to the range of 0 to 1.

[0038] This technical solution employs targeted preprocessing methods tailored to the characteristics of different data types. Transient harmonic signals are susceptible to electromagnetic noise interference in the power environment. Wavelet threshold denoising algorithms possess excellent time-frequency localization characteristics, effectively filtering out high-frequency noise while preserving key features of harmonic signals, ensuring the authenticity of harmonic data. Temperature drift data, electromagnetic coupling strength data, and other parameters exhibit significant differences in dimensions and numerical ranges. Direct use in calculations could lead to weight imbalances. The max-min normalization method maps these data uniformly to the 0-1 interval, preserving relative differences between data while eliminating dimensional influences, enabling effective fusion of different data types in subsequent calculations. The synergistic use of these two preprocessing methods comprehensively resolves noise interference and scale inconsistency issues in the original data, providing high-quality data input for the three-level progressive feature calculation.

[0039] Traditional feature calculation methods are mostly single-dimensional calculations that do not consider the mutual influence between different parameters and cannot effectively eliminate interference factors, resulting in insufficient identification of feature parameters.

[0040] Based on this, in the three-level progressive feature calculation, the first level calculation is based on the transient harmonic signal and temperature drift data to obtain the transient harmonic attenuation coefficient, the second level calculation is based on the transient harmonic attenuation coefficient and electromagnetic coupling strength data to obtain the electromagnetic coupling interference correction coefficient, and the third level calculation is based on the electromagnetic coupling interference correction coefficient, voltage RMS value, current RMS value, power factor and current distortion rate to obtain the load characteristic comprehensive discrimination value.

[0041] This technical solution constructs a progressive and interconnected feature calculation logic. The first-level calculation focuses on the fusion of transient harmonic signals and temperature drift data. Transient harmonic signals are a core feature reflecting load type, but temperature drift causes distortion. By combining the two, a transient harmonic attenuation coefficient to eliminate temperature interference is obtained. The second-level calculation, based on the results of the first level, incorporates electromagnetic coupling strength data. Electromagnetic coupling is another key interference factor. Through correction calculation, an electromagnetic coupling interference correction coefficient is obtained to eliminate electromagnetic coupling interference, achieving secondary elimination of interference factors. The third-level calculation integrates the corrected core features with conventional electrical parameters. Conventional electrical parameters provide basic information about load operation and, together with the corrected core features, form a comprehensive and accurate discrimination value that reflects the load type. The three levels of calculation are progressive, with the results of the previous level providing the basis for the next level. Each level of calculation specifically eliminates a type of interference factor, ultimately achieving precise extraction of feature parameters.

[0042] Traditional transient harmonic characteristic calculations do not consider the influence of temperature drift, resulting in calculation results that cannot accurately reflect the harmonic characteristics of the load. A more accurate calculation method that can incorporate temperature drift factors is needed.

[0043] Based on this, the transient harmonic attenuation coefficient is obtained through the transient harmonic attenuation coefficient calculation formula, which is:

[0044] ;

[0045] Where λ is the transient harmonic attenuation coefficient, dimensionless; Hn is the amplitude of the nth transient harmonic, in volts; N is the total number of transient harmonics, dimensionless; tn is the attenuation time of the nth harmonic, in seconds; τ is the harmonic attenuation time constant, in seconds; Td is the duration of the transient process, in seconds; α is the temperature drift influence coefficient, dimensionless; ΔT is the temperature drift data, in degrees Celsius.

[0046] The core design goal of this formula is to quantify the attenuation characteristics of transient harmonics during the load startup phase and eliminate the interference of temperature drift on harmonic characteristics. Its theoretical basis comes from the physical attenuation law of transient harmonics and the influence mechanism of temperature on conductive circuits in the field of power electronics. The derivation process follows the logical chain of original feature extraction, interference factor quantification and normalization correction.

