Artificial Intelligence-based Intelligent Inspection System for Power Equipment

Abstract

The present invention relates to the technical field of industrial equipment management, specifically an intelligent power equipment inspection system based on artificial intelligence. The system includes: a fault mode generation module, a fault detection module, a fault classification module, an inspection feature optimization module, and an abnormal prediction and evaluation module. In the present invention, by collecting multi-dimensional operating parameters of power equipment, analyzing the signal amplitude distribution and frequency domain changes, the comprehensiveness of equipment status perception is optimized. Combining the dynamic feature range and signal distribution deviation matching, potential fault features are accurately identified, and the accuracy of signal anomaly detection is improved. By extracting the differential characteristic values of current and temperature signals, the fault type classification is optimized, and the positioning ability of the problem root cause is enhanced. Dynamically extracting and matching signal trends, generating an inspection parameter matrix, and realizing global dynamic monitoring of the operating state. Based on the prediction model of signal change rate and time node range, the real-time performance and accuracy of abnormal trend prediction are improved, and the reliability of equipment operation and maintenance is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment management, and particularly to an intelligent inspection system for power equipment based on artificial intelligence. Background Art

[0002] The technical field of industrial equipment management includes technologies for real-time monitoring and analysis of the operating status of industrial production equipment, fault diagnosis, status prediction, and operation and maintenance optimization. The core content of this technical field is to collect equipment operation parameters through sensors and combine data processing technologies to achieve the monitoring and evaluation of the equipment operating status. Systematically speaking, industrial equipment management covers a series of tasks from the collection and storage of equipment operation data, status evaluation and fault diagnosis, to maintenance and optimization decisions. Its purpose is to ensure the safe and stable operation of equipment, improve production efficiency, and extend the service life of equipment.

[0003] Among them, an intelligent inspection system for power equipment based on artificial intelligence refers to a system that uses artificial intelligence technology to automatically inspect and monitor the status of power equipment. The system focuses on the real-time status perception and potential fault analysis of power equipment, covering content such as extracting the appearance features of power equipment based on image recognition technology, detecting abnormalities in the operation parameters of power equipment based on data analysis technology, and comprehensively analyzing the equipment operation status through knowledge graph technology. The system mainly relies on the integration and analysis of multi-dimensional power equipment data to achieve intelligent inspection and comprehensive evaluation of the equipment status.

[0004] In the prior art, for equipment status perception, it relies on single-parameter monitoring and cannot comprehensively analyze multi-dimensional data, resulting in insufficient coverage of the identification of potential problems. Static data models cannot capture the dynamic changes of operating signals, and the diagnosis responds sluggishly to real-time status. Fixed parameter ranges limit the effective identification of non-standard abnormalities and are prone to missing potential faults in complex scenarios. Image recognition and single analysis methods are easily interfered by the external environment, with insufficient stability and accuracy in data collection, affecting the effectiveness of equipment status evaluation, reducing the reliability of anomaly prediction, and being difficult to support the efficient operation and maintenance requirements of complex power equipment. Summary of the Invention

[0005] The purpose of the present invention is to solve the drawbacks existing in the prior art and propose an intelligent inspection system for power equipment based on artificial intelligence.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: An intelligent inspection system for power equipment based on artificial intelligence includes:

[0007] The fault mode generation module obtains the operation parameters of power equipment through the inspection robot, inputs the current value, temperature value and vibration signal value, statistically analyzes the amplitude distribution of the signals, extracts the frequency domain characteristics and change rate of the signals, calculates the dynamic characteristic range of the signals, establishes a fault characteristic mapping model, adjusts the parameters to match the signal distribution deviation, and generates a fault mode distribution value;

[0008] The fault detection module, based on the fault mode distribution value, obtains the current signal offset value and frequency domain deviation amount in the inspection signal, compares the interval difference between the inspection signal and the normal operation parameters, calculates the amplitude difference rate of the signal abnormality, establishes a fault characteristic deviation model, and generates the abnormal signal amplitude ratio;

[0009] The fault classification module, based on the abnormal signal amplitude ratio, analyzes the characteristic values of the current signal and the temperature signal in the differential interval, compares the overlap degree between the signal characteristic values and the fault category interval, establishes a classification characteristic matrix, screens the signal contribution rate, and generates a fault type distribution coefficient;

[0010] The inspection feature optimization module, based on the fault type distribution coefficient, extracts the local trend value and global change rate of the current and temperature signals, normalizes the signal category feature weights, dynamically matches the signal trend, extracts the inspection parameter matrix, and calculates the inspection feature weight distribution value;

[0011] The abnormal prediction and evaluation module, based on the inspection feature weight distribution value, analyzes the change rate of the vibration signal and the temperature signal, establishes a dynamic trend matrix, calculates the signal change range at the time node, establishes a time distribution prediction model, and generates an abnormal trend prediction value.

