Full-life-cycle intelligent management method and system for ultrahigh-voltage metering equipment

Abstract

The invention provides a full-life-cycle intelligent management method and system for ultrahigh-voltage metering equipment, and the method comprises the steps: constructing an equipment life cycle structural body which comprises an equipment unique number and an operation behavior sequence arranged according to a time sequence, carrying out the dual-channel legality verification of each operation behavior, and carrying out the verification of the two-channel legality of each operation behavior; generating a compliance score of each operation and marking legality to obtain a legality marking sequence; based on the legality mark sequence and the operation behavior sequence, an equipment state score is calculated, and the equipment state score integrates three factors of abnormal operation density, early abnormal behavior punishment and operation rhythm sudden change punishment to output an equipment state score in a range of 0 to 1; according to the equipment state score and the abnormal operation record, a structured processing work order is automatically generated and output, and the processing work order comprises a scrap suggestion work order, a recheck suggestion work order and an abnormal recheck work order.

Description

Technical Field

[0001] This invention belongs to the field of data management, and in particular relates to a method and system for intelligent management of the entire life cycle of ultra-high voltage metering equipment. Background Technology

[0002] With the acceleration of digital transformation in the power industry, ultra-high voltage transmission companies are encountering increasing problems in the management of electricity metering equipment. Current management processes largely rely on fragmented business systems and manual operations. From equipment procurement, filing, verification, installation, operation to decommissioning and scrapping, the processes are disjointed and data is isolated, making complete lifecycle traceability difficult. Especially in critical stages such as installation, dismantling, sealing, and verification, unstructured photos, forms, and text documents are only saved as simple attachments, lacking automated consistency verification with system-registered data, easily leading to discrepancies between registration and actual conditions. Furthermore, due to the lack of a unified behavioral sequence model, the system cannot perform step-by-step legality verification for each operation or identify abnormal behavior patterns, resulting in some non-compliant processes circumventing supervision. Even with the introduction of mobile terminal devices in some companies, only the data uploading problem has been solved, remaining at the "information aggregation" level, failing to achieve intelligent verification and automated closed-loop management throughout the entire process. In the judgment of reuse and scrapping, traditional methods still rely on experience or single verification records, lacking quantitative evidence based on historical behavior and status changes, leading to low asset utilization and inherent risks. Summary of the Invention

[0003] The purpose of this invention is to design an intelligent management method and system for the entire lifecycle of ultra-high voltage metering equipment, achieving complete traceability from record-keeping to disposal. By performing dual-channel legality verification on each operation, comparing the on-site image recognition results with system snapshots, and combining this with operation path rules for comprehensive judgment, the authenticity and compliance of the operation are guaranteed.

[0004] To achieve the above objectives, the first aspect of the present invention provides a method for intelligent management of the entire lifecycle of ultra-high voltage metering equipment, the method comprising:

[0005] Construct a device lifecycle structure, which includes a unique device number and a sequence of operation behaviors arranged in chronological order. Each operation behavior record includes operation type, normalized time location, operator number, operation location number, and system status snapshot.

[0006] For each operation, a dual-channel legality check is performed, including the consistency check between the image recognition result and the system registration information, and the compliance check of whether the operation path conforms to the preset lifecycle rules. A compliance score is generated for each operation and the legality is marked to obtain a legality mark sequence.

[0007] Based on the legality marker sequence and the operation behavior sequence, the equipment status score is calculated. The equipment status score integrates three factors: abnormal operation density, early abnormal behavior penalty, and operation rhythm change penalty, and outputs an equipment status score in the range of 0 to 1.

[0008] Based on the equipment status score and abnormal operation records, a structured processing work order is automatically generated and output. The processing work order includes a scrapping suggestion work order, a re-inspection suggestion work order, and an anomaly review work order.

