A Cloud Computing-Based Method and System for Wiring Data Analysis of Multifunctional Instruments

Abstract

This invention relates to the field of data processing technology and discloses a method and system for analyzing wiring data of multifunctional instruments and meters based on cloud computing. The method involves collecting multidimensional time-series data of instrument wiring circuits through a sensor cluster deployed in the field, and uploading this data to a cloud computing platform after standardization and encryption. The cloud platform preprocesses the received multidimensional time-series data, performs deep feature extraction on each data point, and then fuses the extracted data to obtain a high-dimensional feature vector. This high-dimensional feature vector is then input into a MOGA-Transformer model to output the data analysis results. The cloud computing platform pushes the data analysis results to the user through a visual interface and simultaneously connects to the instrument control system to achieve automatic fault alarms and dynamic adjustment of wiring parameters. This invention achieves secure and efficient transmission and processing of massive amounts of wiring data.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method and system for analyzing wiring data of multifunctional instruments and meters based on cloud computing. Background Technology

[0002] Instrumentation is a core device in fields such as industrial control and energy monitoring. Its wiring status directly determines the accuracy of data acquisition and the safety of equipment operation. Wiring data analysis has become a key link in operation and maintenance management. In current technology, wiring data processing mostly relies on local computing power, which is difficult to handle multi-dimensional time-series data generated by multiple instruments concurrently, resulting in poor real-time performance and weak cross-scenario adaptability. Existing analysis algorithms are mostly single models, which can only realize basic functions of fault identification and cannot take into account trend prediction and parameter optimization. Moreover, they are not accurate enough in processing high-noise wiring data. Summary of the Invention

[0003] The purpose of this invention is to solve the above problems by designing a multifunctional instrument wiring data analysis method and system based on cloud computing.

[0004] The first aspect of this invention provides a method for analyzing wiring data of multifunctional instruments based on cloud computing, the method comprising the following steps:

[0005] By deploying a cluster of sensors on-site, multi-dimensional time-series data of instrument wiring circuits are collected, and the multi-dimensional time-series data is uploaded to the cloud computing platform after being standardized and encrypted.

[0006] The cloud platform preprocesses the received multidimensional time-series data and performs deep feature extraction on each data point. After fusion, a high-dimensional feature vector is obtained.

[0007] By inputting high-dimensional feature vectors into the MOGA-Transformer model, the model predicts the changing trends of wiring current and temperature parameters in the next 1-24 hours, identifies potential overload and overheat risks, and identifies fault types through attention weight allocation, outputting data analysis results.

[0008] The cloud computing platform pushes data analysis results to users through a visual interface, and at the same time connects to the instrument control system to realize automatic fault alarm and dynamic adjustment of wiring parameters.

[0009] Optionally, in a first implementation of the first aspect of the present invention, the step of collecting multi-dimensional time-series data of instrument wiring circuits through a sensor cluster deployed on-site, and uploading the multi-dimensional time-series data to a cloud computing platform after standardization and encryption, includes:

[0010] Multiple types of sensors are deployed at the nodes of the instrument wiring circuit to collect multi-dimensional time-series data, which includes at least real-time current value, wiring temperature, signal transmission strength, voltage fluctuation value, and cable vibration frequency.

[0011] The min-max method is used to standardize the multidimensional time series data. The standardized data is then encrypted using the AES-256 encryption algorithm to generate encrypted data packets, which are then uploaded to the cloud computing platform via an encrypted transmission protocol. A fragmentation verification mechanism is used during the transmission process.

[0012] Optionally, in a second implementation of the first aspect of the present invention, the standardized data is encrypted using the AES-256 encryption algorithm, including:

[0013] Obtain the preset AES-256 symmetric key and 128-bit initialization vector, and convert the standardized data into a binary data stream supported by AES encryption;

[0014] The CBC encryption mode using the AES-256 algorithm first splits the binary data stream into 128-bit groups. For the last group of data that is less than 128 bits, it is padded to 128 bits using the PKCS#7 padding rule to form the data group to be encrypted.

[0015] The first set of data to be encrypted is XORed with the initialization vector, and then the result is round-transformed with the AES-256 key to generate the first set of encrypted data.

[0016] Repeated calculations and round transformations are performed to obtain a complete encrypted data stream. The encrypted data stream, initialization vector, and data packet metadata are then concatenated to form the original encrypted data packet.

