Water supply equipment electrical performance detection system based on artificial intelligence

Abstract

The present application relates to the technical field of electrical performance test, specifically to a water supply equipment electrical performance detection system based on artificial intelligence, which comprises an electrical parameter acquisition module, an energy efficiency analysis module, an insulation performance evaluation module and a comprehensive diagnosis module. In the present application, the root mean square values of three-phase voltage and current are dynamically calculated by a wideband current transformer and a sliding window integral method, the 50Hz fundamental component amplitude is extracted to separate power frequency and high frequency harmonics, the insulation detection threshold is triggered by the standard deviation of continuous period energy efficiency ratio, the parameter fluctuation and insulation deterioration response mechanism is established, the energy efficiency ratio and leakage current integral are synchronously processed by harmonic interference correction, the detection error is less than 5%, the temperature rise rate linear regression is cooperated with bearing current threshold to determine, the winding aging cross verification is realized, the fault misjudgment rate is reduced to 26%, the closed-loop detection fuses transient capture, dynamic threshold triggering and multi-parameter diagnosis, the early warning success rate reaches 92%, and the positioning response is reduced to 3 seconds.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrical performance testing, and in particular to a water supply equipment electrical performance detection system based on artificial intelligence. BACKGROUND

[0002] The technical field of electrical performance testing includes detection, analysis and evaluation of electrical parameters of various electrical equipment and systems under different working conditions. The core content of this technical field is to obtain electrical performance indicators such as voltage, current, resistance, insulation performance and power factor in electrical systems through special detection equipment and methods, in order to determine the electrical state and safety performance of the equipment operation. Overall, the technical field of electrical performance testing covers power system monitoring, electrical equipment testing, insulation performance measurement, electrical safety detection and related data acquisition and analysis methods, and is widely used in power, transportation, industrial control, water conservancy and other industries to ensure the stability and reliability of electrical equipment.

[0003] Among them, the water supply equipment electrical performance detection system refers to a device or combination structure for measuring performance parameters of electrical components and lines in the water supply system and diagnosing the state from the false state. The technical matters targeted by this patent subject include the working state detection of key electrical components such as electric pumps, controllers, relays and frequency converters in water supply equipment. Specifically, by configuring an electrical parameter acquisition circuit, setting a voltage and current detection interface, integrating an impedance measurement unit and establishing data analysis rules, the power supply path and load electrical characteristics are analyzed and identified. Such systems usually use analog sampling, direct current impedance measurement, voltage drop monitoring and control signal comparison to complete the detection work, ensuring the rationality and stability of the electrical performance of the water supply equipment under normal working conditions.

[0004] The existing technology uses fixed cycle sampling and static impedance measurement, which cannot capture transient voltage drop and current harmonic distortion caused by load mutation. For example, the instantaneous overcurrent during the start-stop stage of the electric pump is not covered by the detection window, causing an energy efficiency evaluation deviation of more than 15%. Single parameter threshold determination is not associated with environmental temperature rise factors, and cable joint leakage current detection frequently false alarms during high temperature periods. Offline insulation impedance detection is disconnected from the actual running condition of the equipment, and in a certain case, the winding that passed the offline detection broke down after 72 hours of continuous load. Control signal comparison relies on preset rules and lacks variable frequency harmonic dynamic suppression capability, and a certain water supply system was misjudged to stop due to third harmonic interference. The accuracy rate of the existing system for composite fault diagnosis is less than 75%, and the insulation deterioration early warning lags more than 48 hours. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings in the prior art and to provide a water supply equipment electrical performance detection system based on artificial intelligence.

[0006] In order to achieve the above object, the present application adopts the following technical scheme: A water supply equipment electrical performance detection system based on artificial intelligence comprises:

[0007] An electrical parameter acquisition module is configured to acquire three-phase voltage effective values and current effective values through a wide-frequency current transformer, calculate root mean square values in a period by using a sliding window integration method, extract 50Hz fundamental wave component amplitudes in a current waveform, generate voltage effective value sequences and fundamental wave current amplitudes, and deliver the voltage effective value sequences and the fundamental wave current amplitudes to an energy efficiency analysis module;

[0008] The energy efficiency analysis module is configured to calculate active power instantaneous values based on the voltage effective value sequences and the fundamental wave current amplitudes, generate energy efficiency ratio sequences, perform a standard deviation operation on energy efficiency ratios of 10 continuous periods, generate a fluctuation marker when a threshold value 0.05 determined based on a confidence interval analysis of 30 groups of samples is exceeded, and deliver the energy efficiency ratio sequences and the fluctuation marker to an insulation performance evaluation module;

[0009] The insulation performance evaluation module is configured to trigger water pump winding insulation impedance detection based on the fluctuation marker, perform harmonic interference correction on the energy efficiency ratio sequences, unify cable joint leakage current amplitude units into amperes, simultaneously perform time domain integration operation on the cable joint leakage current amplitude, generate an insulation deterioration identifier when an insulation impedance value is lower than 1MΩ and a leakage current integral value is greater than 10mA·s, and deliver the insulation impedance detection value and the insulation deterioration identifier to a comprehensive diagnosis module.

[0010] As a further scheme of the present application, the voltage effective value sequences include period root mean square voltages, three-phase voltage amplitude variation trends and voltage fluctuation characteristics, the fundamental wave current amplitude includes fundamental wave amplitude estimation results, current symmetry indexes and current waveform stability indexes, the energy efficiency ratio sequences include period power factors, active power mean value variation trends and load response characteristics, the fluctuation marker specifically includes energy efficiency ratio fluctuation warning identifiers, fluctuation period markers and fluctuation intensity grades, and the insulation impedance detection value includes water pump winding insulation attenuation degrees, insulation response time indexes and impedance value time sequences, and the insulation deterioration identifier specifically includes insulation performance early warning codes, deterioration severity grades and time stamp records.

[0011] As a further scheme of the present application, the standard deviation determination threshold value 0.05 is determined based on a confidence interval analysis of 30 groups of samples, and the confidence level is 95%.

[0012] The leakage current integral value 0.01A·s is obtained by performing time domain integration operation after unifying the cable joint leakage current amplitude units into amperes.