[0009] Furthermore, the steps for constructing the device lifecycle structure include:

[0010] Collect device operation data from at least one subsystem, including device number, operation timestamp, operation type, operator, operation location, and system status snapshot;

[0011] Sort all operations on the same device by time and normalize the operation time so that it falls within the range of 0 to 1; encapsulate each operation into a 5-tuple and arrange them in ascending order of normalized time to form a behavior sequence.

[0012] Combine the device number with the behavior sequence to form a device lifecycle structure.

[0013] Furthermore, the dual-channel validity check includes:

[0014] The first channel uses image recognition technology to extract device information from images uploaded on-site, compares it with the system registration information, and detects whether the seal number is used repeatedly, generating an image inconsistency score.

[0015] The second channel determines whether the current operation conforms to the process logic based on preset lifecycle path rules and generates a path violation score;

[0016] The two scores are combined into a compliance score, which is then compared with a preset threshold to determine whether the operation is legal.

[0017] Furthermore, image recognition technology includes using convolutional neural networks to extract image features, and combining gated recurrent units and CTC decoders to recognize character sequences in images.

[0018] Furthermore, the calculation of the equipment status score includes:

[0019] The proportion of abnormal operations to the total number of operations is used as the anomaly density.

[0020] Apply higher weight to early-occurring abnormal operations as an early penalty;

[0021] Apply a rhythmic mutation penalty term to operation sequences that frequently switch between legal and illegal states with short time intervals;

[0022] The final score is obtained by weighted fusion of abnormal density, early penalty term, and rhythm mutation penalty term.

[0023] Furthermore, in the calculation of early penalty terms, the closer the normalized time of the abnormal operation is to 0, the higher the penalty weight.

[0024] Furthermore, in the rhythm mutation penalty term, the greater the change in the legality state of adjacent operations and the shorter the time interval, the higher the penalty value.

[0025] Furthermore, the logic for generating work orders includes:

[0026] If the equipment score is lower than the first threshold and the number of abnormal operations exceeds the set value, a scrapping recommendation work order will be generated.

[0027] If the equipment score is between the first and second thresholds and the number of abnormal operations is within the set range, a re-inspection suggestion work order will be generated.

[0028] If there are two consecutive abnormal operations and the time interval is less than the set threshold, an abnormal review work order will be generated.

[0029] Furthermore, the processing work order includes the equipment number, work order generation time, work order type, equipment rating, number of abnormal operations, a list of key operation numbers that triggered the work order, and the system's recommended follow-up actions.

[0030] In a second aspect of the present invention, an intelligent management system for the entire lifecycle of ultra-high voltage metering equipment is provided, the system comprising:

[0031] The data acquisition module is used to construct a device lifecycle structure, which includes a unique device number and a sequence of operation behaviors arranged in chronological order. Each operation behavior record includes operation type, normalized time position, operator number, operation location number, and system status snapshot.

[0032] The legality verification module is used to perform dual-channel legality verification on each operation, including the consistency verification between the image recognition result and the system registration information, and the compliance verification of whether the operation path conforms to the preset lifecycle rules. It generates a compliance score for each operation and marks it as legal to obtain a legality mark sequence.

[0033] The status scoring module is used to perform dual-channel legality verification on each operation, including consistency verification between image recognition results and system registration information, and compliance verification of whether the operation path conforms to preset lifecycle rules. It generates a compliance score for each operation and marks its legality to obtain a legality mark sequence.

[0034] The work order generation module is used to automatically generate and output structured processing work orders based on the equipment status score and abnormal operation records. The processing work orders include scrapping suggestion work orders, re-inspection suggestion work orders, and abnormal review work orders.