[0017] Calculate a 32-bit CRC code for the original encrypted data packet, and append the CRC code to the end of the original encrypted data packet to generate the final encrypted data packet.

[0018] Optionally, in a third implementation of the first aspect of the present invention, the cloud platform preprocesses the received multidimensional time-series data, performs deep feature extraction on each data point, and obtains a high-dimensional feature vector after fusion, including:

[0019] After decrypting the received encrypted data packets, the cloud computing platform performs data cleaning and uses time-series-based interpolation to process missing data.

[0020] The preprocessed multidimensional time-series data is input into a convolutional neural network. After multiple convolution operations and compression of redundant information by pooling layers, a spatial feature vector reflecting the spatial correlation characteristics of the wiring loop is output.

[0021] The preprocessed multidimensional time series data is input into a long short-term memory network. The long-term dependencies of the data are captured through a gating mechanism. After transformation by a fully connected layer, a time series feature vector reflecting the timing evolution characteristics of the wiring loop is output.

[0022] An attention-weighted fusion strategy is adopted to assign weights to spatial feature vectors and temporal feature vectors to generate high-dimensional feature vectors.

[0023] Optionally, in the fourth implementation of the first aspect of the present invention, the step of inputting high-dimensional feature vectors into the MOGA-Transformer model to predict the changing trends of wiring current and temperature parameters over the next 1-24 hours, identifying potential overload and overheat risks, and identifying fault types through attention weight allocation, and outputting data analysis results, includes:

[0024] The MOGA algorithm is used to optimize the parameters of the Transformer model, resulting in the MOGA-Transformer model.

[0025] The high-dimensional feature vector is input into the MOGA-Transformer model, and the encoder calculates the association weights of data at different time steps through a self-attention mechanism to generate contextual features.

[0026] Based on the encoder output and combined with position encoding information, the decoder predicts the trend of wiring current and temperature parameters in the next 1-24 hours and outputs trend curve data.

[0027] In the self-attention layer of the Transformer model, the attention weights of each feature dimension are extracted, and the top 30% of key features by weight are selected.

[0028] Input key features into a pre-set fault feature library and identify specific fault types through similarity matching;

[0029] Integrate trend prediction results with fault identification results to generate data analysis results.

[0030] Optionally, in the fifth implementation of the first aspect of the present invention, the step of optimizing the Transformer model parameters using the MOGA algorithm to obtain the MOGA-Transformer model includes:

[0031] Initialize the population for the MOGA algorithm, where the individuals in the population are the parameters of the Transformer model;

[0032] A dual-objective fitness function is defined, which includes minimizing trend prediction error and maximizing fault identification accuracy.

[0033] The MOGA-Transformer model is obtained by selecting high-quality individuals through roulette wheel selection, generating offspring individuals through crossover, introducing new solutions through mutation, and iterating through optimization. When the maximum number of iterations is reached, the optimal parameter combination is output.

[0034] Optionally, in a sixth implementation of the first aspect of the present invention, the cloud computing platform pushes the data analysis results to the user through a visual interface, and simultaneously connects to the instrument control system to realize automatic fault alarm and dynamic adjustment of wiring parameters, including:

[0035] The cloud computing platform converts the data analysis results into a visual data format, pushes the visual data to the user's terminal, and triggers terminal message reminders;

[0036] The cloud computing platform converts the data analysis results into control signals. After receiving the control signals, the instrument control system automatically performs parameter adjustment operations and feeds back the execution results to the cloud computing platform.

[0037] A second aspect of the present invention provides a cloud computing-based multifunctional instrument wiring data analysis system, the system comprising:

[0038] The data acquisition module is used to collect multi-dimensional time-series data of instrument wiring circuits through a sensor cluster deployed on site, and upload the multi-dimensional time-series data to the cloud computing platform after standardization and encryption.

[0039] The feature extraction module is used by the cloud platform to preprocess the received multidimensional time series data, extract deep features separately, and obtain a high-dimensional feature vector after fusion.

[0040] The identification module is used to input high-dimensional feature vectors into the MOGA-Transformer model to predict the changing trends of wiring current and temperature parameters in the next 1-24 hours, identify potential overload and overheat risks, and identify fault types through attention weight allocation, and output data analysis results.

[0041] The push module is used by the cloud computing platform to push data analysis results to users through a visual interface. It also connects to the instrument control system to realize automatic fault alarm and dynamic adjustment of wiring parameters.