[0013] As a further scheme of the present application, the electrical parameter acquisition module comprises:

[0014] The signal acquisition sub-module synchronously acquires three-phase voltage instantaneous analog and current instantaneous analog through a wide-frequency current transformer, differentially amplifies the analog signals, realizes noise elimination with a common-mode rejection ratio of ≥80 dB, configures a band-pass filter to suppress high-frequency harmonic components with a decay coefficient of -40 dB / dec, and generates three-phase voltage instantaneous sequences and three-phase current instantaneous sequences;

[0015] The effective value calculation sub-module calls the three-phase voltage instantaneous sequences and the three-phase current instantaneous sequences, sets a sliding window width as an integer multiple of a power frequency period of 20 ms, performs a square operation on voltage instantaneous values point by point in the window, calculates a mean value after accumulation and a square root, and generates a voltage effective value sequence;

[0016] The fundamental wave extraction sub-module calls current effective value data in the voltage effective value sequence, decomposes a current spectrum by using a discrete Fourier transform, extracts real and imaginary parts corresponding to a 50 Hz frequency point, calculates a complex modulus value and multiplies it by a spectrum resolution coefficient Δf=1 / T, wherein T is a total signal sampling duration, and generates a fundamental wave current amplitude.

[0017] As a further scheme of the application, the energy efficiency analysis module comprises:

[0018] The power calculation sub-module acquires the voltage effective value sequence and the fundamental wave current amplitude, performs phase alignment processing on voltage values of each sampling point in the sequence, calculates a phase difference by using an error compensation algorithm, adds a cosine phase difference correction amount after multiplying the phase difference by the fundamental wave current amplitude, performs point-by-point operation according to an active power instantaneous value formula, and generates an energy efficiency ratio sequence;

[0019] The standard deviation analysis sub-module calls the energy efficiency ratio sequence, intercepts an energy efficiency ratio data segment of 10 consecutive periods in time sequence, calculates an arithmetic mean value of the data segment, performs a square operation on a difference between each value and the mean value and accumulates the square operation, and calculates a dispersion by using a standard deviation formula to obtain a standard deviation value;

[0020] The fluctuation determination sub-module compares the standard deviation value with a preset fluctuation determination threshold value of 0.05, triggers dynamic threshold adjustment when the threshold value is exceeded for three consecutive times, generates an identifier with a logic value of 1 if the former is greater than the threshold value, otherwise generates an identifier with a logic value of 0, encapsulates the energy efficiency ratio sequence and the logic identifier as a key-value pair structure, and outputs a fluctuation mark.

[0021] As a further scheme of the application, the insulation performance evaluation module comprises:

[0022] The insulation detection triggering sub-module triggers a water pump winding insulation impedance detection based on the fluctuation mark, acquires a winding terminal voltage difference and a leakage current value, eliminates the influence of a contact resistance by using a four-wire measurement method, calculates an insulation impedance by using Ohm's law, and generates an insulation impedance detection value.

[0023] The harmonic correction submodule calls the insulation impedance detection value, extracts the fundamental and harmonic component amplitudes of the energy efficiency ratio sequence, and uses the following formula:

[0024] ;

[0025] Harmonic interference correction is applied to the energy efficiency ratio sequence to generate a harmonic-corrected energy efficiency ratio.

[0026] in, Represents the harmonic correction efficiency ratio. Represents the original energy efficiency ratio sequence. Representing the Subharmonic distortion rate For the first Subharmonic weighting factor The fundamental component proportion coefficient;

[0027] The leakage current integration evaluation submodule collects the time-domain waveform of the leakage current amplitude of the cable joint, calls the harmonic correction efficiency ratio, and applies the trapezoidal method to perform discrete integration calculation on the leakage current amplitude. The integration order is set to second-order precision. When the insulation impedance detection value is less than 1MΩ and the integration result exceeds 10mA·s, an insulation degradation indicator is generated.

[0028] As a further aspect of the present invention, the system further includes:

[0029] The comprehensive diagnostic module is used to determine whether the motor bearing current exceeds the 5mA threshold collected by the Hall sensor at a frequency of 10kHz based on the insulation impedance detection value, to count the number of times the insulation degradation indicator is triggered, to perform linear regression calculation on the temperature rise rate of the junction box, to construct a temperature difference sequence using a time window sliding mechanism, and to generate a pump winding aging fault code when the bearing current exceeds the limit or the temperature rise rate exceeds 2℃ / min.

[0030] As a further aspect of the present invention, the pump body winding aging fault code specifically refers to the motor bearing fault type identifier, fault triggering condition record, and pump body temperature rise trend code.

[0031] As a further aspect of the present invention, the comprehensive diagnostic module includes:

[0032] The current threshold judgment submodule detects the motor bearing current data, extracts the effective value based on a 10ms sampling interval, extracts the insulation impedance detection value, compares the detection value with the preset current threshold point by point, calculates the length of the continuous over-limit time window, and determines whether the continuous over-limit condition is met based on the length of the time window, and generates a current over-limit indicator.

[0033] The identification statistics submodule calls the trigger signal in the current over-limit identifier, accumulates the number of trigger signals with a fixed period as the statistical unit, calculates the average time interval between adjacent triggers and the standard deviation of the duration of a single trigger, and generates a trigger frequency statistics value.

[0034] The temperature rise calculation submodule collects the junction box temperature time series data, constructs a difference sequence based on the temperature difference between adjacent 10 seconds within the sliding time window, uses the least squares method to perform linear fitting on the sequence, extracts the slope as the temperature rise rate per unit time, and generates the temperature rise rate coefficient.

[0035] The fault determination submodule calls the true or false status of the current over-limit indicator, the cumulative trend of the trigger frequency statistics, and the temperature rise rate coefficient. It compares the temperature rise rate coefficient with a preset rate threshold. If the current over-limit indicator is true or the temperature rise rate coefficient exceeds the limit, it generates a pump body winding aging fault code by combining the continuous upward trend of the trigger frequency statistics.

[0036] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0037] In this invention, the root mean square values ​​of three-phase voltage and current are dynamically calculated using a wideband current transformer combined with a sliding window integration method, improving the accuracy of transient operating condition parameter acquisition. A 50Hz fundamental component amplitude extraction technique separates the power frequency signal from high-frequency harmonics, reducing errors in the baseline data for energy efficiency analysis. Continuous periodic energy efficiency ratio standard deviation calculation triggers the insulation impedance detection threshold, establishing a dynamic response mechanism for parameter fluctuations and insulation degradation. A harmonic interference correction algorithm simultaneously processes the energy efficiency ratio sequence and the time-domain integral of cable leakage current, suppressing impedance detection errors to within 5%. Linear regression of temperature rise rate and bearing current threshold are used in synergistic judgment to achieve multi-dimensional cross-verification of winding aging, reducing the fault misjudgment rate by 26%. The closed-loop detection system integrates transient parameter capture, dynamic threshold triggering, and multi-parameter fusion diagnosis, increasing the insulation degradation early warning success rate to 92% and shortening the fault location response time to the 3-second level. Attached Figure Description

[0038] Figure 1 This is a system flowchart of the present invention;

[0039] Figure 2 This is a flowchart of the electrical parameter acquisition module of the present invention;

[0040] Figure 3 This is a flowchart of the energy efficiency analysis module of the present invention;

[0041] Figure 4 This is a flowchart of the insulation performance evaluation module of the present invention;

[0042] Figure 5 This is a flowchart of the comprehensive diagnostic module of the present invention. Detailed Implementation

[0043] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0044] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0045] Embodiment one

[0046] Please refer to Figure 1 An electrical performance detection system for water supply equipment based on artificial intelligence comprises:

[0047] An electrical parameter acquisition module is configured to obtain three-phase voltage effective values and current effective values through a wide-frequency current transformer, calculate the root mean square value in a period by using a sliding window integration method, extract the amplitude of the 50Hz fundamental wave component in the current waveform, generate a voltage effective value sequence and a fundamental wave current amplitude, and deliver them to an energy efficiency analysis module.