[0047] From a theoretical perspective, load startup generates transient harmonics containing rich spectral information. The amplitude of these harmonics decays exponentially over time, determined by the load's equivalent impedance characteristics—the inductive components of an inductive load and the capacitive components of a capacitive load undergo energy storage and release processes upon energization, causing the harmonic amplitude to gradually approach a steady state. Current technologies simply collect harmonic amplitudes without considering their dynamic decay characteristics, resulting in insufficient feature identification. This formula, however, accurately captures this dynamic process through summation. In the summation term, This represents the amplitude of the nth transient harmonic. The difference in amplitude between different harmonic orders directly reflects the spectral characteristics of the load. For example, the transient harmonic amplitude of resistive loads decays quickly and the proportion of higher harmonics is low, while that of inductive loads is the opposite. It is an exponentially decaying term. As the harmonic decay time constant, it is determined by the ratio of the load's equivalent inductance to resistance and is an inherent property of the load. The decay time of the nth harmonic is used to characterize the decay rate of a single harmonic. By summing the products of the amplitude and decay rate of all harmonics, the overall decay profile of transient harmonics can be comprehensively characterized, avoiding the one-sidedness of single harmonic characteristics.

[0048] The design of the denominator specifically addresses the interference problem caused by temperature drift, which is one of the core shortcomings of existing technologies. Temperature changes in the internal conductive circuit of a circuit breaker lead to changes in resistance, which in turn affects the transmission and detection accuracy of harmonic signals. The greater the temperature drift, the more severe the distortion of harmonic characteristics. The duration of the transient process is used to normalize the summation result of the numerator in the time dimension, ensuring that the load harmonic attenuation coefficients of different transient durations are comparable. Without normalization, the summation result of a long transient process will naturally be too large and cannot truly reflect the differences in attenuation characteristics. It is the temperature drift correction factor, where Directly collect temperature change data of the internal conductive circuit of the circuit breaker. The temperature drift influence coefficient was determined through extensive experimental calibration. Under standard temperature conditions, multiple transient harmonic acquisitions were performed on different types of loads. The ambient temperature was gradually changed, and the changes in harmonic attenuation characteristics were recorded. Linear regression analysis was used to determine the percentage shift in the harmonic attenuation coefficient for every 1°C temperature change, ultimately determining... The reasonable range of values ​​for this correction factor. The physical meaning of this correction factor is that the degree of harmonic characteristic distortion caused by temperature drift has an approximately linear relationship with the amount of temperature change. This factor can counteract this distortion, making the calculated values ​​more accurate. It more closely approximates the true transient harmonic attenuation characteristics of the load at standard temperature.

[0049] The derivation of the entire formula proceeds logically in a progressive manner: first, the dynamic attenuation characteristics of transient harmonics are extracted through the numerator; then, the time dimension difference and temperature drift interference are eliminated through the denominator; finally, a transient harmonic attenuation coefficient that accurately reflects the essential characteristics of the load is obtained. This design not only conforms to the physical propagation laws of transient harmonics but also specifically addresses the pain point of temperature interference, which has not been resolved in existing technologies. Its calculation form has clear theoretical support and the rationality of technical improvement. Those skilled in the art can calibrate it using conventional experimental methods according to the load type and usage environment. and The specific value is sufficient to repeat the calculation process.

[0050] The theoretical basis of this formula is the attenuation characteristics of transient harmonics and the interference mechanism of temperature drift. The numerator accurately characterizes the overall attenuation process of transient harmonics by summing the amplitude of each transient harmonic and the attenuation exponent, where the exponent term... This reflects the attenuation law of harmonic amplitude over time, where τ is the attenuation time constant, determined by the characteristics of the load itself. A temperature drift correction term (1+α·ΔT) is introduced into the denominator, where α is the temperature drift influence coefficient, obtained through experimental calibration, and ΔT is the temperature drift data. This correction term quantifies the degree of influence of temperature changes on the harmonic attenuation characteristics. d The duration of the transient process is used to normalize the effect of the time dimension. The entire formula characterizes the original harmonic attenuation properties through the numerator and eliminates temperature drift interference through the denominator, achieving accurate calculation of the transient harmonic attenuation coefficient and providing a reliable foundation for subsequent characteristic calculations.

