A power equipment test data acquisition method and device based on multi-source data fusion

Abstract

The application discloses a kind of based on multi-source data fusion's electric power equipment test data acquisition method and device, the method includes: each sensor real-time collection electric power equipment's operating data;Based on abnormal situation and equipment state, operating data is evaluated to generate multi-source data fusion parameter;Based on multi-source data fusion parameter, generate compression strategy parameter;Based on multi-source data fusion parameter, the operating data of each sensor real-time collection electric power equipment is fused, and fusion multi-source operating data is obtained;According to compression strategy parameter, fusion multi-source operating data is compressed;Compressed fusion multi-source operating data is transmitted to central processing unit.The application improves the real-time monitoring capability and fault warning level of electric power equipment data acquisition system, reduces the cost of data transmission and storage.

Description

Technical Field

[0001] This invention belongs to the field of computer technology, and in particular relates to a method and device for acquiring test data of power equipment based on multi-source data fusion. Background Technology

[0002] With the continuous development and increasing intelligence of power systems, the demand for monitoring the operational status and providing early warning of faults in power equipment is growing. Traditional power equipment data acquisition methods mainly rely on single sensors for data monitoring. This approach often fails to comprehensively and accurately reflect the actual operating conditions of equipment in the face of complex operating environments and changing equipment states. As the types and quantities of power equipment increase, the amount of data generated is experiencing explosive growth. Single-source data acquisition methods are insufficient to meet the real-time processing and analysis needs of large-scale, multi-dimensional data. Furthermore, existing data acquisition systems suffer from high redundancy and transmission delays during data transmission, resulting in insufficient real-time performance and an inability to promptly detect and respond to equipment anomalies, thus impacting the overall operational efficiency and safety of the power system.

[0003] Therefore, there is an urgent need for an efficient and intelligent data acquisition method based on multi-source data fusion to improve the response speed, data processing capability and overall reliability of power equipment monitoring systems. Summary of the Invention

[0004] To address the shortcomings of the existing technology, this invention provides a method for acquiring test data of power equipment based on multi-source data fusion, the method comprising:

[0005] Step 1: Each sensor collects real-time operating data of the power equipment;

[0006] Step 2: Evaluate the operational data based on abnormal conditions and equipment status to generate multi-source data fusion parameters;

[0007] Step 3: Generate compression strategy parameters based on multi-source data fusion parameters;

[0008] Step 4: Based on the multi-source data fusion parameters, the real-time operating data of the power equipment collected by each sensor is fused to obtain fused multi-source operating data;

[0009] Step 5: Compress the fused multi-source runtime data according to the compression strategy parameters;

[0010] Step 6: Transmit the compressed fused multi-source running data to the central processing unit.

[0011] Furthermore, the method includes:

[0012] Step 1: Each sensor collects real-time operating data of the power equipment and transmits the data to the intelligent decision engine and adaptive data fusion module;

[0013] Step 2: The intelligent decision engine receives real-time operating data of the power equipment from various sensors, evaluates the operating data based on abnormal conditions and equipment status to generate multi-source data fusion parameters, and sends the multi-source data fusion parameters to the adaptive data fusion module.

[0014] Step 3: The intelligent decision engine generates compression strategy parameters based on the multi-source data fusion parameters;

[0015] Step 4: The adaptive data fusion module, based on the multi-source data fusion parameters determined by the intelligent decision engine, fuses the multi-source operating data of the power equipment collected in real time by each sensor to obtain fused multi-source operating data, and sends the fused multi-source operating data to the intelligent compression module.

[0016] Step 5: The intelligent compression module compresses the fused multi-source operating data according to the compression strategy parameters determined by the intelligent decision engine.

[0017] Step 6: The compressed, fused multi-source operating data is transmitted to the central processing unit in the cloud via the transmission module.

[0018] The execution time of step 4 is after step 2 and before step 5; the execution time of step 3 is after step 2 and before step 5; that is, the execution times of steps 2 and 3 at least partially overlap.

[0019] In step 2, the sensors collect real-time operating data of the power equipment, including voltage, current, temperature, vibration, and humidity parameters at key locations.

[0020] Among them, multi-source data fusion parameters are generated by evaluating operational data based on abnormal conditions and equipment status, including:

[0021] The Isolation Forest algorithm is used to detect anomalies in the operational data of each type of sensor, and an anomaly score is obtained, specifically:

[0022] s(x): Anomaly score for data point x;

[0023] E(h(x)): The average path length of data point x in the isolated forest;

[0024] c(n): Adjustment parameter determined by the number of sensors n.

[0025] H(n): the nth harmonic number, That is, H(n-1) is the (n-1)th harmonic number;

[0026] A threshold is set based on the anomaly score. Data points with anomaly scores higher than the threshold are marked as abnormal data for this type of sensor, while the rest are normal data.

