A big data intelligent decision analysis method and system

Abstract

The present application provides a big data intelligent decision-making analysis method and system. Among them, the vibration data and mechanical node stress distribution data in the transportation of power equipment are obtained, and the high-frequency harmonic distortion characteristics aligned with the vibration data timestamp are extracted; the stress data fluctuations and the dynamic changes of harmonic characteristics are cross-domain correlated and analyzed, and the symbiotic pattern of mechanical stress anomalies and electrical harmonic distortion is identified using a machine learning model; based on logistics path planning and equipment constraints, a multi-objective collaborative optimization algorithm is used to generate collaborative control instructions for adjusting the transportation path and power supply circuit parameters; a joint risk assessment matrix is ​​constructed, and according to the quantitative analysis results and collaborative control instructions, the collaborative relationship between the transportation path and the harmonic suppression parameters is dynamically adjusted to achieve closed-loop decision-making of power equipment. The technical solution provided by the present application significantly improves the efficiency of power equipment transportation data processing.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for intelligent decision-making analysis of big data. Background Art

[0002] During the logistics and transportation of power equipment, mechanical vibration and electrical harmonic distortion are key factors affecting the safety and reliability of the equipment. Power equipment often faces complex road conditions and dynamic electrical environments during transportation. Mechanical vibration can cause structural damage to the equipment, while electrical harmonic distortion can trigger internal electrical failures.

[0003] Currently, existing solutions address the mechanical vibration and electrical harmonics issues associated with power equipment transportation by using independent monitoring and static optimization. This approach monitors mechanical stress and electrical harmonics during transportation and then makes static adjustments based on preset thresholds. For example, if mechanical stress exceeds a set threshold, the transportation route is adjusted to reduce vibration; if electrical harmonics exceed a threshold, the harmonic suppression parameters of the power supply circuit are adjusted.

[0004] However, this existing solution has significant limitations. First, mechanical stress and electrical harmonics are monitored independently, lacking a comprehensive analysis of their coupling relationship. This makes it impossible to accurately identify the interaction between mechanical vibration and electrical harmonics and their potential impact on equipment. Second, static adjustment methods cannot respond in real time to dynamically changing road conditions and electrical environments during transportation, making it difficult to effectively respond to sudden mechanical or electrical anomalies. Therefore, the existing solution lacks adaptability and reliability under complex transportation conditions and cannot meet the high standards required for the safe transportation of power equipment. Summary of the Invention

[0005] The embodiments of the present application provide a big data intelligent decision-making analysis method and system to solve the problem of poor processing effect of power equipment transportation data in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a big data intelligent decision analysis method, comprising:

[0007] Acquire transportation vibration data of power equipment, synchronously collect stress distribution data of key mechanical nodes of power equipment, and extract high-frequency harmonic distortion features aligned with the timestamp of transportation vibration data in the power supply circuit;

[0008] A cross-domain correlation analysis is conducted between the fluctuation amplitude of stress distribution data and the dynamic changes in high-frequency harmonic distortion characteristics. A machine learning model is used to identify the symbiotic correlation pattern between mechanical stress anomalies and electrical harmonic distortion under conditions of sudden changes in logistics transportation routes.

[0009] Based on the logistics transportation path planning parameters and the equipment operating environment constraints, a multi-objective collaborative optimization algorithm is used to make joint decisions on the symbiotic association model, generating collaborative control instructions that simultaneously adjust the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit.

[0010] A joint risk assessment matrix for mechanical stress anomalies and electrical harmonic distortion is constructed. Based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions, the collaborative relationship between logistics transportation paths and harmonic suppression parameters is dynamically adjusted to achieve closed-loop decision-making for power equipment.

[0011] Optionally, performing cross-domain correlation analysis on the fluctuation amplitude of stress distribution data and the dynamic changes of high-frequency harmonic distortion characteristics, and identifying the symbiotic correlation pattern between mechanical stress anomaly and electrical harmonic distortion under conditions of sudden changes in logistics transportation routes through a machine learning model, includes:

[0012] The fluctuation amplitude of the stress distribution data is divided into time windows. The stress peak sequence within the vibration impact interval is extracted based on the timestamp of the sudden change event in the logistics transportation path. At the same time, the frequency domain energy distribution of the high-frequency harmonic distortion characteristics within the same time window is decomposed to extract the harmonic energy mutation interval.

[0013] The temporal evolution of the stress peak sequence is spatiotemporally coupled with the frequency-domain diffusion characteristics of the harmonic energy mutation interval to construct a cross-domain correlation tensor weighted by the path mutation intensity, where the path mutation intensity is jointly calibrated by the curvature change rate of the transport path and the acceleration shock threshold.

[0014] Embedding mechanical node topology constraints in the cross-domain correlation tensor, capturing the cross-interference relationship between stress propagation paths and harmonic distortion conduction paths through dynamic graph convolution operations, and establishing a joint representation space for mechanical-electrical coupling features;

[0015] Based on the migration characteristics of equipment states before and after transportation route mutations, the boundary conditions of latent variables are iteratively optimized in the joint representation space, so that mechanical stress anomalies and harmonic distortion events form causally directed symbiotic clusters in the feature space.

[0016] A multi-scale path dependency analysis is performed on the symbiotic clusters. The transient correlation component induced by path mutations and the steady-state correlation component of the inherent characteristics of the equipment are separated through an adaptive gating mechanism, and a symbiotic correlation pattern topology map including the mechanical-electrical coupling strength and failure propagation path is output.

[0017] Optionally, the method of making a joint decision on the symbiotic association mode based on the logistics transportation path planning parameters and the equipment operating environment constraints through a multi-objective collaborative optimization algorithm to generate collaborative control instructions for simultaneously adjusting the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit includes:

[0018] The path curvature change rate and acceleration shock threshold in logistics transportation path planning parameters are converted into vibration suppression constraints. At the same time, the electromagnetic compatibility limit and temperature rise threshold in the equipment operating environment constraints are mapped into harmonic suppression constraints, thus constructing a joint decision space for mechanical vibration suppression and electrical harmonic suppression.

[0019] Based on the coupling intensity distribution of mechanical stress anomalies and harmonic distortion in the symbiotic correlation mode, the vibration suppression priority and harmonic suppression priority are divided in the joint decision space. The priority is dynamically adjusted by the ratio of the mechanical vibration propagation path length to the harmonic distortion conduction path length at the path mutation point.

[0020] The vibration attenuation characteristic curve of the transport path vibration avoidance parameters and the frequency domain response characteristic curve of the harmonic suppression parameters are introduced into the joint decision space. The conflict area and cooperative area of ​​the mechanical-electrical control parameters are determined through dual-channel feature cross-validation, and a collaborative control instruction set including the vibration avoidance path correction vector and the harmonic suppression frequency adjustment amount is output.

[0021] Optionally, the temporal-spatial coupling of the time-domain evolution law of the stress peak sequence and the frequency-domain diffusion characteristics of the harmonic energy mutation interval is performed to construct a cross-domain correlation tensor with the path mutation intensity as the weight, wherein the path mutation intensity is jointly calibrated by the curvature change rate of the transport path and the acceleration shock threshold, including:

[0022] The time-domain evolution law of the stress peak sequence is segmented and fitted to extract the rising slope, falling slope, and duration characteristics of the stress peak in the vibration impact interval. At the same time, the frequency-domain diffusion characteristics of the harmonic energy mutation interval are divided into frequency bands to extract the peak frequency and energy attenuation rate characteristics of the energy distribution in each frequency band.

[0023] The rising slope, falling slope and duration characteristics of the stress peak sequence are temporally and spatially aligned with the peak frequency and energy attenuation rate characteristics of the harmonic energy mutation interval. Based on the time evolution curve of the stress peak and the frequency domain diffusion curve of the harmonic energy, a cross-domain correlation tensor with the path mutation intensity as the weight is constructed, where the path mutation intensity is dynamically calibrated by the product of the curvature change rate of the transport path and the acceleration shock threshold.

[0024] Optionally, the cross-domain correlation tensor with path mutation intensity as weight is constructed based on the time evolution curve of the stress peak and the frequency domain diffusion curve of the harmonic energy, including: extracting the rising slope, falling slope and duration characteristics of the stress peak in the vibration impact interval based on the time evolution curve of the stress peak, and extracting the peak frequency and energy attenuation rate characteristics of the harmonic energy in each frequency band based on the frequency domain diffusion curve of the harmonic energy;

[0025] The temporal evolution characteristics of the stress peak and the frequency-domain diffusion characteristics of the harmonic energy are spatially and temporally aligned, and the characteristics are weighted based on the path mutation intensity, where the path mutation intensity is dynamically calibrated by the product of the curvature change rate of the transport path and the acceleration shock threshold;

[0026] The weighted spatiotemporal alignment features are integrated according to the spatiotemporal distribution of path mutation events to generate a cross-domain correlation tensor with the path mutation intensity as the weight. The cross-domain correlation tensor cross-validates the features through the geometric distance of the stress propagation path and the electrical distance of the harmonic distortion conduction path.

[0027] Optionally, the method of constructing a joint risk assessment matrix of mechanical stress anomalies and electrical harmonic distortion, dynamically adjusting the collaborative relationship between logistics transportation paths and harmonic suppression parameters based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions to achieve closed-loop decision-making for power equipment includes:

[0028] Based on the stress peak sequence of mechanical stress anomaly events and the frequency domain energy distribution of harmonic distortion events, a joint risk assessment matrix for mechanical stress anomaly and electrical harmonic distortion is constructed. The row vectors of the joint risk assessment matrix represent the intensity distribution of stress anomaly events, and the column vectors represent the frequency domain energy distribution of harmonic distortion events. The matrix elements are calibrated by the coupling strength of stress peak and harmonic energy.

[0029] Based on the quantitative analysis results of the joint risk assessment matrix, high-risk areas for mechanical stress anomalies and electrical harmonic distortion are extracted. Combined with the vibration avoidance path correction vector and harmonic suppression frequency adjustment in the collaborative control instructions, the curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit are dynamically adjusted.

[0030] The adjusted curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit are fed back to the joint risk assessment matrix, and closed-loop decision-making of power equipment is achieved by iteratively updating the matrix elements.

[0031] Optionally, the method extracts high-risk areas of mechanical stress anomaly and electrical harmonic distortion based on the quantitative analysis results of the joint risk assessment matrix, combines the vibration avoidance path correction vector and the harmonic suppression frequency adjustment amount in the collaborative control instruction, and dynamically adjusts the curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit, including:

[0032] The joint risk assessment matrix was used to screen out regions with significant coupling strength between mechanical stress anomalies and electrical harmonic distortion. The significant regions were identified through cross-validation of the time-domain evolution of the stress peak sequence and the frequency-domain diffusion characteristics of the harmonic energy mutation interval. The coupling strength of the significant regions was prioritized based on the quantitative analysis results.

[0033] Combined with the vibration avoidance path correction vector in the collaborative control instruction, the curvature change rate of the logistics transportation path is adjusted. At the same time, combined with the harmonic suppression frequency adjustment amount, the harmonic suppression parameters of the power supply circuit are dynamically adjusted. The curvature change rate is dynamically calibrated by the combined weight of the path mutation intensity and the harmonic suppression frequency adjustment amount.

[0034] The adjusted curvature change rate and harmonic suppression parameters are fed back to the joint risk assessment matrix, and the coupling intensity distribution in significant areas is iteratively updated to achieve dynamic collaborative optimization of logistics transportation paths and harmonic suppression parameters.

