Partial discharge monitoring and positioning system and method based on Internet of Things architecture

Abstract

The invention discloses a partial discharge monitoring and positioning system and method based on an Internet of Things architecture, and relates to the technical field of power monitoring. Ideal operation parameters of power equipment are collected, an optimal operation contrast array is established, and a plurality of ultrasonic emission point locations and ultrasonic collection point locations are selected based on to-be-detected power equipment; the method comprises the following steps: acquiring a plurality of power equipment acoustic signal arrays, analyzing acoustic signals in the plurality of power equipment acoustic signal arrays based on the plurality of power equipment acoustic signal arrays, determining feature data in the acoustic signals, establishing a power equipment feature matrix, and determining the optimal operation contrast array based on the power equipment feature matrix and the optimal operation contrast array. And evaluating the abnormal features in the power equipment feature matrix, determining the abnormal state of the power equipment, and marking the abnormal position of the power equipment in the abnormal state based on the abnormal state of the power equipment. The method has the advantages that abnormal discharge of the power equipment is accurately identified, the maintenance cost is reduced, and the stability of the power equipment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring, and in particular to a partial discharge monitoring and positioning system and method based on an Internet of Things architecture. Background Art

[0002] Partial discharge will damage the service life of line insulation materials. Due to partial discharge corrosion, it will accelerate insulation aging and degradation. Through partial discharge detection, these potential problems can be discovered and dealt with in a timely manner, preventing the occurrence of malicious failures, avoiding large-scale power outages and economic losses.

[0003] Existing partial discharge detection technology lacks feature recognition and extraction for multi-point detection technology. In practical applications, it is difficult to achieve accurate monitoring and positioning of the partial discharge position of power equipment during multi-point detection. Summary of the invention

[0004] In order to solve the above technical problems, a local discharge monitoring and positioning system and method based on the Internet of Things architecture is provided. This technical solution solves the problem that the above-mentioned existing local discharge detection technology lacks feature recognition and extraction for multi-point detection technology. In practical applications, it is difficult to achieve accurate monitoring and positioning of the local discharge position of power equipment during multi-point detection.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A partial discharge monitoring and positioning method based on an Internet of Things architecture, comprising:

[0007] Collect the ideal operating parameters of all power equipment connected to the IoT architecture and establish an optimal operating comparison array;

[0008] Based on the power equipment to be detected, a number of ultrasonic emission points and ultrasonic collection points are selected to obtain a number of power equipment acoustic signal arrays;

[0009] Based on a plurality of electric power equipment acoustic signal arrays, analyzing the acoustic signals in a plurality of groups of electric power equipment acoustic signal arrays, determining characteristic data in the acoustic signals, and establishing an electric power equipment characteristic matrix;

[0010] Based on the power equipment feature matrix and the optimal operation comparison array, the abnormal features in the power equipment feature matrix are evaluated to determine the abnormal state of the power equipment;

[0011] Based on the abnormal state of the electric power equipment, the abnormal discharge position of the abnormal state electric power equipment is marked.

[0012] Preferably, the method of selecting a plurality of ultrasonic emission points and ultrasonic collection points based on the power equipment to be detected and obtaining a plurality of power equipment acoustic signal arrays specifically includes:

[0013] Mark the power equipment to be inspected, select a number of ultrasonic emission points and ultrasonic collection points for the power equipment in the marked order, and obtain ultrasonic signal data of each power equipment;

[0014] Based on the ultrasonic signal data of each electric power device, the ultrasonic signal data is amplified;

[0015] According to the amplified ultrasonic signal data, the continuous ultrasonic signal data is discretized into a series of pulses in the form of analog signals, and the value of the analog signal is represented by encoding the amplitude and time of the pulses, thereby realizing the conversion of the ultrasonic signal into a digital signal;

[0016] The ultrasonic signal of each power device is converted into a digital signal, the digital signal is mapped according to the order of the power devices, and a plurality of power device acoustic signal arrays are established.

[0017] Preferably, the analyzing of the acoustic signals in the plurality of groups of electric equipment acoustic signal arrays, determining the characteristic data in the acoustic signals, and establishing the electric equipment characteristic matrix specifically includes:

[0018] Based on a plurality of groups of electric power equipment acoustic signal arrays, the acoustic data in the arrays are quantized to obtain a quantized array of electric power equipment acoustic signals;

[0019] Based on the quantized array of acoustic signals of the power equipment, a time domain diagram is drawn, and the waveform starting point, peak, trough and waveform ending point in the time domain diagram are marked to determine the time domain diagram of the power equipment;

[0020] Based on the time domain diagram of the power equipment, the maximum amplitude value characteristics in the time domain diagram of the power equipment are calculated using the maximum amplitude formula;

[0021] Based on the time domain diagram of the power equipment, the root mean square amplitude value characteristics in the time domain diagram of the power equipment are calculated using the root mean square amplitude formula;

[0022] Based on the time domain diagram of the power equipment, the waveform kurtosis characteristics in the time domain diagram of the power equipment are calculated using the waveform kurtosis formula;

[0023] Based on the time domain diagram of the power equipment, the waveform skewness characteristics in the time domain diagram of the power equipment are calculated using the waveform skewness formula;

[0024] Based on the maximum amplitude value characteristics in the power equipment time domain diagram, the root mean square amplitude value characteristics in the power equipment time domain diagram, the waveform kurtosis characteristics in the power equipment time domain diagram, and the waveform skewness characteristics in the power equipment time domain diagram, the power equipment feature matrix G is constructed, G = [g 11 …g ij …g nm ], where G is the power equipment characteristic matrix, g ij is the jth feature data of the ith sampling point, n is the total number of sampling points, and m is the total number of features.