[0035] The beneficial technical effects of the present invention are at least as follows:

[0036] To address the aforementioned issues, this invention provides an intelligent management method and system for the entire lifecycle of ultra-high voltage metering equipment. Its core lies in constructing a structured lifecycle behavior model centered on the equipment, achieving complete traceability from record-keeping to scrapping. By performing dual-channel legality verification on each operational behavior, comparing on-site image recognition results with system snapshots, and combining this with operational path rules for comprehensive judgment, the authenticity and compliance of operations are guaranteed. Based on this, this invention designs a scoring mechanism combining anomaly density, early violation penalties, and sudden changes in operational rhythm to quantitatively evaluate the equipment's operating status, providing a scientific quantitative basis for reuse and scrapping. Furthermore, the system automatically generates scrapping recommendation work orders, re-inspection recommendation work orders, or anomaly review work orders based on the scoring results and anomaly behavior distribution, and links with the existing marketing metering management system to form a closed-loop control from modeling, verification, evaluation to execution. This solution not only ensures the verifiability and transparency of each stage of the ultra-high voltage metering equipment's lifecycle but also improves the scientific nature of equipment management decisions and the automation level of process execution, thereby improving the efficiency and safety of ultra-high voltage metering management. Attached Figure Description

[0037] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0038] Figure 1 This is a flowchart of an intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to the present invention.

[0039] Figure 2 This is a framework diagram of an intelligent management system for the entire life cycle of ultra-high pressure metering equipment according to the present invention. Detailed Implementation

[0040] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0041] In one or more embodiments, such as Figure 1As shown, a method for intelligent management of the entire lifecycle of ultra-high voltage metering equipment is disclosed, the method comprising the following:

[0042] S1: Construct a device lifecycle structure, which includes a unique device number and a sequence of operation behaviors arranged in chronological order. Each operation behavior record includes operation type, normalized time location, operator number, operation location number, and system status snapshot.

[0043] Specifically, the goal of this step is to construct the device lifecycle structure. dev This is used to encapsulate the entire lifecycle of an ultra-high voltage metering device, from filing, installation, verification, sealing to scrapping. Because existing systems have data scattered across multiple subsystems (such as the filing system, operation system, verification system, and sealing system), with inconsistent field formats, timestamp precision, and recording methods, direct and complete traceability is impossible. Therefore, this step requires collecting, processing, and structurally encapsulating this data to form a standardized device behavior sequence S. dev and combined with the device ID dev Composition of lifecycle structure dev This structure serves as the input basis for subsequent steps to perform legality checks and state assessments.

[0044] In actual data collection, the device's unique ID is used. dev This number, from the metering equipment filing system, uniquely identifies an ultra-high voltage power metering device within the company. (Operation timestamp t) i Originating from assembly / disassembly and calibration systems, the original format is typically ISO 8601 (e.g., "2023-08-01T12:30:00Z"). During processing, it is uniformly converted to a Unix timestamp for calculation. Operation type a i These values ​​originate from work orders such as "Install Energy Meter," "Installation Transformer," and "Replace Seal," and are predefined enumeration values ​​in the system. Operator ID u i Retrieved from work order processing records, such as the employee ID "A03219" of a field worker, ensuring personnel traceability. Operation location l i A unique identification number for the power station or substation, such as "YD-1201," is automatically attached by the work order system. Finally, a system snapshot during operation is provided. i Originating from the record system and seal management system, this is a collection of system-registered statuses at the time of the operation, including fields such as device model (e.g., "DTSD341 type electricity meter"), seal number (e.g., "S-89213"), and device status (e.g., "running" or "pending inspection").

[0045] Specifically, if a certain device ID dev =D-0001320, a sealing operation was performed on September 1, 2022. The work order record shows that the operator was "A03564", the location was "YD-1201", and the equipment status changed from "pending inspection" to "running". The sealing system also registered the seal number "S-89213". Therefore, the input data for this action includes the ID. dev =D-0001320,t i =2022-09-01 10:00:00 (converted to Unix timestamp), a i =Seal, u i =A03564,l i =YD-1201,m i ={model:"DTSD341",seal_code:"S-89213",status:"Running"}.