[0012] The fault mode distribution value specifically includes the signal amplitude distribution, the frequency domain characteristics and change rate of the signal, and the dynamic characteristic range of the signal. The fault characteristic deviation model includes the current signal offset value, the frequency domain deviation amount, and the signal abnormal amplitude difference rate. The abnormal signal amplitude ratio includes the current signal characteristic value, the temperature signal characteristic value, and the overlap degree between the signal characteristic value and the fault category interval. The fault type distribution coefficient specifically includes the classification characteristic matrix and the signal contribution rate. The inspection feature weight distribution value specifically includes the local trend value, the global change rate, and the signal category feature weight. The abnormal trend prediction value includes the vibration signal change rate, the temperature signal change rate, and the signal change range at the time node.

[0013] As a further solution of the present invention, the steps for obtaining the fault mode distribution value are specifically as follows:

[0014] Extract the amplitude distribution of the current value, temperature value and vibration signal value, calculate the change rate of the amplitudes of multiple signals in the frequency domain, and generate an amplitude distribution change rate parameter;

[0015] Call the parameter of the amplitude distribution change rate, compare its value with the upper and lower limits to determine whether it exceeds the dynamic feature range, classify the signal amplitudes according to the frequency domain characteristics, extract the signal feature change values that meet the conditions for the upper and lower limits of the dynamic feature range, and calculate and generate the signal change rate within the dynamic feature range;

[0016] Call the signal change rate within the dynamic feature range, analyze the distribution deviation, and at the same time correct the signal feature value mapping relationship based on the adjustment parameter, using the formula:

[0017] ;

[0018] Calculate and generate the fault mode distribution value;

[0019] Wherein, represents the fault mode distribution value, represents the change rate of the signal feature value, represents the weight of the signal amplitude, represents the lower limit of the dynamic feature range, represents the upper limit of the dynamic feature range, represents the weight coefficient of the adjustment parameter, represents the signal feature mapping value, represents the signal feature mean value, represents the number of signal feature points, represents the number of signal mapping points, 、 are the indexes of the signal feature point and the mapping point respectively.

[0020] As a further solution of the present invention, the specific steps for obtaining the abnormal signal amplitude ratio are as follows:

[0021] According to the fault mode distribution value, obtain the offset value and the frequency domain deviation amount of the current signal in the inspection signal, use the frequency domain deviation amount to statistically analyze the change range of the differential signal, classify and organize the offset value and the change range, and generate the current signal deviation data;

[0022] Call the current signal deviation data, compare the interval difference between the inspection signal and the normal operation parameters, analyze the change trend of the deviation amplitude by calculating the deviation amplitude of the inspection signal in multiple intervals, statistically analyze the amplitude difference rate of the signal abnormality, and generate the signal abnormal amplitude difference data;

[0023] Use the signal abnormal amplitude difference data to establish a fault feature deviation model, using the formula:

[0024] ;

[0025] Generate the abnormal signal amplitude ratio;

[0026] Wherein, represents the overall proportion of signal deviation, represents the amplitude of the th signal observation value, represents the normal amplitude reference of the th signal, represents the number of all signal data points,

[0027] As a further solution of the present invention, the steps for obtaining the fault type distribution coefficient are specifically as follows:

[0028] Based on the abnormal signal amplitude ratio, analyze the characteristic values of the current signal and the temperature signal in the differential interval, and at the same time classify the fluctuation values and frequency domain characteristics of the signals in the differential interval item by item to generate differential characteristic data;

[0029] Call the differential characteristic data, compare the overlap degree between the signal characteristic values and the fault category intervals, and through the statistics and sorting of the signal amplitude contribution rate in the overlapping intervals, combine the signal characteristic weight parameters to analyze the key points of multiple category intervals to generate signal contribution rate data;

[0030] Use the signal contribution rate data to establish a classification characteristic matrix, and by calculating the weight relationship between the characteristic distribution of the differential signal categories and the fault category intervals, use the formula:

[0031] ;

[0032] Calculate and generate the fault type distribution coefficient;

[0033] Among them, represents the fault type distribution coefficient, represents the th type of signal contribution rate, represents the th type of signal weight, represents the th type of signal normal reference contribution rate, represents the th type of signal amplitude contribution in the th interval, represents the number of signal categories, represents the number of intervals, is the signal category index,

[0034] As a further solution of the present invention, the steps for obtaining the inspection feature weight distribution value are specifically as follows:

[0035] Based on the fault type distribution coefficient, extract the local trend values and global change rates of the current and temperature signals. By analyzing the fluctuation characteristics of the signals in the local and global ranges item by item and combining the change rules of the signal trends, generate local and global signal analysis data;

[0036] Call the local and global signal analysis data, normalize the signal category feature weights. By calculating the proportion of multi-category signal feature values, normalize the signal categories to a unified range and assign the feature weights of multi-category signals to generate normalized signal weight data;

[0037] Use the normalized signal weight data to dynamically match the signal trends, extract the inspection parameter matrix, and use the formula:

[0038] ;

[0039] Calculate and generate the inspection feature weight distribution value;

[0040] Among them, represents the inspection feature weight distribution value, represents the local trend value of the th type of signal, represents the global change rate of the th type of signal, represents the normalized weight of the th type of signal, represents the stability index of the th type of signal, represents the number of signal categories, is the signal category index.