[0025] Preferably, the maximum amplitude formula is:

[0026] A max =max(|x(t)|)

[0027] In the formula, A max is the maximum amplitude value characteristic in the time domain diagram of the power equipment, x is the amplitude value, and t is the time;

[0028] The formula for the root mean square amplitude is:

[0029]

[0030] In the formula, B rms is the root mean square amplitude value characteristic in the time domain diagram of the power equipment, N is the total number of sampling points in the time domain diagram, and i is the i-th sampling point;

[0031] The waveform kurtosis formula is:

[0032]

[0033] Where K is the peak characteristic of the waveform in the time domain diagram of the power equipment, x i is the amplitude value of the i-th sampling point, is the mean value of the amplitude;

[0034] Among them, the waveform skewness formula is:

[0035]

[0036] Where S is the waveform skewness characteristic in the time domain diagram of the power equipment, and V is the standard deviation in the time domain diagram of the power equipment.

[0037] Preferably, the step of evaluating the abnormal features in the power equipment feature matrix based on the power equipment feature matrix and the optimal operation comparison array to determine the abnormal state of the power equipment specifically includes:

[0038] Based on the power equipment feature matrix, several feature subsets of power equipment are screened out according to the tag order;

[0039] Based on the feature subsets of the plurality of electric devices, using the correlation coefficient formula, the correlation score in each feature subset of the electric device is calculated to obtain an array of correlation scores in the feature subsets of the plurality of electric devices;

[0040] Standardizing the correlation score arrays and the optimal operation comparison arrays in the plurality of power equipment feature subsets to obtain a standardized power equipment feature subset array and a standardized optimal operation comparison array;

[0041] using the standardized operating parameters of the standardized optimal operating control array as the optimal operating threshold;

[0042] Based on the standardized electric power equipment feature subset array, the maximum feature score is used as the segmentation threshold, and the standardized electric power equipment feature subset array is segmented into two cotyledon sets to obtain a left cotyledon tree and a right cotyledon tree;

[0043] Calculate the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree respectively, and calculate the average path length of each cotyledon based on the path length;

[0044] Based on the path length of each cotyledon and the average path length of each cotyledon, the anomaly score is calculated using the exponential function formula;

[0045] Based on the comparison between the abnormal score and the optimal operation threshold, it is determined whether the abnormal score exceeds the optimal operation threshold. If so, it is determined to be abnormal operation, otherwise, it is determined not to output;

[0046] Preferably, the correlation coefficient formula is:

[0047] C=|ρ(g ij ,Y)|

[0048] Where C is the correlation score within each power equipment feature subset, ρ is the density symbol, and Y is the total number of cotyledons in the cotyledon tree;

[0049] Among them, the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree is calculated respectively, and the average path length of each cotyledon is calculated according to the path length:

[0050]

[0051] In the formula, is the average length of the rth cotyledon path, k is the cotyledon, h is the processing function, and r is the cotyledon path;

[0052] The exponential function formula is:

[0053]

[0054] In the formula, C 异Score for anomaly.

[0055] Furthermore, a partial discharge monitoring and positioning system based on the Internet of Things architecture is proposed, which is used to implement the partial discharge monitoring and positioning method based on the Internet of Things architecture as described above, including:

[0056] Standard parameter acquisition module: The standard parameter acquisition module is used to collect ideal operating parameters of power equipment and establish an optimal operating comparison array;

[0057] The acoustic data acquisition module is used to select a number of ultrasonic emission points and ultrasonic collection points based on the power equipment to be detected, and obtain a number of acoustic signal arrays of the power equipment;

[0058] The acoustic data analysis module is electrically connected to the acoustic data acquisition module, and is used to analyze the acoustic signals in several groups of acoustic signal arrays of electric equipment based on several acoustic signal arrays of electric equipment, determine the characteristic data in the acoustic signals, and establish a characteristic matrix of electric equipment;

[0059] An abnormality assessment module, the abnormality assessment module is electrically connected to the sound data analysis module, and the abnormality assessment module is used to evaluate the abnormal characteristics in the power equipment feature matrix based on the power equipment feature matrix and the optimal operation comparison array, and determine the abnormal state of the power equipment;

[0060] The marking module is electrically connected to the abnormality assessment module, and is used to mark the abnormal discharge position of the abnormal state power equipment based on the abnormal state of the power equipment.

[0061] Optionally, the sound data collection module includes:

[0062] The collection unit marks the power equipment to be detected, selects a number of ultrasonic emission points and ultrasonic collection points for the power equipment in the marked order, and obtains ultrasonic signal data of each power equipment;

[0063] an amplification processing unit, based on the ultrasonic signal data of each electric device, amplifying the ultrasonic signal data therein;

[0064] The signal conversion unit discretizes the continuous ultrasonic signal data into a series of pulses in the form of analog signals according to the amplified ultrasonic signal data, and encodes the amplitude and time of the pulses to represent the value of the analog signal, thereby converting the ultrasonic signal into a digital signal;

[0065] The acoustic signal array unit converts the ultrasonic signal of each power device into a digital signal, maps the digital signal according to the order of the power devices, and establishes several acoustic signal arrays of the power devices.