[0046] In building Struct dev At this time, the first step is to register the same device ID. dev All operational behaviors were collected into a single original sequence S. raw In, and by time field t i Sort in ascending order. Due to the significant differences in the lifespan of different devices—for example, some devices have a service life of over 10 years, while others are decommissioned due to malfunctions within just two years—directly comparing the length of time is not conducive to modeling. Therefore, it is necessary to normalize the operation time.

[0047] Time normalization is performed using the following formula:

[0048]

[0049] Among them, t i It is the timestamp of the i-th operation; t start This refers to the initial recording time of the equipment, such as the purchase and filing time; t end This is the latest operating time of the equipment. The calculated τ is... i If the value falls within the range [0,1], it indicates the relative position of the behavior within the device's lifecycle. For example, device D-0001320 was created on January 1, 2020 (t...). start He retired on August 1, 2024. end One sealing operation occurred on September 1, 2022 (t). i ), then τ i ≈0.58 indicates that the operation occurred in the middle to late part of the lifecycle.

[0050] Next, construct a quintuple for each operation record:

[0051] s i =(a i ,τ i ,u i ,l i ,m i );

[0052] Where a i u i l i m i The values ​​of τ all come from the aforementioned input acquisition process. i It is calculated using the normalization formula. For example, the sealing operation mentioned earlier yields a quintuple of (seal, 0.58, A03564, YD-1201, {model:"DTSD341", seal_code:"S-89213", status:"Running"}).

[0053] All s i According to τ i Arrange in ascending order to obtain an ordered sequence of behaviors:

[0054] S dev ={s1,s2,...,s N};

[0055] Finally, combined with the equipment number, a complete structure is formed:

[0056] Struct dev ={ID dev ,S dev};

[0057] S2: Perform dual-channel legality verification on each operation, including consistency verification between image recognition results and system registration information, and compliance verification of whether the operation path conforms to the preset lifecycle rules. Generate a compliance score for each operation and mark its legality to obtain a legality mark sequence.

[0058] Specifically, the goal of this step is to build upon the device lifecycle structure (Struct) constructed in the first step. dev ={ID dev ,S dev}, for each operation record s i =(a i ,τ i ,u i ,l i ,n i Perform a validity check and generate a validity marker sequence L. check .

[0059] In this embodiment, although some illegal operations appear compliant (such as uploading photos of seals and completing system registration fields), issues such as inconsistencies between on-site operations and system status, and bypassing of illegal procedures still occur frequently. This invention proposes a mechanism of "dual-channel verification + compliance score weighted fusion": the first channel performs image structure matching degree verification, and the second channel performs lifecycle path compliance judgment. Finally, a unified model is achieved through a compliance score function with a penalty term, which not only identifies explicit violations but also improves the system's ability to perceive potential illegal paths.

[0060] In the image consistency verification channel, image data (such as photos of sealing labels and nameplates) from operation nodes such as sealing, installation, and inspection are uploaded to the backend system via mobile terminals. The images are processed through a lightweight visual recognition pipeline, including three layers of convolutional coding (extracting shape features of character regions), a bidirectional gated recurrent network (GRU) modeling the character sequence context, and finally, CTC (Connectionist Temporal Classification) decoding to obtain the image content string. The identification result is compared with the system registration snapshot m i The image is compared with the seal number and device model fields. If there is a discrepancy or the seal number has appeared in the history (i.e., the seal has been reused), an image inconsistency score M is defined. i It is in the following form:

[0061]

[0062] in, This represents the string distance (e.g., Levenshtein distance) between the image recognition result and the system registration information. It is an indicator function, if m i The seal number is 1 if it has appeared in history, and 0 otherwise. λ1 is the penalty coefficient for repeated use of the seal, which is fixed to an empirical value (e.g., 0.4). The higher the score, the less reliable the image information is.