[0041] As a further solution of the present invention, the specific steps for obtaining the abnormal trend prediction value are as follows:

[0042] Based on the inspection feature weight distribution value, analyze the change rates of the vibration signal and the temperature signal. By calculating the change ratio between the signal fluctuation amplitude and the time interval and combining the signal characteristic parameters, extract the dynamic change rate of each signal to generate change rate data;

[0043] Call the change rate data, establish a dynamic trend matrix. By calculating the change amplitude and distribution law of the signal at different time nodes and combining the signal fluctuation characteristics, extract the time node signal change range data;

[0044] Use the time node signal change range data to establish a time distribution prediction model. Combining the dynamic changes of the signal and the time node distribution, use the formula:

[0045] ;

[0046] Calculate and generate the abnormal trend prediction value;

[0047] Wherein, represents the abnormal trend prediction value, represents the change rate of the type of signal, represents the time node value of the type of signal, represents the mean value of the time nodes, represents the standard deviation of the time nodes, represents the th signal strength value, represents the number of signal categories, represents the number of time nodes, , are the indices of the signal category and the time node respectively.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0049] In the present invention, by collecting multi-dimensional operation parameters of power equipment, including current values, temperature values, and vibration signal values, analyzing the signal amplitude distribution and frequency domain changes, the comprehensiveness of equipment status perception is optimized. Combining the dynamic feature range and signal distribution deviation matching, potential fault features are accurately identified, and the accuracy of signal abnormality detection is improved. By extracting the differential feature values of current and temperature signals, the fault type classification is optimized, and the positioning ability of the problem root cause is enhanced. Dynamically extracting and matching signal trends, generating an inspection parameter matrix, and realizing global dynamic monitoring of the operation status. Based on the prediction model of signal change rate and time node range, the real-time performance and accuracy of abnormal trend prediction are improved, and the reliability of equipment operation and maintenance is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is the system flow chart of the present invention;

[0051] Figure 2 is the flow chart of the steps for obtaining the fault mode distribution value of the present invention;

[0052] Figure 3 is the flow chart of the steps for obtaining the abnormal signal amplitude ratio of the present invention;

[0053] Figure 4 is the flow chart of the steps for obtaining the fault type distribution coefficient of the present invention;

[0054] Figure 5 is the flow chart of the steps for obtaining the inspection feature weight distribution value of the present invention;

[0055] Figure 6 is the flow chart of the steps for obtaining the abnormal trend prediction value of the present invention. Specific Embodiments

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the accompanying drawings. These are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0058] Embodiment 1: Please refer to Figure 1 , the intelligent inspection system for power equipment based on artificial intelligence includes:

[0059] The fault mode generation module obtains the operation parameters of the power equipment through the inspection robot, inputs the current value, temperature value and vibration signal value, statistically analyzes the amplitude distribution of the signals, extracts the frequency domain characteristics and change rate of the signals, calculates the dynamic characteristic range of the signals, establishes a fault characteristic mapping model, adjusts the parameters to match the signal distribution deviation, and generates a fault mode distribution value;

[0060] The fault detection module, based on the fault mode distribution value, obtains the current signal offset value and frequency domain deviation amount in the inspection signal, compares the interval difference between the inspection signal and the normal operation parameters, calculates the amplitude difference rate of the signal abnormality, establishes a fault characteristic deviation model, and generates the abnormal signal amplitude ratio;

[0061] The fault classification module, based on the abnormal signal amplitude ratio, analyzes the characteristic values of the current signal and the temperature signal in the differential interval, compares the overlap degree between the signal characteristic values and the fault category interval, establishes a classification characteristic matrix, screens the signal contribution rate, and generates a fault type distribution coefficient;

[0062] The inspection feature optimization module, based on the fault type distribution coefficient, extracts the local trend value and global change rate of the current and temperature signals, normalizes the signal category feature weights, dynamically matches the signal trends, extracts the inspection parameter matrix, and calculates the inspection feature weight distribution value;

[0063] Based on the distribution value of the inspection feature weights, the anomaly prediction and evaluation module analyzes the change rates of vibration signals and temperature signals, establishes a dynamic trend matrix, calculates the signal change range at time nodes, establishes a time distribution prediction model, and generates anomaly trend prediction values.

[0064] The failure mode distribution values specifically include signal amplitude distribution, signal frequency domain characteristics and change rates, and signal dynamic characteristic ranges. The failure feature deviation model includes current signal offset values, frequency domain deviation amounts, and signal anomaly amplitude difference rates. The abnormal signal amplitude ratio includes current signal characteristic values, temperature signal characteristic values, and the overlap degree between signal characteristic values and the fault category interval. The failure type distribution coefficient specifically includes a classification feature matrix and a signal contribution rate. The inspection feature weight distribution value specifically includes local trend values, global change rates, and signal category feature weights. The anomaly trend prediction values include vibration signal change rates, temperature signal change rates, and signal change ranges at time nodes.