[0066] Optionally, the vocalization data analysis module includes:

[0067] A quantization unit, based on a plurality of groups of electric power equipment sound signal arrays, performs quantization processing on the sound data in the arrays to obtain a quantized array of the electric power equipment sound signal;

[0068] A time domain diagram unit, based on the quantized array of acoustic signals of the electric power equipment, draws a time domain diagram, marks the waveform starting point, peak, trough and waveform ending point in the time domain diagram, and determines the time domain diagram of the electric power equipment;

[0069] The maximum amplitude characteristic unit calculates the maximum amplitude value characteristic in the time domain diagram of the power equipment by using the maximum amplitude formula based on the time domain diagram of the power equipment;

[0070] A root mean square amplitude characteristic unit, based on the time domain diagram of the power equipment, uses a root mean square amplitude formula to calculate the root mean square amplitude value characteristics in the time domain diagram of the power equipment;

[0071] A waveform kurtosis characteristic unit, based on a time domain diagram of the power equipment, uses a waveform kurtosis formula to calculate a waveform kurtosis characteristic in the time domain diagram of the power equipment;

[0072] A waveform skewness characteristic unit, based on a time domain diagram of the power equipment and using a waveform skewness formula, calculates waveform skewness characteristics in the time domain diagram of the power equipment;

[0073] The feature matrix unit constructs a power equipment feature matrix G based on the maximum amplitude value feature in the power equipment time domain diagram, the root mean square amplitude value feature in the power equipment time domain diagram, the waveform kurtosis feature in the power equipment time domain diagram, and the waveform skewness feature in the power equipment time domain diagram.

[0074] Optionally, the anomaly assessment module includes:

[0075] A screening unit, based on the power equipment feature matrix, screens out feature subsets of several power equipment according to the tag order;

[0076] A correlation calculation unit, based on the feature subsets of the plurality of electric devices, uses a correlation coefficient formula to calculate the correlation score in each feature subset of the electric device, and obtains an array of correlation scores in the feature subsets of the plurality of electric devices;

[0077] A standardization unit, which performs standardization processing on correlation score arrays and optimal operation comparison arrays in a plurality of power equipment feature subsets to obtain a standardized power equipment feature subset array and a standardized optimal operation comparison array;

[0078] A threshold unit, which uses the standardized operation parameter of the standardized optimal operation reference array as the optimal operation threshold;

[0079] A segmentation unit, based on the standardized electric power equipment feature subset array, uses the maximum feature score as a segmentation threshold, and segments the standardized electric power equipment feature subset array into two cotyledon sets to obtain a left cotyledon tree and a right cotyledon tree;

[0080] A path length calculation unit calculates the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree respectively, and calculates the average path length of each cotyledon according to the path length;

[0081] The anomaly score calculation unit calculates the anomaly score through an exponential function formula based on the path length of each cotyledon and the average path length of each cotyledon;

[0082] The abnormality judgment unit compares the abnormality score with the optimal operation threshold to judge whether the abnormality score exceeds the optimal operation threshold. If so, it is judged as abnormal operation. If not, it is judged not to output.

[0083] Compared with the prior art, the present invention has the following beneficial effects:

[0084] The present invention proposes a partial discharge monitoring and positioning solution based on the Internet of Things architecture. By collecting and analyzing ultrasonic signals of ultrasonic detection equipment set at multiple points, the operating status of power equipment is evaluated, the abnormal discharge location of power equipment is accurately identified, the maintenance cost is reduced, and the stability of power equipment is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 Flowchart of the partial discharge monitoring and positioning method based on the Internet of Things architecture proposed in this solution;

[0086] Figure 2 This is a flow chart of the method for obtaining an array of acoustic signals of electric power equipment in this solution;

[0087] Figure 3 This is a flow chart of the method for establishing a power equipment characteristic matrix in this solution;

[0088] Figure 4 This is a flow chart of the method for determining the abnormal state of power equipment in this solution. DETAILED DESCRIPTION

[0089] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0090] Reference Figure 1 As shown, a partial discharge monitoring and positioning method based on the Internet of Things architecture includes:

[0091] Collect the ideal operating parameters of all power equipment connected to the IoT architecture and establish an optimal operating comparison array;

[0092] Based on the power equipment to be detected, a number of ultrasonic emission points and ultrasonic collection points are selected to obtain a number of power equipment acoustic signal arrays;

[0093] Based on a plurality of electric power equipment acoustic signal arrays, analyzing the acoustic signals in a plurality of groups of electric power equipment acoustic signal arrays, determining characteristic data in the acoustic signals, and establishing an electric power equipment characteristic matrix;

[0094] Based on the power equipment feature matrix and the optimal operation comparison array, the abnormal features in the power equipment feature matrix are evaluated to determine the abnormal state of the power equipment;

[0095] Based on the abnormal state of the electric power equipment, the abnormal discharge position of the abnormal state electric power equipment is marked.

[0096] This scheme forms an optimal operation reference array by collecting the ideal operating parameters of the power equipment. Subsequently, several ultrasonic emission points and ultrasonic collection points are selected on the power equipment to be tested, and the corresponding acoustic signal array is obtained. By analyzing these acoustic signal arrays, the key acoustic signal features are extracted, and the feature matrix of the power equipment is established. Next, the feature matrix is ​​compared with the optimal operation reference array to evaluate the abnormal features therein, so as to determine whether the power equipment is in an abnormal state. Finally, by screening out the power equipment in abnormal state and marking the abnormal discharge position, the abnormal state is accurately located. In this way: rapid monitoring of power equipment and identification of abnormal state are achieved, thereby improving the safety and reliability of power equipment operation.