[0051] The transient harmonic attenuation coefficient is still affected by electromagnetic coupling. Traditional calculation methods do not take into account the combined effects of electromagnetic coupling strength, installation distance, frequency offset, etc., which leads to deviations in characteristic parameters.

[0052] Based on this, the electromagnetic coupling interference correction coefficient is obtained through the electromagnetic coupling interference correction formula, which is as follows:

[0053]

[0054] Where μ is the electromagnetic coupling interference correction coefficient, dimensionless; λ is the transient harmonic attenuation coefficient, dimensionless; β is the electromagnetic coupling influence weighting coefficient, dimensionless; C s γ represents electromagnetic coupling strength data in microtesla; D represents the installation distance between the load and the circuit breaker detection unit in meters; γ represents the frequency offset correction coefficient, dimensionless; Δf represents the offset between the load operating frequency and the rated frequency in Hertz.

[0055] The core function of this formula is in the transient harmonic attenuation coefficient. Based on this, the influence of electromagnetic coupling interference on characteristic parameters is further eliminated. Its theoretical design is based on the radiation coupling principle in electromagnetics and the frequency characteristics of load operation in power systems. The derivation process revolves around "interference factor identification - interference intensity quantification - correction factor construction", which is a deep optimization of the previous stage characteristic parameters.

[0056] From a theoretical perspective, an electromagnetic coupling effect exists between the circuit breaker and the load. This effect stems from the alternating magnetic field generated when current flows through the conductors of both. This alternating magnetic field can penetrate each other and affect the detection of the other's electrical signal, which is another key factor leading to distortion of load characteristic parameters. Current technology does not consider this interference, resulting in limited recognition accuracy. This formula uses data that has eliminated temperature interference. Based on this, electromagnetic coupling interference is quantified and canceled through correction terms. The core logic is "basic characteristic parameters × interference cancellation factor", ensuring that the corrected parameters are... It more closely reflects the true characteristics of the load.

[0057] The internal design of the correction term fully reflects the coordinated consideration of multiple factors related to electromagnetic coupling interference. First, The design of this project is based on the inverse square law of electromagnetic radiation—the electromagnetic coupling strength. The distance from the radiation source to the receiver is inversely proportional to the square of the distance; this is a fundamental law of electromagnetism. The electromagnetic coupling strength data between the load and the circuit breaker is directly collected; the larger the value, the stronger the interference. The installation distance between the load and the circuit breaker detection unit is considered. The closer the distance, the higher the coupling strength and the more severe the interference with harmonic characteristics. Therefore, the reciprocal of the square of the distance is used to quantify this distance dependence. For example, when the installation distance increases from 0.5 meters to 1 meter, the square of the distance becomes four times the original value, and the influence of the coupling strength decreases to 1 / 4 of the original value. This quantitative relationship accurately reflects the propagation characteristics of electromagnetic coupling.

[0058] Secondly This section provides supplementary corrections for interference caused by load operating frequency deviation. In actual operation, the load may deviate from its rated frequency due to changes in operating conditions. Since the resonant frequency of electromagnetic coupling is related to the load's operating frequency, frequency deviation leads to changes in the coupling resonance strength, thereby exacerbating interference. This represents the offset between the load operating frequency and the rated frequency. This is the frequency offset correction coefficient, and its calibration logic is ANDed with... Similarly: by collecting data on the relationship between electromagnetic coupling strength and characteristic parameter distortion at different frequency offsets, the change ratio of interference strength for every 1 Hz frequency offset is determined, ensuring that this factor can accurately quantify the impact of frequency offset on coupling interference.

[0059] As a weighting coefficient for the effects of electromagnetic coupling, its role is to balance , , The combined interference contribution of the three factors. Because the degree of influence of the three interference factors varies in different application scenarios, such as in industrial scenarios with intensive loads... The impact is more significant, and frequency shift may be more common in civilian scenarios; therefore, experimental calibration is necessary. The range of values ​​allows the correction term to adapt to the interference characteristics of different scenarios. The correction term is generally expressed as "1 - interference quantization value" because the larger the interference quantization value, the more severe the damage to the feature parameters, and the higher the proportion that needs to be offset. When the interference quantization value is 0, the correction term is 1. This meets the ideal condition of no interference.