[0065] Please refer to Figure 2 , and the steps for obtaining the failure mode distribution values are specifically as follows:

[0066] Extract the amplitude distributions of current values, temperature values, and vibration signal values, calculate the change rates of multi-signal amplitudes in the frequency domain, and generate amplitude distribution change rate parameters;

[0067] Screen the numerical ranges for each signal type, classify their segmented distributions into multiple intervals according to the magnitude of the amplitude, calculate the average amplitude and standard deviation of each segment one by one, and use the calculation results to draw an amplitude distribution diagram to display the frequency domain feature distribution and change rates of the signals, and obtain the amplitude distribution change rate parameters.

[0068] Call the amplitude distribution change rate parameters, compare their values with the dynamic characteristic range according to the upper and lower limits, classify the signal amplitudes according to the frequency domain characteristics, extract the signal characteristic change values that meet the conditions for the upper and lower limits of the dynamic characteristic range, and calculate and generate the signal change rate within the dynamic characteristic range;

[0069] By setting the upper and lower limits of the dynamic characteristic range as reference values respectively, gradually screen whether the signal amplitude distribution exceeds the upper and lower limit ranges, compare the filtered signal characteristic change values with the dynamic characteristic range to extract the signal change rate within the dynamic range; accumulate each signal value that meets the range item by item and then calculate the average change rate, and combine the cumulative amplitude change rate to generate the signal change rate within the dynamic characteristic range.

[0070] Call the signal change rate within the dynamic characteristic range, analyze the distribution deviation, and at the same time correct the signal characteristic value mapping relationship based on the adjustment parameters, using the formula:

[0071] ;

[0072] Calculate and generate the failure mode distribution values;

[0073] Among them, represents the failure mode distribution value, represents the change rate of the signal characteristic value, represents the weight of the signal amplitude, represents the lower limit of the dynamic characteristic range, represents the upper limit of the dynamic characteristic range, represents the weight coefficient of the adjustment parameter, represents the signal characteristic mapping value, represents the signal characteristic mean value, represents the number of signal characteristic points, represents the number of signal mapping points, 、 are the indexes of the signal characteristic points and mapping points respectively.

[0074] Formula:

[0075] ;

[0076] The advantage of the formula is that by simultaneously introducing the signal amplitude change rate, weight, dynamic characteristic range, and signal characteristic mapping value into the calculation, the dynamic change characteristics of the signal can be comprehensively evaluated, and the accuracy of the signal distribution model can be significantly improved.

[0077] Detailed explanation of the formula and the derivation process of the formula calculation:

[0078] ;

[0079] Calculate the denominator:

[0080] ;

[0081] Calculate the numerator:

[0082] ;

[0083] Calculate the fractional term:

[0084] ;

[0085] Calculate the summation term:

[0086] ;

[0087] Calculate the square term:

[0088] ;

[0089] Calculate the sum of squares:

[0090] ;

[0091] Calculate the square root term:

[0092] ;

[0093] Calculate the weighted term:

[0094] ;

[0095] Calculate the final result:

[0096] ;

[0097] The result shows that the fault mode distribution value of the signal is 2.191, which is directly related to the amplitude distribution change rate, the change rate within the dynamic characteristic range, and the mapping characteristic value of the signal. Through this value, the signal distribution characteristics can be effectively characterized, and further, it can be used to generate a fault feature mapping model.

[0098] Please refer to Figure 3 , and the specific steps for obtaining the abnormal signal amplitude ratio are as follows:

[0099] According to the fault mode distribution value, obtain the offset value and frequency domain deviation amount of the current signal in the inspection signal, use the frequency domain deviation amount to statistically analyze the change range of the differential signal, classify and organize the offset value and the change range, and generate current signal deviation data;

[0100] Use the signal offset value and frequency domain deviation amount in the fault mode distribution data to perform segmented analysis on the signal offset value, compare the frequency domain deviation amount with the preset reference signal, determine the offset amplitude interval, and quantify the change amplitude in each frequency domain segment by calculating the relative change between the offset value and the reference signal in each frequency domain segment. Adopt the frequency domain segment average calculation formula: , where represents the average offset amount in the frequency domain, represents the offset value within the signal frequency domain segment, represents the reference frequency domain segment value of the signal, represents the number of frequency domain segments, and use this calculation formula to process all offset signals segment by segment, and generate current signal deviation data through the normalization method.