[0027] Among them, multi-source data fusion parameters are generated by evaluating operational data based on abnormal conditions and equipment status, including:

[0028] If the proportion of abnormal data from a certain sensor exceeds a certain percentage of the total number of data samples collected by that sensor, all operational data from that sensor are determined to be abnormal data, and all operational data collected by the sensor that caused the abnormality are marked as abnormal data.

[0029] In addition, the operating data of other sensors, except for those that produce abnormalities, are considered normal data.

[0030] This includes generating multi-source data fusion parameters by evaluating operational data based on abnormal conditions and equipment status, and also includes:

[0031] For each type of sensor, normal data is used to assess the equipment status, identify potential equipment failure characteristics, and determine key data.

[0032] This involves assessing the equipment status based on normal data from each type of sensor, identifying potential equipment failure characteristics, and determining key data, including:

[0033] Principal component analysis is performed on the operational data of each type of sensor parameter, including constructing the data matrix of each type of sensor parameter, calculating the covariance matrix, and performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors.

[0034] Select the top k principal components so that the cumulative contribution rate reaches the set threshold η;

[0035] Project the data into the principal component space;

[0036] Calculate the reconstruction error for each sensor: in:

[0037] e i : Reconstruction error of the i-th sensor;

[0038] x i : The i-th original sensor vector;

[0039] The reconstruction vector of the i-th sensor is: Z i W is the dimensionality-reduced data matrix of the i-th sensor. k Let T be the matrix composed of the first k eigenvectors, and let T be the transpose of the matrix. This is the mean vector of the data matrix;

[0040] Set an error threshold ε, when e i When the value is greater than ε, all corresponding sensor operating data will be marked as key data in that type of sensor.

[0041] The data matrix satisfies the following relationship:

[0042]

[0043] in:

[0044] X: A normal data matrix with dimensions n×p;

[0045] x ij : The j-th feature value of the i-th sensor corresponding to the sensor type, wherein the sensor type is voltage, current, temperature, vibration, or humidity, and the j-th feature value is the value collected in the j-th acquisition cycle;

[0046] n: Number of sensors;

[0047] p: Number of features (number of acquisition cycles);

[0048] In step 3, compression strategy parameters are generated based on multi-source data fusion parameters. This includes an intelligent decision engine determining the compression ratio based on the proportion of abnormal data and key data, as well as the available bandwidth, according to the multi-source data fusion parameters.

[0049] Among them, a compression algorithm is determined based on the determined compression ratio, and the received fused multi-source running data is compressed;

[0050] When compression begins, the available bandwidth is determined and a compression strategy is established, including appending abnormal and critical data segments to normal data packets if the available bandwidth allows; and comparing the abnormal and critical data segments appended to normal data packets with the lossless compressed abnormal and critical data packets at the receiving end to determine whether retransmission is necessary.

[0051] This invention also discloses a power equipment test data acquisition system based on multi-source data fusion, employing the aforementioned power equipment test data acquisition method based on multi-source data fusion. The system comprises:

[0052] A multi-source data acquisition module is used to collect real-time operating data of power equipment;

[0053] The intelligent decision engine is used to evaluate operational data based on abnormal conditions and equipment status to generate multi-source data fusion parameters; and to generate compression strategy parameters based on the multi-source data fusion parameters.

[0054] An adaptive data fusion module is used to fuse the real-time operating data of the power equipment collected by each sensor based on multi-source data fusion parameters to obtain fused multi-source operating data.

[0055] The intelligent compression module is used to compress the fused multi-source operating data according to the compression strategy parameters;

[0056] The transmission module is used to transmit compressed, fused multi-source running data to the central processing unit.

[0057] This invention employs a method combining an intelligent decision engine and an adaptive data fusion module. This achieves efficient fusion and dynamic compression of multi-source data, effectively reducing data redundancy and improving data transmission and processing efficiency. The intelligent decision engine can perform anomaly detection and equipment status assessment based on real-time monitoring data, generating multi-source data fusion parameters and compression strategy parameters suitable for the current environment, thereby guiding the adaptive data fusion module to optimize the data processing flow. The fused results after data compression are efficiently transmitted to the cloud-based central processing unit via a transmission module, ensuring data real-time performance and integrity. The overall technical solution not only enhances the real-time monitoring capabilities and fault early warning level of the power equipment data acquisition system but also significantly reduces data transmission and storage costs, improving the overall reliability and scalability of the system.

[0058] The method of this invention not only improves the real-time monitoring capability and fault early warning level of the power equipment data acquisition system, but also significantly reduces the cost of data transmission and storage, and improves the overall reliability and scalability of the system. Attached Figure Description

[0059] The above and other objects, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the present disclosure are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein:

[0060] Figure 1 This is a flowchart illustrating a method for acquiring test data of power equipment based on multi-source data fusion according to an embodiment of the present invention.