[0097] Reference Figure 2 As shown, the method of selecting a plurality of ultrasonic emission points and ultrasonic collection points based on the power equipment to be detected and obtaining a plurality of power equipment acoustic signal arrays specifically includes:

[0098] Mark the power equipment to be inspected, select a number of ultrasonic emission points and ultrasonic collection points for the power equipment in the marked order, and obtain ultrasonic signal data of each power equipment;

[0099] Based on the ultrasonic signal data of each electric power device, the ultrasonic signal data is amplified;

[0100] According to the amplified ultrasonic signal data, the continuous ultrasonic signal data is discretized into a series of pulses in the form of analog signals, and the value of the analog signal is represented by encoding the amplitude and time of the pulses, thereby realizing the conversion of the ultrasonic signal into a digital signal;

[0101] The ultrasonic signal of each power device is converted into a digital signal, the digital signal is mapped according to the order of the power devices, and a plurality of power device acoustic signal arrays are established.

[0102] It is understandable that due to the complexity of the interior of power equipment, when ultrasonic detection is used, the ultrasonic signal is interfered by the environment. Therefore, when using a signal amplifier, multiple amplifiers should be used to amplify the ultrasonic signal in stages according to its different characteristics.

[0103] It is understandable that when converting ultrasonic signals into digital signals, the collected ultrasonic signals should be filtered to reduce signal distortion and insufficient sampling during conversion.

[0104] Reference Figure 3 As shown, the analysis of the acoustic signals in the acoustic signal arrays of several groups of electric equipment, determining the characteristic data in the acoustic signals, and establishing the electric equipment characteristic matrix specifically includes:

[0105] Based on a plurality of groups of electric power equipment acoustic signal arrays, the acoustic data in the arrays are quantized to obtain a quantized array of electric power equipment acoustic signals;

[0106] Based on the quantized array of acoustic signals of the power equipment, a time domain diagram is drawn, and the waveform starting point, peak, trough and waveform ending point in the time domain diagram are marked to determine the time domain diagram of the power equipment;

[0107] Based on the time domain diagram of the power equipment, the maximum amplitude value characteristics in the time domain diagram of the power equipment are calculated using the maximum amplitude formula;

[0108] Based on the time domain diagram of the power equipment, the root mean square amplitude value characteristics in the time domain diagram of the power equipment are calculated using the root mean square amplitude formula;

[0109] Based on the time domain diagram of the power equipment, the waveform kurtosis characteristics in the time domain diagram of the power equipment are calculated using the waveform kurtosis formula;

[0110] Based on the time domain diagram of the power equipment, the waveform skewness characteristics in the time domain diagram of the power equipment are calculated using the waveform skewness formula;

[0111] Based on the maximum amplitude value characteristics in the power equipment time domain diagram, the root mean square amplitude value characteristics in the power equipment time domain diagram, the waveform kurtosis characteristics in the power equipment time domain diagram, and the waveform skewness characteristics in the power equipment time domain diagram, the power equipment feature matrix G is constructed, G = [g 11 …g ij …g nm ], where G is the power equipment characteristic matrix, g ij is the jth feature data of the ith sampling point, n is the total number of sampling points, and m is the total number of features.

[0112] The maximum amplitude formula is:

[0113] A max =max(|x(t)|)

[0114] In the formula, A max is the maximum amplitude value characteristic in the time domain diagram of the power equipment, x is the amplitude value, and t is the time;

[0115] The root mean square amplitude formula is:

[0116]

[0117] In the formula, B rms is the root mean square amplitude value characteristic in the time domain diagram of the power equipment, N is the total number of sampling points in the time domain diagram, and i is the i-th sampling point;

[0118] The waveform kurtosis formula is:

[0119]

[0120] Where K is the peak characteristic of the waveform in the time domain diagram of the power equipment, x i is the amplitude value of the i-th sampling point, is the mean value of the amplitude;

[0121] Among them, the waveform skewness formula is:

[0122]

[0123] Where S is the waveform skewness characteristic in the time domain diagram of the power equipment, and V is the standard deviation in the time domain diagram of the power equipment.

[0124] This scheme first quantifies the acoustic signal of the power equipment and converts it into a numerical data array. Then, by drawing a time domain diagram, marking the starting point, peak, trough and end point of the waveform, a time domain image of the power equipment is formed. Next, using the maximum amplitude formula, root mean square amplitude formula, waveform kurtosis formula and waveform skewness formula, the maximum amplitude value, root mean square amplitude value, waveform kurtosis and waveform skewness in the time domain diagram are calculated respectively. Finally, these features are combined into a feature matrix, which contains the key features of the time domain diagram of the acoustic signal of the power equipment, providing a basis for subsequent analysis and processing.

[0125] Reference Figure 4 As shown, the abnormal characteristics in the power equipment characteristic matrix are evaluated based on the power equipment characteristic matrix and the optimal operation comparison array, and determining the abnormal state of the power equipment specifically includes:

[0126] Based on the power equipment feature matrix, several feature subsets of power equipment are screened out according to the tag order;

[0127] Based on the feature subsets of the plurality of electric devices, using the correlation coefficient formula, the correlation score in each feature subset of the electric device is calculated to obtain an array of correlation scores in the feature subsets of the plurality of electric devices;

[0128] Standardizing the correlation score arrays and the optimal operation comparison arrays in the plurality of power equipment feature subsets to obtain a standardized power equipment feature subset array and a standardized optimal operation comparison array;

[0129] using the standardized operating parameters of the standardized optimal operating control array as the optimal operating threshold;

[0130] Based on the standardized electric power equipment feature subset array, the maximum feature score is used as the segmentation threshold, and the standardized electric power equipment feature subset array is segmented into two cotyledon sets to obtain a left cotyledon tree and a right cotyledon tree;

[0131] Calculate the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree respectively, and calculate the average path length of each cotyledon based on the path length;

[0132] Based on the path length of each cotyledon and the average path length of each cotyledon, the anomaly score is calculated using the exponential function formula;

[0133] Based on the comparison between the abnormal score and the optimal operation threshold, it is determined whether the abnormal score exceeds the optimal operation threshold. If so, it is determined to be abnormal operation, otherwise, it is determined not to output;

[0134] The correlation coefficient formula is:

[0135] C=|ρ(g ij ,Y)|

[0136] Where C is the correlation score within each power equipment feature subset, ρ is the density symbol, and Y is the total number of cotyledons in the cotyledon tree;

[0137] Among them, the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree is calculated respectively, and the average path length of each cotyledon is calculated according to the path length:

[0138]

[0139] In the formula, is the average length of the rth cotyledon path, k is the cotyledon, h is the processing function, and r is the cotyledon path;

[0140] The exponential function formula is:

[0141]

[0142] In the formula, C 异 Score for anomaly.