[0042] A third aspect of the present invention provides a cloud computing-based multi-functional instrument wiring data analysis device, the cloud computing-based multi-functional instrument wiring data analysis device comprising a memory and at least one processor, the memory storing instructions; the at least one processor calling the instructions in the memory to cause the cloud computing-based multi-functional instrument wiring data analysis device to perform various steps of the cloud computing-based multi-functional instrument wiring data analysis method as described in any of the preceding claims.

[0043] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the steps of the cloud computing-based multifunctional instrument wiring data analysis method as described in any of the preceding claims.

[0044] In the technical solution provided by this invention, a sensor cluster deployed on-site collects multi-dimensional time-series data of instrument wiring circuits. This multi-dimensional time-series data is then standardized and encrypted before being uploaded to a cloud computing platform. The cloud platform preprocesses the received multi-dimensional time-series data, extracts deep features from each, and fuses them to obtain a high-dimensional feature vector. This high-dimensional feature vector is then input into a MOGA-Transformer model to predict the changing trends of wiring current and temperature parameters over the next 1-24 hours, identify potential overload and overheat risks, and identify fault types through attention weight allocation, outputting data analysis results. The cloud computing platform pushes the data analysis results to users through a visual interface and simultaneously connects to the instrument control system to achieve fault self-diagnosis. This invention features automatic alarm and dynamic adjustment of wiring parameters. Leveraging cloud computing to overcome local computing power limitations, it combines multi-dimensional data acquisition and standardized encryption processing to achieve secure and efficient transmission and processing of massive amounts of wiring data. Through deep feature extraction and the application of the MOGA-Transformer model, it accurately predicts current and temperature trends within 1-24 hours, identifying overload and overheating risks in advance. An attention weight allocation mechanism enables precise fault type localization, improving fault identification reliability. Simultaneously, data analysis results are linked to the instrument control system, enabling automatic alarm and dynamic parameter adjustment without manual intervention. It integrates data processing, trend prediction, fault identification, and safety protection, simplifying maintenance processes, reducing labor costs, and adapting to the instrument management needs of multiple fields. Attached Figure Description

[0045] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention.

[0046] Figure 1 A flowchart illustrating the cloud computing-based multi-functional instrument wiring data analysis method provided in this embodiment of the invention;

[0047] Figure 2 A schematic diagram of the structure of a cloud computing-based multifunctional instrument wiring data analysis system provided in an embodiment of the present invention;

[0048] Figure 3 This is a schematic diagram of the structure of a cloud computing-based multifunctional instrument wiring data analysis device provided in an embodiment of the present invention. Detailed Implementation

[0049] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” or “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0050] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 The flowchart of the cloud computing-based multi-functional instrument wiring data analysis method provided in this embodiment of the invention includes the following steps:

[0051] Step 101: Collect multi-dimensional time-series data of instrument wiring circuits through a sensor cluster deployed on site, and upload the multi-dimensional time-series data to the cloud computing platform after standardization and encryption.

[0052] In this embodiment, multiple types of sensors are deployed at the nodes of the instrument wiring circuit to collect multi-dimensional time-series data. The multi-dimensional time-series data includes at least real-time current value, wiring temperature, signal transmission strength, voltage fluctuation value, and cable vibration frequency. The multi-dimensional time-series data is standardized using the min-max method. The standardized data is then encrypted using the AES-256 encryption algorithm to generate encrypted data packets, which are then uploaded to the cloud computing platform via an encrypted transmission protocol. A fragmentation verification mechanism is used during the transmission process.

[0053] In this embodiment, a preset AES-256 symmetric key and a 128-bit initialization vector are obtained. The standardized data is converted into a binary data stream supported by AES encryption. Using the CBC encryption mode of the AES-256 algorithm, the binary data stream is first split into 128-bit groups. For the last group of data that is less than 128 bits, it is padded to 128 bits using the PKCS#7 padding rule to form the data group to be encrypted. The initialization vector is used to perform an XOR operation on the first group of data to be encrypted, and then the AES-256 key is used to perform a round transformation operation on the operation result to generate the first group of encrypted data. The operation and round transformation operation are repeated to finally obtain a complete encrypted data stream. The encrypted data stream, the initialization vector, and the data packet metadata are concatenated to form the original encrypted data packet. A 32-bit CRC code is calculated on the original encrypted data packet, and the CRC code is added to the end of the original encrypted data packet to generate the final encrypted data packet.