[0063] In the path verification channel, for each operation s i Using its operation type a i Time and position τ i System status m i Model the process consistency with preceding operations. For example: if a i The equipment is listed as "operational and commissioned," but it has not previously exhibited any "calibration qualified" behavior, or its condition is m. i If a device is marked as "uninspected," the action is considered illegal. For example, if the same device is in an adjacent... i The "seal" operation occurs consecutively, and the time interval is less than a threshold (e.g., τ). i+1 -τi If the value is less than 0.01, it is considered frequent reuse of the seal. These rules can be uniformly modeled as a path violation score R. i :

[0064]

[0065] in This is the violation indicator function for the k-th path rule, returning 1 to indicate that s i Violations of this rule (such as "direct commissioning without inspection", "insufficient sealing interval", etc.) k Assign a weight to each rule (e.g., 0.6 for major violations and 0.2 for minor violations), S dev This is a complete sequence of device behaviors used to determine the context.

[0066] Final compliance score: C i It can be obtained by fusing the scoring results of two channels, as defined below:

[0067] C i =1-min(1,M) i +R i );

[0068] Where C i The value range is [0,1], representing the overall compliance level of the i-th operation. If M... i and R i Both 0 and 0 indicate that both the image and the path are valid. i =1; if there are inconsistent images or process violations, then C i It will decrease, down to a minimum of 0. We then set the validity flag y based on the threshold η. i :

[0069]

[0070] Where η is an empirical threshold, such as 0.7, which means that when the operation compliance score is lower than this value, the operation is marked as illegal and subsequent review or abnormal work order needs to be triggered.

[0071] This step yields the legality marker sequence L. check ={(s1,y1),(s2,y2),...,(s N ,y N )}, where each y i It is aimed at lifecycle behaviors. i The overall legality determination result.

[0072] S3: Based on the legality marker sequence and the operation behavior sequence, calculate the equipment status score. The equipment status score integrates three factors: abnormal operation density, early abnormal behavior penalty, and operation rhythm change penalty, and outputs an equipment status score in the range of 0 to 1.

[0073] Specifically, this step aims to utilize the device's lifecycle behavior data (Struct) dev ={ID dev ,S dev} and the corresponding operation validity marker sequence L chech ={(s1,y1),(s2,y2),...,(s N ,y N The system comprehensively quantifies the operational status of each device throughout its lifecycle and outputs a score. dev The scoring results will be used to support subsequent intelligent operation and maintenance decisions, including reuse assessments, disposal recommendations, and triggering manual review.

[0074] Compared to traditional methods that rely primarily on static fields such as "last verification result" or "current operating status" for equipment status assessment, this step designs a dynamic scoring mechanism that combines multiple factors, including equipment operation history, behavioral compliance, operation rhythm, and temporal distribution. Especially considering the unique characteristics of ultra-high voltage metering equipment in actual operation and maintenance: long service life, few but critical maintenance tasks, extremely uneven operation distribution, and significant impact of early operations on later operations, this step introduces the following three modeling mechanisms: (1) anomaly density factor; (2) early anomaly penalty term; and (3) rhythm mutation penalty term. These mechanisms are logically related to the operation behavior sequence S in step one. dev Structure and normalized time τ i Maintain consistency in modeling, and also mark y with the validity of step two. i Based on this, it strictly inherits all the input results from the first two steps, without introducing any new external data or variables.

[0075] First, calculate the comprehensive anomaly density score D for all operations throughout the equipment's lifecycle. dev Based on this, two types of compensation items, "early abnormality penalty" and "rhythm change penalty," are added to construct the following scoring formula:

[0076]

[0077] Where: N represents the total number of device operations, from S dev Chinese statistics; y i Indicates operation s i The validity marker comes from L check 1 for valid, 0 for invalid; τ i It is si The normalized time ([0,1]) is derived from the Struct dev The first term is the anomaly density, i.e., the proportion of abnormal behavior to total operations; the second term is the early anomaly penalty, which applies if abnormal behavior is concentrated in the early stages of the lifecycle (τ). i →0), the larger the value of this term; the third term is the rhythm mutation term, which judges the frequent switching between legal and illegal states in the device operation sequence. If legal and illegal states alternate frequently and the time interval is short, it is considered that the behavior rhythm is unstable, |τ i -τ i-1 | -1 It is a reverse weight for the interval of operation rhythm to prevent unreasonable operation behaviors such as repeated assembly and disassembly and repeated sealing in a short period of time; the coefficients α and β are two regularization factors that control the impact of early abnormalities and rhythm changes on the score, respectively. The empirical value range is [0.2, 0.6], which can be set to be dynamically adjustable in the system.