[0035] In a second aspect, the present application provides a big data intelligent decision analysis system, including:

[0036] The acquisition module acquires the transportation vibration data of the power equipment, synchronously collects the stress distribution data of the key mechanical nodes of the power equipment, and extracts the high-frequency harmonic distortion characteristics aligned with the timestamp of the transportation vibration data in the power supply circuit;

[0037] The analysis module conducts cross-domain correlation analysis on the fluctuation amplitude of stress distribution data and the dynamic changes of high-frequency harmonic distortion characteristics. It uses machine learning models to identify the symbiotic correlation pattern between mechanical stress anomalies and electrical harmonic distortion under conditions of sudden changes in logistics transportation routes.

[0038] The adjustment module, based on the logistics transportation path planning parameters and the equipment operating environment constraints, uses a multi-objective collaborative optimization algorithm to make joint decisions on the symbiotic association model and generate collaborative control instructions to simultaneously adjust the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit;

[0039] The control module constructs a joint risk assessment matrix for mechanical stress anomalies and electrical harmonic distortion. Based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions, it dynamically adjusts the collaborative relationship between logistics transportation paths and harmonic suppression parameters to achieve closed-loop decision-making for power equipment.

[0040] In a third aspect, an embodiment of the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a big data intelligent decision-making analysis method as described in the first aspect above.

[0041] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a big data intelligent decision-making analysis method as described in the first aspect.

[0042] In an embodiment of the present application, transportation vibration data of the power equipment is obtained, stress distribution data of the key mechanical nodes of the power equipment are synchronously collected, and high-frequency harmonic distortion features aligned with the timestamps of the transportation vibration data are extracted in the power supply circuit; the fluctuation amplitude of the stress distribution data and the dynamic changes of the high-frequency harmonic distortion features are cross-domain correlated and analyzed, and the symbiotic correlation pattern of mechanical stress anomaly and electrical harmonic distortion under the condition of sudden changes in the logistics transportation path is identified through a machine learning model; based on the logistics transportation path planning parameters and the equipment operating environment constraints, a joint decision is made on the symbiotic correlation pattern through a multi-objective collaborative optimization algorithm, and a collaborative control instruction is generated to simultaneously adjust the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit; a joint risk assessment matrix of mechanical stress anomaly and electrical harmonic distortion is constructed, and the collaborative relationship between the logistics transportation path and the harmonic suppression parameters is dynamically adjusted based on the quantitative analysis results of the joint risk assessment matrix and the collaborative control instructions to achieve closed-loop decision-making of the power equipment.

[0043] The technical solution of this application has the following beneficial effects:

[0044] This application realizes the spatiotemporal synchronous monitoring of mechanical vibration and electrical characteristics by synchronously collecting the transportation vibration data of power equipment, mechanical node stress distribution data and high-frequency harmonic distortion characteristics aligned with timestamps, laying a data foundation for cross-domain analysis. By correlating the dynamic changes of stress fluctuations and harmonic distortion characteristics, the machine learning model is used to identify the symbiotic correlation pattern of mechanical stress anomalies and harmonic distortion when the transportation path suddenly changes, revealing the mechanical-electrical coupling mechanism. Based on the path planning parameters and equipment constraints, the coordinated control instructions of the vibration avoidance parameters and harmonic suppression parameters of the transportation path are generated through multi-objective optimization to solve the conflict problem between mechanical and electrical control and realize global optimization of cross-domain parameters. Construct a joint risk assessment matrix of mechanical stress and harmonic distortion, and dynamically adjust the curvature change rate and harmonic suppression frequency of the transportation path in combination with the quantitative analysis results to form a closed-loop control logic and enhance the adaptability of power equipment in complex transportation.

[0045] Furthermore, stress peak sequences and harmonic energy mutation intervals are extracted through time window partitioning, enabling refined extraction of mechanical-electrical features. The time-domain stress evolution pattern and harmonic frequency-domain diffusion characteristics are spatiotemporally coupled, and a cross-domain correlation tensor weighted by path mutation strength (calibrated by the curvature change rate and acceleration shock threshold) is constructed to quantify the mechanical-electrical coupling strength. After embedding mechanical node topological constraints, dynamic graph convolution is used to capture the cross-interference between stress propagation and harmonic conduction paths, establishing a joint feature space and clarifying the failure propagation paths of mechanical vibration and harmonic distortion. Iterative optimization of latent variable boundary conditions generates causal directed co-occurrence clusters. Multi-scale analysis is combined to separate transient and steady-state correlation components, and a topological map containing coupling strength and failure paths is output. This method achieves closed-loop control of power equipment transportation safety and provides technical support for the coordinated optimization of mechanical-electrical systems.

[0046] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0048] Figure 1 A flowchart of a big data intelligent decision-making analysis method provided by the present application is shown;

[0049] Figure 2 A schematic diagram of the structure of a big data intelligent decision-making analysis system provided by the present application is shown;

[0050] Figure 3 A schematic structural diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0052] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0053] This application establishes a spatiotemporal correlation data foundation of mechanical vibration and electrical characteristics by synchronously collecting vibration data of the power equipment transportation path, stress distribution data of key mechanical nodes, and high-frequency harmonic distortion characteristics with time stamp alignment in the power supply circuit; uses a machine learning model to perform cross-domain correlation analysis on the dynamic changes of mechanical stress fluctuation amplitude and harmonic distortion characteristics, and explores the symbiotic correlation pattern of mechanical stress anomalies and harmonic distortion under the condition of sudden changes in the transportation path; combines logistics path planning parameters and equipment operating environment constraints, and makes joint decisions on the symbiotic correlation pattern through a multi-objective collaborative optimization algorithm to generate collaborative control instructions for synchronously adjusting the vibration avoidance parameters and harmonic suppression parameters of the transportation path; constructs a mechanical-electrical joint risk assessment matrix, and dynamically optimizes the collaborative relationship between the transportation path curvature and the harmonic suppression frequency based on the quantitative analysis results, forming a complete decision-making chain from state perception to closed-loop control, and realizing intelligent management and control of power equipment transportation safety.

[0054] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0055] Figure 1 A flowchart of a big data intelligent decision analysis method is provided for the embodiment of the present application, such as Figure 1 As shown, the method includes:

[0056] 101. Obtain transportation vibration data of power equipment, synchronously collect stress distribution data of key mechanical nodes of power equipment, and extract high-frequency harmonic distortion features aligned with the timestamp of transportation vibration data in the power supply circuit;

[0057] Transport vibration data: refers to a collection of information such as the vibration intensity, frequency, and duration experienced by electrical equipment during transportation, used to assess the mechanical stability of the equipment during transportation.

[0058] Stress distribution data: reflects the magnitude and distribution of internal stress at key mechanical nodes of power equipment when subjected to external forces, and is an important indicator for judging the structural safety of equipment.

[0059] High-frequency harmonic distortion characteristics: describes the degree of distortion of the current or voltage waveform in the power supply circuit, especially in the high-frequency band, which is closely related to the electrical performance of the equipment.

[0060] Timestamp alignment: It is a data synchronization technology that ensures that data from different sensors are consistent in the time dimension for subsequent correlation analysis.

[0061] In the embodiment of the present application, high-precision vibration sensors, strain gauges and other monitoring equipment are first deployed on the surface and key internal nodes of the power equipment to collect transport vibration data such as vibration acceleration and frequency during transportation, as well as stress values ​​(i.e., stress distribution data) at key parts of the equipment in real time. These sensors transmit the data to the local data acquisition module for preliminary processing and storage. At the same time, a power quality monitor is installed in the power supply circuit, and its sampling frequency is set to be consistent with that of the vibration data acquisition equipment to monitor high-frequency harmonic distortion characteristics. The timestamps of the two data are aligned through a time synchronization algorithm, such as using GPS signals or the Network Time Protocol (NTP). During the data collection process, the sensors need to be calibrated regularly to ensure the accuracy and reliability of the data. Ultimately, a comprehensive data set containing transport vibration data, stress distribution data, and high-frequency harmonic distortion characteristics aligned with them in time is obtained, providing a basis for subsequent cross-domain correlation analysis.

[0062] In a real-world power equipment transportation project, a power supply company needed to transport a large transformer from a manufacturing plant to a substation. Before transportation, technicians installed vibration sensors and strain gauges on key locations, such as the transformer's casing and internal windings, and connected a power quality monitor to the transformer's power supply circuit. Once the transport vehicle was in operation, these monitoring devices began operating synchronously, collecting data in real time. A time synchronization algorithm ensured a one-to-one correspondence between vibration data and power quality data. For example, during transportation, when the vehicle passed over a bumpy road, the vibration sensor recorded the peak vibration acceleration, while the power quality monitor simultaneously captured the high-frequency harmonic distortion characteristics in the power supply circuit. The two were precisely time-matched through time stamps, providing an accurate data foundation for subsequent analysis.

[0063] 102. Conduct cross-domain correlation analysis on the fluctuation amplitude of stress distribution data and the dynamic changes of high-frequency harmonic distortion characteristics, and use machine learning models to identify the symbiotic correlation pattern between mechanical stress anomalies and electrical harmonic distortion under sudden changes in logistics transportation routes;

[0064] Fluctuation amplitude of stress distribution data: refers to the range and rate of change of stress value with time, position and other factors during transportation. It reflects the dynamic response of the internal structure of the equipment under the influence of transportation vibration.

[0065] Dynamic changes in high-frequency harmonic distortion characteristics: describes the trend and pattern of the harmonic distortion level in the power supply circuit as it changes with transportation status, which may be indirectly affected by changes in mechanical stress of the equipment.

[0066] Cross-domain correlation analysis: It is an analysis method that integrates multi-source data and aims to explore the potential relationships between data in different fields.

[0067] Machine learning model: An intelligent tool that is trained through algorithms and can learn patterns and make predictions from large amounts of data. It is used here to identify complex symbiotic association patterns.

[0068] In this embodiment of the present application, the stress distribution data and high-frequency harmonic distortion feature data obtained in step 101 are first preprocessed, including data cleaning and normalization, to eliminate dimensional differences and noise. Then, a machine learning algorithm, such as a long short-term memory (LSTM) network or a convolutional neural network (CNN), is used to train the processed data. During the training process, the fluctuation amplitude of the stress distribution data and the dynamic changes in the high-frequency harmonic distortion features are used as input features, and sudden changes in the logistics transportation route (such as sharp turns, uphill and downhill slopes, etc.) are used as labels. The model learns the correlation patterns between the two under different transportation conditions. By continuously adjusting the model parameters and optimizing the loss function, the model's accuracy and generalization ability are improved. Ultimately, a machine learning model is obtained that can identify the symbiotic correlation patterns between mechanical stress anomalies and electrical harmonic distortion under sudden changes in the logistics transportation route, providing a basis for subsequent joint decision-making.

[0069] Continuing with the transformer transportation example, during transportation, the vehicle suddenly encountered a sharp turn, causing the transformer to experience significant lateral vibration. The strain gauges installed on the transformer recorded significant fluctuations in stress distribution data, and the power quality monitor detected changes in the high-frequency harmonic distortion characteristics of the power supply circuit. This data was transmitted in real time to the data analysis center, preprocessed, and then input into a pre-trained machine learning model. Based on previously learned patterns, the model quickly identified the symbiotic correlation between stress anomalies and harmonic distortion, determining that the current transportation conditions could adversely affect the mechanical and electrical performance of the transformer. For example, the model discovered that when the stress fluctuation amplitude exceeded a certain threshold, the dynamic changes in the high-frequency harmonic distortion characteristics also exhibited a specific pattern. This matched the patterns observed in the training data for sudden changes in the transportation path, providing critical information for subsequent control decisions.