[0054] In this embodiment, the MQTTs encrypted transmission protocol is selected. The TLS server certificate and client certificate of the cloud computing platform are imported into the MQTTs client of the edge gateway, and the TLS encryption suite is configured. According to the maximum message length of the MQTTs protocol, the final encrypted data packet is fragmented: if the data packet length is ≤1024 bytes, it is directly used as a single fragment; if it exceeds 1024 bytes, it is split into 1024 bytes / fragment, and a fragment header is added to each fragment.

[0055] In this embodiment, a 16-bit FCS checksum is calculated separately for each data fragment. The checksum is added after the fragment header and before the data fragment to form a verifiable fragment unit. The fragment units are sent sequentially to the MQTTs server of the cloud computing platform according to their fragment sequence numbers via the MQTTs protocol. After receiving each fragment unit, the server first extracts the FCS checksum and performs FCS verification on the fragment data. If the verification passes, the fragment is temporarily stored and the received fragment sequence number is recorded. If the verification fails, a retransmission request is sent to the gateway. After the server has received all fragments, it reassembles the fragment data according to the sequence number to restore the complete encrypted data packet. Then, the CRC code at the end of the data packet is extracted, and the reassembled data packet is subjected to CRC verification. If the verification passes, the subsequent decryption process begins. If the verification fails, the entire data packet is retransmitted.

[0056] Step 102: The cloud platform preprocesses the received multidimensional time series data and performs deep feature extraction on each data point. After fusion, a high-dimensional feature vector is obtained.

[0057] In this embodiment, after decrypting the received encrypted data packets, the cloud computing platform performs data cleaning and uses time-series-based interpolation to process missing data. The preprocessed multidimensional time-series data is input into a convolutional neural network. After multi-layer convolution operations and pooling layers to compress redundant information, a spatial feature vector reflecting the spatial correlation characteristics of the wiring loop is output. The preprocessed multidimensional time-series data is then input into a long short-term memory network. A gating mechanism is used to capture long-term dependencies in the data. After transformation by a fully connected layer, a time-series feature vector reflecting the time-series evolution characteristics of the wiring loop is output. An attention-weighted fusion strategy is used to assign weights to the spatial feature vector and the time-series feature vector to generate a high-dimensional feature vector.

[0058] Step 103: Input the high-dimensional feature vector into the MOGA-Transformer model to predict the changing trends of wiring current and temperature parameters in the next 1-24 hours, identify potential overload and overheat risks, and identify fault types through attention weight allocation, and output data analysis results.

[0059] In this embodiment, the MOGA algorithm is used to optimize the Transformer model parameters to obtain the MOGA-Transformer model. High-dimensional feature vectors are input into the MOGA-Transformer model, and the encoder calculates the association weights of data at different time steps using a self-attention mechanism to generate contextual features. Based on the encoder output and combined with position encoding information, the decoder predicts the changing trends of wiring current and temperature parameters over the next 1-24 hours and outputs trend curve data. In the self-attention layer of the Transformer model, attention weights for each feature dimension are extracted, and the top 30% of key features are selected. These key features are input into a pre-defined fault feature library, and specific fault types are identified through similarity matching. The trend prediction results and fault identification results are integrated to generate data analysis results.

[0060] In this embodiment, a high-dimensional feature vector is input into the MOGA-Transformer model. The encoder calculates the association weights of data at different time steps through a self-attention mechanism to generate context features. The high-dimensional feature vector contains spatial association and temporal evolution information of the wiring data. The encoder first maps it into three types of matrices: Query, Key, and Value. The similarity score of features between any two time steps is calculated through matrix operations. After normalization by the Softmax function, attention weights are obtained. The higher the weight value, the closer the feature association at the corresponding time step. Then, the Value matrix is ​​combined with weighted summation to generate context features that integrate global temporal association information.

[0061] Based on the encoder output and combined with position encoding information, the decoder predicts the trend of wiring current and temperature parameters over the next 1-24 hours and outputs trend curve data. The position encoding is generated using sine and cosine functions to inject time sequence information into the context features, solving the problem that the Transformer model is insensitive to the order of time-series data. The decoder adopts an autoregressive approach, using the encoder output as the initial input and generating prediction results step by step. Each prediction result serves as the input reference for the next step, and the final output contains trend curve data containing the predicted current and temperature values ​​every 10 minutes over the next 1-24 hours, clearly showing the pattern of parameter changes.