[0060] The theoretical basis of this formula is the interference law of electromagnetic coupling and the correlation characteristics of influencing factors. The formula is based on the transient harmonic attenuation coefficient λ, and modifies it with the term [1-β·C]. s / (D²)·(1+γ·Δf)] eliminates electromagnetic coupling interference. C s The strength of electromagnetic coupling is represented by a 1 / D² term, where a larger value indicates stronger interference. D represents the installation distance; the electromagnetic coupling strength is inversely proportional to the square of the distance, hence the introduction of this term. Δf represents the frequency shift, which exacerbates electromagnetic coupling interference; this effect is quantified by the (1+γ·Δf) term. β and γ are weighting coefficients, determined through experimental calibration. The correction term comprehensively considers three key factors—electromagnetic coupling strength, installation distance, and frequency shift—to accurately calculate the degree of interference of electromagnetic coupling on harmonic characteristics and corrects λ, resulting in an electromagnetic coupling interference correction coefficient μ to eliminate electromagnetic coupling interference, further improving the accuracy of the characteristic parameters.

[0061] A single characteristic parameter or a simple superposition of parameters cannot fully reflect the load type. A calculation method that can integrate multiple effective parameters and achieve a comprehensive characterization of load characteristics is needed.

[0062] Based on this, the comprehensive load characteristic discriminant value is obtained through the comprehensive load characteristic discriminant formula, which is:

[0063]

[0064] Wherein, Φ is the comprehensive judgment value of load characteristics, dimensionless; μ is the electromagnetic coupling interference correction coefficient, dimensionless; k1 is the voltage weighting coefficient, dimensionless; U is the normalized effective voltage value, dimensionless; k2 is the current weighting coefficient, dimensionless; I is the normalized effective current value, dimensionless; k3 is the power factor weighting coefficient, dimensionless; cosφ is the power factor, dimensionless; k4 is the current distortion rate weighting coefficient, dimensionless; THD is the current distortion rate, dimensionless.

[0065] The core objective of this formula is to integrate multi-dimensional effective feature parameters to form a comprehensive discrimination index that can accurately distinguish different load types. Its theoretical basis stems from the differences in sensitivity of different load types to various electrical parameters. The derivation process follows the logic of core feature dominance, auxiliary feature supplementation, and weighted fusion optimization, which solves the technical problem that a single feature parameter cannot fully characterize the load type.

[0066] From a theoretical perspective, the essential differences between different load types are reflected in multiple electrical parameter dimensions: resistive loads have a power factor close to 1, low current distortion rate, and fast transient harmonic decay; inductive loads have a low power factor and slow transient harmonic decay; capacitive loads have a capacitive power factor and moderate current distortion rate; and hybrid loads exhibit mixed characteristics with multiple parameters. Existing technologies rely on only one or a few parameters, which cannot cover these differences, while this formula achieves a comprehensive characterization of load types through multi-parameter weighted fusion.

[0067] Formula Part 1 This forms the core basis for the comprehensive discrimination value. As a core feature corrected for both temperature and electromagnetic coupling interference, it can reflect the essential harmonic characteristics of the load. Using it as the dominant factor ensures the core discriminant value of the comprehensive judgment. The term is used to integrate the synergistic characteristics of the effective values ​​of voltage and current, voltage and current These are the fundamental electrical parameters for load operation, but their individual effects cannot effectively distinguish load types. For example, resistive and inductive loads may have the same effective voltage value, but their current variation patterns differ. The square root form is used because the contributions of voltage and current to load power are quadratic, and this form accurately characterizes the combined power-related characteristics of both. , These are the voltage and current weighting coefficients, calibrated based on the differences in the sensitivity of different load types to voltage and current: by collecting a large amount of voltage and current data for standard load types, the contribution of each factor in load type identification is analyzed. For example, the current and voltage of a resistive load have a linear relationship. and They can be set to be approximately equal. The current of an inductive load lags behind the voltage, and the current contributes more significantly to the load characteristics; therefore, they can be appropriately increased. The value of is chosen to ensure that this part can highlight the differences in voltage and current synergy characteristics between different load types.