[0070] 103. Based on the logistics transportation path planning parameters and the equipment operating environment constraints, a multi-objective collaborative optimization algorithm is used to make joint decisions on the symbiotic association model, generating collaborative control instructions that simultaneously adjust the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit;

[0071] Logistics transportation path planning parameters: covers the selection of transportation routes, the setting of transportation speed, the slope and curve conditions of the road sections, etc. These parameters directly affect the vibration environment of the equipment during transportation.

[0072] Equipment operating environment constraints: including the equipment's mechanical strength limitations, electrical performance requirements, transportation time limitations, etc., are the boundary conditions for formulating a reasonable transportation plan.

[0073] Multi-objective collaborative optimization algorithm: It is an algorithm that can seek the optimal balance between multiple conflicting objectives. It is used here to comprehensively consider the dual goals of transportation route optimization and power supply circuit harmonic suppression.

[0074] Symbiotic correlation pattern: refers to the correlation relationship pattern between the mechanical stress anomaly and the electrical harmonic distortion identified in step 102, which is an important reference for making joint decisions.

[0075] Collaborative control instruction: a comprehensive control command used to simultaneously adjust the transportation path and power supply circuit parameters to achieve the optimal state of power equipment during transportation.

[0076] In this embodiment, the adjustable range of logistics transport route planning parameters and specific indicators for the equipment's operating environment constraints are first determined based on the specific type and transportation requirements of the power equipment. Then, an appropriate multi-objective collaborative optimization algorithm, such as a particle swarm optimization (PSO) algorithm or a multi-objective genetic algorithm (MOGA), is selected, and the symbiotic association pattern identified in step 102 is used as one of the constraints to construct an optimization model. In this model, minimizing the impact of equipment vibration during transportation and harmonic distortion in the power supply circuit is used as the optimization objective. An iterative algorithm search is performed to find the optimal combination of transport route planning parameters and power supply circuit harmonic suppression parameters. During the optimization process, candidate solutions are continuously simulated and evaluated to verify whether they meet the equipment's operating environment constraints, such as equipment stress limits and permissible harmonic distortion ranges. Finally, a collaborative control instruction is generated, containing specific transport route adjustment recommendations (e.g., avoiding certain bumpy sections) and adjustments to the power supply circuit harmonic suppression parameters (e.g., adjusting filter parameters), achieving precise control over the power equipment's transportation process.

[0077] In the transformer transportation case, based on previously identified symbiotic association patterns and current transportation conditions, technicians utilized a multi-objective collaborative optimization algorithm to optimize the transport route and power supply circuit parameters. The algorithm comprehensively considered factors such as transport time, road conditions, and the transformer's mechanical strength and electrical performance. After multiple iterative calculations, an optimal solution was determined: A section of the transport route with frequent sharp turns and potholes was avoided, and a relatively flat alternative route with fewer curves was chosen. In the power supply circuit, filter parameters were adjusted to enhance their ability to suppress specific frequency harmonics. Collaborative control instructions simultaneously communicated these recommendations to the transport dispatch center and the power supply circuit control system. Transport vehicles followed the new route, and the power supply circuit operated according to the adjusted parameters, effectively reducing mechanical and electrical risks during transformer transportation.

[0078] 104. Construct a joint risk assessment matrix for mechanical stress anomalies and electrical harmonic distortion. Based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions, dynamically adjust the synergistic relationship between logistics transportation routes and harmonic suppression parameters to achieve closed-loop decision-making for power equipment.

[0079] Mechanical stress abnormality risk assessment: From the perspective of the mechanical structure safety of the equipment, a quantitative assessment of the risks of excessive stress, structural damage, etc. that may occur during transportation is conducted.

[0080] Electrical harmonic distortion risk assessment: focuses on analyzing the impact of harmonic distortion in the power supply circuit on the electrical performance and power quality of the equipment, and predicting the possible failure risks.

[0081] Joint risk assessment matrix: It is a quantitative analysis tool that comprehensively considers the risks of mechanical stress anomaly and electrical harmonic distortion. By setting different weights and evaluation criteria, it achieves a fusion assessment of the risks of both.

[0082] Dynamic adjustment of collaborative control instructions: refers to the real-time updating and optimization of the transportation path and power supply circuit parameter adjustment suggestions in the collaborative control instructions based on the results of the joint risk assessment to adapt to dynamic changes in the transportation process.

[0083] Closed-loop decision-making: Emphasizes the self-feedback and self-adjustment capabilities of the entire system, ensuring the safety and reliability of power equipment during transportation through continuous cycles of risk assessment and control instruction adjustment.

[0084] In the embodiment of the present application, first, based on historical data and professional knowledge, the risk assessment indicators and weight coefficients for each of mechanical stress anomalies and electrical harmonic distortion are determined to construct a joint risk assessment matrix. The data and results obtained in steps 101 to 103 are then input into the matrix for quantitative analysis. During the analysis, a comprehensive risk value is calculated by comprehensively considering factors such as the severity and duration of the stress anomaly, as well as the amplitude and frequency of the harmonic distortion. Based on this risk value, it is determined whether the current transportation and power supply circuit control strategies need to be adjusted. If the risk value exceeds a preset threshold, the information is passed to the multi-objective collaborative optimization algorithm in step 103 through a feedback mechanism, and collaborative control instructions are regenerated to dynamically adjust the transportation path and power supply circuit parameters. After the adjustment, data collection and risk assessment are performed again, forming a closed-loop decision-making process until the comprehensive risk value is reduced to an acceptable range.

[0085] During the transformer's transportation, technicians used a joint risk assessment matrix to monitor the transformer's transport status in real time as the transport environment, such as weather and road conditions, changed. When the transport vehicle entered a bumpy section of road, monitoring data revealed abnormal stress distribution and an increase in harmonic distortion in the power supply circuit. This data was input into the joint risk assessment matrix, and the resulting comprehensive risk value exceeded the preset safety threshold. The system automatically triggered a feedback mechanism, passing this risk information to the optimization algorithm, which recalculated and generated new coordinated control instructions: recommending that the transport vehicle reduce speed while navigating the bumpy section and further optimizing the power supply circuit's harmonic suppression parameters. Upon receiving these instructions, the transport vehicle and power supply circuit control systems immediately implemented the appropriate adjustments. Following these adjustments, data was collected again for risk assessment, revealing a significant reduction in the comprehensive risk value, restoring the transport process to a safe state. This continuous closed-loop decision-making process ensured the mechanical and electrical safety of the transformer throughout its transportation.

[0086] In summary, steps 101 to 104 enable comprehensive monitoring, precise analysis, and dynamic control of the mechanical and electrical status of power equipment during transportation. Multi-source data collection and timestamp alignment ensure data accuracy and synchronization. Leveraging machine learning models and multi-objective collaborative optimization algorithms, we deeply explore the inherent connections between data and develop a scientific and rational control strategy. Utilizing a joint risk assessment matrix and closed-loop decision-making mechanism, we achieve real-time risk monitoring and dynamic adjustment during transportation. This approach effectively reduces the risk of mechanical damage and electrical failure during transportation, ensuring safe transportation and stable operation of equipment, and improving the overall reliability and economic efficiency of the power system.

[0087] In order to achieve safe and efficient control of power equipment during logistics and transportation, this study aims to accurately identify the symbiotic pattern of mechanical stress anomalies and electrical harmonic distortion through cross-domain correlation analysis and collaborative optimization technology. The research and development idea is to synchronously collect the transportation vibration data of power equipment, the stress distribution data of mechanical nodes, and the high-frequency harmonic distortion characteristics of the power supply circuit, and use machine learning models to identify abnormal symbiotic patterns under conditions of sudden changes in logistics and transportation paths. Based on path planning and equipment operation constraints, collaborative control instructions are generated through a multi-objective collaborative optimization algorithm to dynamically adjust the parameters of transportation vibration avoidance and power supply harmonic suppression. At the same time, a joint risk assessment matrix is ​​constructed to achieve closed-loop decision-making and ensure the dual protection of the mechanical and electrical performance of power equipment during transportation. In some embodiments, the fluctuation amplitude of the stress distribution data and the dynamic changes of the high-frequency harmonic distortion characteristics are cross-domain correlated and analyzed as described in step 102, and the symbiotic correlation pattern of mechanical stress anomalies and electrical harmonic distortion under conditions of sudden changes in logistics and transportation paths is identified through a machine learning model, including:

[0088] 201. The fluctuation amplitude of stress distribution data is divided into time windows. The stress peak sequence within the vibration impact interval is extracted based on the timestamp of the sudden change event of the logistics transportation path. At the same time, the frequency domain energy distribution of the high-frequency harmonic distortion characteristics within the same time window is decomposed to extract the harmonic energy sudden change interval.

[0089] Stress distribution data: refers to the record of stress changes caused by vibration, impact and other factors during the transportation of equipment. Time window division is to divide the continuous stress data into several representative segments to facilitate subsequent analysis.

[0090] The timestamp of the logistics transportation route mutation event refers to the specific time point when the route change, sudden braking, and other events occur during the transportation process; the stress peak sequence refers to the set of points where the stress reaches the maximum value within the vibration impact range;

[0091] High-frequency harmonic distortion characteristics: refers to the high-frequency signal distortion caused by nonlinear factors in the electrical system;

[0092] Frequency domain energy distribution decomposition: It is to divide the energy of the signal according to the frequency distribution in the frequency domain;

[0093] Harmonic energy mutation interval: refers to the area where harmonic energy changes significantly within a specific time range.

[0094] In an embodiment of the present application, first, stress distribution data is collected in real time by a stress sensor installed on the equipment, and the data is divided into multiple time windows according to a preset time interval. Secondly, combined with the timestamp of the path mutation event provided by the logistics transportation path monitoring system, the interval where the vibration impact occurs is located, and the stress peak sequence is extracted from it. Then, the fast Fourier transform (FFT) algorithm is used to perform frequency domain analysis on the high-frequency harmonic distortion characteristics, calculate the energy distribution of each frequency component within the same time window, and identify the harmonic energy mutation interval. This step requires precise time synchronization technology and efficient signal processing algorithms to ensure the accuracy of the data and the reliability of the analysis, and finally obtain the stress peak sequence and harmonic energy mutation interval as the basis for subsequent analysis.

[0095] 202. The temporal evolution of the stress peak sequence is spatiotemporally coupled with the frequency-domain diffusion characteristics of the harmonic energy mutation interval to construct a cross-domain correlation tensor weighted by the path mutation intensity, where the path mutation intensity is jointly calibrated by the curvature change rate of the transport path and the acceleration shock threshold.

[0096] The time domain evolution law of the stress peak sequence refers to the change trend of the stress peak over time; the frequency domain diffusion characteristics of the harmonic energy mutation interval refer to the distribution change of the harmonic energy in different frequency components;

[0097] Spatiotemporal coupling: It combines the information of time domain and frequency domain for comprehensive analysis; cross-domain correlation tensor is a multidimensional data structure used to describe the correlation relationship between different fields;

[0098] Path mutation intensity: used to measure the severity of transport path mutation;

[0099] Transport path curvature change rate: reflects the change in the degree of path curvature; acceleration shock threshold is the critical value for judging whether the shock intensity exceeds the normal range.