[0101] Call the current signal deviation data, compare the interval difference between the inspection signal and the normal operation parameters, analyze the change trend of the deviation amplitude by calculating the deviation amplitude of the inspection signal in multiple intervals, statistically analyze the amplitude difference rate of signal anomalies, and generate signal anomaly amplitude difference data;

[0102] Perform segmented classification analysis on the interval difference between the signal deviation value and the normal operation parameters, extract the interval data with larger deviation values according to the classification results, and calculate the change rate of the deviation amplitude within the deviation interval by using the change rate calculation formula: , where represents the deviation change rate, represents the absolute change in the deviation amplitude, represents the average amplitude of the reference signal. Calculate the change rate for each interval and combine them to form the global signal deviation change rate curve, generating signal abnormal amplitude difference data.

[0103] Using the signal abnormal amplitude difference data, establish a fault feature deviation model, using the formula:

[0104] ;

[0105] Generate the abnormal signal amplitude ratio;

[0106] where represents the overall ratio of the signal deviation, represents the th amplitude of the signal observation value, represents the th normal amplitude reference of the signal, represents the number of all signal data points, is the index of the signal data point.

[0107] Formula:

[0108] ;

[0109] The advantage of the formula is that by introducing the sum of squares of the relative differences in signal amplitudes for normalization, the sensitivity of the deviation calculation to the abnormal signal distribution is enhanced, and the accuracy of signal deviation quantification and the robustness of the calculation are improved;

[0110] Detailed explanation of the formula and the derivation process of formula calculation:

[0111] where represents the overall ratio of the signal deviation, represents the th amplitude of the signal observation value, represents the th normal amplitude reference of the signal, represents the number of all signal data points, is the index of the signal data point. Assume the observed signal amplitude is , and the reference signal amplitude is , substitute into the formula:

[0112] ;

[0113] Calculate step by step to get:

[0114] ;

[0115] ;

[0116] ;

[0117] The result shows that the abnormal signal amplitude ratio is 0.0295, indicating a low degree of signal deviation. The reasons and distribution characteristics of signal anomalies can be further analyzed by combining other data to generate the abnormal signal amplitude ratio.

[0118] Please refer to Figure 4 , and the specific steps for obtaining the fault type distribution coefficient are as follows:

[0119] Based on the abnormal signal amplitude ratio, analyze the characteristic values of the current signal and temperature signal in the differential interval. At the same time, classify the fluctuation values and frequency domain characteristics of the signals in the differential interval item by item to generate differential characteristic data;

[0120] Call the numerical value in the abnormal signal amplitude ratio as the benchmark, cross-compare it with the characteristic signals in the differential interval, identify the range of intervals with significant signal differences, extract the amplitude fluctuation parameters and time series characteristic values of the current signal and temperature signal in each differential interval respectively, and perform normalization processing in combination with the change range of the differential amplitude to standardize the statistical benchmark values of each signal. Subsequently, classify the normalized results using the frequency domain distribution characteristics in the time series, map the differential signals to different characteristic value intervals, classify and statistically analyze the signal amplitude fluctuations in each interval to generate differential characteristic data.

[0121] Call the differential characteristic data, compare the overlap degree between the signal characteristic values and the fault category intervals, and generate signal contribution rate data by statistically sorting and analyzing the signal amplitude contribution rates in the overlapping intervals and combining the signal characteristic weight parameters to analyze the key points of multiple category intervals;

[0122] Perform boundary judgment on the signal characteristic values through the characteristic boundary range of the fault category interval to determine whether each signal category is in the overlapping interval, statistically analyze the contribution rate of the signal amplitude in each overlapping interval, classify and summarize the amplitude contribution rates of the signal categories, calculate the distribution range and central value of the amplitude for the category with a larger contribution rate, adjust the central value in combination with the characteristic weight parameters of the signal category, and statistically obtain the overall contribution rate of each signal category to generate signal contribution rate data.

[0123] Use the signal contribution rate data to establish a classification feature matrix. By calculating the weight relationship between the characteristic distribution of the differential signal categories and the fault category intervals, using the formula:

[0124] ;

[0125] Calculate and generate the fault type distribution coefficient;

[0126] Among them, represents the fault type distribution coefficient, represents the contribution rate of the th type of signal, represents the weight of the th type of signal, represents the normal reference contribution rate of the th type of signal, represents the amplitude contribution of the th type in the rd interval, represents the number of signal categories, represents the number of intervals, is the signal category index, is the interval index.

[0127] Formula:

[0128] ;

[0129] The advantage of the formula is that by combining the calculation of the signal category weight parameter and the signal contribution rate , and combining the logarithmic deviation and absolute value operation of the normal reference contribution rate , the ability to distinguish the fault category feature distribution is improved, and then the accuracy of fault classification is optimized;

[0130] Detailed explanation of the formula and the derivation process of the formula calculation:

[0131] Assume that the number of signal categories is , and the number of intervals is ;

[0132] The signal contribution rate is , , ;

[0133] The weight corresponding to the signal category is , , ;

[0134] The corresponding normal reference contribution rate is , , ;

[0135] The sum of the contribution rates of each interval is , , ;

[0136] Specific calculation process:

[0137] 1. Calculate the logarithmic deviation:

[0138] ;

[0139] ;

[0140] ;

[0141] 2. Calculate the product of the absolute value of the logarithm and the weight:

[0142] ;

[0143] ;

[0144] ;

[0145] 3. Take the square root after summation:

[0146] ;

[0147] ;

[0148] ;

[0149] The result shows that the fault type distribution coefficient indicates that there are significant differences in the contribution rates of signal categories within the interval. After adjusting the weights and deviations of the classification feature matrix, fault classification can more accurately distinguish the distribution of signal category features.