[0068] Formula Part 2 Focusing on power factor The power factor plays a distinguishing role. It is a key parameter reflecting the impedance characteristics of a resistive load. Approaching 1, inductive load For inductive loads with a capacitance value less than 1, It is capacitive and less than 1, which is the core criterion for distinguishing the three types of basic loads. This is the power factor weighting coefficient. Its calibration logic is based on experimental analysis of the impact of the power factor on load type misjudgment. For example, when the power factor is close to 1, the probability of misjudging it as a non-resistive load is extremely low, therefore it is assigned a weighting factor of 1. Appropriate weighting ensures that this parameter effectively dominates the differentiation of basic load types.

[0069] Formula Part 3 For current distortion rate The supplementary role of current distortion rate. Current distortion rate reflects the degree of nonlinearity of the load; for purely resistive loads... Extremely low for inductive and capacitive loads. Medium-duty, mixed-type loads (such as loads containing nonlinear elements) The higher the value, the more important it is to distinguish between mixed loads and single-type loads. This is the current distortion rate weighting coefficient, and its calibration is based on different load types. Distribution differences, such as mixed loads Typically more than 50% higher than a single type of load, by assigning Appropriate weighting ensures that this parameter can effectively identify mixed loads.

[0070] The theoretical basis of this formula is the correlation between load type and multi-dimensional electrical parameters. The first part of the formula... The formula integrates the corrected core feature μ with the effective values ​​of voltage and current. Voltage and current are fundamental parameters for load operation, and their combined effect is represented by the sum of squares and the square root. k1 and k2 are weighting coefficients, calibrated according to the characteristics of different load types. The second part, k3·cosφ, represents the power factor, a key parameter for distinguishing resistive, inductive, and capacitive loads, and its influence is assigned an appropriate weight by the weighting coefficient k3. The third part, k4·THD, reflects the nonlinear characteristics of the load and is of great significance for identifying mixed loads; its role is reflected by the weighting coefficient k4. The entire formula comprehensively covers the essential characteristics of the load by weighted integration of the corrected core feature and conventional electrical parameters, forming a comprehensive discrimination value Φ that can accurately distinguish different load types.

[0071] Traditional load type feature libraries are mostly built based on empirical thresholds, lacking coverage of different operating conditions, resulting in insufficient adaptability and accuracy of the feature libraries.

[0072] Based on this, the load type feature library is constructed by collecting comprehensive discrimination values ​​of load characteristics of various standard load types under different operating conditions, and then classifying and clustering all discrimination values ​​using the K-means clustering algorithm. The standard load types include resistive loads, capacitive loads, inductive loads, and mixed loads.

[0073] This technical solution constructs a widely adaptable load type feature library. First, data is collected for four standard load types: resistive loads, inductive loads, capacitive loads, and mixed loads, covering common load types in power systems. Data for each standard load type is collected under different operating conditions, including varying load power, ambient temperature, and operating frequency, ensuring that the collected comprehensive load characteristic discrimination values ​​fully reflect the load's characteristics in actual operation. The K-means clustering algorithm is used to classify and cluster all collected discrimination values. This algorithm automatically identifies cluster centers in the data, grouping discrimination values ​​belonging to the same load type together to form feature intervals for each category. The feature library constructed using this method not only covers common load types but also adapts to changes in different operating conditions, providing an accurate and reliable reference for subsequent comparison and identification.

[0074] Traditional comparison methods often rely on simple threshold judgments, which cannot effectively distinguish the feature differences of similar load types, resulting in low recognition accuracy.

[0075] Based on this, the comparison operation uses the cosine similarity algorithm to calculate the similarity between the comprehensive discriminant value of the load features and the discriminant values ​​of each category center in the load type feature library, and determines the category with the highest similarity as the final load type.