[0100] In an embodiment of the present application, first, a time domain analysis is performed on the stress peak sequence obtained in step 201 to extract key characteristic parameters of its evolution law, such as the frequency of peak occurrence, growth or attenuation trend, etc. Secondly, a quantitative analysis is performed on the frequency domain diffusion characteristics of the harmonic energy mutation interval to determine the energy change amplitude and range of different frequency components. Then, combined with the transportation path monitoring data, the path curvature change rate and the acceleration impact threshold are calculated to jointly calibrate the path mutation intensity. Finally, with the path mutation intensity as the weight, the time domain characteristics of the stress peak sequence and the frequency domain characteristics of the harmonic energy mutation interval are coupled to construct a cross-domain correlation tensor. This step requires complex mathematical modeling and tensor operation technology to realize the fusion of multi-dimensional information, and finally obtain a cross-domain correlation tensor that can reflect the coupling relationship between mechanical stress and electrical harmonics.

[0101] 203. Embedding mechanical node topology constraints in cross-domain correlation tensors, capturing the cross-interference relationship between stress propagation paths and harmonic distortion conduction paths through dynamic graph convolution operations, and establishing a joint representation space for mechanical-electrical coupling features;

[0102] Mechanical node topology constraints: refers to restricting the connection relationship between nodes based on the mechanical structure characteristics of the equipment;

[0103] Dynamic graph convolution operation: a deep learning algorithm based on graph structure, used to process complex relationships between nodes;

[0104] Stress propagation path: refers to the transmission route of stress in the equipment structure;

[0105] Harmonic distortion conduction path: refers to the propagation path of harmonic signals in the electrical system;

[0106] Cross-interference relationship: refers to the mutual influence between the two;

[0107] Joint representation space: a unified feature space that integrates mechanical and electrical features.

[0108] In an embodiment of the present application, first, a node topology model is established according to the mechanical structure of the device, and is embedded into the cross-domain correlation tensor obtained in step 202. Secondly, the data in the tensor is processed using a dynamic graph convolution algorithm, and the cross-interference relationship between the stress propagation path and the harmonic distortion conduction path is captured by learning the connection weights and feature propagation laws between the nodes. Then, these relationships are integrated into a unified feature space to form a joint representation space of mechanical-electrical coupling features. This step requires advanced deep learning technology and optimization algorithms to realize complex graph structure analysis, and ultimately obtain a joint representation space that can fully reflect the mechanical-electrical coupling characteristics of the device.

[0109] Based on the migration characteristics of equipment states before and after transportation route mutations, the latent variable boundary conditions are iteratively optimized in the joint representation space, so that mechanical stress anomaly events and harmonic distortion events form causal symbiotic clusters in the feature space.

[0110] The migration characteristics of equipment status before and after the transportation route mutation: refers to the changes in equipment performance indicators before and after the route mutation;

[0111] Hidden variable boundary conditions: refers to the conditions used to limit the value range of hidden variables in the model;

[0112] Co-occurrence cluster: refers to the mutually correlated regions formed by abnormal mechanical stress events and harmonic distortion events in the feature space;

[0113] In an embodiment of the present application, first, the migration characteristic parameters of the equipment state before and after the transportation path mutation, such as changes in stress level and harmonic content, are extracted based on the equipment state monitoring data. Secondly, these parameters are introduced into the joint representation space as prior knowledge, and the latent variable boundary conditions are adjusted through an iterative optimization algorithm. Then, in the optimized feature space, the symbiotic clusters of mechanical stress abnormality events and harmonic distortion events are identified, and the causal directionality is determined by analyzing the correlation characteristics between them. This step requires efficient optimization algorithms and causal inference techniques to achieve effective division of the feature space and clear representation of causal relationships, and ultimately obtain symbiotic clusters with clear causal directionality.

[0114] 205. Multi-scale path dependency analysis is performed on symbiotic clusters. The transient correlation components induced by path mutations are separated from the steady-state correlation components of the device's inherent characteristics through an adaptive gating mechanism. The output is a symbiotic correlation pattern topology map that includes the mechanical-electrical coupling strength and failure propagation path.

[0115] Multi-scale path dependence analysis: refers to analyzing the characteristics of symbiotic clusters from different time and spatial scales;

[0116] Adaptive gating mechanism: a control mechanism that can dynamically adjust the output according to the input signal;

[0117] Transient correlation component: refers to the short-term correlation change caused by path mutation; steady-state correlation component refers to the long-term correlation characteristics inherent in the device itself;

[0118] Symbiotic association pattern topology diagram: a graphical tool used to display various association relationships in symbiotic clusters.

[0119] In an embodiment of the present application, first, a multi-scale path dependency analysis is performed on the symbiotic cluster obtained in step 204, and its features are extracted from both macroscopic and microscopic levels. Secondly, an adaptive gating mechanism is used to separate the associated components in the symbiotic cluster, and transient associated components and steady-state associated components are identified. Then, the mechanical-electrical coupling strength is calculated based on the separation results, and the failure propagation path is determined. Finally, this information is output in the form of a symbiotic association pattern topology diagram to intuitively display the complex coupling relationship between mechanical stress and electrical harmonics in the equipment. This step requires the comprehensive use of signal processing technology and graphical display technology to achieve the effective presentation of complex relationships, and ultimately obtain a symbiotic association pattern topology diagram that can guide equipment fault diagnosis and maintenance.

[0120] Here's a specific example:

[0121] During a long-distance transport mission for a large transformer, the route required traversing multiple complex road conditions, including mountainous sections with continuous sharp turns and bumpy urban construction roads. To ensure the safety of the transformer during transportation, technicians implemented the method described in steps 201 to 205 for real-time monitoring and control. In step 201, based on the transportation plan and road condition information, a 10-second time window was set to segment the stress distribution data at key parts of the transformer. When the transport vehicle entered a sharp turn in the mountainous area, the stress peak sequence within the vibration impact interval was extracted based on the timestamp of the sharp turn event. Simultaneously, the high-frequency harmonic distortion characteristics in the power supply circuit were decomposed in the frequency domain, revealing a sudden change in harmonic energy within a specific frequency band. In step 202, the time-domain evolution of the stress peak sequence was spatiotemporally coupled with the frequency-domain diffusion characteristics of the harmonic energy sudden change interval. Analysis revealed that the stress peak exhibited a periodic increase after entering the sharp turn, while the frequency-domain diffusion characteristics of the harmonic energy sudden change interval indicated a significant increase in high-frequency energy. By combining the curvature change rate of the transport route (high in mountainous areas) and the acceleration shock threshold (acceleration shock exceeds a preset threshold when the vehicle makes a sharp turn), a cross-domain correlation tensor weighted by the strength of the path mutation is constructed. In step 203, the topological constraints of the transformer's internal mechanical structure are embedded in the cross-domain correlation tensor. Using dynamic graph convolution, the cross-interference relationship between stress propagation paths and harmonic distortion conduction paths is captured. For example, when stress propagates at a transformer winding node, it causes increased harmonic distortion at adjacent electrical nodes. By establishing a joint representation space for mechanical-electrical coupling features, these cross-interference relationships are integrated into a multidimensional feature representation. In step 204, based on the transition characteristics of the transformer state before and after the transport route mutation, it is found that both the stress distribution and high-frequency harmonic distortion change significantly after entering a sharp turn. In this joint representation space, by iteratively optimizing the latent variable boundary conditions, causal co-occurrence clusters are ultimately formed. These co-occurrence clusters clearly demonstrate a direct causal relationship between mechanical stress anomalies and harmonic distortion in the case of path mutations such as sharp turns. In step 205, a multi-scale path dependency analysis of the symbiotic clusters revealed that transient correlation components were primarily concentrated in special sections such as sharp turns, while steady-state correlation components were related to the mechanical and electrical characteristics of the transformer itself. Through an adaptive gating mechanism, these two correlation components were successfully separated, and a symbiotic correlation pattern topology diagram, including the mechanical-electrical coupling strength and failure propagation paths, was output. This topology diagram intuitively demonstrates the coupling between the transformer's internal stress and harmonic distortion, as well as the possible failure propagation paths, under different transport sections. Based on this topology diagram, technicians promptly adjusted the transport speed and route, and optimized the harmonic suppression parameters of the power supply circuit, effectively reducing the risks during the transformer's transportation and ensuring its safe delivery to its destination.

[0122] In summary, steps 201 to 205 enable precise monitoring, in-depth analysis, and coordinated control of the mechanical stress and electrical harmonic distortion of power equipment during transportation. This approach not only captures the real-time changes in the mechanical and electrical states of equipment in complex transportation environments, but also deeply explores the inherent correlations between the two, providing a scientific basis for optimizing transportation routes and adjusting equipment parameters. Multi-scale path dependency analysis and an adaptive gating mechanism further enhance the understanding and prediction of equipment behavior, effectively preventing equipment failures caused by mechanical and electrical issues during transportation and ensuring the reliability and economic efficiency of the power system.

[0123] In order to accurately identify the coupling relationship between mechanical stress and electrical harmonics in logistics transportation, this study proposes a spatiotemporal coupling and multi-scale analysis method. By dividing the time window, the stress peak sequence and the harmonic energy mutation interval are extracted, and a cross-domain correlation tensor with the path mutation intensity as the weight is constructed, and the mechanical node topology constraint is embedded. The cross-interference between stress and harmonic conduction paths is captured by dynamic graph convolution, and a joint representation space is established. The boundary conditions of the latent variables are iteratively optimized to form causal directional symbiotic clusters, separate the transient and steady-state correlation components, and output the symbiotic correlation pattern topology map of the coupling intensity and failure propagation path to achieve accurate evaluation of the equipment status and fault warning. In some embodiments, the multi-objective collaborative optimization algorithm is used to make a joint decision on the symbiotic correlation pattern based on the logistics transportation path planning parameters and the equipment operating environment constraints in step 103, and generate collaborative control instructions for simultaneously adjusting the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit, including:

[0124] 301. Convert the path curvature change rate and acceleration shock threshold in logistics transportation path planning parameters into vibration suppression constraints. At the same time, map the electromagnetic compatibility limit and temperature rise threshold in the equipment operating environment constraints into harmonic suppression constraints, and construct a joint decision space for mechanical vibration suppression and electrical harmonic suppression.

[0125] Vibration suppression constraints: These are conditions that limit mechanical vibration based on the path curvature change rate and acceleration shock threshold.

[0126] Harmonic suppression constraints: refers to the conditions for limiting electrical harmonics based on electromagnetic compatibility limits and temperature rise thresholds;

[0127] Joint decision space: It is a multi-dimensional parameter space that comprehensively considers mechanical vibration and electrical harmonic suppression, and is used for subsequent optimization decisions.

[0128] In this embodiment, the path curvature change rate and acceleration shock threshold are first obtained from the logistics path planning system and converted into quantitative constraints for vibration suppression. Simultaneously, the electromagnetic compatibility limit and temperature rise threshold are obtained from the equipment operating environment monitoring system and mapped into quantitative constraints for harmonic suppression. These constraints are then integrated into a unified joint decision space, forming a multidimensional parameter space that provides a foundation for subsequent optimization.

[0129] 302. Based on the coupling intensity distribution of mechanical stress anomalies and harmonic distortion in the symbiotic correlation mode, the vibration suppression priority and harmonic suppression priority are divided in the joint decision space. The priority is dynamically adjusted by the ratio of the mechanical vibration propagation path length to the harmonic distortion conduction path length at the path mutation point.