[0150] Please refer to Figure 5 for the specific steps to obtain the distribution values of the inspection feature weights:

[0151] Based on the fault type distribution coefficient, extract the local trend values and global change rates of the current and temperature signals. By analyzing the fluctuation characteristics of the signals in the local and global ranges item by item, and combining the change rules of the signal trends, generate local and global signal analysis data;

[0152] By extracting the local trend values and global change rates of the current and temperature signals, according to the fluctuation characteristics of the signals in different time periods, first extract the maximum value, minimum value, and average change rate of each signal within a fixed time interval, then classify the fluctuation range of the signal into segments, calculate its local trend value through segmented statistics, compare it with the global signal change range to calculate the global change rate. The global change rate is obtained by dividing the total change amount of the signal by the number of samples within the complete time period. At the same time, combine the classified local trend values and global change rates for cross-comparison, and analyze the change pattern of the signal through the superposition of the two to generate local and global signal analysis data.

[0153] Call the local and global signal analysis data, normalize the signal category feature weights, normalize the signal categories to a unified range by calculating the proportion of multi-category signal feature values, and assign the feature weights of multi-category signals to generate normalized signal weight data;

[0154] First, divide the feature weights of each signal category proportionally, normalize its feature values to the range between 0 and 1 according to the total weight within the category, and use the normalization formula: , calculate the normalized weight, where represents the original weight of the signal, and the normalized weight After calculation, it will be redistributed by category, and at the same time, the weight will be dynamically adjusted according to the ratio of the signal fluctuation frequency and the total number of samples. Through the dynamic adjustment formula: , in is the fluctuation frequency of the signal. Then, combine the feature weights of the normalized signal with the dynamic weight adjustment comparison to generate normalized signal weight data.

[0155] Use the normalized signal weight data to dynamically match the signal trend, extract the inspection parameter matrix, and use the formula:

[0156] ;

[0157] Calculate and generate the inspection feature weight distribution value;

[0158] Among them, represents the inspection feature weight distribution value, represents the local trend value of the th category of signal, represents the global change rate of the th category of signal, represents the normalized weight of the th category of signal, represents the stability index of the th category of signal, represents the number of signal categories,

[0159] Formula:

[0160] ;

[0161] The benefit of the formula is that by combining the local trend value, global change rate, normalized weight, and signal stability factor, it can dynamically reflect the contribution of different signal categories to the overall inspection parameter matrix and improve the accuracy of the signal weight distribution;

[0162] Detailed explanation of the formula and the derivation process of formula calculation:

[0163] Set the local trend value , the global change rate , the normalized weight , the signal stability index , substitute the above parameters into the formula:

[0164] ;

[0165] Calculate item by item:

[0166] ;

[0167] ;

[0168] ;

[0169] ;

[0170] ;

[0171] The result shows that the inspection feature weight distribution value is 0.339, which reflects the overall weight distribution characteristics of each signal category in the inspection parameter matrix and is used for the comprehensive evaluation and trend analysis of subsequent inspection parameters.

[0172] Please refer to Figure 6 , and the specific steps for obtaining the abnormal trend prediction value are as follows:

[0173] Based on the inspection feature weight distribution value, analyze the change rates of the vibration signal and the temperature signal, generate the change rate data by calculating the change ratio between the signal fluctuation amplitude and the time interval, and extracting the dynamic change rate of each signal in combination with the signal characteristic parameters;

[0174] By monitoring the time series data of the vibration signal and the temperature signal, extract the fluctuation values and average values of each signal within different time intervals, and obtain the change rate by calculating the ratio between the fluctuation amplitude and the time interval. Specifically, collect the vibration signal fluctuation values and the temperature signal fluctuation values , and use the formula: , calculate the change rate data, where and represent the time values of two time points respectively, and represent the corresponding fluctuation values of the vibration signal respectively. Generate the complete change rate sequence data by calculating the change rate for each time interval, use the change rate sequence for time series trend analysis, classify the change rate in combination with the characteristics of the vibration signal, and extract the change characteristics of different category signals to generate the change rate data.

[0175] Call the rate of change data, establish a dynamic trend matrix, calculate the change amplitude and distribution law of the signal at different time nodes, and combine the signal fluctuation characteristics to extract the signal change range data at the time nodes;

[0176] By classifying the rate of change sequence according to time nodes, calculate the average change value within each time period, and calculate the signal change range according to the distribution law of the time node signals. Specifically, first divide the time series signal into time nodes through the formula: , calculate the average rate of change of the time node signal, where represents the average rate of change within the time period , represents the rate of change of the signal, is the number of signals within the time period. Compare the average rate of change with the fluctuation range of the signals within the time node through the formula: , calculate the signal change range, is the signal change range within the time period , represents all the signal values within this time period. Establish a dynamic trend matrix through the above process to generate the signal change range data at the time nodes.