[0048] The energy efficiency analysis module is configured to calculate the active power instantaneous value based on the voltage effective value sequence and the fundamental wave current amplitude, generate an energy efficiency ratio sequence, perform a standard deviation operation on the energy efficiency ratio of 10 consecutive periods, generate a fluctuation marker when the result exceeds the threshold value 0.05 determined based on a 30-group sample confidence interval analysis, and deliver the energy efficiency ratio sequence and the fluctuation marker to an insulation performance evaluation module.

[0049] The insulation performance evaluation module is configured to trigger water pump winding insulation impedance detection based on the fluctuation marker, perform harmonic interference correction on the energy efficiency ratio sequence, unify the cable joint leakage current amplitude unit into amperes, simultaneously perform time domain integration operation on the cable joint leakage current amplitude, generate an insulation deterioration identifier when the insulation impedance value is lower than 1MΩ and the leakage current integral value is greater than 10mA·s, and deliver the insulation impedance detection value and the insulation deterioration identifier to a comprehensive diagnosis module.

[0050] The comprehensive diagnosis module is used for judging whether the motor bearing current exceeds the 5mA threshold value collected by the Hall sensor at a frequency of 10kHz based on the insulation impedance detection value, counting the number of insulation deterioration identification triggers, performing linear regression calculation on the temperature rise rate of the junction box temperature synchronously, constructing a temperature difference value sequence by using a time window sliding mechanism, and generating a pump winding aging fault code when the bearing current exceeds the limit or the temperature rise rate exceeds 2℃ / min.

[0051] The voltage effective value sequence includes the periodic root mean square voltage, the three-phase voltage amplitude change trend and the voltage fluctuation characteristics, the fundamental current amplitude includes the fundamental amplitude estimation result, the current symmetry index and the current waveform stability index, the energy efficiency ratio sequence includes the periodic power factor, the active power mean value change trend and the load response characteristics, the fluctuation mark is specifically the energy efficiency ratio fluctuation warning mark, the fluctuation period calibration and the fluctuation intensity grade, the insulation impedance detection value includes the water pump winding insulation attenuation degree, the insulation response time index and the impedance value time sequence, the insulation deterioration identification is specifically the insulation performance early warning code, the deterioration severity grade and the timestamp record, and the pump winding aging fault code is specifically the motor bearing fault type identification, the fault trigger condition record and the pump body temperature rise trend code.

[0052] The standard deviation determination threshold value 0.05 is determined based on the confidence interval analysis of 30 groups of samples, and the confidence level is 95%;

[0053] The leakage current integral value 0.01A·s is obtained by performing time domain integral operation after uniformly converting the leakage current amplitude of the cable joint into ampere.

[0054] Please refer to Figure 2 The electrical parameter acquisition module includes:

[0055] The signal acquisition sub-module synchronously acquires the three-phase voltage instantaneous analog quantity and the current instantaneous analog quantity through the wideband current transformer, performs differential amplification processing on the analog signal, realizes noise elimination with a common mode rejection ratio≥80dB, configures a band-pass filter to suppress high-frequency harmonic components with a decay coefficient of-40dB / dec, and generates three-phase voltage instantaneous sequences and three-phase current instantaneous sequences.

[0056] The signal acquisition submodule synchronously acquires the instantaneous analog quantities of three-phase voltage and current through a wideband current transformer. In specific implementation, for a specific model of centrifugal water pump motor in operation (rated voltage 380V, rated current 25A), a wideband current transformer (model LEMATO-10-B333-D10, bandwidth DC-1MHz, accuracy 0.5%) is installed on the U, V, and W phases of the motor's three-phase power supply cable. Simultaneously, a high-precision differential voltage probe (model Tektronix P5200A, bandwidth 50MHz, attenuation ratio adjustable) is connected between the motor's three-phase input terminals and the neutral point. The sensor's output analog signal is input to a multi-channel synchronous data acquisition card (model NIUSB-6363, 16-bit resolution), with the data acquisition card's sampling frequency set to 10kHz to ensure the capture of the power frequency (50Hz) and its higher harmonic components. The data acquisition card synchronously performs analog-to-digital conversion on the analog signals of six channels (voltage signals Ua, Ub, Uc and current signals Ia, Ib, Ic) at a sampling rate of 10kHz to obtain the original voltage and current digital signal sequences.

[0057] To eliminate common-mode noise interference introduced by line conduction and spatial electromagnetic field coupling, the acquired voltage signal of each phase (e.g., phase Ua) and its reference ground signal are sent to the front-end differential amplifier conditioning circuit built into the data acquisition card. This circuit configuration achieves a common-mode rejection ratio of 85dB, significantly reducing common-mode noise components. Specifically, if a common-mode interference voltage with an amplitude of 5V and a frequency of 1kHz is superimposed on the original signal, after passing through a common-mode rejection ratio of 85dB (i.e., ... After differential amplification (with a suppression capability of 100 times), the common-mode interference component in the output signal is suppressed to 100%. The amplitude is significantly lower than the effective signal amplitude. The signal then flows through a digital bandpass filter, configured as a fourth-order Butterworth filter with a passband range of 45Hz to 2kHz. This is intended to retain the fundamental frequency and major low-order harmonic components while filtering out high-frequency noise such as DC bias and switching frequencies. Outside the passband, especially at higher frequencies (above 2kHz), the filter's attenuation slope is designed to be -40dB / dec. For a noise component with an interference frequency of 5kHz, its frequency is 2.5 times the upper limit of the passband (2kHz). The attenuation reached That is, the amplitude decays to The above processing yields clear instantaneous sequences of three-phase voltage and three-phase current. Table 1 shows partial sampled data of phase A within one power frequency cycle (20ms).

[0058] Table 1. Example of instantaneous sampling data for phase A voltage and current.