[0062] In the self-attention layer of the Transformer model, attention weights for each feature dimension are extracted, and the top 30% of key features by weight are selected. The self-attention layer assigns independent weights to each dimension in the high-dimensional feature vector. The core dimensions that have the greatest impact on the analysis results are selected by weight ranking. These key features usually contain early signals of wiring abnormalities, such as the magnitude of current surges and the rate of temperature rise in a short time, providing accurate targets for subsequent fault identification.

[0063] Key features are input into a pre-set fault feature library, and specific fault types are identified through similarity matching. The fault feature library pre-stores feature templates for eight typical faults, such as short circuit, loose connection, and overload. Each template contains the value range and variation pattern of the key features for the corresponding fault. The cosine similarity algorithm is used to calculate the similarity between the input key features and each template. When the similarity exceeds a preset threshold, it is determined to be a fault of the corresponding type, and the similarity value is output to reflect the reliability of the identification.

[0064] By integrating trend prediction results with fault identification results, data analysis results are generated. Information such as future parameter change trend curves, risk warning nodes, fault types, fault locations, and identification credibility are structured and integrated to supplement risk level assessment, ultimately forming standardized data analysis results that include text descriptions, data tables, and visual chart indexes.

[0065] In this embodiment, the population of the MOGA algorithm is initialized, where the individuals in the population are the parameters of the Transformer model; a dual-objective fitness function is set, which includes minimizing the trend prediction error and maximizing the fault identification accuracy; high-quality individuals are selected through roulette wheel selection, offspring individuals are generated through crossover, and new solutions are introduced through mutation; the optimization is iterated, and the optimal parameter combination is output when the maximum number of iterations is reached, thus obtaining the MOGA-Transformer model.

[0066] In this embodiment, the population of the MOGA algorithm is initialized, where each individual in the population represents a parameter of the Transformer model. Specifically, this includes key parameters such as the number of encoder layers, the number of attention heads, the dimension of hidden layer neurons, the expansion coefficient of the feed-forward network, and the learning rate. Each parameter is set within a preset engineering range, such as 2-8 encoder layers, 4-16 attention heads, and a population size of 50-100 individuals. Initial parameter values ​​are assigned to each individual using a random number generation algorithm to ensure that the parameter combinations cover the core dimensions affecting model performance. A dual-objective fitness function is set, comprising minimizing trend prediction error and maximizing fault identification accuracy. The trend prediction error is calculated using the average absolute error between the predicted and true values, and the fault identification accuracy is determined by the ratio of the number of correctly identified fault data points to the total amount of data. Weight coefficients are introduced to balance the importance of the two objectives, ensuring the fitness value... It can comprehensively reflect the core performance of the model; through roulette wheel selection to select high-quality individuals, crossover to generate offspring individuals, and mutation to introduce new solutions, iterative optimization is performed, and the optimal parameter combination is output when the maximum number of iterations is reached, resulting in the MOGA-Transformer model; roulette wheel selection allocates the selection probability based on the proportion of individual fitness values, with individuals with higher fitness having a greater probability of being selected to participate in reproduction; the crossover operation adopts a single-point crossover method, randomly selecting crossover points in the parameter sequence and exchanging parameter fragments of two parent individuals to generate offspring; the mutation operation performs small-amplitude random perturbations on individual parameters, with the maximum number of iterations set to 50-100 times, recording the best individual in each generation during the iteration process, and finally outputting the parameter combination with the best overall performance.

[0067] Step 104: The cloud computing platform pushes the data analysis results to the user through a visual interface, and at the same time connects to the instrument control system to realize automatic fault alarm and dynamic adjustment of wiring parameters.

[0068] In this embodiment, the cloud computing platform converts the data analysis results into a visual data format, pushes the visual data to the user terminal, and triggers a terminal message reminder; the cloud computing platform converts the data analysis results into control signals, and after receiving the control signals, the instrument control system automatically performs parameter adjustment operations and feeds back the execution results to the cloud computing platform.

[0069] Please see Figure 2 A schematic diagram of the structure of a cloud-based multifunctional instrument wiring data analysis system provided in this embodiment of the invention. The system includes:

[0070] The data acquisition module is used to collect multi-dimensional time-series data of instrument wiring circuits through a sensor cluster deployed on site, and upload the multi-dimensional time-series data to the cloud computing platform after standardization and encryption.

[0071] The feature extraction module is used by the cloud platform to preprocess the received multidimensional time series data, extract deep features separately, and obtain a high-dimensional feature vector after fusion.