[0177] Use the signal change range data at the time nodes to establish a time distribution prediction model, combine the dynamic changes of the signal and the time node distribution, and adopt the formula:

[0178] ;

[0179] Calculate and generate the abnormal trend prediction value;

[0180] Among them, represents the abnormal trend prediction value, represents the rate of change of the th type of signal, represents the time node value of the th type of signal, represents the mean of the time nodes, represents the th signal strength value, represents the number of signal categories, represents the number of time nodes, 、 are the indexes of the signal category and the time node respectively.

[0181] Formula:

[0182] ;

[0183] The advantage of the formula is that by combining the dynamic change rate of the signal and the Gaussian distribution model, it can accurately predict the signal behavior at time nodes, enhancing the sensitivity and adaptability of the model to abnormal trends;

[0184] Detailed explanation of the formula and the derivation process of formula calculation:

[0185] Assume that the monitored signal data is , , , and the corresponding time nodes are , , , and the mean of the time nodes is , and the standard deviation is , and the signal intensities are respectively , , , then the derivation of the calculation formula is as follows:

[0186] ;

[0187] ;

[0188] ;

[0189] ;

[0190] ;

[0191] ;

[0192] This result indicates that the calculated predicted value of the abnormal trend is 0.6329, indicating that the abnormal trend of the signal at the current time node is close to the medium range, which can be used as a reference input for dynamic trend prediction and further for the classification and response processing of signal anomaly prediction.

[0193] The above is only a preferred embodiment of the present invention, and it is not intended to limit the present invention in other forms. Any person skilled in the relevant art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. The intelligent inspection system for power equipment based on artificial intelligence is characterized by: The system comprises: The fault mode generation module obtains the operating parameters of the power equipment through the inspection robot, inputs the current value, temperature value and vibration signal value, counts the amplitude distribution of the signal, extracts the frequency domain characteristics and change rate of the signal, calculates the dynamic characteristic range of the signal, establishes the fault characteristic mapping model, adjusts the parameters to match the signal distribution deviation, and generates the fault mode distribution value; It is characterized in that the step of obtaining the failure mode distribution value is specifically as follows: Extract the amplitude distribution of current value, temperature value and vibration signal value, calculate the change rate of multiple signal amplitudes in the frequency domain, and generate amplitude distribution change rate parameters; Call the amplitude distribution change rate parameter, compare its value to see if it exceeds the dynamic feature range according to the upper and lower limits, classify the signal amplitude according to the frequency domain characteristics, extract the signal feature change value that meets the conditions of the upper and lower limits of the dynamic feature range, and calculate and generate the signal change rate within the dynamic feature range; The signal change rate within the dynamic feature range is called, the distribution deviation is analyzed, and the signal characteristic value mapping relationship is corrected based on the adjustment parameters, using the formula: ； Calculate and generate failure mode distribution values; in, represents the failure mode distribution value, Represents the rate of change of the signal characteristic value, represents the weight of the signal amplitude, Represents the lower limit of the dynamic feature range, Represents the upper limit of the dynamic feature range, represents the weight coefficient of the adjustment parameter, represents the signal feature mapping value, represents the mean value of signal characteristics, Represents the number of signal feature points, Represents the number of signal mapping points, , are the indexes of signal feature points and mapping points respectively; The fault detection module obtains the current signal offset value and the frequency domain deviation in the inspection signal based on the fault mode distribution value, compares the interval difference between the inspection signal and the normal operating parameters, calculates the amplitude difference rate of the signal abnormality, establishes a fault feature deviation model, and generates the abnormal signal amplitude ratio; The fault classification module analyzes the characteristic values ​​of the current signal and the temperature signal in the differentiation interval based on the abnormal signal amplitude ratio, compares the overlap between the signal characteristic values ​​and the fault category interval, establishes a classification feature matrix, screens the signal contribution rate, and generates a fault type distribution coefficient; The inspection feature optimization module extracts the local trend value and global change rate of the current and temperature signals based on the fault type distribution coefficient, normalizes the signal category feature weight, dynamically matches the signal trend, extracts the inspection parameter matrix, and calculates the inspection feature weight distribution value; The abnormal prediction evaluation module analyzes the change rates of vibration signals and temperature signals based on the inspection feature weight distribution values, establishes a dynamic trend matrix, calculates the signal change range of time nodes, establishes a time distribution prediction model, and generates abnormal trend prediction values.