[0143] This scheme is an anomaly detection method designed for power equipment systems. First, according to the power equipment feature matrix, feature subsets are screened out and their correlation scores are calculated. Then, the correlation score array is standardized with the optimal operation control array, and the standardized parameters of the optimal operation control array are used as the threshold. Next, the standardized feature subset array is split according to the maximum feature score value to form left and right cotyledon trees, and the path length and average path length of each cotyledon are calculated. The anomaly score is calculated by the exponential function formula and compared with the optimal operation threshold to determine whether there is an abnormal operation. This scheme combines multiple indicators such as feature correlation, path length and anomaly score, and can effectively monitor abnormal conditions in power equipment systems.

[0144] Further, based on the same inventive concept as the above-mentioned partial discharge monitoring and positioning method based on the Internet of Things architecture, a partial discharge monitoring and positioning system based on the Internet of Things architecture is proposed, comprising:

[0145] Standard parameter acquisition module: The standard parameter acquisition module is used to collect ideal operating parameters of power equipment and establish an optimal operating comparison array;

[0146] The acoustic data acquisition module is used to select a number of ultrasonic emission points and ultrasonic collection points based on the power equipment to be detected, and obtain a number of acoustic signal arrays of the power equipment;

[0147] The acoustic data analysis module is electrically connected to the acoustic data acquisition module, and is used to analyze the acoustic signals in several groups of acoustic signal arrays of electric equipment based on several acoustic signal arrays of electric equipment, determine the characteristic data in the acoustic signals, and establish a characteristic matrix of electric equipment;

[0148] An abnormality assessment module, the abnormality assessment module is electrically connected to the sound data analysis module, and the abnormality assessment module is used to evaluate the abnormal characteristics in the power equipment feature matrix based on the power equipment feature matrix and the optimal operation comparison array, and determine the abnormal state of the power equipment;

[0149] The marking module is electrically connected to the abnormality assessment module, and is used to mark the abnormal position of the abnormal state power equipment based on the abnormal state of the power equipment.

[0150] The sound data acquisition module includes:

[0151] The collection unit marks the power equipment to be detected, selects a number of ultrasonic emission points and ultrasonic collection points for the power equipment in the marked order, and obtains ultrasonic signal data of each power equipment;

[0152] an amplification processing unit, based on the ultrasonic signal data of each electric device, amplifying the ultrasonic signal data therein;

[0153] The signal conversion unit discretizes the continuous ultrasonic signal data into a series of pulses in the form of analog signals according to the amplified ultrasonic signal data, and encodes the amplitude and time of the pulses to represent the value of the analog signal, thereby converting the ultrasonic signal into a digital signal;

[0154] The acoustic signal array unit converts the ultrasonic signal of each power device into a digital signal, maps the digital signal according to the order of the power devices, and establishes several acoustic signal arrays of the power devices.

[0155] The sound data analysis module includes:

[0156] A quantization unit, based on a plurality of groups of electric power equipment sound signal arrays, performs quantization processing on the sound data in the arrays to obtain a quantized array of the electric power equipment sound signal;

[0157] A time domain diagram unit, based on the quantized array of acoustic signals of the electric power equipment, draws a time domain diagram, marks the waveform starting point, peak, trough and waveform ending point in the time domain diagram, and determines the time domain diagram of the electric power equipment;

[0158] The maximum amplitude characteristic unit calculates the maximum amplitude value characteristic in the time domain diagram of the power equipment by using the maximum amplitude formula based on the time domain diagram of the power equipment;

[0159] A root mean square amplitude characteristic unit, based on the time domain diagram of the power equipment, uses a root mean square amplitude formula to calculate the root mean square amplitude value characteristics in the time domain diagram of the power equipment;

[0160] A waveform kurtosis characteristic unit, based on a time domain diagram of the power equipment, uses a waveform kurtosis formula to calculate a waveform kurtosis characteristic in the time domain diagram of the power equipment;

[0161] A waveform skewness characteristic unit, based on a time domain diagram of the power equipment and using a waveform skewness formula, calculates waveform skewness characteristics in the time domain diagram of the power equipment;

[0162] The feature matrix unit constructs a power equipment feature matrix G based on the maximum amplitude value feature in the power equipment time domain diagram, the root mean square amplitude value feature in the power equipment time domain diagram, the waveform kurtosis feature in the power equipment time domain diagram, and the waveform skewness feature in the power equipment time domain diagram.