[0130] Symbiotic correlation mode: refers to the coupling relationship between mechanical stress anomaly and harmonic distortion;

[0131] Coupling intensity distribution: refers to the distribution of the intensity of this coupling relationship in different regions;

[0132] Priority: refers to the relative importance of vibration suppression and harmonic suppression in the joint decision space.

[0133] In an embodiment of the present application, first, based on the joint decision space constructed in step 301, the coupling relationship between mechanical stress anomaly and harmonic distortion is analyzed in combination with the coupling strength distribution in the symbiotic association pattern. Then, the ratio of the mechanical vibration propagation path length to the harmonic distortion conduction path length at the path mutation point is calculated, and the priority of vibration suppression and harmonic suppression is dynamically adjusted according to the ratio. For example, when the mechanical vibration propagation path length is much greater than the harmonic distortion conduction path length, the priority of vibration suppression is increased; otherwise, the priority of harmonic suppression is increased. Finally, the adjusted priority division result is applied to the joint decision space to provide a basis for subsequent optimization.

[0134] 303. The vibration attenuation characteristic curve of the transport path vibration avoidance parameters and the frequency domain response characteristic curve of the harmonic suppression parameters are introduced into the joint decision space. The conflict area and cooperative area of ​​the mechanical-electrical control parameters are determined through dual-channel feature cross-validation, and a collaborative control instruction set containing the vibration avoidance path correction vector and the harmonic suppression frequency adjustment amount is output.

[0135] Vibration attenuation characteristic curve: refers to the curve showing the vibration suppression effect of vibration avoidance parameters as the path changes;

[0136] Frequency domain response characteristic curve: refers to the curve of the suppression effect of harmonic suppression parameters on harmonics of different frequencies;

[0137] Dual-channel feature cross-validation: refers to the feature validation of two channels, vibration and harmonics, to determine the conflicting and collaborative areas of control parameters;

[0138] Collaborative control instruction set: refers to an instruction set that includes the vibration avoidance path correction vector and the harmonic suppression frequency adjustment amount.

[0139] In an embodiment of the present application, the vibration attenuation characteristic curve of the vibration avoidance parameters of the transport path and the frequency domain response characteristic curve of the harmonic suppression parameters are first introduced into the joint decision space. Then, through dual-channel feature cross-validation, the characteristics of the two channels of vibration and harmonics are analyzed to determine the conflict area and collaborative area of ​​the mechanical-electrical control parameters. For example, when the vibration attenuation characteristic curve and the frequency domain response characteristic curve overlap in certain areas, it indicates that the area is a collaborative area; when the two contradict each other, it indicates that the area is a conflict area. Finally, based on the analysis results of the collaborative area and the conflict area, a collaborative control instruction set containing the vibration avoidance path correction vector and the harmonic suppression frequency adjustment amount is generated to optimize the parameters of the transport path and the power supply circuit.

[0140] Here's a specific example:

[0141] During a long-distance transport of power equipment, the transport route planning system provided the path curvature change rate and acceleration shock threshold, while the equipment operating environment monitoring system provided electromagnetic compatibility limits and temperature rise thresholds. First, according to step 301, these parameters were converted into vibration suppression constraints and harmonic suppression constraints, and a joint decision space was constructed. Next, in step 302, the coupling intensity distribution of mechanical stress anomalies and harmonic distortion was analyzed using the symbiotic correlation model, and the priority of vibration suppression and harmonic suppression was dynamically adjusted. For example, near a sudden change point in the route, the mechanical vibration propagation path is longer, so the priority of vibration suppression is increased. Finally, in step 303, the vibration attenuation characteristic curve of the vibration avoidance parameters and the frequency domain response characteristic curve of the harmonic suppression parameters were introduced. Through dual-channel feature cross-validation, conflicting and cooperative areas were identified, and a coordinated control instruction set was generated. Based on this instruction set, the vibration avoidance parameters of the transport route were adjusted, and the harmonic suppression parameters of the power supply circuit were optimized, ultimately ensuring that both mechanical vibration and electrical harmonics of the power equipment remained within controllable ranges during transportation.

[0142] In summary, steps 301 to 303 achieve coordinated optimization control of mechanical vibration and electrical harmonics in power equipment during logistics transportation. This method not only effectively suppresses the impact of mechanical vibration on equipment during transportation, but also optimizes the suppression of electrical harmonics, reducing the risk of equipment failure due to mechanical-electrical coupling. By dynamically adjusting priorities and generating coordinated control instruction sets, real-time optimization of transportation routes and power supply circuit parameters is achieved, improving the safety and reliability of power equipment transportation.

[0143] To achieve coordinated suppression of mechanical vibration and electrical harmonics in power equipment during logistics transportation, this study proposes an optimization method based on a joint decision space. This joint decision space is constructed by converting the path curvature change rate and acceleration shock threshold into vibration suppression constraints, while simultaneously mapping the electromagnetic compatibility limit and temperature rise threshold into harmonic suppression constraints. Based on the coupling strength distribution of mechanical stress anomalies and harmonic distortion, the priority of vibration suppression and harmonic suppression is dynamically adjusted. The vibration attenuation characteristic curve of the vibration avoidance parameter and the frequency domain response characteristic curve of the harmonic suppression parameter are introduced. Through dual-channel feature cross-validation, the conflict and coordination regions of mechanical and electrical control parameters are determined, and a coordinated control instruction set containing a vibration avoidance path correction vector and a harmonic suppression frequency adjustment value is output. This optimizes the transportation path and power supply circuit parameters, improving the safety and reliability of power equipment transportation. In some embodiments, step 202 couples the time-domain evolution of the stress peak sequence with the frequency-domain diffusion characteristics of the harmonic energy mutation interval in a temporal and spatial manner to construct a cross-domain correlation tensor weighted by the path mutation strength. The path mutation strength is jointly calibrated by the transportation path curvature change rate and the acceleration shock threshold, including:

[0144] 401. Perform segmented fitting on the time-domain evolution of the stress peak sequence to extract the rising slope, falling slope, and duration characteristics of the stress peak within the vibration impact interval. Simultaneously, divide the frequency-domain diffusion characteristics of the harmonic energy mutation interval into frequency bands to extract the peak frequency and energy attenuation rate characteristics of each frequency band's energy distribution.

[0145] Segmented fitting: refers to dividing the variation pattern of the stress peak sequence in the time domain into several segments for fitting;

[0146] Rising slope, falling slope and duration characteristics: refer to the key characteristic parameters of the stress peak in the vibration impact range; frequency band division refers to dividing the frequency domain diffusion characteristics of the harmonic energy mutation range according to the frequency range;

[0147] In the embodiment of the present application, the signal analysis technology is first used to segment the collected stress peak sequence, and the three key features of the rising slope, falling slope and duration in the vibration impact interval are extracted through mathematical model fitting. At the same time, the frequency domain analysis method is used to divide the frequency domain diffusion characteristics of the harmonic energy mutation interval into frequency bands, determine the energy distribution in each frequency band, and calculate its peak frequency and energy attenuation rate. For example, during the transportation of wind turbines, this method is used to analyze the stress and high-frequency harmonic data during transportation, accurately identify potential mechanical and electrical risk points, and provide reliable data support for subsequent transportation route optimization and equipment protection measures.

[0148] 402. The rising slope, falling slope, and duration characteristics of the stress peak sequence are spatially and temporally aligned with the peak frequency and energy decay rate characteristics of the harmonic energy mutation interval. Based on the time evolution curve of the stress peak and the frequency domain diffusion curve of the harmonic energy, a cross-domain correlation tensor with the path mutation intensity as the weight is constructed, where the path mutation intensity is dynamically calibrated by the product of the transport path curvature change rate and the acceleration shock threshold.

[0149] Time and space alignment: refers to aligning the time domain characteristics of the stress peak sequence with the frequency domain characteristics of the harmonic energy mutation interval in time and space;

[0150] Cross-domain correlation tensor: refers to a multidimensional data structure used to describe the relationship between different fields;

[0151] In an embodiment of the present application, the time domain characteristics of the stress peak sequence obtained in step 401 are first aligned in time and space with the frequency domain characteristics of the harmonic energy mutation interval. Then, based on the time evolution curve of the stress peak and the frequency domain diffusion curve of the harmonic energy, a cross-domain correlation tensor is constructed. Finally, the product of the curvature change rate of the transport path and the acceleration shock threshold is used as a dynamic calibration of the path mutation intensity, and is embedded as a weight into the cross-domain correlation tensor. This step requires complex mathematical modeling and tensor operation technology to provide a basis for subsequent optimization decisions. For example, in the long-distance transportation of large transformers, through the construction of time and space alignment and cross-domain correlation tensors, the coupling relationship between mechanical vibration and electrical harmonics at the mutation point of the transport path is accurately captured, providing a scientific basis for adjusting the transport path and optimizing the power supply circuit parameters.

[0152] Here's a specific example:

[0153] During a long-distance transport mission for a high-voltage transformer, the transport route planning system provided detailed route parameters, including the path curvature change rate (maximum curvature change rate of 0.03 rad / m) and the acceleration shock threshold (set to 2.0g). Furthermore, the equipment operating environment monitoring system provided electromagnetic compatibility limits (total harmonic voltage distortion rate not exceeding 3%) and temperature rise thresholds (equipment operating temperature not exceeding 55°C). During transportation, the equipment was equipped with high-precision vibration sensors and electrical parameter monitoring devices to collect real-time stress and high-frequency harmonic data. During the transport, the vehicle passed through a sharp curve (where the path curvature change rate suddenly changed to 0.03 rad / m) and experienced a brief acceleration shock (reaching 1.8g). At this point, the vibration sensor recorded a significant change in the stress peak sequence. According to step 401, a segmented fitting of the stress peak sequence was performed, extracting the following features: the stress peak had an increasing slope of 1.5 MPa / s, a decreasing slope of 0.9 MPa / s, and a duration of 0.2 seconds. At the same time, the frequency-domain diffusion characteristics of the harmonic energy mutation interval were divided into frequency bands, revealing that the primary energy is concentrated in the 150 Hz to 250 Hz band, with a peak frequency of 220 Hz and an energy decay rate of 12 dB / s. Next, in step 402, the time-domain characteristics of the stress peak (rising slope, falling slope, and duration) are spatially and temporally aligned with the frequency-domain characteristics of the harmonic energy (peak frequency and energy decay rate). A cross-domain correlation tensor is constructed based on the time evolution curve of the stress peak and the frequency-domain diffusion curve of the harmonic energy. The path mutation intensity is dynamically calibrated by multiplying the curvature change rate of the transport path (0.03 rad / m) by the acceleration shock threshold (2.0 g), resulting in a path mutation intensity of 0.06. This intensity is embedded as a weight in the cross-domain correlation tensor. Analysis of the cross-domain correlation tensor reveals that the impact of mechanical vibration on electrical harmonics is particularly significant in sharp bends. Specifically, there is a clear spatial and temporal correlation between the high-slope changes in mechanical vibration and the high-frequency energy mutations in the electrical harmonics. Based on the analysis, the transportation team adjusted the vibration mitigation parameters along the transport route. For example, they added high-damping vibration-damping pads to the bottom of the transformer, reducing vibration transmissibility by 40%. They also optimized the harmonic suppression parameters of the power supply circuit. By adjusting the harmonic filter parameters, they reduced the total harmonic voltage distortion within the 220 Hz frequency band to 2.5%, below the electromagnetic compatibility limit. As a result of these optimization measures, the transformer experienced no anomalies during subsequent transportation due to mechanical vibration or excessive electrical harmonics, ensuring the safety and reliability of the equipment during transportation.