[0072] The identification module is used to input high-dimensional feature vectors into the MOGA-Transformer model to predict the changing trends of wiring current and temperature parameters in the next 1-24 hours, identify potential overload and overheat risks, and identify fault types through attention weight allocation, and output data analysis results.

[0073] The push module is used by the cloud computing platform to push data analysis results to users through a visual interface. It also connects to the instrument control system to realize automatic fault alarm and dynamic adjustment of wiring parameters.

[0074] Figure 3 This is a schematic diagram of the structure of a cloud-based multifunctional instrument wiring data analysis device 300 provided in an embodiment of the present invention. This cloud-based multifunctional instrument wiring data analysis device 300 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 310 (e.g., one or more processors) and a memory 320, and one or more storage media 330 (e.g., one or more mass storage devices) for storing application programs 333 or data 332. The memory 320 and storage media 330 can be temporary or persistent storage. The program stored in the storage media 330 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the cloud-based multifunctional instrument wiring data analysis device 300. Furthermore, the processor 310 may be configured to communicate with the storage media 330 and execute the series of instruction operations in the storage media 330 on the cloud-based multifunctional instrument wiring data analysis device 300 to implement the method provided in the above embodiment.

[0075] The cloud-based multifunctional instrumentation and data analysis device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input / output interfaces 360, and / or one or more operating systems 331, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 3 The structure of the cloud-based multifunctional instrument wiring data analysis device shown does not constitute a limitation on the computer device provided by the present invention. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0076] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the various steps of the cloud computing-based multifunctional instrument wiring data analysis method provided in the above embodiments.

[0077] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described equipment or apparatus / unit can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0078] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0079] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A cloud computing-based method for analyzing wiring data of multifunctional instruments and meters, characterized in that, The method includes the following steps: By deploying a cluster of sensors on-site, multi-dimensional time-series data of instrument wiring circuits are collected, and the multi-dimensional time-series data is uploaded to the cloud computing platform after being standardized and encrypted. The cloud platform preprocesses the received multidimensional time-series data and performs deep feature extraction on each data point. After fusion, a high-dimensional feature vector is obtained. By inputting high-dimensional feature vectors into the MOGA-Transformer model, the model predicts the changing trends of wiring current and temperature parameters in the next 1-24 hours, identifies potential overload and overheat risks, and identifies fault types through attention weight allocation, outputting data analysis results. The cloud computing platform pushes data analysis results to users through a visual interface, and at the same time connects to the instrument control system to realize automatic fault alarm and dynamic adjustment of wiring parameters.

2. The cloud computing-based multi-functional instrument wiring data analysis method as described in claim 1, characterized in that, The process involves collecting multi-dimensional time-series data of instrument wiring circuits through a sensor cluster deployed on-site, and then uploading this data to a cloud computing platform after standardization and encryption. This includes: Multiple types of sensors are deployed at the nodes of the instrument wiring circuit to collect multi-dimensional time-series data, which includes at least real-time current value, wiring temperature, signal transmission strength, voltage fluctuation value, and cable vibration frequency. The min-max method is used to standardize the multidimensional time series data. The standardized data is then encrypted using the AES-256 encryption algorithm to generate encrypted data packets, which are then uploaded to the cloud computing platform via an encrypted transmission protocol. A fragmentation verification mechanism is used during the transmission process.

3. The cloud computing-based multifunctional instrument wiring data analysis method as described in claim 2, characterized in that, The standardized data is encrypted using the AES-256 encryption algorithm, including: Obtain the preset AES-256 symmetric key and 128-bit initialization vector, and convert the standardized data into a binary data stream supported by AES encryption; The CBC encryption mode using the AES-256 algorithm first splits the binary data stream into 128-bit groups. For the last group of data that is less than 128 bits, it is padded to 128 bits using the PKCS#7 padding rule to form the data group to be encrypted. The first set of data to be encrypted is XORed with the initialization vector, and then the result is round-transformed with the AES-256 key to generate the first set of encrypted data. Repeated calculations and round transformations are performed to obtain a complete encrypted data stream. The encrypted data stream, initialization vector, and data packet metadata are then concatenated to form the original encrypted data packet. Calculate a 32-bit CRC code for the original encrypted data packet, and append the CRC code to the end of the original encrypted data packet to generate the final encrypted data packet.