[0163] The anomaly assessment module includes:

[0164] A screening unit, based on the power equipment feature matrix, screens out feature subsets of several power equipment according to the tag order;

[0165] A correlation calculation unit, based on the feature subsets of the plurality of electric devices, uses a correlation coefficient formula to calculate the correlation score in each feature subset of the electric device, and obtains an array of correlation scores in the feature subsets of the plurality of electric devices;

[0166] A standardization unit, which performs standardization processing on correlation score arrays and optimal operation comparison arrays in a plurality of power equipment feature subsets to obtain a standardized power equipment feature subset array and a standardized optimal operation comparison array;

[0167] A threshold unit, which uses the standardized operation parameter of the standardized optimal operation reference array as the optimal operation threshold;

[0168] A segmentation unit, based on the standardized electric power equipment feature subset array, uses the maximum feature score as a segmentation threshold, and segments the standardized electric power equipment feature subset array into two cotyledon sets to obtain a left cotyledon tree and a right cotyledon tree;

[0169] A path length calculation unit calculates the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree respectively, and calculates the average path length of each cotyledon according to the path length;

[0170] The anomaly score calculation unit calculates the anomaly score through an exponential function formula based on the path length of each cotyledon and the average path length of each cotyledon;

[0171] The abnormality judgment unit compares the abnormality score with the optimal operation threshold to judge whether the abnormality score exceeds the optimal operation threshold. If so, it is judged as abnormal operation. If not, it is judged not to output.

[0172] The usage process of the above partial discharge monitoring and positioning system based on the Internet of Things architecture is as follows:

[0173] Step 1: Collect ideal operating parameters of power equipment and establish an optimal operating comparison array;

[0174] Step 2: Mark the power equipment to be tested, select a number of ultrasonic emission points and ultrasonic collection points for the power equipment in the marked order, and obtain ultrasonic signal data of each power equipment;

[0175] Step 3: Based on the ultrasonic signal data of each power device, amplify the ultrasonic signal data;

[0176] Step 4: According to the amplified ultrasonic signal data, the continuous ultrasonic signal data is discretized into a series of pulses in the form of analog signals, and the amplitude and time of the pulses are encoded to represent the value of the analog signal, thereby realizing the conversion of the ultrasonic signal into a digital signal;

[0177] Step 5: Convert the ultrasonic signal of each power device into a digital signal, map the digital signal according to the order of the power devices, and establish several power device acoustic signal arrays;

[0178] Step 6: Based on a plurality of groups of electric power equipment acoustic signal arrays, quantize the acoustic data in the arrays to obtain a quantized array of electric power equipment acoustic signals;

[0179] Step 7: Based on the quantized array of the acoustic signal of the power equipment, a time domain diagram is drawn, and the waveform starting point, peak, trough and waveform ending point in the time domain diagram are marked to determine the time domain diagram of the power equipment;

[0180] Step 8: Based on the time domain diagram of the power equipment, use the maximum amplitude formula to calculate the maximum amplitude value feature in the time domain diagram of the power equipment;

[0181] Step 9: Based on the time domain diagram of the power equipment, use the root mean square amplitude formula to calculate the root mean square amplitude value characteristics in the time domain diagram of the power equipment;

[0182] Step 10: Based on the time domain diagram of the power equipment, the waveform kurtosis characteristics in the time domain diagram of the power equipment are calculated using the waveform kurtosis formula;

[0183] Step 11: Based on the time domain diagram of the power equipment, using the waveform skewness formula, calculate the waveform skewness characteristics in the time domain diagram of the power equipment;

[0184] Step 12: construct a power equipment feature matrix G based on the maximum amplitude value feature in the power equipment time domain diagram, the root mean square amplitude value feature in the power equipment time domain diagram, the waveform kurtosis feature in the power equipment time domain diagram, and the waveform skewness feature in the power equipment time domain diagram;

[0185] Step 13: Based on the power equipment feature matrix, select feature subsets of several power equipment according to the tag order;

[0186] Step 14: Based on the feature subsets of the plurality of power devices, using the correlation coefficient formula, calculate the correlation score in each feature subset of the power device, and obtain an array of correlation scores in the feature subsets of the plurality of power devices;

[0187] Step 15: normalizing the correlation score arrays and the optimal operation comparison arrays in the plurality of power equipment feature subsets to obtain a standardized power equipment feature subset array and a standardized optimal operation comparison array;

[0188] Step 16: using the standardized operation parameters of the standardized optimal operation control array as the optimal operation threshold;

[0189] Step 17: Based on the standardized electric power equipment feature subset array, the maximum feature score is used as the segmentation threshold, and the standardized electric power equipment feature subset array is segmented into two cotyledon sets to obtain a left cotyledon tree and a right cotyledon tree;

[0190] Step 18: Calculate the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree respectively, and calculate the average path length of each cotyledon based on the path length;

[0191] Step 19: Based on the path length of each cotyledon and the average path length of each cotyledon, calculate the anomaly score using an exponential function formula;

[0192] Step 20: Based on the comparison between the abnormal score and the optimal operation threshold, it is determined whether the abnormal score exceeds the optimal operation threshold. If so, it is determined to be abnormal operation. If not, it is determined not to output;

[0193] Step 21: Based on the abnormal state of the power equipment, mark the abnormal position of the abnormal power equipment.

[0194] In summary, the advantages of the present invention are: through the collection and analysis of ultrasonic signals, the operating status of the power equipment is evaluated, abnormal partial discharge is accurately identified, the maintenance cost is reduced, and the stability of the power equipment is improved.

[0195] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A partial discharge monitoring and positioning method based on the Internet of Things architecture, characterized in that: include: Collect the ideal operating parameters of all power equipment connected to the IoT architecture and establish an optimal operating comparison array; Based on the power equipment to be detected, a number of ultrasonic emission points and ultrasonic collection points are selected to obtain a number of power equipment acoustic signal arrays; Based on a plurality of electric power equipment acoustic signal arrays, analyzing the acoustic signals in a plurality of groups of electric power equipment acoustic signal arrays, determining characteristic data in the acoustic signals, and establishing an electric power equipment characteristic matrix; Based on the power equipment feature matrix and the optimal operation comparison array, the abnormal features in the power equipment feature matrix are evaluated to determine the abnormal state of the power equipment; Based on the abnormal state of the electric power equipment, the abnormal discharge position of the abnormal state electric power equipment is marked.