[0061] Figure 2 This is a schematic diagram illustrating a power equipment test data acquisition system based on multi-source data fusion according to an embodiment of the present invention. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0063] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0064] It should be understood that although the terms first, second, third, etc., may be used to describe... in the embodiments of the present invention, these... should not be limited to these terms. These terms are only used to distinguish... For example, first... may also be referred to as second... without departing from the scope of the embodiments of the present invention, and similarly, second... may also be referred to as first...

[0065] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0066] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0067] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0068] Traditional data acquisition methods often struggle to effectively integrate real-time data from multiple sensors, resulting in low data processing efficiency and difficulty in timely detection of equipment anomalies or condition assessment. Furthermore, the dramatic increase in data volume leads to significantly higher transmission and storage costs, further restricting the performance and reliability of power equipment monitoring systems. Existing technologies lack adaptability in the fusion and compression of multi-source data, making it difficult to dynamically adjust data processing strategies to adapt to different operating environments and equipment status changes, thus affecting the overall system's response speed and accuracy. This invention provides a solution to the technical problems of data redundancy, transmission delay, and insufficient real-time performance in the acquisition and processing of massive multi-source data generated during power equipment operation.

[0069] This invention aims to provide a method for acquiring power equipment test data based on multi-source data fusion. Through an intelligent decision engine, it achieves adaptive fusion and compression of data in a coordinated manner, thereby improving the efficiency and quality of power equipment test data acquisition.

[0070] like Figure 1 As shown, this invention discloses a method for acquiring test data of power equipment based on multi-source data fusion, the method comprising:

[0071] Step 1: Each sensor collects real-time operating data of the power equipment and transmits the data to the intelligent decision engine and adaptive data fusion module.

[0072] Step 2: The intelligent decision engine receives real-time operating data of power equipment collected from various sensors, evaluates the operating data based on abnormal conditions and equipment status to generate multi-source data fusion parameters, and sends the multi-source data fusion parameters to the adaptive data fusion module.

[0073] Step 3: The intelligent decision engine generates compression strategy parameters based on the multi-source data fusion parameters.

[0074] Step 4: The adaptive data fusion module, based on the multi-source data fusion parameters determined by the intelligent decision engine, fuses the real-time operating data of the power equipment collected by each sensor to obtain fused multi-source operating data, and sends the fused multi-source operating data to the intelligent compression module.

[0075] Step 5: The intelligent compression module compresses the fused multi-source operating data according to the compression strategy parameters determined by the intelligent decision engine.

[0076] Step 6: The compressed, fused multi-source operating data is transmitted to the central processing unit in the cloud via the transmission module.

[0077] This invention achieves efficient fusion and dynamic compression of multi-source data by combining an intelligent decision engine with an adaptive data fusion module, effectively reducing data redundancy and improving data transmission and processing efficiency. The intelligent decision engine can perform anomaly detection and equipment status assessment based on real-time monitoring data, generating multi-source data fusion parameters and compression strategy parameters suitable for the current environment, thereby guiding the adaptive data fusion module to optimize the data processing flow. The fused results after data compression are efficiently transmitted to the cloud-based central processing unit via a transmission module, ensuring data real-time performance and integrity.

[0078] Specifically, step 4 is executed after step 2 and before step 5; step 3 is executed after step 2 and before step 5. That is, steps 2 and 3 at least partially overlap in execution time.

[0079] In this invention, the execution times of steps 2 and 3 are arranged before step 5 and at least partially overlap, forming a parallel processing mechanism.

[0080] By partially overlapping the execution of steps 2 (generating multi-source data fusion parameters by the intelligent decision engine) and 3 (generating compression strategy parameters by the intelligent decision engine), the system can achieve parallel processing of multiple tasks. This parallelism effectively shortens the overall data processing time cycle and improves data processing efficiency. Compared to executing each step sequentially, which results in a longer overall processing time and affects real-time performance.

[0081] In the process of multi-source data fusion and data compression, the required computing resources may have a certain degree of independence or partial overlap. Parallel processing can make more efficient use of processor and memory resources, avoiding resource idleness and waste, thereby improving the overall performance and processing capacity of the system. By optimizing the execution time arrangement of the steps, the method of this invention achieves higher parallelism and lower latency in multi-source data processing, significantly improving the efficiency of data transmission and processing. This not only reduces the overall operating cost of the system but also enhances the system's scalability and adaptability, enabling it to better cope with the dynamic changes in the operating environment of power equipment and the rapid growth of data volume.

[0082] In one embodiment, the multi-source data acquisition module consists of multiple sensor nodes, which are installed in key parts of the power equipment.

[0083] Each sensor node transmits the collected data to the adaptive data fusion module via a wireless network.