[0059] Sample point number Time (ms) Voltage instantaneous value (V) Current instantaneous value (A) 1 0.1 15.71 0.82 2 0.2 31.40 1.64 100 10.0 310.55 15.11 199 19.9 -15.68 -0.81 200 20.0 0.00 0.00

[0060] As shown in Table 1, the table lists some instantaneous values ​​of phase A voltage and current obtained after signal acquisition and processing within one power frequency cycle (20ms, corresponding to 200 sampling points), including the beginning, near the peak, and the end times. These data will be used for subsequent effective value calculation.

[0061] The effective value calculation submodule calls the three-phase voltage instantaneous sequence and the three-phase current instantaneous sequence, sets the sliding window width to an integer multiple of the power frequency period of 20ms, performs a square operation on the instantaneous voltage values ​​within the window point by point, accumulates them, calculates the mean and square root, and generates the effective voltage value sequence.

[0062] The RMS value calculation submodule calls the three-phase voltage instantaneous sequence and the three-phase current instantaneous sequence. During execution, it obtains the A-phase voltage instantaneous sequence from the previous module. and the instantaneous sequence of phase A current Read data from the middle. Set a sliding window with a width of It must be the power frequency cycle. Number of internal sampling points An integer multiple of the number of sampling points. Select As an integer multiple, the window width is determined as follows: One sampling point. Select a single-period window ( This is to quickly respond to changes in the effective value while ensuring coverage of the complete power frequency cycle to obtain an accurate effective value. Select the current calculation window (set to start from the [number]th [period]). From the sampling point to the... Instantaneous voltage value at (number of sampling points) .

[0063] For each instantaneous voltage value within the window Performing the square operation yields All windows within the window The squares of each point are summed to calculate... Within a specific calculation window, the cumulative sum of the squares of the voltages is: Then sum and divide by the window width. Calculate the mean, and get Finally, the square root of this mean is calculated to obtain the effective value of the A-phase voltage corresponding to this window. The sliding window moves forward one sampling point to... In the new window, repeat the above calculations of squaring, summing, averaging, and taking the square root. This applies to the instantaneous current sequence. Perform the exact same calculation steps, if the sum of squares of the corresponding window currents is The mean is The effective value of the current is The process continues, generating sequences of effective voltage and effective current values.

[0064] The fundamental frequency extraction submodule calls the current effective value data in the voltage effective value sequence, uses discrete Fourier transform to decompose the current spectrum, extracts the real and imaginary components corresponding to the 50Hz frequency point, calculates the complex modulus and multiplies it by the spectral resolution coefficient Δf=1 / T, where T is the total signal sampling time, to generate the fundamental frequency current amplitude.

[0065] The fundamental frequency extraction submodule calls the instantaneous current sequence. Specifically, it obtains the A-phase current instantaneous sequence from the signal acquisition submodule. A segment is extracted from the signal for analysis. The total signal duration used for spectrum analysis is set. The choice of frequency resolution and real-time computation needs to be balanced; here, we choose... Corresponding to include A data segment containing 10,000 sampling points. The Discrete Fourier Transform (DFT) algorithm is used to process this instantaneous current sequence containing 10,000 points. (in ) Perform spectral decomposition.

[0066] DFT calculations will output a series of discrete frequency points. Complex spectral components The spectral resolution is determined by the total sampling duration. The calculation process involves indexing each frequency. ( )implement We need to extract the component corresponding to the 50Hz power frequency point. The index of this frequency is... Calculations yielded real part and the virtual part Through calculation, we obtain and Next, the modulus of the complex component is calculated.

[0067]

[0068] Modulus of DFT calculation results Amplitude correction is needed to obtain the actual physical current amplitude. The standard correction method is to multiply by... The peak value is obtained. Therefore, the peak value of the fundamental current is... The fundamental current amplitude (RMS value) is the peak value divided by... ,Right now This step generates the fundamental current amplitude. .

[0069] Please see Figure 3 The energy efficiency analysis module includes:

[0070] The power calculation sub-module obtains the voltage effective value sequence and the fundamental current amplitude, performs phase alignment processing on the voltage value of each sampling point in the sequence, calculates the phase difference through an error compensation algorithm, multiplies the fundamental current amplitude after superimposing the cosine phase difference correction amount, and performs point-by-point operation according to the active power instantaneous value formula to generate an energy efficiency ratio sequence.

[0071] The power calculation sub-module obtains the voltage effective value sequence and the fundamental current amplitude. The A-phase voltage effective value (taken from the result of paragraph 2) is obtained from the effective value calculation sub-module, and the A-phase fundamental current amplitude (taken from the result of paragraph 3) is obtained from the fundamental extraction sub-module. To calculate the active power, the phase difference between the voltage and current fundamental components needs to be determined . This can be achieved by analyzing the voltage instantaneous sequence and the current instantaneous sequence . One method is to apply DFT to the voltage and current sequences respectively, extract the complex components corresponding to the 50Hz frequency point and , and the argument difference of them is the phase difference . The phase difference is obtained by calculation.

[0072] Considering that fixed phase errors may be introduced by sensors, lines, etc. in actual measurement, an error compensation algorithm is applied for correction. The calibration process can be tested by inputting signals with known phase differences, and a compensation lookup table or function is established. Let the compensated phase difference be , the compensation value be , then . The active power is calculated according to the formula . Substitute the obtained value into: . Calculate . Then the active power of A-phase is . The value obtained by this calculation represents the average active power at that moment or in that window, which is taken as a point in an “energy efficiency ratio” sequence (the term “energy efficiency ratio” is derived from the original text, and the actual calculation is the active power). Repeat this process for each calculation window to generate an energy efficiency ratio (active power) sequence.

[0073] The standard deviation analysis sub-module calls the energy efficiency ratio sequence, extracts the energy efficiency ratio data segment of 10 consecutive cycles in time sequence, calculates the arithmetic mean value of the data segment, executes square operation and accumulation on the difference between each value and the mean value, and calculates the dispersion through the standard deviation formula to obtain the standard deviation value.

[0074] The standard deviation analysis submodule calls the energy efficiency ratio (active power) sequence. The generated A-phase active power sequence is obtained from the power calculation submodule . A continuous data segment is taken in chronological order for volatility analysis, and a data segment with a length of 10 consecutive power frequency cycles is selected. If the power calculation is performed cycle by cycle, the latest 10 power values are taken. The obtained data segment is .

[0075] The arithmetic mean of this data segment containing numerical values is calculated . The calculation is

[0076] Then, the difference between each numerical value in the data segment and the mean value is calculated . The difference of the first point is . Then, a square operation is performed on each difference, and the squared difference of the first point is . All squared differences are accumulated to obtain . Then, the formula for the sample standard deviation is applied to calculate the degree of dispersion. The standard deviation value is . The standard deviation value of the data segment is 48.37 W.