2. A partial discharge monitoring and positioning method based on the Internet of Things architecture according to claim 1, characterized in that: The method of selecting a plurality of ultrasonic emission points and ultrasonic collection points based on the power equipment to be detected and obtaining a plurality of power equipment acoustic signal arrays specifically includes: Mark the power equipment to be inspected, select a number of ultrasonic emission points and ultrasonic collection points for the power equipment in the marked order, and obtain ultrasonic signal data of each power equipment; Based on the ultrasonic signal data of each electric power device, the ultrasonic signal data is amplified; According to the amplified ultrasonic signal data, the continuous ultrasonic signal data is discretized into a series of pulses in the form of analog signals, and the value of the analog signal is represented by encoding the amplitude and time of the pulses, thereby realizing the conversion of the ultrasonic signal into a digital signal; The ultrasonic signal of each power device is converted into a digital signal, the digital signal is mapped according to the order of the power devices, and a plurality of power device acoustic signal arrays are established.

3. A partial discharge monitoring and positioning method based on the Internet of Things architecture according to claim 2, characterized in that: The analyzing the acoustic signals in the plurality of groups of electric equipment acoustic signal arrays, determining the characteristic data in the acoustic signals, and establishing the electric equipment characteristic matrix specifically includes: Based on a plurality of groups of electric power equipment acoustic signal arrays, the acoustic data in the arrays are quantized to obtain a quantized array of electric power equipment acoustic signals; Based on the quantized array of acoustic signals of the power equipment, a time domain diagram is drawn, and the waveform starting point, peak, trough and waveform ending point in the time domain diagram are marked to determine the time domain diagram of the power equipment; Based on the time domain diagram of the power equipment, the maximum amplitude value characteristics in the time domain diagram of the power equipment are calculated using the maximum amplitude formula; Based on the time domain diagram of the power equipment, the root mean square amplitude value characteristics in the time domain diagram of the power equipment are calculated using the root mean square amplitude formula; Based on the time domain diagram of the power equipment, the waveform kurtosis characteristics in the time domain diagram of the power equipment are calculated using the waveform kurtosis formula; Based on the time domain diagram of the power equipment, the waveform skewness characteristics in the time domain diagram of the power equipment are calculated using the waveform skewness formula; Based on the maximum amplitude value characteristics in the power equipment time domain diagram, the root mean square amplitude value characteristics in the power equipment time domain diagram, the waveform kurtosis characteristics in the power equipment time domain diagram, and the waveform skewness characteristics in the power equipment time domain diagram, the power equipment feature matrix G is constructed, G = [g 11 …g ij …g nm ], where G is the power equipment characteristic matrix, g ij is the jth feature data of the ith sampling point, n is the total number of sampling points, and m is the total number of features.

4. The method for partial discharge monitoring and positioning based on the Internet of Things architecture according to claim 3 is characterized in that: The maximum amplitude formula is: A max =max(|x(t)|) In the formula, A max is the maximum amplitude value characteristic in the time domain diagram of the power equipment, x is the amplitude value, and t is the time; The root mean square amplitude formula is: In the formula, B rms is the root mean square amplitude value characteristic in the time domain diagram of the power equipment, N is the total number of sampling points in the time domain diagram, and i is the i-th sampling point; The waveform kurtosis formula is: Where K is the peak characteristic of the waveform in the time domain diagram of the power equipment, x i is the amplitude value of the i-th sampling point, is the mean value of the amplitude; Among them, the waveform skewness formula is: Where S is the waveform skewness characteristic in the time domain diagram of the power equipment, and V is the standard deviation in the time domain diagram of the power equipment.

5. The method for partial discharge monitoring and positioning based on the Internet of Things architecture according to claim 4 is characterized in that: The step of evaluating the abnormal features in the power equipment feature matrix based on the power equipment feature matrix and the optimal operation comparison array to determine the abnormal state of the power equipment specifically includes: Based on the power equipment feature matrix, several feature subsets of power equipment are screened out according to the tag order; Based on the feature subsets of the plurality of electric devices, using the correlation coefficient formula, the correlation score in each feature subset of the electric device is calculated to obtain an array of correlation scores in the feature subsets of the plurality of electric devices; Standardizing the correlation score arrays and the optimal operation comparison arrays in the plurality of power equipment feature subsets to obtain a standardized power equipment feature subset array and a standardized optimal operation comparison array; using the standardized operating parameters of the standardized optimal operating control array as the optimal operating threshold; Based on the standardized electric power equipment feature subset array, the maximum feature score is used as the segmentation threshold, and the standardized electric power equipment feature subset array is segmented into two cotyledon sets to obtain a left cotyledon tree and a right cotyledon tree; Calculate the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree respectively, and calculate the average path length of each cotyledon based on the path length; Based on the path length of each cotyledon and the average path length of each cotyledon, the anomaly score is calculated using the exponential function formula; Based on the comparison between the abnormal score and the optimal operation threshold, it is determined whether the abnormal score exceeds the optimal operation threshold. If so, it is determined to be abnormal operation. If not, it is determined not to output.