[0076] This technical solution achieves accurate comparison using a cosine similarity algorithm. The cosine similarity algorithm quantifies the cosine of the angle between two vectors, reflecting their degree of similarity. The value ranges from -1 to 1, with values ​​closer to 1 indicating higher similarity. During the comparison process, the comprehensive discriminant value of the load features is used as the vector to be identified, and the center discriminant values ​​of each category in the load type feature library are used as reference vectors. The cosine similarity between the vector to be identified and each reference vector is calculated. Since the center discriminant values ​​of different load types differ significantly, similarity calculation can accurately determine the degree of matching between the load to be identified and various standard loads, identifying the category with the highest similarity as the final load type. Compared to traditional threshold judgment, this comparison method can more accurately identify differences between similar load types, effectively improving the accuracy of load type identification.

[0077] A single identification process may lead to deviations in identification results due to accidental factors, and the lack of an effective verification mechanism makes it impossible to guarantee the reliability of the identification results.

[0078] Based on this, after outputting the load type identification result, the method further includes a step of verifying the identification result. The verification step involves collecting electrical parameter data during the load operation process again, repeating the operations from S2 to S4 to obtain a secondary load feature comprehensive discrimination value. If the deviation between the secondary load feature comprehensive discrimination value and the first obtained load feature comprehensive discrimination value is less than a preset threshold, the identification result is confirmed to be valid; otherwise, the entire identification process is re-executed.

[0079] This technical solution ensures the reliability of the identification results through a secondary verification mechanism. After the initial identification output, the electrical parameter data of the load is collected again, and the preprocessing and three-level progressive feature calculation steps are repeated to obtain a secondary comprehensive discriminant value of the load characteristics. The deviation between the two discriminant values ​​is calculated. If the deviation is less than a preset threshold, it indicates that the two identification results are consistent, the initial identification result is less affected by accidental factors, and the identification result is confirmed to be valid. If the deviation is greater than or equal to the preset threshold, it indicates that the initial identification result may have errors, and the entire identification process needs to be repeated until the deviation between the two identification results meets the requirements. This verification mechanism can effectively filter out identification errors caused by accidental factors, significantly improve the reliability and stability of load type identification results, and provide a reliable decision-making basis for subsequent circuit breaker control and power system optimization.

[0080] The embodiments and / or implementation methods described above are merely preferred embodiments and / or implementation methods for implementing the technology of the present invention, and are not intended to limit the implementation methods of the technology of the present invention in any way. Any person skilled in the art can make some modifications or alterations to other equivalent embodiments without departing from the scope of the technical means disclosed in the content of the present invention, but they should still be regarded as the technology or embodiments that are substantially the same as the present invention.

[0081] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. The above descriptions are only preferred embodiments of this application. It should be noted that due to the limitations of written expression, while there are objectively infinite specific structures, those skilled in the art can make several improvements, modifications, or changes without departing from the principles of this application, and can also combine the above technical features in an appropriate manner. These improvements, modifications, changes, or combinations, or the direct application of the inventive concept and technical solution to other situations without modification, should all be considered within the scope of protection of this application.

Claims

1. A load type identification method based on a circuit breaker intelligent algorithm, comprising collecting electrical parameter data during load operation through the detection unit of the circuit breaker, performing feature processing on the collected electrical parameter data, and completing load type identification based on the processed feature parameters, characterized in that, The feature processing includes: S1: The detection unit collects the transient harmonic signal, temperature drift data, electromagnetic coupling strength data, effective voltage value, effective current value, power factor and current distortion rate of the load. S2: Perform preprocessing operations such as denoising and normalization on all collected data; S3: Based on the preprocessed data, a three-level progressive feature calculation is performed to obtain the transient harmonic attenuation coefficient, electromagnetic coupling interference correction coefficient and load characteristic comprehensive discrimination value in sequence; S4: Compare the comprehensive judgment value of the load features with the preset load type feature library, and output the load type identification result; In the three-level progressive feature calculation, the first level calculation is based on transient harmonic signal and temperature drift data to obtain transient harmonic attenuation coefficient; the second level calculation is based on the transient harmonic attenuation coefficient and electromagnetic coupling strength data to obtain electromagnetic coupling interference correction coefficient; and the third level calculation is based on the electromagnetic coupling interference correction coefficient, voltage RMS value, current RMS value, power factor and current distortion rate to obtain load characteristic comprehensive discrimination value.