[0084] In one embodiment, the system collects real-time operating data of power equipment using multiple sensors to ensure comprehensive monitoring of equipment performance and status, including:

[0085] First, various sensors are used, including voltage sensors, current sensors, temperature sensors, vibration sensors, and humidity sensors. These sensors can be fixedly installed in critical parts of the equipment, or measured by wired connections from detection equipment at specific points on the electrical equipment. For example, current and voltage sensors may be installed at the equipment's input and output lines, temperature sensors may be distributed near critical heat sources, and vibration sensors may be placed near mechanical connection points or rotating parts.

[0086] Each sensor is equipped with a real-time data acquisition module. The operational data acquired by the sensors undergoes preliminary processing by a local processing unit, such as filtering, noise reduction, and signal amplification, to improve data quality and reliability. The processed data is then transmitted to an adaptive data fusion module via a wireless communication protocol, such as WiFi or LoRa.

[0087] In one embodiment, power equipment test data acquisition is achieved through multi-source data fusion based on a distributed sensor network. Sensor nodes are connected to an adaptive data fusion module via a wireless communication network, and the adaptive data fusion module is deployed on a local server or edge computing device. The adaptive data fusion module has high-performance data reception and processing capabilities, enabling it to simultaneously process large amounts of real-time data streams from multiple sensors.

[0088] In one embodiment, in step 1, the sensor node is responsible for collecting specific types of operational data in real time and performing preliminary processing. A wireless communication network enables efficient data transmission between the sensor node and the adaptive data fusion module, ensuring low latency and high bandwidth. The adaptive data fusion module centrally receives, manages, and preprocesses data from each sensor, providing high-quality input for subsequent data fusion and compression.

[0089] In one embodiment, the intelligent decision engine receives real-time operational data from various sensors via a high-efficiency communication interface. This data includes voltage, current, temperature, vibration, and humidity parameters at key locations, with each sensor collecting data of any type among voltage, current, temperature, vibration, and humidity. The intelligent decision engine employs a high-throughput data reception mechanism, supporting concurrent processing of multiple data streams. The received data first undergoes a preprocessing module.

[0090] In one embodiment, the intelligent decision engine sends the generated optimization parameters (multi-source data fusion parameters) to the adaptive data fusion module and the intelligent compression module through a secure and reliable communication protocol.

[0091] In one embodiment, the system architecture of the intelligent decision engine includes:

[0092] The data receiving module is responsible for receiving data streams from various sensors in real time;

[0093] The data preprocessing module includes data normalization functionality;

[0094] The data analysis and evaluation module uses machine learning models and statistical analysis methods to analyze the received data and evaluate the current data fusion and compression requirements.

[0095] The parameter determination module is used to generate optimal data fusion and compression parameters;

[0096] Parameter distribution module: Responsible for distributing parameters to the corresponding modules.

[0097] In one embodiment, in step 2, the intelligent decision engine receives real-time power equipment operation data collected from various sensors, including parameters such as voltage, current, temperature, vibration, and humidity at key locations. Based on the assessment of abnormal conditions and equipment status, the intelligent decision engine generates multi-source data fusion parameters and sends these parameters to the adaptive data fusion module.

[0098] In one embodiment, the intelligent decision engine receives operational data collected by various sensors in real time through an efficient communication interface, standardizing parameter data with different dimensions and units to a unified range.

[0099] For each type of sensor (voltage, current, temperature, vibration, humidity), a normalization operation is performed. The normalization formula is:

[0100]

[0101] in:

[0102] x i The i-th value of the original data;

[0103] x i ′: The i-th value of the normalized data;

[0104] x min x max The minimum and maximum values ​​in the dataset.

[0105] Then, the intelligent decision engine uses machine learning models and statistical analysis methods to detect anomalies in the preprocessed data, identify anomalies in the data, and classify the data.

[0106] Optionally, the isolated forest algorithm is used to perform anomaly detection on the data of each type of sensor parameter, including voltage, current, temperature, vibration, and humidity.

[0107] The anomaly scoring formula is:

[0108] in:

[0109] s(x): Anomaly score for data point x;

[0110] E(h(x)): The average path length of data point x in the isolated forest;

[0111] c(n): Adjustment parameter determined by the number of sensors n.

[0112] H(n): the nth harmonic number,

[0113] Based on the anomaly score, a threshold is set, and data points with anomaly scores higher than the threshold are marked as abnormal data for that type of sensor data, while the rest are normal data.

[0114] Based on the anomaly detection results, the data is divided into:

[0115] Normal data: Data that is not marked as abnormal.

[0116] Abnormal data: Data that has been marked as abnormal.

[0117] Optionally, when the proportion of abnormal data from a certain sensor exceeds a certain percentage of the total number of data sampled by that sensor, all data from that sensor are determined to be abnormal data, and all data collected by the sensor that caused the abnormality are marked as abnormal data.