6. A partial discharge monitoring and positioning method based on the Internet of Things architecture according to claim 5, characterized in that: The correlation coefficient formula is: C=|ρ(g ij ,Y)| Where C is the correlation score within each power equipment feature subset, ρ is the density symbol, and Y is the total number of cotyledons in the cotyledon tree; Among them, the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree is calculated respectively, and the average path length of each cotyledon is calculated according to the path length: In the formula, is the average length of the rth cotyledon path, k is the cotyledon, h is the processing function, and r is the cotyledon path; The exponential function formula is: In the formula, C 异 Score for anomaly.

7. A partial discharge monitoring and positioning system based on the Internet of Things architecture, characterized in that: A partial discharge monitoring and positioning method based on an Internet of Things architecture is used to implement any one of claims 1 to 6, comprising: Standard parameter acquisition module: The standard parameter acquisition module is used to collect ideal operating parameters of power equipment and establish an optimal operating comparison array; The acoustic data acquisition module is used to select a number of ultrasonic emission points and ultrasonic collection points based on the power equipment to be detected, and obtain a number of acoustic signal arrays of the power equipment; The acoustic data analysis module is electrically connected to the acoustic data acquisition module, and is used to analyze the acoustic signals in several groups of acoustic signal arrays of electric equipment based on several acoustic signal arrays of electric equipment, determine the characteristic data in the acoustic signals, and establish a characteristic matrix of electric equipment; An abnormality assessment module, the abnormality assessment module is electrically connected to the sound data analysis module, and the abnormality assessment module is used to evaluate the abnormal characteristics in the power equipment feature matrix based on the power equipment feature matrix and the optimal operation comparison array, and determine the abnormal state of the power equipment; The marking module is electrically connected to the abnormality assessment module, and is used to mark the abnormal discharge position of the abnormal state power equipment based on the abnormal state of the power equipment.

8. A partial discharge monitoring and positioning system based on the Internet of Things architecture according to claim 7, characterized in that: The sound data acquisition module includes: The collection unit marks the power equipment to be detected, selects a number of ultrasonic emission points and ultrasonic collection points for the power equipment in the marked order, and obtains ultrasonic signal data of each power equipment; an amplification processing unit, based on the ultrasonic signal data of each electric device, amplifying the ultrasonic signal data therein; The signal conversion unit discretizes the continuous ultrasonic signal data into a series of pulses in the form of analog signals according to the amplified ultrasonic signal data, and encodes the amplitude and time of the pulses to represent the value of the analog signal, thereby converting the ultrasonic signal into a digital signal; The acoustic signal array unit converts the ultrasonic signal of each power device into a digital signal, maps the digital signal according to the order of the power devices, and establishes several acoustic signal arrays of the power devices.

9. The partial discharge monitoring and positioning system based on the Internet of Things architecture according to claim 7 is characterized in that: The sound data analysis module includes: A quantization unit, based on a plurality of groups of electric power equipment sound signal arrays, performs quantization processing on the sound data in the arrays to obtain a quantized array of the electric power equipment sound signal; A time domain diagram unit, based on the quantized array of acoustic signals of the electric power equipment, draws a time domain diagram, marks the waveform starting point, peak, trough and waveform ending point in the time domain diagram, and determines the time domain diagram of the electric power equipment; The maximum amplitude characteristic unit calculates the maximum amplitude value characteristic in the time domain diagram of the power equipment by using the maximum amplitude formula based on the time domain diagram of the power equipment; A root mean square amplitude characteristic unit, based on the time domain diagram of the power equipment, uses a root mean square amplitude formula to calculate the root mean square amplitude value characteristics in the time domain diagram of the power equipment; A waveform kurtosis characteristic unit, based on a time domain diagram of the power equipment, uses a waveform kurtosis formula to calculate a waveform kurtosis characteristic in the time domain diagram of the power equipment; A waveform skewness characteristic unit, based on a time domain diagram of the power equipment and using a waveform skewness formula, calculates waveform skewness characteristics in the time domain diagram of the power equipment; The feature matrix unit constructs a power equipment feature matrix G based on the maximum amplitude value feature in the power equipment time domain diagram, the root mean square amplitude value feature in the power equipment time domain diagram, the waveform kurtosis feature in the power equipment time domain diagram, and the waveform skewness feature in the power equipment time domain diagram.

10. The partial discharge monitoring and positioning system based on the Internet of Things architecture according to claim 7, characterized in that: The anomaly assessment module includes: A screening unit, based on the power equipment feature matrix, screens out feature subsets of several power equipment according to the tag order; A correlation calculation unit, based on the feature subsets of the plurality of power devices, uses a correlation coefficient formula to calculate the correlation score in each feature subset of the power devices, and obtains an array of correlation scores in the feature subsets of the plurality of power devices; A standardization unit, which performs standardization processing on correlation score arrays and optimal operation comparison arrays in a plurality of power equipment feature subsets to obtain a standardized power equipment feature subset array and a standardized optimal operation comparison array; A threshold unit, which uses the standardized operation parameter of the standardized optimal operation reference array as the optimal operation threshold; A segmentation unit, based on the standardized electric power equipment feature subset array, uses the maximum feature score as a segmentation threshold, and segments the standardized electric power equipment feature subset array into two cotyledon sets to obtain a left cotyledon tree and a right cotyledon tree; A path length calculation unit calculates the path length of each cotyledon in the left cotyledon tree and the right cotyledon tree respectively, and calculates the average path length of each cotyledon according to the path length; The anomaly score calculation unit calculates the anomaly score through an exponential function formula based on the path length of each cotyledon and the average path length of each cotyledon; The abnormality judgment unit compares the abnormality score with the optimal operation threshold to judge whether the abnormality score exceeds the optimal operation threshold. If so, it is judged as abnormal operation. If not, it is judged not to output.

Images