[0077] The volatility determination submodule compares the standard deviation value with the preset volatility determination threshold value 0.05. When the threshold value is exceeded for 3 consecutive times, dynamic threshold adjustment is triggered. If the former is greater than the threshold value, a logical value of 1 is generated, otherwise a logical value of 0 is generated. The energy efficiency ratio sequence and the logical identifier are packaged into a key-value pair structure, and the volatility marker is output.

[0078] The volatility determination submodule compares the standard deviation value with the preset volatility determination threshold value. The active power standard deviation value calculated in the previous module is obtained. This value is compared with the preset volatility determination threshold value . The threshold value is set by referring to the power fluctuation statistical characteristics of the model of the water pump under a large number of normal operating conditions. Through analysis of historical data, the standard deviation of the 10-cycle power sequence during normal operation is calculated, and a series of standard deviation values are obtained. Let the average of these standard deviation values be , and the standard deviation of the standard deviation be . To cover most normal fluctuations (such as a 95% confidence interval), the threshold value is set to the mean plus twice the standard deviation, i.e. .

[0079] The standard deviation obtained in this calculation is compared with the threshold value The comparison is made. Because , the result of this determination is not over-limit. If the standard deviation calculation and determination are performed continuously three times, the results are , all of the three results are greater than the threshold , it is determined that the over-limit occurs continuously for three times. At this time, the dynamic threshold adjustment mechanism is triggered: the threshold is adjusted according to the average of the last three over-limit values, and the new threshold is , and the subsequent comparison will use the new threshold. According to the comparison result, if , an identification with a logical value of 1 is generated; if , an identification with a logical value of 0 is generated. The comparison , and therefore the logical identification is generated. Finally, the active power sequence and the generated logical identification are packaged into a key-value pair structure, which is represented as , and the fluctuation marker is output.

[0080] Please refer to Figure 4 , the insulation performance evaluation module includes:

[0081] The insulation detection triggering submodule triggers the water pump winding insulation impedance detection based on the fluctuation marker. The voltage difference between the two ends of the winding and the leakage current value are collected. The four-wire measurement method is used to eliminate the influence of contact resistance. Ohm's law is applied to calculate the insulation impedance, and the insulation impedance detection value is generated;

[0082] The insulation detection triggering submodule triggers the water pump winding insulation impedance detection based on the fluctuation marker. The system continuously monitors the fluctuation marker output by the last module. When the logical identification in the fluctuation marker becomes 1 (indicating abnormal power fluctuation, which may indicate potential problems), the insulation impedance detection program of the water pump motor winding is automatically started. Before performing the detection, the control system safely disconnects the three-phase power supply of the water pump motor. An insulation resistance tester (model Fluke1507, test voltage can be selected 250V, 500V, 1000V) is used, and a four-wire measurement method is used to eliminate the influence of lead resistance and contact resistance. The current output end L of the tester is connected to one phase terminal (U phase) of the motor winding, and the current return end E is connected to the ground terminal of the motor shell. At the same time, the voltage measurement end Guard line is connected to the U phase terminal, and the other voltage measurement line is connected to the motor shell ground terminal.

[0083] The test voltage range is selected as 500VDC. After starting the test, the tester applies a 500V DC voltage between the winding and the shell, and accurately measures the leakage current flowing through the insulation medium and the actual voltage difference between the two ends of the insulation medium. The voltage difference obtained in this measurement is , leakage current . The leakage current unit needs to be converted to amperes (A) for calculation, and the conversion rule is 1A=1000mA, so . Apply Ohm's law to calculate the insulation impedance. The insulation impedance detection value . Convert the result to the more commonly used unit of megaohms (MΩ), and the conversion rule is 1MΩ=1,000,000Ω, so . Generate the insulation impedance detection value .

[0084] The harmonic correction submodule calls the insulation impedance detection value, extracts the fundamental component and harmonic component amplitude of the energy efficiency ratio sequence, and uses the formula:

[0085] ;

[0086] The energy efficiency ratio sequence is corrected for harmonic interference to generate a harmonic-corrected energy efficiency ratio;

[0087] wherein, represents the harmonic-corrected energy efficiency ratio, represents the original energy efficiency ratio sequence, represents the harmonic distortion rate, is the harmonic weight factor, is the fundamental component proportion coefficient;

[0088] The harmonic correction submodule calls the insulation impedance detection value, and calls the energy efficiency ratio sequence (corrected to call the current instantaneous sequence for harmonic analysis). Get the insulation impedance detection value from the previous module . At the same time, for harmonic analysis, the current instantaneous sequence obtained by calling the signal acquisition submodule again , or get the calculated harmonic amplitude from the fundamental extraction submodule. Here we use the harmonic information obtained by DFT analysis in paragraph 3: the fundamental current effective value , and the effective values of the 2nd to 5th harmonic currents (n=2,3,4,5) also need to be calculated. By performing similar amplitude correction calculations on the modulus at the corresponding frequency , we get:

[0089] Second harmonic ( );

[0090] Third harmonic ( );

[0091] Fourth harmonic​ );

[0092] fifth harmonic );

[0093] these i.e. the harmonic distortion rate.

[0094] Set the weight factor of each harmonic These weight factors reflect the relative influence of different harmonics on the specific evaluation target (here, the correction of the energy efficiency ratio). The basis for their setting is statistical analysis of a large amount of operating data of similar water pumps, to study the correlation between different harmonic content and parameters such as energy efficiency index deviation, equipment failure rate, etc. Analysis shows that low-order harmonics (especially the 2nd and 3rd) have relatively greater impact on winding additional loss and temperature rise, so they are given higher weights. The set value is determined as: Calculate the fundamental component proportion coefficient This coefficient represents the proportion of the fundamental current in the total current. First, calculate the total current effective value containing the fundamental and 2nd to 5th harmonics

[0095] ;

[0096] Then the fundamental proportion coefficient is .

[0097] Call an original energy efficiency ratio index (here, it is assumed that the basic efficiency evaluation value without considering the influence of harmonics is set as ), and calculate using the harmonic correction formula . In the formula , represents the corrected energy efficiency ratio, represents the original energy efficiency ratio, is the th harmonic distortion rate, is the th harmonic weight factor, is the fundamental component proportion coefficient. All the sum terms are unitless ratios, so and have the same unit or are unitless ratios. Substitute the numerical values for calculation:

[0098] ;

[0099] ;

[0100] ;

[0101] ​​ ;

[0102] The benefit of the formula is that, by distinguishing the influence of different harmonics (through and ) and considering the dominant degree of the fundamental (through ), the overall influence of harmonics on the system energy efficiency index can be assessed more finely, resulting in a more accurate assessment result than relying solely on the original energy efficiency ratio or total harmonic distortion . The calculated harmonic-modified energy efficiency ratio . This result shows that, after considering the influence of key harmonics, the modified energy efficiency evaluation index is significantly different from the original value, which will serve as the input for subsequent evaluation. The harmonic-modified energy efficiency ratio .