[0118] Furthermore, data from sensors other than those exhibiting anomalies are considered normal. Optionally, equipment condition assessment is performed on the normal data for each type of sensor parameter to identify potential equipment fault characteristics and determine key data, including the following processes:

[0119] Principal component analysis (PCA) was performed on the data of each type of sensor parameters:

[0120] Construct a data matrix for the parameters of each type of sensor:

[0121] in:

[0122] X: The preprocessed normal data matrix, with dimensions n×p;

[0123] x ij : The j-th feature value of the i-th sensor corresponding to the sensor type, wherein the sensor type is voltage, current, temperature, vibration, or humidity, and the j-th feature value can be the value collected in the j-th acquisition cycle;

[0124] n: Number of sensors;

[0125] p: Number of features (number of acquisition cycles).

[0126] Calculate the covariance matrix:

[0127] in:

[0128] C: Covariance matrix, with dimensions p×p;

[0129] The mean vector of the data matrix.

[0130] Eigenvalue decomposition of the covariance matrix yields eigenvalues ​​and eigenvectors: in:

[0131] Λ=diag(λ1λ2,…,λ p ): A diagonal matrix containing eigenvalues ​​arranged in descending order;

[0132] W = [w1, w2, ..., w p ]: The corresponding eigenvector matrix.

[0133] Select the top k principal components so that the cumulative contribution rate reaches a set threshold η (e.g., 90%):

[0134]

[0135] Project the data onto the principal component space: Z = XW k ,

[0136] in:

[0137] Z: The data matrix after dimensionality reduction, with dimensions n×k;

[0138] W k : A matrix consisting of the first k eigenvectors, with dimensions p×k.

[0139] Key data identification includes:

[0140] Calculate the reconstruction error for each sensor:

[0141] in:

[0142] e i : Reconstruction error of the i-th sensor;

[0143] x i : The i-th original sensor vector;

[0144] The reconstruction vector of the i-th sensor.

[0145] Set an error threshold ε, when e i When the value is greater than ε, all corresponding sensor data will be marked as key data in that type of sensor.

[0146] In one embodiment, once the intelligent decision engine has identified abnormal and key data, this information needs to be effectively transmitted to the adaptive data fusion module, which then performs the corresponding data fusion according to the instructions.

[0147] The intelligent decision engine labels the data, classifying it into "normal data," "abnormal data," or "critical data." This labeling process is based on previous anomaly detection and equipment status assessment results.

[0148] In one embodiment, to ensure that the intelligent decision engine and the adaptive data fusion module have a consistent understanding of the parameters, a predefined structured format is adopted:

[0149] All sensor attributes are arranged in a fixed order, such as voltage, current, temperature, vibration, and humidity.

[0150] Status coding uses 2-bit binary numbers to represent the status of each sensor:

[0151] Normal: 00

[0152] Abnormal: 01

[0153] Critical: 10

[0154] The status information and fusion weights are packaged into compact binary bytes in a predefined order: for example, when there are five temperature sensors with the statuses of normal, abnormal, critical, normal, and abnormal, their binary representation is 0001100001, which is then combined into 0001100001.

[0155] In one embodiment, in step 3, the intelligent decision engine generates compression strategy parameters based on multi-source data fusion parameters. This includes the intelligent decision engine determining an appropriate compression ratio by comprehensively considering the proportion of abnormal data and key data, as well as the available bandwidth, according to the multi-source data fusion parameters.

[0156] In one embodiment, the intelligent decision engine first calculates the proportion of abnormal data and critical data in the total data to determine the compression ratio that the normal data needs to achieve.

[0157] Specifically, calculate the ratio of outlier data to key data:

[0158]

[0159] in:

[0160] P abnormal The percentage of abnormal data in the total data;

[0161] V abnormal Total amount of abnormal data (in bytes);

[0162] V total Total data volume (in bytes).

[0163] in,

[0164] in:

[0165] P critical The proportion of key data to total data;

[0166] V critical Total data volume of key data (unit: bytes).

[0167] The percentage of normal data is: P normal =1-P abnormal -P critical ,

[0168] Determine the compression ratio required for normal data:

[0169] First, calculate the bandwidth required for abnormal and critical data without compression:

[0170] BW abnormal =R abnormal =V abnormal ×f sampling ,

[0171] BW critical =R critical =V critical ×f sampling ,

[0172] in:

[0173] BW abnormal BW critical : Bandwidth required for abnormal and critical data;

[0174] R abnomal R critical : Data rate of abnormal data and key data;

[0175] f sampling : The sampling frequency of the sensor.

[0176] The remaining bandwidth available for normal data transmission is: BW normal =BWa vailable -BW abnormal -BWcritical，

[0177] in:

[0178] BW normal : Bandwidth available for normal data;

[0179] BW available Total available bandwidth of the system.

[0180] Then, calculate the compression ratio that normal data needs to achieve: in:

[0181] CR normal The compression ratio required for normal data;

[0182] V normal Total amount of normal data.