2. The load type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The detection unit includes a harmonic sensor, a temperature sensor, an electromagnetic coupling detector, a voltage transformer, and a current transformer. The harmonic sensor is used to collect transient harmonic signals within 0.1s to 1s during the load startup phase. The temperature sensor is used to collect temperature drift data of the internal conductive circuit of the circuit breaker. The electromagnetic coupling detector is used to collect electromagnetic coupling strength data between the load and the circuit breaker.

3. The load type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The preprocessing operation includes using a wavelet threshold denoising algorithm to denoise the transient harmonic signal, and using a maximum-minimum normalization method to normalize the temperature drift data, electromagnetic coupling strength data, voltage RMS value, current RMS value, power factor, and current distortion rate to the range of 0 to 1.

4. The load type identification method based on circuit breaker intelligent algorithm according to claim 3, characterized in that, The transient harmonic attenuation coefficient is obtained through the transient harmonic attenuation coefficient calculation formula, which is: where λ is the transient harmonic decay coefficient, dimensionless; H n is the amplitude of the nth transient harmonic, in volts; N is the total number of transient harmonics, dimensionless; t n is the decay time of the nth harmonic, in seconds; τ is the harmonic decay time constant, in seconds; T d is the duration of the transient, in seconds; α is the temperature drift influence coefficient, dimensionless; ΔT is the temperature drift data, in degrees Celsius.

5. The load type identification method based on circuit breaker intelligent algorithm according to claim 3, characterized in that, The electromagnetic coupling interference correction coefficient is obtained through an electromagnetic coupling interference correction formula, which is as follows: Where μ is the electromagnetic coupling interference correction coefficient, dimensionless; λ is the transient harmonic attenuation coefficient, dimensionless; β is the electromagnetic coupling influence weighting coefficient, dimensionless; C s γ represents electromagnetic coupling strength data in microtesla; D represents the installation distance between the load and the circuit breaker detection unit in meters; γ represents the frequency offset correction coefficient, dimensionless; Δf represents the offset between the load operating frequency and the rated frequency in Hertz.

6. The load type identification method based on circuit breaker intelligent algorithm according to claim 3, characterized in that, The comprehensive load characteristic discriminant value is obtained through the comprehensive load characteristic discriminant formula, which is: in, k1 is the comprehensive judgment value of load characteristics, dimensionless; μ is the electromagnetic coupling interference correction coefficient, dimensionless; k1 is the voltage weighting coefficient, dimensionless; U is the normalized effective voltage value, dimensionless; k2 is the current weighting coefficient, dimensionless; I is the normalized effective current value, dimensionless; k3 is the power factor weighting coefficient, dimensionless. is the power factor, dimensionless; k4 is the current distortion rate weighting coefficient, dimensionless; THD is the current distortion rate, dimensionless.

7. The load type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The load type feature library is constructed by collecting comprehensive discrimination values ​​of load characteristics of various standard load types under different operating conditions, and then classifying and clustering all discrimination values ​​using the K-means clustering algorithm. The standard load types include resistive loads, inductive loads, capacitive loads, and mixed loads.

8. The load type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The comparison uses a cosine similarity algorithm to calculate the similarity between the comprehensive discriminant value of the load features and the discriminant values ​​of each category center in the load type feature library, and the category with the highest similarity is determined as the final load type.

9. The load type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, After outputting the load type identification result, the method further includes a step of verifying the identification result. The verification step involves collecting electrical parameter data during the load operation process again, repeating the operations from S2 to S4 to obtain a secondary load feature comprehensive discrimination value. If the deviation between the secondary load feature comprehensive discrimination value and the first obtained load feature comprehensive discrimination value is less than a preset threshold, the identification result is confirmed to be valid; otherwise, the entire identification process is re-executed.

Images