[0103] The leakage current integral evaluation submodule collects the leakage current amplitude time-domain waveform of the cable joint, calls the harmonic-modified energy efficiency ratio, applies the trapezoidal method for discrete integral operation of the leakage current amplitude, sets the integral order to 2-order precision, and generates an insulation deterioration identifier when the insulation impedance detection value is less than 1 MΩ and the integral result exceeds 10 mA·s.

[0104] The leakage current integral evaluation submodule collects the leakage current amplitude time-domain waveform of the cable joint and calls the harmonic-modified energy efficiency ratio. In the case where the insulation impedance detection value (from paragraph 7) and the harmonic-modified energy efficiency ratio (from paragraph 8) are available, the system starts monitoring the leakage current at the connection between the water pump motor power cable and the junction box. A clamp-type leakage current sensor (model Hantek CC-65, measurement range 1 mA-65 ADC / AC) is used, which is clamped on the three-phase cable bundle near the cable joint (or measured separately for each phase and then combined). The sampling frequency of the sensor output signal is set to 1 kHz, and continuous monitoring is performed for a certain period of time, with the monitoring duration set to . The leakage current time series data is obtained, containing sampling points.

[0105] The trapezoidal integral rule is applied to the collected leakage current amplitude for discrete integral operation, estimating the total charge flowing through the insulation defect path within the monitoring period. The trapezoidal integral formula is , where is the sampling time interval. Setting the integral order to 2-order precision reflects the selection of the trapezoidal rule, which has a truncation error of . By accumulating the leakage current data (unit: mA) of 60000 sampling points, the integral result is . The result unit needs to be converted to The conversion rule is 1s = 1000ms. Therefore .

[0106] The calculated integral result is compared with the preset integral threshold . At the same time, it is checked whether the insulation impedance detection value is less than the preset insulation threshold . The setting of the insulation threshold is based on the requirement of the national or industry related electrical safety regulations on the insulation resistance of low voltage rotating motor, which generally stipulates that the insulation resistance of the motor in operation should not be lower than 1MΩ / kV (working voltage). For a 380V motor, the threshold is set to . The setting of the integral threshold is based on the risk assessment of heat accumulation and accelerated aging of insulation caused by long-term leakage of cable joints. Through experiments and experience, it is determined that when the cumulative leakage charge exceeds a certain value, the risk of failure increases significantly. Here, it is set to . In this example, , the condition of (i.e. ) is not met. Although the integral result meets the condition of (i.e. ), since the insulation resistance condition is not met, no insulation deterioration identifier is generated. In another scenario, if is measured, the condition is met, and the condition is also met. At this time, both conditions are met, and the insulation deterioration identifier is generated, with a logic value of 1.

[0107] Please refer to Figure 5 , the comprehensive diagnosis module includes:

[0108] The current threshold judgment submodule detects the motor bearing current data, extracts the effective value based on a 10ms sampling interval, extracts the insulation impedance detection value, compares the detection value with the preset current threshold point by point, and counts the length of the time window of continuous overrun. At the same time, based on the length of the time window, it is judged whether the continuous overrun condition is met, and the current overrun identifier is generated;

[0109] The current threshold judgment submodule detects the motor bearing current data. The bearing current is extracted by installing an insulating bearing on the non-driving end bearing seat of the motor or installing a grounding brush on the shaft, and connecting a special shaft current sensor (such as a Hall effect sensor). Real-time monitoring of the bearing current of the water pump motor. The sampling interval of the sensor is set to 10ms (corresponding to a sampling frequency ), and the instantaneous data of the bearing current is collected. The collected data is calculated for effective value, which adopts a similar method as paragraph 2, and the window width for effective value calculation is set to , comprising sampling points. Calculate the bearing current effective value of each window.

[0110] Obtain the bearing current effective value sequence. At the same time, obtain the insulation impedance detection value (using the value of paragraph 7 ). Compare the calculated bearing current effective value sequence with the preset bearing current threshold value point by point. The setting needs to consider the motor design (such as whether there is internal asymmetry), bearing type, lubrication state, load size and manufacturer's recommendations. According to the manual of the water pump motor of this model and the operation experience of similar equipment, the bearing current effective value under normal operating condition is usually less than 0.5A, so the threshold value is set to . Analyze a sequence of bearing current effective values: . Compare each value with the threshold value . It is found that the 3rd value (0.58A) to the 6th value (0.53A) exceeds the threshold value.

[0111] Statistical length of time window of continuous overrun. In this sequence, from the 3rd window to the 6th window, there are 4 windows of continuous overrun. Each window is 100ms long, so the total time of continuous overrun is . Determine whether the duration meets the preset continuous overrun condition . The setting is to prevent false judgment caused by temporary electrical transient or measurement noise, and its value is determined according to the cumulative effect of bearing corrosion damage, which is set to . Because the calculated continuous overrun time is greater than the set continuous overrun condition , the continuous overrun condition is met. Accordingly, a current overrun identifier is generated, and its state is set to true (logical value 1). If , the identifier state is false (logical value 0). A current overrun identifier with a true state is generated.

[0112] The identifier statistics submodule calls the trigger signal in the current overrun identifier, takes a fixed period as the statistical unit, accumulates the number of trigger signals, calculates the average of the time interval of adjacent triggers and the standard deviation of the duration of single trigger, and generates a trigger frequency statistics value;

[0113] The identifier statistics submodule calls the trigger signal in the current overrun identifier. The system monitors the state change of the current overrun identifier generated by the previous module. When the identifier state changes from false 0 to true 1, it is recorded as a trigger event. A fixed statistical period is set to summarize the trigger information, The selection should adapt to the typical time scale of fault development, while taking into account the timeliness of the alarm, which is set to In each 5-minute statistical cycle, the following statistics are performed:

[0114] 1. Accumulate the total number of times the current over-limit flag is triggered In a statistical cycle, if it is recorded that the flag changes from 0 to 1 a total of 4 times, then .

[0115] 2. Record the start time and end time of each triggering event (k = 1, 2, 3, 4).

[0116] 3. Calculate the time interval between the start times of two adjacent triggering events . If the triggering times are the 10th, 70th, 150th, and 250th seconds in the statistical cycle, respectively, then the time intervals are , , . Calculate the average of these time intervals .