2. The artificial intelligence-based intelligent inspection system for electric power equipment according to claim 1 is characterized in that: The fault mode distribution value is specifically the signal amplitude distribution, signal frequency domain characteristics and change rate, and signal dynamic feature range. The fault feature deviation model includes the current signal offset value, frequency domain deviation, and signal abnormal amplitude difference rate. The abnormal signal amplitude ratio includes the current signal characteristic value, the temperature signal characteristic value, and the overlap between the signal characteristic value and the fault category interval. The fault type distribution coefficient is specifically the classification feature matrix and the signal contribution rate. The inspection feature weight distribution value is specifically the local trend value, the global change rate, and the signal category feature weight. The abnormal trend prediction value includes the vibration signal change rate, the temperature signal change rate, and the time node signal change range.

3. The artificial intelligence-based intelligent inspection system for electric power equipment according to claim 2 is characterized in that: The steps for obtaining the abnormal signal amplitude ratio are specifically as follows: According to the fault mode distribution value, the offset value and frequency domain deviation of the current signal in the inspection signal are obtained, the frequency domain deviation is used to statistically calculate the variation range of the differentiated signal, the offset value and the variation range are classified and sorted, and the current signal deviation data is generated; Calling the current signal deviation data, comparing the interval difference between the inspection signal and the normal operating parameters, calculating the deviation amplitude of the inspection signal in multiple intervals, analyzing the variation trend of the deviation amplitude, and counting the amplitude difference rate of the signal abnormality to generate signal abnormality amplitude difference data; Using the signal abnormal amplitude difference data, a fault feature deviation model is established using the formula: ； Generate abnormal signal amplitude ratio; in, represents the overall proportion of signal deviation, Representative The amplitude of the signal observation, Representative The normal amplitude reference of a signal, represents the number of all signal data points, is the index of the signal data point.

4. The artificial intelligence-based intelligent inspection system for electric power equipment according to claim 3 is characterized in that: The steps for obtaining the fault type distribution coefficient are specifically as follows: Based on the abnormal signal amplitude ratio, the characteristic values ​​of the current signal and the temperature signal in the differentiated interval are analyzed, and the fluctuation values ​​and frequency domain characteristics of the signals in the differentiated interval are classified item by item to generate differentiated characteristic data; The differentiated feature data is called, the overlap between the signal feature value and the fault category interval is compared, and the criticality of the multi-category interval is analyzed by counting and sorting the contribution rate of the signal amplitude in the overlapping interval and combining the signal feature weight parameter to generate the signal contribution rate data; Using the signal contribution rate data, a classification feature matrix is ​​established, and the weight relationship between the feature distribution of the differentiated signal category and the fault category interval is calculated using the formula: ； Calculate and generate the fault type distribution coefficient; in, represents the fault type distribution coefficient, Representative Class signal contribution rate, Representative The weight of the class signal, Representative The normal baseline contribution rate of the class signal, Representative Class The amplitude contribution of each interval is Represents the number of signal categories, represents the number of intervals, is the signal category index, is the interval index.

5. The artificial intelligence-based intelligent inspection system for electric power equipment according to claim 4 is characterized in that: The steps for obtaining the inspection feature weight distribution value are specifically as follows: Based on the fault type distribution coefficient, extract the local trend value and global change rate of the current and temperature signals, and generate local and global signal analysis data by analyzing the fluctuation characteristics of the signals in the local and global ranges item by item and combining the change law of the signal trend; Calling the local and global signal analysis data, normalizing the signal category feature weights, normalizing the signal categories to a unified range by calculating the ratio of multi-category signal feature values, and allocating feature weights of multi-category signals to generate normalized signal weight data; Using the normalized signal weight data, dynamically matching the signal trend, and extracting the inspection parameter matrix, the formula is: ； Calculate and generate inspection feature weight distribution values; in, Represents the inspection feature weight distribution value, Representative The local trend value of the class signal, Representative The global rate of change of the class signal, Representative The normalized weight of the class signal, Representative Stability index of class signal, Represents the number of signal categories, Signal category index.

6. The artificial intelligence-based intelligent inspection system for electric power equipment according to claim 5 is characterized in that: The steps for obtaining the abnormal trend prediction value are specifically as follows: Based on the inspection feature weight distribution value, the change rate of the vibration signal and the temperature signal is analyzed, and the dynamic change rate of each signal is extracted by calculating the change ratio between the signal fluctuation amplitude and the time interval, and combining the signal feature parameters to generate the change rate data; Call the change rate data, establish a dynamic trend matrix, calculate the change amplitude and distribution law of the signal at the differentiated time nodes, and extract the signal change range data at the time nodes in combination with the signal fluctuation characteristics; Using the signal change range data of the time nodes, a time distribution prediction model is established, combining the dynamic change of the signal with the time node distribution, and using the formula: ； Calculate and generate abnormal trend prediction values; in, represents the abnormal trend prediction value, Representative The rate of change of the signal, Representative The time node value of the class signal, represents the mean value of the time node, Represents the standard deviation of the time node, Representative The strength value of the signal, Represents the number of signal categories, Represents the number of time nodes, , They are the indexes of signal category and time node respectively.

Images