[0154] In summary, steps 401 to 402 enable coupled analysis and optimization of mechanical stress and electrical harmonics in power equipment during transportation. This method not only effectively identifies the coupled relationship between mechanical stress and electrical harmonics during transportation but also, by constructing a cross-domain correlation tensor, provides a scientific basis for optimizing parameters of transportation routes and power supply circuits. By dynamically adjusting transportation routes and power supply circuit parameters, the safety and reliability of power equipment transportation are improved, reducing the risk of equipment failures caused by mechanical-electrical coupling issues.

[0155] In order to accurately identify the coupling relationship between mechanical stress and electrical harmonics of power equipment in logistics transportation, this study proposes a method based on spatiotemporal alignment and cross-domain correlation analysis. By performing segmented fitting on the stress peak sequence, the rising slope, falling slope, and duration characteristics within the vibration impact interval are extracted. At the same time, the harmonic energy mutation interval is divided into frequency bands to extract the peak frequency and energy attenuation rate characteristics. Furthermore, these features are spatiotemporally aligned to construct a cross-domain correlation tensor with the path mutation intensity as the weight. The path mutation intensity is dynamically calibrated by the product of the curvature change rate of the transportation path and the acceleration shock threshold. This method aims to realize the coupled analysis of mechanical stress and electrical harmonics, provide a scientific basis for transportation path optimization and equipment protection, and improve the safety and reliability of power equipment transportation. In some embodiments, step 402 constructs a cross-domain correlation tensor with path mutation intensity as a weight based on the time evolution curve of the stress peak and the frequency domain diffusion curve of the harmonic energy, including: 501. Based on the time evolution curve of the stress peak, extracting the rising slope, falling slope, and duration characteristics of the stress peak in the vibration impact interval, and based on the frequency domain diffusion curve of the harmonic energy, extracting the peak frequency and energy attenuation rate characteristics of the harmonic energy in each frequency band;

[0156] Stress peak time evolution curve: refers to the change pattern of stress peak over time. The rising slope and falling slope represent the rate of increase and decrease of stress peak respectively. The duration refers to the length of time that the stress peak is maintained at a high level.

[0157] Harmonic energy frequency domain diffusion curve: refers to the distribution of harmonic energy at different frequencies. The peak frequency is the frequency point with the highest energy, and the energy decay rate indicates how quickly the energy decreases over time.

[0158] In the embodiment of the present application, the collected stress peak data is first analyzed by signal processing technology, its time evolution curve is extracted, and the rising slope, falling slope and duration are calculated. At the same time, the harmonic energy data is analyzed in the frequency domain, divided into different frequency bands, and the peak frequency and energy attenuation rate of each frequency band are extracted. For example, during the transportation of electric power equipment, the stress peak collected by the sensor showed the characteristics of rapid rise (rising slope 1.8 MPa / s) and slow decline (falling slope 0.6 MPa / s) in the vibration impact range, with a duration of 0.4 seconds. The harmonic energy is clearly distributed in the frequency band of 100 Hz to 300 Hz, with a peak frequency of 250 Hz and an energy attenuation rate of 10 dB / s.

[0159] 502. The time evolution characteristics of the stress peak and the frequency domain diffusion characteristics of the harmonic energy are aligned in time and space, and the characteristics are weighted based on the path mutation intensity, where the path mutation intensity is dynamically calibrated by the product of the curvature change rate of the transport path and the acceleration shock threshold;

[0160] Time-space alignment: refers to aligning the time domain characteristics of the stress peak and the frequency domain characteristics of the harmonic energy in time and space in order to analyze the correlation between them.

[0161] Path mutation intensity: It is an indicator that measures the severity of the change in the transportation path. It is used to weight the features to highlight the impact of path mutation on the equipment.

[0162] In this embodiment of the present application, the stress peak signature and harmonic energy signature extracted in step 501 are first spatially and temporally aligned to ensure their temporal synchronization. Next, the path mutation intensity (0.088) is calculated based on the curvature change rate of the transport path (e.g., 0.04 radians / meter) and the acceleration shock threshold (e.g., 2.2g), and this is used as a weight to weight the signatures. For example, at sharp bends in the transport path, the path mutation intensity is higher, and its impact on the stress peak and harmonic energy signature is more significant. This weighted processing can more accurately reflect the impact of path mutations on equipment.

[0163] The weighted spatiotemporal alignment features are integrated according to the spatiotemporal distribution of path mutation events to generate a cross-domain correlation tensor weighted by the path mutation intensity. The cross-domain correlation tensor cross-validates the features using the geometric distance of the stress propagation path and the electrical distance of the harmonic distortion conduction path.

[0164] Cross-domain correlation tensor: It is a multidimensional data structure used to represent the correlation between stress and harmonic energy characteristics.

[0165] The geometric distance of the stress propagation path refers to the propagation distance of stress in the equipment structure, and the electrical distance of the harmonic distortion conduction path refers to the conduction distance of harmonic energy in the electrical system.

[0166] Cross-validation: refers to verifying features through distance information of two different paths to improve the reliability of the results.

[0167] In this embodiment of the present application, the weighted features from step 502 are first integrated according to the spatiotemporal distribution of path mutation events to generate a cross-domain correlation tensor. The features are then cross-validated by calculating the geometric distance of the stress propagation path and the electrical distance of the harmonic distortion conduction path. For example, during the transportation of power equipment, the geometric distance of the stress propagation path is 1.2 meters, and the electrical distance of the harmonic distortion conduction path is 0.8 meters. Through cross-validation, the correlation between the stress and harmonic energy features is confirmed, providing a reliable basis for subsequent optimization decisions.

[0168] Here's a specific example:

[0169] During a long-distance transport mission for a high-voltage transformer, the transport route planning system provided the path curvature change rate (maximum 0.04 rad / m) and acceleration shock threshold (2.2g). The equipment operating environment monitoring system provided electromagnetic compatibility limits (total harmonic voltage distortion not exceeding 3%) and temperature rise threshold (not exceeding 55°C). During transportation, the equipment was equipped with high-precision vibration sensors and electrical parameter monitoring devices to collect stress and high-frequency harmonic data in real time. During transportation, the vehicle passed through a sharp curve (where the path curvature change rate suddenly changed to 0.04 rad / m) and experienced a brief acceleration shock (impact acceleration reaching 2.0g). At this point, the vibration sensor recorded a significant change in the stress peak sequence. According to step 501, the stress peak's rising slope was extracted to be 1.8 MPa / s, its falling slope to be 0.6 MPa / s, and its duration to be 0.4 seconds. The harmonic energy was clearly distributed in the 100 Hz to 300 Hz frequency band, with a peak frequency of 250 Hz and an energy decay rate of 10 dB / s. Secondly, in step 502, the stress peak signature was spatially and temporally aligned with the harmonic energy signature, and the signatures were weighted based on the path mutation intensity (0.088). Finally, in step 503, the weighted signatures were integrated according to the spatial and temporal distribution of the path mutation events to generate a cross-domain correlation tensor. The signatures were cross-validated using the geometric distance of the stress propagation path (1.2 meters) and the electrical distance of the harmonic distortion conduction path (0.8 meters), confirming the coupling relationship between stress and harmonic energy. Based on the analysis of the cross-domain correlation tensor, the transportation team adjusted the vibration avoidance parameters of the transportation path and optimized the harmonic suppression parameters of the power supply circuit to ensure that the mechanical stress and electrical harmonics of the equipment were within controllable ranges during transportation.

[0170] In summary, steps 501 to 503 enable coupled analysis and optimization of mechanical stress and electrical harmonics in power equipment during logistics transportation. This method not only effectively identifies the coupled relationship between mechanical stress and electrical harmonics during transportation but also, by constructing a cross-domain correlation tensor, provides a scientific basis for optimizing parameters of transportation routes and power supply circuits. By dynamically adjusting transportation routes and power supply circuit parameters, the safety and reliability of power equipment transportation are improved, reducing the risk of equipment failures caused by mechanical-electrical coupling issues.

[0171] To accurately identify the coupling relationship between mechanical stress and electrical harmonics in power equipment during logistics and transportation, this study proposes a method for spatiotemporal alignment and weighted feature integration. By extracting the time-domain features of stress peaks (rising slope, falling slope, and duration) and the frequency-domain features of harmonic energy (peak frequency and energy decay rate), spatiotemporal alignment is performed and features are weighted based on the path mutation intensity (dynamically calibrated by the product of the curvature change rate of the transportation path and the acceleration shock threshold). Finally, features are integrated according to the spatiotemporal distribution of path mutation events to generate a cross-domain correlation tensor. This is then cross-validated using the geometric distance of the stress propagation path and the electrical distance of the harmonic conduction path, providing a basis for transportation path optimization and equipment protection, thereby improving transportation safety and reliability. In some embodiments, step 104 constructs a joint risk assessment matrix for mechanical stress anomalies and electrical harmonic distortion. Based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions, the collaborative relationship between the logistics transportation path and harmonic suppression parameters is dynamically adjusted to achieve closed-loop decision-making for power equipment, including:

[0172] 601. Based on the stress peak sequence of mechanical stress anomaly events and the frequency domain energy distribution of harmonic distortion events, a joint risk assessment matrix for mechanical stress anomaly and electrical harmonic distortion is constructed;

[0173] The row vectors of the joint risk assessment matrix represent the intensity distribution of stress anomaly events, the column vectors represent the frequency domain energy distribution of harmonic distortion events, and the matrix elements are calibrated by the coupling strength of stress peak and harmonic energy.

[0174] Stress peak sequence: refers to the peak data sequence of stress changes over time during an abnormal mechanical stress event.

[0175] Frequency domain energy distribution: refers to the distribution of harmonic energy in different frequency bands in a harmonic distortion event.

[0176] Coupling strength: A measure of the strength of the interaction between mechanical stress and electrical harmonics.

[0177] In the embodiment of the present application, the stress peak sequence of the mechanical stress anomaly event is first obtained by a stress sensor, and the frequency domain energy distribution of the harmonic distortion event is obtained by an electrical monitoring device. Then, a joint risk assessment matrix is ​​constructed, in which the row vectors of the matrix correspond to the intensity distribution of the stress anomaly event, and the column vectors correspond to the energy distribution of the harmonic distortion event. The matrix elements are obtained by calculating the coupling strength between the stress peak and the harmonic energy. For example, if the stress peak is 1.2 MPa, the peak value of the harmonic energy in the 200 Hz frequency band is 10 dB, and the coupling strength is 0.8, the corresponding matrix element is 0.8.

[0178] 602. Based on the quantitative analysis results of the joint risk assessment matrix, high-risk areas for mechanical stress anomalies and electrical harmonic distortion are extracted. Combined with the vibration avoidance path correction vector and harmonic suppression frequency adjustment in the collaborative control instructions, the curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit are dynamically adjusted.

[0179] High-risk area: refers to the area with higher coupling intensity in the joint risk assessment matrix, which usually indicates the part with higher coupling risk between stress anomaly and harmonic distortion.

[0180] Vibration-Avoiding Path Correction Vector: A parameter vector used to adjust the transport path to reduce the effects of vibration.

[0181] Harmonic suppression frequency adjustment value: used to adjust the value of the harmonic suppression parameters in the power supply circuit.