[0117] 4. Calculate the duration of a single triggering event . According to the records, the durations of the 4 triggers are . Calculate the standard deviation of these durations . First, calculate the average duration . Then calculate the standard deviation

[0118] ;

[0119] Take the number of triggers , the average time interval , and the standard deviation of the duration in the statistical cycle as output results. Generate trigger frequency statistics.

[0120] The temperature rise calculation submodule collects the terminal box temperature time series data. Based on the temperature difference of the adjacent 10 seconds in the sliding time window, a difference sequence is constructed, and the least squares method is used for linear fitting of the sequence. The slope is extracted as the temperature rise rate per unit time, and the temperature rise rate coefficient is generated;

[0121] The temperature rise calculation submodule collects the terminal box temperature time series data. Through the PT100 platinum thermal resistance temperature sensor pre-installed inside the water pump motor terminal box near the terminal row position, connected to the data acquisition system, set the collection time interval to 1 second, continuously record the internal temperature of the terminal box, and get the temperature time series data in Celsius (°C). To analyze the temperature trend, a moving window is used to calculate the temperature rise rate. A moving time window is selected, with a length of .

[0122] At each time point, 60 temperature data points in the current window (past 60 seconds) are extracted , where is the relative time (e.g., 0s, 1s, …, 59s). The least squares method is used to linearly fit these 60 data points to find the best fitting straight line . The least squares method calculates the slope of the straight line (i.e., the temperature rise rate) using the formula , where . By calculating the data of a specific window (see Table 2), the slope of the fitting straight line .

[0123] Table 2: Time series data segment of junction box temperature (partial data in the window)

[0124] Time (relative seconds within the window) Temperature (°C) 0 55.21 1 55.25 … … 30 56.28 … … 59 57.35

[0125] As shown in Table 2, part of the temperature sampling data in a 60-second window used to calculate the temperature rise rate is shown. The calculated slope is considered as the temperature rise rate per unit time at the current time. This slope value is output as the temperature rise rate coefficient. The window is continuously moved and the calculation is repeated to generate a time series of temperature rise rate coefficients .

[0126] The fault determination submodule calls the state truth of the current overrun identification, the cumulative trend of the trigger frequency statistical value, and the temperature rise rate coefficient. The temperature rise rate coefficient is compared with the preset rate threshold value. If the current overrun identification is true or the temperature rise rate coefficient is overrun, the sustained rising trend of the trigger frequency statistical value is combined to generate the pump body winding aging fault code.

[0127] The fault determination submodule calls the state truth of the current overrun identification, the cumulative trend of the trigger frequency statistical value, and the temperature rise rate coefficient. This module integrates the output information of multiple previous modules for comprehensive diagnosis. 1. The current current overrun identification state is obtained from the current threshold judgment submodule. In this case, the state is true (logical value 1), indicating that sustained bearing current overrun is detected (from paragraph 10). 2. The trigger frequency statistical value is obtained from the identification statistical submodule, and its trend over time is analyzed. The number of triggers in the last three statistical periods (each 5 minutes) , resulting in the sequence (From paragraph 11). The sequence shows that the trigger frequency increases from 2 to 4 and remains at a high level, showing a continuous abnormality or upward trend. 3. Obtain the current terminal box temperature rise rate coefficient from the temperature rise calculation submodule (From paragraph 12).

[0128] Compare the obtained temperature rise rate coefficient with the preset temperature rise rate threshold . The setting needs to be based on the insulation level of the motor (such as F level, allowing temperature rise of 105K), rated operating temperature, heat dissipation conditions and related safety standards. For this water pump motor, according to its design and operating environment, the temperature rise rate continues to exceed is considered abnormal and may cause accelerated aging of insulation, so is set. Compare the current value with the threshold , the result is , indicating that the temperature rise rate is out of limit.

[0129] Finally, the fault logic is determined. The determination rule is: if (current out-of-limit flag is true) or (temperature rise rate coefficient is out of limit), and (trigger frequency statistical value shows a continuous high level or upward trend), it is determined that there is a fault. In this example:

[0130] Is the current out-of-limit flag true? Yes (state = 1).

[0131] Is the temperature rise rate coefficient out of limit? Yes .

[0132] Does the trigger frequency show a continuous high level or upward trend? Yes (sequence [2, 4, 4] shows a high level). Since at least one main condition (current out-of-limit or temperature rise out-of-limit, both are met here) is met, and the auxiliary condition (trigger frequency trend) is also met, the system determines that the fault condition of "pump body winding aging" is met. The corresponding fault code, such as "PUMP_AGING_01", is generated, and an alarm or record is output. If the main conditions are not met, or the main conditions are met but the trigger frequency trend is stable or decreasing, the fault code is not generated. The pump body winding aging fault code is generated.

[0133] The above is only a preferred embodiment of the present application, and is not intended to limit the present application in other forms. Any skilled person in the art can use the disclosed technical content to make changes or modifications to equivalent embodiments applied to other fields, but any simple modification, equivalent change and modification made according to the technical essence of the present application to the above embodiments, without departing from the technical solution content of the present application, still belongs to the protection scope of the present application technical solution.