[0183] To ensure data transmission complies with bandwidth limits, the following conditions must be met:

[0184] Secondly, the intelligent decision engine incorporates factors such as the bit error rate, adjusting the formula for calculating the compression ratio, and comprehensively considering these factors to achieve a higher compression ratio (ECR). normal The calculation formula is:

[0185] in:

[0186] E normal The maximum allowable bit error rate for normal data, which should generally not exceed 0.15.

[0187] H: The maximum augmentation ratio for normal data. H is a natural number greater than or equal to 2.

[0188] Other parameters are the same as described above.

[0189] Then determine the bandwidth (EBW) corresponding to the compression ratio based on comprehensive factors. normal For: EBW normal =BW normal ×H (1-Enormal) .

[0190] Optionally, the maximum augmentation ratio H of normal data is related to the current sensor data reporting cycle, which is an integer multiple of the base reporting cycle. The base reporting cycle is preset, for example, the base reporting cycle is equal to 4 times the sensor acquisition cycle.

[0191] The current sensor data reporting cycle is optional for the user.

[0192] The maximum augmentation ratio H for normal data is set to 2. When the current sensor data reporting cycle is longer than the basic reporting cycle, the formula for calculating the maximum augmentation ratio H for normal data is as follows:

[0193]

[0194] Where floor is the floor function, period is the current acquisition period, and the base acquisition period is period. base .

[0195] In one embodiment, step 5, the intelligent compression module compresses the data according to the compression ratio determined by the intelligent decision engine, including:

[0196] The received fused multi-source operational data is compressed. When the intelligent compression module starts compression, the currently available transmission bandwidth is determined again. If the available bandwidth allows, a compression strategy is formulated, specifically including:

[0197] If the currently available bandwidth BW is determined <BW normal (where BW) normal If the available bandwidth for normal data is determined in step 4, then wait to detect available bandwidth BW≥BW. normal Then the transmission will proceed.

[0198] If the currently available bandwidth BW is determined normal ≤BW<EBW normal In such cases, the following strategy shall be adopted:

[0199] Use the calculated CR for normal data normal Compress (data packet 1);

[0200] Lossless compression is performed on abnormal data (data packet 2) and critical data (data packet 3);

[0201] Transmit data packets 1, 2, and 3.

[0202] If the currently available bandwidth BW is greater than or equal to EBW normal Then the following strategy will be adopted:

[0203] Lossless compression is performed on abnormal data (data packet 2) and critical data (data packet 3);

[0204] After appending abnormal and critical data segments to normal data packets, the calculated CR is used. normal Compress (data packet 4);

[0205] Transmit data packets 4, 2, and 3;

[0206] Furthermore, at the receiving end, a comparison is performed, and based on the comparison of lossless data, a determination is made as to whether retransmission is necessary, including:

[0207] At the receiving end, the received data packet 4 is decompressed and compared with the data in data packets 2 and 3. Calculation error: E = |D normal -D important |,

[0208] in:

[0209] E: Error matrix;

[0210] D normal : Abnormal data segments and critical data segments in the decompressed data packet 4;

[0211] D important Lossless data for abnormal and critical data.

[0212] If the error E exceeds the preset threshold E threshold If so, the sender is requested to retransmit the corresponding data to ensure data accuracy.

[0213] When bandwidth is insufficient, abnormal and critical data segments are not appended to normal data packets, nor are comparison, calibration, or retransmission performed. Only normal data packets and lossless compressed abnormal and critical data are transmitted to avoid further network congestion and exacerbating data upload delays. The intelligent decision engine of this invention, considering the proportion of abnormal and critical data, data statistical characteristics, and available bandwidth, prioritizes lossless transmission of abnormal and critical data when available bandwidth allows. Abnormal and critical data segments are appended to normal data packets, resulting in a comprehensive data packet. The receiving end compares the abnormal and critical data segments in the comprehensive data packet with the lossless compressed abnormal and critical data to determine whether retransmission is necessary, ensuring the reliability and accuracy of data transmission. If bandwidth is insufficient, abnormal and critical data segments are not appended to normal data segments; only compressed normal data is transmitted, and the compression ratio and sampling frequency are adjusted according to specific circumstances to ensure system efficiency and data transmission effectiveness.

[0214] In one embodiment, in step four, the adaptive data fusion module processes the real-time power equipment operation data collected by each sensor according to the multi-source data fusion parameters provided by the intelligent decision engine. This includes dividing the data into four different data packets based on the labeling of the data by the intelligent decision engine: normal data packets, abnormal data packets, critical data packets, and comprehensive data packets containing all the data.