[0182] In an embodiment of the present application, a quantitative analysis is first performed on the joint risk assessment matrix to identify high-risk areas (such as areas in the matrix where the coupling strength is greater than 0.7). Then, the vibration avoidance path correction vector (such as reducing the path curvature change rate by 0.02 radians / meter) and the harmonic suppression frequency adjustment amount (such as adjusting the harmonic suppression parameters of the 200 Hz frequency band) in the collaborative control instruction are combined to dynamically adjust the curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit. For example, at a sharp turn in the transportation path, based on the analysis results of the high-risk area, the path curvature change rate is adjusted from 0.04 radians / meter to 0.02 radians / meter, and the harmonic suppression parameters of the 200 Hz frequency band are adjusted from 10% to 15%.

[0183] 603. Feedback the adjusted curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit to the joint risk assessment matrix, and achieve closed-loop decision-making for power equipment by iteratively updating the matrix elements.

[0184] Closed-loop decision-making: refers to the process of feeding back adjusted parameters into the risk assessment model to achieve dynamic optimization through iterative updates.

[0185] In an embodiment of the present application, the adjusted path curvature change rate and the harmonic suppression parameter of the power supply circuit in step 602 are first fed back to the joint risk assessment matrix. Then, the coupling strength of the stress peak and the harmonic energy is recalculated based on the new parameters, and the matrix elements are updated. For example, if the adjusted path curvature change rate is 0.02 radians / meter and the harmonic suppression parameter is 15%, the recalculated coupling strength is 0.5, and the matrix element is updated to 0.5. Through iterative updates, a closed-loop decision-making process for the transportation of power equipment is achieved, ensuring that the equipment is always in a safe state during transportation.

[0186] Here's a specific example:

[0187] During a long-distance transport of a large transformer, the transport route planning system provided route curvature change rate (maximum 0.04 rad / m) and acceleration shock threshold (2.2g). The equipment operating environment monitoring system provided electromagnetic compatibility limits (total harmonic voltage distortion rate no more than 3%) and temperature rise threshold (no more than 55°C). During transportation, high-precision vibration sensors and electrical parameter monitoring devices were installed on the equipment to collect real-time stress and high-frequency harmonic data.

[0188] During transportation, the vehicle passed through a sharp curve (where the path curvature rate of change suddenly changed to 0.04 rad / m) and experienced a brief acceleration shock (reaching 2.0g). At this point, the vibration sensor recorded a significant change in the stress peak sequence. According to step 601, a joint risk assessment matrix was constructed, extracting a stress peak of 1.2 MPa, a harmonic energy peak of 10 dB in the 200 Hz band, and a coupling strength of 0.8. Next, in step 602, based on the analysis of high-risk areas, the path curvature rate of change was adjusted from 0.04 rad / m to 0.02 rad / m, and the harmonic suppression parameter in the 200 Hz band was adjusted from 10% to 15%. Finally, in step 603, the adjusted parameters were fed back into the joint risk assessment matrix, the coupling strength was recalculated to 0.5, and the matrix elements were updated. This closed-loop decision-making process ensured that the transformer experienced no abnormalities during subsequent transportation due to excessive mechanical vibration or electrical harmonics.

[0189] In summary, steps 601 to 603 achieve a joint risk assessment and closed-loop decision-making process for mechanical stress and electrical harmonics in power equipment during logistics transportation. This method not only effectively identifies high-risk areas for mechanical stress and electrical harmonics during transportation but also ensures the safety and reliability of equipment during transportation by dynamically adjusting transportation routes and power supply circuit parameters. This closed-loop decision-making mechanism further optimizes transportation routes and power supply circuit parameters, reducing the risk of equipment failure due to mechanical-electrical coupling issues and improving transportation efficiency and equipment operational stability.

[0190] To precisely manage the coupling risk between mechanical stress and electrical harmonics in power equipment during logistics and transportation, this study proposes a closed-loop decision-making method based on a joint risk assessment matrix. By analyzing the stress peak sequence of mechanical stress anomalies and the frequency domain energy distribution of harmonic distortion events, a joint risk assessment matrix is ​​constructed, where row vectors represent the stress anomaly intensity distribution, column vectors represent the harmonic distortion energy distribution, and matrix elements are calibrated by coupling strength. High-risk areas are extracted based on matrix quantitative analysis. The curvature change rate of the transportation path and the harmonic suppression parameters of the power supply circuit are dynamically optimized by combining the vibration avoidance path correction vector and the harmonic suppression frequency adjustment value. By feeding the adjusted parameters back into the matrix and iteratively updating them, closed-loop decision-making is achieved during the power equipment transportation process, aiming to reduce coupling risks and ensure equipment transportation safety and stability. In some embodiments, step 602, based on the quantitative analysis results of the joint risk assessment matrix, extracts high-risk areas for mechanical stress anomalies and electrical harmonic distortion, and dynamically adjusts the curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit by combining the vibration avoidance path correction vector and the harmonic suppression frequency adjustment value in the collaborative control instructions. This includes:

[0191] 701. Screen out regions with significant coupling strength between mechanical stress anomalies and electrical harmonic distortion from the joint risk assessment matrix. The significant regions are identified through cross-validation of the time-domain evolution of stress peak sequences and the frequency-domain diffusion characteristics of harmonic energy mutation intervals. The coupling strength of the significant regions is prioritized based on the quantitative analysis results.

[0192] Joint risk assessment matrix: A matrix used to quantify the risk of coupling between mechanical stress anomalies and electrical harmonic distortion, whose elements represent the coupling strength.

[0193] Significant areas: areas with high coupling intensity that require priority treatment.

[0194] Prioritization: Rank significant regions based on coupling strength for dynamic optimization.

[0195] In an embodiment of the present application, regions with significant coupling strength are first screened out from the joint risk assessment matrix. By analyzing the time domain evolution law of the stress peak sequence and the frequency domain diffusion characteristics of the harmonic energy mutation interval, cross-validation is performed to confirm the significant regions. For example, the time domain analysis shows that the stress peak rising slope is 1.5 MPa / s, and the frequency domain analysis shows that the peak frequency of the harmonic energy in the 200 Hz band is 10 dB. After cross-validation, the region with significant coupling strength is confirmed. Combined with the quantitative analysis results, the coupling strength of the significant regions is prioritized to provide a basis for subsequent optimization.

[0196] 702. Combined with the vibration avoidance path correction vector in the collaborative control instruction, the curvature change rate of the logistics transportation path is adjusted. At the same time, combined with the harmonic suppression frequency adjustment amount, the harmonic suppression parameters of the power supply circuit are dynamically adjusted.

[0197] The curvature change rate is dynamically calibrated by the joint weight of the path mutation intensity and the harmonic suppression frequency adjustment amount.

[0198] Vibration-Avoiding Path Correction Vector: A parameter vector used to adjust the transport path to reduce the effects of vibration.

[0199] Harmonic suppression frequency adjustment value: used to adjust the value of the harmonic suppression parameters in the power supply circuit.

[0200] Joint weight: The weight of the comprehensive path mutation intensity and frequency adjustment amount is used to dynamically calibrate the curvature change rate.

[0201] In an embodiment of the present application, the curvature change rate of the logistics transportation path is first adjusted according to the vibration avoidance path correction vector in the collaborative control instruction. For example, the path curvature change rate is adjusted from 0.04 radians / meter to 0.02 radians / meter. At the same time, the harmonic suppression parameters of the power supply circuit are dynamically adjusted in combination with the harmonic suppression frequency adjustment amount. For example, the harmonic suppression parameters of the 200 Hz frequency band are adjusted from 10% to 15%. The curvature change rate is dynamically calibrated by the joint weight of the path mutation intensity (0.04 radians / meter) and the harmonic suppression frequency adjustment amount (15%) to ensure that the adjusted parameters can effectively reduce the coupling risk.

[0202] 703. The adjusted curvature change rate and harmonic suppression parameters are fed back to the joint risk assessment matrix, and the coupling intensity distribution of significant areas is iteratively updated to achieve dynamic collaborative optimization of logistics transportation paths and harmonic suppression parameters.

[0203] Feedback mechanism: The adjusted parameters are re-input into the risk assessment model to update the coupling strength distribution.

[0204] Dynamic collaborative optimization: Dynamic optimization of transportation routes and power supply loop parameters is achieved through iterative updates.

[0205] In this embodiment, the adjusted curvature change rate (0.02 rad / m) and harmonic suppression parameter (15%) in step 702 are first fed back into the joint risk assessment matrix. The coupling strength distribution in the significant regions is iteratively updated, and the coupling strength is recalculated. For example, a decrease in the updated coupling strength from 0.8 to 0.5 indicates that the adjustment was effective. Through closed-loop feedback and iterative updates, dynamic coordinated optimization of the logistics transport path and the harmonic suppression parameter is achieved, ensuring the safety and reliability of equipment during transportation.

[0206] Here's a specific example:

[0207] During a long-distance transport of a large transformer, the transport route planning system provided the path curvature change rate (maximum 0.04 rad / m) and acceleration shock threshold (2.2g). The equipment operating environment monitoring system provided electromagnetic compatibility limits (total harmonic voltage distortion not exceeding 3%) and temperature rise threshold (not exceeding 55°C). During transportation, the equipment was equipped with high-precision vibration sensors and electrical parameter monitoring devices to collect real-time stress and high-frequency harmonic data. During the transport, the vehicle passed a sharp curve (where the path curvature change rate suddenly changed to 0.04 rad / m) and experienced a brief acceleration shock (reaching 2.0g). At this point, the vibration sensor recorded a significant change in the stress peak sequence. According to step 701, regions with significant coupling strength were screened from the joint risk assessment matrix. These significant regions were confirmed through cross-validation in the time and frequency domains and prioritized. Next, in step 702, the path curvature change rate was adjusted from 0.04 rad / m to 0.02 rad / m, combined with the vibration-avoidance path correction vector, and the harmonic suppression parameter in the 200 Hz band was adjusted from 10% to 15%. Finally, in step 703, the adjusted parameters were fed back into the joint risk assessment matrix, and the coupling strength was recalculated. The coupling strength in the significant area was reduced from 0.8 to 0.5. This closed-loop feedback and iterative updates ensured that no abnormalities caused by excessive mechanical vibration or electrical harmonics occurred during the subsequent transportation of the transformer.

[0208] In summary, through steps 701 to 703, dynamic optimization of the coupling risk between mechanical stress and electrical harmonics in power equipment during logistics transportation is achieved. This method not only effectively identifies areas of significant coupling risk but also reduces coupling risk by dynamically adjusting transportation routes and power supply circuit parameters, thereby improving the safety and reliability of equipment transportation. Through a closed-loop feedback and iterative update mechanism, transportation routes and power supply circuit parameters are further optimized, reducing the risk of equipment failure due to mechanical-electrical coupling issues and improving transportation efficiency and equipment operational stability.

[0209] Figure 2 A schematic diagram of the structure of a big data intelligent decision analysis system is provided for the embodiment of the present application. Figure 2 As shown, the device includes:

[0210] Acquisition module 21 acquires transport vibration data of power equipment, synchronously collects stress distribution data of key mechanical nodes of power equipment, and extracts high-frequency harmonic distortion features aligned with the timestamp of the transport vibration data in the power supply circuit;

[0211] Analysis module 22 performs cross-domain correlation analysis on the fluctuation amplitude of stress distribution data and the dynamic changes of high-frequency harmonic distortion characteristics. It uses a machine learning model to identify the symbiotic correlation pattern between mechanical stress anomalies and electrical harmonic distortion under conditions of sudden changes in logistics transportation routes.