4. The cloud computing-based multi-functional instrument wiring data analysis method as described in claim 1, characterized in that, The cloud platform preprocesses the received multidimensional time-series data, performs deep feature extraction on each data point, and then fuses them to obtain a high-dimensional feature vector, including: After decrypting the received encrypted data packets, the cloud computing platform performs data cleaning and uses time-series-based interpolation to process missing data. The preprocessed multidimensional time-series data is input into a convolutional neural network. After multiple convolution operations and pooling layers to compress redundant information, a spatial feature vector reflecting the spatial correlation characteristics of the wiring loop is output. The preprocessed multidimensional time series data is input into a long short-term memory network. The long-term dependencies of the data are captured through a gating mechanism. After transformation by a fully connected layer, a time series feature vector reflecting the timing evolution characteristics of the wiring loop is output. An attention-weighted fusion strategy is adopted to assign weights to spatial feature vectors and temporal feature vectors to generate high-dimensional feature vectors.

5. The cloud computing-based multi-functional instrument wiring data analysis method as described in claim 1, characterized in that, The process involves inputting high-dimensional feature vectors into the MOGA-Transformer model to predict the changing trends of wiring current and temperature parameters over the next 1-24 hours, identifying potential overload and overheat risks, and identifying fault types through attention weight allocation. The resulting data analysis results include: The MOGA algorithm is used to optimize the parameters of the Transformer model, resulting in the MOGA-Transformer model. The high-dimensional feature vector is input into the MOGA-Transformer model, and the encoder calculates the association weights of data at different time steps through a self-attention mechanism to generate contextual features. Based on the encoder output and combined with position encoding information, the decoder predicts the trend of wiring current and temperature parameters in the next 1-24 hours and outputs trend curve data. In the self-attention layer of the Transformer model, the attention weights of each feature dimension are extracted, and the top 30% of key features by weight are selected. Input key features into a pre-set fault feature library and identify specific fault types through similarity matching; Integrate trend prediction results with fault identification results to generate data analysis results.

6. The cloud computing-based multi-functional instrument wiring data analysis method as described in claim 5, characterized in that, The process of optimizing the Transformer model parameters using the MOGA algorithm to obtain the MOGA-Transformer model includes: Initialize the population for the MOGA algorithm, where the individuals in the population are the parameters of the Transformer model; A dual-objective fitness function is defined, which includes minimizing trend prediction error and maximizing fault identification accuracy. The MOGA-Transformer model is obtained by selecting high-quality individuals through roulette wheel selection, generating offspring individuals through crossover, introducing new solutions through mutation, and iterating through optimization. When the maximum number of iterations is reached, the optimal parameter combination is output.

7. The cloud computing-based multi-functional instrument wiring data analysis method as described in claim 1, characterized in that, The cloud computing platform pushes data analysis results to users through a visual interface, and simultaneously connects to the instrument control system to achieve automatic fault alarms and dynamic adjustment of wiring parameters, including: The cloud computing platform converts the data analysis results into a visual data format, pushes the visual data to the user's terminal, and triggers terminal message reminders; The cloud computing platform converts the data analysis results into control signals. After receiving the control signals, the instrument control system automatically performs parameter adjustment operations and feeds back the execution results to the cloud computing platform.

8. A cloud computing-based multifunctional instrument wiring data analysis system, characterized in that, The system includes: The data acquisition module is used to collect multi-dimensional time-series data of instrument wiring circuits through a sensor cluster deployed on site, and upload the multi-dimensional time-series data to the cloud computing platform after standardization and encryption. The feature extraction module is used by the cloud platform to preprocess the received multidimensional time series data, extract deep features separately, and obtain a high-dimensional feature vector after fusion. The identification module is used to input high-dimensional feature vectors into the MOGA-Transformer model to predict the changing trends of wiring current and temperature parameters in the next 1-24 hours, identify potential overload and overheat risks, and identify fault types through attention weight allocation, and output data analysis results. The push module is used by the cloud computing platform to push data analysis results to users through a visual interface. It also connects to the instrument control system to realize automatic fault alarm and dynamic adjustment of wiring parameters.

9. A multi-functional instrument wiring and data analysis device based on cloud computing, characterized in that, The cloud-based multi-functional instrument wiring data analysis device includes a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the cloud-based multi-functional instrument wiring data analysis device to perform each step of the cloud-based multi-functional instrument wiring data analysis method as described in any one of claims 1-7.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement each step of the cloud computing-based multifunctional instrument wiring data analysis method as described in any one of claims 1-7.

Images