[0215] In one embodiment, the adaptive data fusion module receives real-time data from various sensors, along with labels from the intelligent decision engine. Based on the labeling information, the adaptive data fusion module categorizes the data. For example, sensor data labeled "normal" and "critical" is categorized into a normal data packet; sensor data labeled "abnormal" is categorized into an abnormal data packet; and sensor data labeled "critical" is categorized into a critical data packet. Furthermore, to enable rapid compression in certain situations by the intelligent compression module, the adaptive data fusion module also creates a comprehensive data packet containing all sensor data. After categorization, the adaptive data fusion module appends necessary metadata, such as timestamps, to each data packet. After data packetization, the adaptive data fusion module sends these data packets to the intelligent compression module for compression processing.

[0216] In one embodiment, in step five, the intelligent compression module determines the compression ratio CR based on the intelligent decision engine. normal Choose an appropriate compression algorithm and based on CR normal Determine the specific compression parameters and compress the received fused multi-source runtime data.

[0217] The intelligent compression module first receives four data packets from the adaptive data fusion module, and formulates an appropriate compression strategy for the selected data packets based on the compression ratio provided by the intelligent decision engine and the available transmission bandwidth.

[0218] For normal data packets, the intelligent compression module selects an appropriate lossy compression algorithm to compress the data. Commonly used lossy compression algorithms include predictive coding, quantization, and wavelet transform.

[0219] Taking quantization compression as an example, specific compression parameters (such as quantization step size) can be determined based on CR. normal Confirmed. The basic principle of quantization is to discretize the continuous signal amplitude, reducing the amount of data by decreasing the number of bits required to represent each sample point.

[0220] First, determine the number of quantization bits n:

[0221] Assuming the original data is a 16-bit integer, to achieve a compression ratio CR normal =4,

[0222] The quantization bits are:

[0223] Next, calculate the quantization step size Δ:

[0224] Where, x max and x minThese represent the maximum and minimum values ​​of the dataset, respectively. The quantization step size Δ determines the quantization precision. A larger Δ leads to a larger quantization error but a higher compression ratio; a smaller Δ has the opposite effect.

[0225] By adjusting the quantization bit depth n and step size Δ, the intelligent compression module can achieve the desired compression ratio CR. normal During the compression process, the intelligent compression module quantizes the original data according to the quantization step size, mapping continuous values ​​to a finite set of discrete values, thereby reducing the amount of data.

[0226] For abnormal data packets, the intelligent compression module uses lossless compression algorithms. Commonly used lossless compression algorithms include Huffman coding and arithmetic coding.

[0227] For critical data packets, the intelligent compression module can perform lossless compression.

[0228] If you need to select a composite data packet, then do not select a normal data packet. The intelligent compression module should use the same compression algorithm and compression ratio as the normal data packet. Alternatively, you can select a compression ratio of (ECR). normal -TH), where TH is a user-defined overflow prevention value or a preset ratio (ECR). normal A certain proportion) needs to meet (ECR) normal -TH)>CR normal After compression and encapsulation are complete, the intelligent compression module sends the compressed data packet to the transmission module. The transmission module is responsible for implementing data strategies.

[0229] In one embodiment, in step six, the transmission module selects an appropriate transmission protocol (such as TCP, UDP, etc.) and adopts necessary transmission control mechanisms (such as flow control, congestion control, etc.) to reliably and efficiently transmit the compressed, fused multi-source running data to the central processing unit (CPU) in the cloud.

[0230] This invention employs a method combining an intelligent decision engine and an adaptive data fusion module. This achieves efficient fusion and dynamic compression of multi-source data, effectively reducing data redundancy and improving data transmission and processing efficiency. The intelligent decision engine can perform anomaly detection and equipment status assessment based on real-time monitoring data, generating multi-source data fusion parameters and compression strategy parameters suitable for the current environment, thereby guiding the adaptive data fusion module to optimize the data processing flow. The fused results after data compression are efficiently transmitted to the cloud-based central processing unit via a transmission module, ensuring data real-time performance and integrity. The overall technical solution not only enhances the real-time monitoring capabilities and fault early warning level of the power equipment data acquisition system but also significantly reduces data transmission and storage costs, improving the overall reliability and scalability of the system.

[0231] The method of this invention not only improves the real-time monitoring capability and fault early warning level of the power equipment data acquisition system, but also significantly reduces the cost of data transmission and storage, and improves the overall reliability and scalability of the system.

[0232] like Figure 2 As shown, the present invention also provides a power equipment test data acquisition system based on multi-source data fusion, employing the above-mentioned power equipment test data acquisition method based on multi-source data fusion. The system includes:

[0233] A multi-source data acquisition module is used to collect real-time operating data of power equipment;

[0234] The intelligent decision engine is used to evaluate operational data based on abnormal conditions and equipment status to generate multi-source data fusion parameters; and to generate compression strategy parameters based on the multi-source data fusion parameters.

[0235] An adaptive data fusion module is used to fuse the real-time operating data of the power equipment collected by each sensor based on multi-source data fusion parameters to obtain fused multi-source operating data; an intelligent compression module is used to compress the fused multi-source operating data according to compression strategy parameters.