[0212] Adjustment module 23, based on the logistics transportation path planning parameters and the equipment operating environment constraints, uses a multi-objective collaborative optimization algorithm to make joint decisions on the symbiotic association model and generates collaborative control instructions for simultaneously adjusting the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit;

[0213] The control module 24 constructs a joint risk assessment matrix of mechanical stress anomalies and electrical harmonic distortion, and dynamically adjusts the collaborative relationship between logistics transportation paths and harmonic suppression parameters based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions to achieve closed-loop decision-making for power equipment.

[0214] Figure 2 The big data intelligent decision analysis system can execute Figure 1 The implementation principle and technical effects of the big data intelligent decision analysis method described in the illustrated embodiment are not further described. The specific manner in which each module and unit performs operations in the big data intelligent decision analysis system in the above embodiment has been described in detail in the embodiment of the method and will not be elaborated on here.

[0215] In one possible design, Figure 2 A big data intelligent decision analysis system of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0216] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0217] The processing component 32 is used for the above Figure 1 The embodiment provides a big data intelligent decision-making analysis method.

[0218] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0219] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0220] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0221] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0222] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0223] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0224] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 A big data intelligent decision analysis method of the illustrated embodiment.

[0225] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0226] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0227] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0228] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A big data intelligent decision analysis method, characterized in that: include: Acquire transportation vibration data of power equipment, synchronously collect stress distribution data of key mechanical nodes of power equipment, and extract high-frequency harmonic distortion features aligned with the timestamp of transportation vibration data in the power supply circuit; A cross-domain correlation analysis is conducted between the fluctuation amplitude of stress distribution data and the dynamic changes in high-frequency harmonic distortion characteristics. A machine learning model is used to identify the symbiotic correlation pattern between mechanical stress anomalies and electrical harmonic distortion under conditions of sudden changes in logistics transportation routes. Based on the logistics transportation path planning parameters and the equipment operating environment constraints, a multi-objective collaborative optimization algorithm is used to make joint decisions on the symbiotic association model, generating collaborative control instructions that simultaneously adjust the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit. Construct a joint risk assessment matrix for mechanical stress anomalies and electrical harmonic distortion. Based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions, dynamically adjust the synergistic relationship between logistics transportation routes and harmonic suppression parameters to achieve closed-loop decision-making for power equipment. A cross-domain correlation analysis is performed between the fluctuation amplitude of stress distribution data and the dynamic changes in high-frequency harmonic distortion characteristics. A machine learning model is used to identify the symbiotic correlation patterns between mechanical stress anomalies and electrical harmonic distortion under sudden changes in logistics transportation routes, including: The fluctuation amplitude of the stress distribution data is divided into time windows. The stress peak sequence within the vibration impact interval is extracted based on the timestamp of the sudden change event in the logistics transportation path. At the same time, the frequency domain energy distribution of the high-frequency harmonic distortion characteristics within the same time window is decomposed to extract the harmonic energy mutation interval. The temporal evolution of the stress peak sequence is spatiotemporally coupled with the frequency-domain diffusion characteristics of the harmonic energy mutation interval to construct a cross-domain correlation tensor weighted by the path mutation intensity, where the path mutation intensity is jointly calibrated by the curvature change rate of the transport path and the acceleration shock threshold. Embedding mechanical node topology constraints in the cross-domain correlation tensor, capturing the cross-interference relationship between stress propagation paths and harmonic distortion conduction paths through dynamic graph convolution operations, and establishing a joint representation space for mechanical-electrical coupling features; Based on the migration characteristics of equipment states before and after transportation route mutations, the boundary conditions of latent variables are iteratively optimized in the joint representation space, so that mechanical stress anomalies and harmonic distortion events form causally directed symbiotic clusters in the feature space. Perform multi-scale path dependency analysis on symbiotic clusters, separating transient correlation components induced by path mutations from steady-state correlation components of device intrinsic characteristics through an adaptive gating mechanism. Output is a topological map of symbiotic correlation patterns that includes mechanical-electrical coupling strength and failure propagation paths. The time-domain evolution law of the stress peak sequence is spatiotemporally coupled with the frequency-domain diffusion characteristics of the harmonic energy mutation interval, and a cross-domain correlation tensor with the path mutation intensity as the weight is constructed, including: The time-domain evolution law of the stress peak sequence is segmented and fitted to extract the rising slope, falling slope, and duration characteristics of the stress peak in the vibration impact interval. At the same time, the frequency-domain diffusion characteristics of the harmonic energy mutation interval are divided into frequency bands to extract the peak frequency and energy attenuation rate characteristics of the energy distribution in each frequency band. The rising slope, falling slope and duration characteristics of the stress peak sequence are temporally and spatially aligned with the peak frequency and energy attenuation rate characteristics of the harmonic energy mutation interval. Based on the time evolution curve of the stress peak and the frequency domain diffusion curve of the harmonic energy, a cross-domain correlation tensor with the path mutation intensity as the weight is constructed, where the path mutation intensity is dynamically calibrated by the product of the curvature change rate of the transport path and the acceleration shock threshold.

2. The method according to claim 1, characterized in that Based on the logistics transportation path planning parameters and the equipment operating environment constraints, a multi-objective collaborative optimization algorithm is used to make joint decisions on the symbiotic association model, generating collaborative control instructions that simultaneously adjust the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit, including: The path curvature change rate and acceleration shock threshold in logistics transportation path planning parameters are converted into vibration suppression constraints. At the same time, the electromagnetic compatibility limit and temperature rise threshold in the equipment operating environment constraints are mapped into harmonic suppression constraints, thus constructing a joint decision space for mechanical vibration suppression and electrical harmonic suppression. Based on the coupling intensity distribution of mechanical stress anomalies and harmonic distortion in the symbiotic correlation mode, the vibration suppression priority and harmonic suppression priority are divided in the joint decision space. The priority is dynamically adjusted by the ratio of the mechanical vibration propagation path length to the harmonic distortion conduction path length at the path mutation point. The vibration attenuation characteristic curve of the transport path vibration avoidance parameters and the frequency domain response characteristic curve of the harmonic suppression parameters are introduced into the joint decision space. The conflict area and cooperative area of ​​the mechanical-electrical control parameters are determined through dual-channel feature cross-validation, and a collaborative control instruction set including the vibration avoidance path correction vector and the harmonic suppression frequency adjustment amount is output.

3. The method according to claim 2, characterized in that Based on the time evolution curve of the stress peak and the frequency domain diffusion curve of the harmonic energy, a cross-domain correlation tensor with the path mutation intensity as the weight is constructed, including: Based on the time evolution curve of the stress peak, the rising slope, falling slope and duration characteristics of the stress peak in the vibration impact range are extracted. At the same time, based on the frequency domain diffusion curve of the harmonic energy, the peak frequency and energy attenuation rate characteristics of the harmonic energy in each frequency band are extracted. The temporal evolution characteristics of the stress peak and the frequency-domain diffusion characteristics of the harmonic energy are spatially and temporally aligned, and the characteristics are weighted based on the path mutation intensity, where the path mutation intensity is dynamically calibrated by the product of the curvature change rate of the transport path and the acceleration shock threshold; The weighted spatiotemporal alignment features are integrated according to the spatiotemporal distribution of path mutation events to generate a cross-domain correlation tensor with the path mutation intensity as the weight. The cross-domain correlation tensor cross-validates the features through the geometric distance of the stress propagation path and the electrical distance of the harmonic distortion conduction path.

4. The method according to claim 1, wherein Construct a joint risk assessment matrix for mechanical stress anomalies and electrical harmonic distortion. Based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions, dynamically adjust the synergistic relationship between logistics transportation routes and harmonic suppression parameters to achieve closed-loop decision-making for power equipment, including: Based on the stress peak sequence of mechanical stress anomaly events and the frequency domain energy distribution of harmonic distortion events, a joint risk assessment matrix for mechanical stress anomaly and electrical harmonic distortion is constructed. The row vectors of the joint risk assessment matrix represent the intensity distribution of stress anomaly events, and the column vectors represent the frequency domain energy distribution of harmonic distortion events. The matrix elements are calibrated by the coupling strength of stress peak and harmonic energy. Based on the quantitative analysis results of the joint risk assessment matrix, high-risk areas for mechanical stress anomalies and electrical harmonic distortion are extracted. Combined with the vibration avoidance path correction vector and harmonic suppression frequency adjustment in the collaborative control instructions, the curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit are dynamically adjusted. The adjusted curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit are fed back to the joint risk assessment matrix, and closed-loop decision-making of power equipment is achieved by iteratively updating the matrix elements.

5. The method according to claim 4, characterized in that Based on the quantitative analysis results of the joint risk assessment matrix, high-risk areas for mechanical stress anomalies and electrical harmonic distortion are extracted. Combined with the vibration avoidance path correction vector and harmonic suppression frequency adjustment in the collaborative control instructions, the curvature change rate of the logistics transportation path and the harmonic suppression parameters of the power supply circuit are dynamically adjusted, including: The joint risk assessment matrix was used to screen out regions with significant coupling strength between mechanical stress anomalies and electrical harmonic distortion. The significant regions were identified through cross-validation of the time-domain evolution of the stress peak sequence and the frequency-domain diffusion characteristics of the harmonic energy mutation interval. The coupling strength of the significant regions was prioritized based on the quantitative analysis results. Combined with the vibration avoidance path correction vector in the collaborative control instruction, the curvature change rate of the logistics transportation path is adjusted. At the same time, combined with the harmonic suppression frequency adjustment amount, the harmonic suppression parameters of the power supply circuit are dynamically adjusted. The curvature change rate is dynamically calibrated by the combined weight of the path mutation intensity and the harmonic suppression frequency adjustment amount. The adjusted curvature change rate and harmonic suppression parameters are fed back to the joint risk assessment matrix, and the coupling intensity distribution in significant areas is iteratively updated to achieve dynamic collaborative optimization of logistics transportation paths and harmonic suppression parameters.

6. A big data intelligent decision analysis system, used to execute the big data intelligent decision analysis method according to any one of claims 1 to 5, characterized in that: include: The acquisition module acquires the transportation vibration data of the power equipment, synchronously collects the stress distribution data of the key mechanical nodes of the power equipment, and extracts the high-frequency harmonic distortion characteristics aligned with the timestamp of the transportation vibration data in the power supply circuit; The analysis module conducts cross-domain correlation analysis on the fluctuation amplitude of stress distribution data and the dynamic changes of high-frequency harmonic distortion characteristics. It uses machine learning models to identify the symbiotic correlation pattern between mechanical stress anomalies and electrical harmonic distortion under conditions of sudden changes in logistics transportation routes. The adjustment module, based on the logistics transportation path planning parameters and the equipment operating environment constraints, uses a multi-objective collaborative optimization algorithm to make joint decisions on the symbiotic association model and generate collaborative control instructions to simultaneously adjust the vibration avoidance parameters of the transportation path and the harmonic suppression parameters of the power supply circuit; The control module constructs a joint risk assessment matrix for mechanical stress anomalies and electrical harmonic distortion. Based on the quantitative analysis results of the joint risk assessment matrix and collaborative control instructions, it dynamically adjusts the collaborative relationship between logistics transportation paths and harmonic suppression parameters to achieve closed-loop decision-making for power equipment.

7. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a big data intelligent decision analysis method as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, a big data intelligent decision analysis method as described in any one of claims 1 to 5 is implemented.

Images