Claims

1. An artificial intelligence-based water supply equipment electrical performance detection system, characterized in that, The system comprises: An electrical parameter acquisition module, configured to acquire three-phase voltage effective values and current effective values through a wide-frequency current transformer, calculate root mean square values in a cycle by using a sliding window integration method, extract 50Hz fundamental component amplitudes in a current waveform, generate voltage effective value sequences and fundamental current amplitudes, and deliver the voltage effective value sequences and the fundamental current amplitudes to an energy efficiency analysis module; The energy efficiency analysis module is configured to calculate active power instantaneous values based on the voltage effective value sequences and the fundamental current amplitudes, generate energy efficiency ratio sequences, perform a standard deviation operation on energy efficiency ratios of consecutive 10 cycles, generate a fluctuation mark when a threshold value 0.05 determined based on a 30-group sample confidence interval analysis is exceeded, and deliver the energy efficiency ratio sequences and the fluctuation mark to an insulation performance evaluation module; The insulation performance evaluation module is configured to trigger water pump winding insulation impedance detection based on the fluctuation mark, perform harmonic interference correction on the energy efficiency ratio sequences, unify cable joint leakage current amplitude units into amperes, simultaneously perform time domain integration operation on the cable joint leakage current amplitude, generate an insulation deterioration mark when an insulation impedance value is lower than 1MΩ and a leakage current integration value is greater than 10mA·s, and deliver the insulation impedance detection value and the insulation deterioration mark to a comprehensive diagnosis module; The energy efficiency analysis module comprises: A power calculation sub-module, configured to acquire the voltage effective value sequences and the fundamental current amplitudes, perform phase alignment processing on voltage values of each sampling point in the sequences, calculate a phase difference by using an error compensation algorithm, multiply the phase difference by the fundamental current amplitudes, superimpose a cosine phase difference correction amount, perform point-by-point operation according to an active power instantaneous value formula, and generate energy efficiency ratio sequences; A standard deviation analysis sub-module, configured to call the energy efficiency ratio sequences, intercept energy efficiency ratio data segments of consecutive 10 cycles in time sequence, calculate an arithmetic mean value of values in the data segments, perform square operation on a difference between each value and the mean value and accumulation, and calculate a dispersion by using a standard deviation formula to obtain a standard deviation value; A fluctuation determination sub-module, configured to perform numerical comparison between the standard deviation value and a preset fluctuation determination threshold value 0.05, trigger dynamic threshold value adjustment when the determination is out of limit for three times in succession, generate a mark with a logical value of 1 if the former is greater than the threshold value, otherwise generate a mark with a logical value of 0, encapsulate the energy efficiency ratio sequences and the logical mark into a key-value pair structure, and output a fluctuation mark; The insulation performance evaluation module comprises: An insulation detection triggering sub-module, configured to trigger water pump winding insulation impedance detection based on the fluctuation mark, acquire voltage differences and leakage current values at both ends of the winding, eliminate the influence of contact resistance by using a four-wire measurement method, calculate insulation impedance by using Ohm's law, and generate insulation impedance detection values; A harmonic correction sub-module, configured to call the insulation impedance detection values, extract fundamental component amplitudes and harmonic component amplitudes of the energy efficiency ratio sequences, perform harmonic interference correction on the energy efficiency ratio sequences by using a formula: ； ​ wherein, represents a harmonic corrected energy efficiency ratio, represents a raw energy efficiency ratio sequence, represents a first harmonic distortion rate, is a first harmonic weight factor, is a fundamental component proportion coefficient; The leakage current integral evaluation submodule collects the leakage current amplitude time domain waveform of the cable joint, calls the harmonic correction energy efficiency ratio, applies the trapezoidal method to perform discrete integral operation on the leakage current amplitude, sets the integral order to 2-order precision, generates an insulation deterioration identifier when the insulation impedance detection value is less than 1MΩ and the integral result exceeds 10mA·s; The comprehensive diagnosis module comprises: The current threshold judgment submodule detects the motor bearing current data, extracts the effective value based on a 10ms sampling interval, extracts the insulation impedance detection value, compares the detection value with a preset current threshold point by point, counts the length of the time window that continuously exceeds the limit, and simultaneously judges whether the continuous exceeding condition is met based on the length of the time window, to generate a current exceeding limit identifier; The identifier statistics submodule calls the trigger signal in the current exceeding limit identifier, takes a fixed period as a statistical unit, accumulates the number of trigger signals, calculates the average of the time interval of adjacent triggers and the standard deviation of the duration of a single trigger, and generates a trigger frequency statistical value; The temperature rise calculation submodule collects the terminal box temperature time series data, constructs a difference sequence based on the adjacent 10-second temperature difference values in the sliding time window, performs linear fitting on the sequence using the least squares method, extracts the slope as the temperature rise rate per unit time, and generates a temperature rise rate coefficient; The fault determination submodule calls the state authenticity of the current exceeding limit identifier, the cumulative trend of the trigger frequency statistical value, and the temperature rise rate coefficient, compares the temperature rise rate coefficient with a preset rate threshold, and if the current exceeding limit identifier is true or the temperature rise rate coefficient exceeds the limit, combines the rising trend of the trigger frequency statistical value to generate a pump body winding aging fault code. 2.The artificial intelligence-based water supply equipment electrical performance detection system according to claim 1, wherein The voltage effective value sequence includes the periodic root mean square voltage, the three-phase voltage amplitude change trend, and the voltage fluctuation characteristics; the fundamental current amplitude includes the fundamental amplitude estimation result, the current symmetry index, and the current waveform stability index; the energy efficiency ratio sequence includes the periodic power factor, the active power mean value change trend, and the load response characteristic; the fluctuation marker specifically includes the energy efficiency ratio fluctuation warning identifier, the fluctuation period calibration, and the fluctuation intensity level; and the insulation impedance detection value includes the water pump winding insulation decay degree, the insulation response time index, and the impedance value time sequence. 3.The water supply equipment electrical performance detection system based on artificial intelligence according to claim 2, characterized in that, The standard deviation determination threshold value 0.05 is determined based on confidence interval analysis of 30 groups of samples, and the confidence level is 95%; The leakage current integral value 0.01A·s is obtained by performing time domain integral operation after unifying the cable joint leakage current amplitude unit to amperes.

4. The artificial intelligence-based water supply equipment electrical performance detection system according to claim 3, characterized in that, The electrical parameter acquisition module comprises: The signal acquisition submodule synchronously acquires three-phase voltage instantaneous analog quantities and current instantaneous analog quantities through a wide-frequency current transformer, performs differential amplification processing on the analog signals, realizes noise elimination with a common-mode rejection ratio ≥80dB, configures a band-pass filter to suppress high-frequency harmonic components with a decay coefficient of -40dB / dec, and generates three-phase voltage instantaneous sequences and three-phase current instantaneous sequences; The effective value calculation submodule calls the three-phase voltage instantaneous sequence and the three-phase current instantaneous sequence, sets a sliding window width as an integer multiple of a power frequency period of 20 ms, performs a square operation on voltage instantaneous values point by point in the window, calculates a mean value after accumulation and calculates a square root, and generates a voltage effective value sequence; The fundamental wave extraction submodule calls current effective value data in the voltage effective value sequence, decomposes a current spectrum by using a discrete Fourier transform, extracts real and imaginary parts corresponding to a 50 Hz frequency point, calculates a complex modulus and multiplies the complex modulus by a spectrum resolution coefficient Δf=1 / T, wherein T is a total signal sampling duration, and generates a fundamental wave current amplitude. 5.The artificial intelligence-based water supply equipment electrical performance detection system according to claim 1, wherein, The system further comprises: The comprehensive diagnosis module is used for judging whether a motor bearing current exceeds a 5 mA threshold value collected by a Hall sensor at a frequency of 10 kHz based on the insulation impedance detection value, counting a number of times of triggering of the insulation degradation identifier, performing linear regression calculation on a temperature rise rate of a junction box simultaneously, constructing a temperature difference value sequence by using a time window sliding mechanism, and generating a pump body winding aging fault code when the bearing current is out of limit or the temperature rise rate exceeds 2 ℃ / min. 6.The system for detecting electrical performance of water supply equipment based on artificial intelligence according to claim 5, wherein, The pump body winding aging fault code specifically refers to a motor bearing fault type identifier, a fault triggering condition record and a pump body temperature rise trend code.

Images