[0236] The transmission module is used to transmit compressed, fused multi-source running data to the central processing unit.

[0237] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0238] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0239] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0240] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0241] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0242] The preferred embodiments of the present invention have been described above to make the spirit of the present invention clearer and easier to understand, and are not intended to limit the present invention. All modifications, substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope summarized by the appended claims.

Claims

1. A power equipment test data acquisition method based on multi-source data fusion, the method comprising: Step 1, each sensor acquires real-time operation data of the power equipment; Step 2, based on abnormal conditions and equipment states, the operation data is evaluated to generate multi-source data fusion parameters; Step 3, based on the multi-source data fusion parameters, compression strategy parameters are generated, including determining a compression ratio based on the proportion of abnormal data and key data and available bandwidth according to the multi-source data fusion parameters; Step 4, based on the multi-source data fusion parameters, the real-time operation data of the power equipment acquired by each sensor is fused to obtain fused multi-source operation data; Step 5, the fused multi-source operation data is compressed according to the compression strategy parameters, including: determining a compression algorithm according to the determined compression ratio to compress the received fused multi-source operation data; when starting compression, determining the current available bandwidth and determining the compression strategy, including, in the case where the available bandwidth allows, appending abnormal data segments and key data segments after normal data packets; and, through the receiving end, comparing the appended abnormal data segments and key data segments after the normal data packets with lossless compressed abnormal data packets and key data packets to determine whether retransmission is needed; in the case where the bandwidth is insufficient, transmitting normal data packets and lossless compressed abnormal data and key data; Step 6, the compressed fused multi-source operation data is transmitted to a central processing unit. 2.The power equipment test data acquisition method based on multi-source data fusion according to claim 1, wherein: the execution time of step 4 is after step 2 and before step 5; the execution time of step 3 is after step 2 and before step 5; that is, step 2 and step 3 at least partially overlap in execution time. 3.The power equipment test data acquisition method based on multi-source data fusion according to claim 1, wherein: in step 2, the power equipment operation data acquired by each sensor in real time includes voltage, current, temperature, vibration, and humidity parameters at key positions.

4. The power equipment test data acquisition method based on multi-source data fusion according to claim 3, characterized in that, based on abnormal conditions and equipment states, the operation data is evaluated to generate multi-source data fusion parameters, including: using an isolation forest algorithm to perform anomaly detection on the operation data of each type of sensor; according to the anomaly score threshold, data points with an anomaly score higher than the threshold are marked as abnormal data of the type of sensor, and the rest are normal data.

5. The power equipment test data acquisition method based on multi-source data fusion according to claim 4, characterized in that, based on abnormal conditions and equipment states, the operation data is evaluated to generate multi-source data fusion parameters, including: after the proportion of abnormal data of a certain sensor exceeds a certain proportion of the total number of sampling data of the sensor, it is determined that all operation data of the sensor is abnormal data, and all operation data collected by the sensor that generates abnormal data is marked as abnormal data; and, the operation data of other sensors is recognized as normal data except for the sensor that generates abnormal data.

6. The power equipment test data acquisition method based on multi-source data fusion according to claim 4, characterized in that, based on abnormal conditions and equipment states, the operation data is evaluated to generate multi-source data fusion parameters, further including: performing equipment state evaluation on normal data of each type of sensor to identify potential equipment failure features and determine key data.

7. The power equipment test data acquisition method based on multi-source data fusion according to claim 6, characterized in that, device state assessment on normal data of each type of sensor, identifying potential device failure features, determining key data, including: principal component analysis on operational data of each type of sensor, including constructing a data matrix of each type of sensor, calculating a covariance matrix, performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues and eigenvectors; before selection one principal component, so that the cumulative contribution rate reaches a set threshold ; projecting the data into a principal component space; Compute the reconstruction error for each sensor: where: : the reconstruction error of the first sensor; : first sensor vector; : the reconstructed vector of the first sensor : the reconstructed vector of the second sensor Setting error thresholds When the operating data of the corresponding sensor is marked as critical data in the type of sensor.

8. A power equipment test data acquisition system based on multi-source data fusion, characterized in that, using the power equipment test data acquisition method based on multi-source data fusion according to any one of claims 1-7, the system comprises: a multi-source data acquisition module for acquiring real-time operational data of the power equipment; an intelligent decision engine for evaluating the operational data based on abnormal conditions and device states to generate multi-source data fusion parameters, and generating compression strategy parameters based on the multi-source data fusion parameters; an adaptive data fusion module for fusing the operational data of the power equipment collected by the sensors in real time based on the multi-source data fusion parameters to obtain fused multi-source operational data; an intelligent compression module for compressing the fused multi-source operational data according to the compression strategy parameters; a transmission module for transmitting the compressed fused multi-source operational data to a central processing unit.

Images