[0078] This invention not only considers the overall ratio of legal to illegal operations, but also combines timeline location information and behavioral rhythm change patterns to depict the reliability of equipment status from multiple dimensions. Especially in ultra-high voltage scenarios, operations such as frequent seal replacement, non-compliance with procedures during installation and disassembly, and disconnection between inspection and commissioning, although not serious in a single instance, may hide significant management risks due to their timing and manner. This scoring mechanism can effectively identify these deep-seated abnormal patterns.

[0079] Specifically, assuming device D-00123 has 6 operations, including 2 sealing operations with a very short interval (τ difference less than 0.01), one of which did not upload image information, and the other sealing number has already appeared in the history. Both of these are judged as y=0, and their time positions both fall within τ≈0.12, belonging to the early stage of the life cycle. In this case, the early penalty and rhythm change in the above three scoring formulas will contribute significantly to the final score. dev A significant decrease (e.g., to 0.45) will cause it to be pushed to the system as a key review target in the next step.

[0080] S4: Based on the equipment status score and abnormal operation record, automatically generate and output structured processing work orders, which include scrapping suggestion work orders, re-inspection suggestion work orders, and abnormal review work orders.

[0081] Specifically, the goal of this step is to calculate the device status score based on the score obtained in step three. dev The operation validity determination result L output in the second step check ={(s1,y1),...,(s N ,y N In the marketing measurement management system, structured processing work orders (WorkOrders) are automatically generated. devSimultaneously, it outputs corresponding task suggestions, such as initiating the review process, starting the scrapping approval, and marking it as a pending reuse status. This operation belongs to the control link in the "analysis-judgment-control" chain of this patent, and is an important link in realizing closed-loop life cycle management.

[0082] To generate structured work orders, this invention employs a hierarchical decision-making rule, combining scoring with abnormal operations to form the following logic:

[0083] If Score dev <θ1 and the number of anomalies E dev If ≥∈1, generate a suggested scrapping work order;

[0084] If θ1≤Score dev <θ2 and E dev ∈[1,∈1), generate a suggested reuse verification work order;

[0085] If two consecutive abnormal behaviors exist and the time interval is less than the threshold δ, an abnormal review work order will be generated.

[0086] The total number of abnormalities E dev for:

[0087]

[0088] This formula directly uses the validity determination result from the second step, without requiring remodeling or recalculation. The condition for triggering the "continuous anomaly review" logic is:

[0089] There exists i such that y i =0,y i+1 =0 and |τ i+1 -τ i |<δ

[0090] Specifically, in this embodiment, device D-202308 has a score. dev =0.28, number of abnormal behaviors E dev =3, where s2 and s3 are consecutively abnormal with a time difference of 0.006 (meaning less than 5 days), then the system will generate: scrap work order (because the score is <0.3 and the number of abnormalities is ≥3); abnormality review work order (because there are intensive violations).

[0091] The system supports generating multiple work orders, but aggregates them using a unique device ID to ensure process consistency.

[0092] Work orders are output in structure form:

[0093] ID dev Equipment number;

[0094] T gen Work order generation time;

[0095] Type: Work order type, enumeration values: scrapping suggestion, re-inspection suggestion, review suggestion;

[0096] Score dev : Rating value;

[0097] E dev : Abnormal operand;

[0098] TriggerOps: A list of critical operation numbers that triggered this work order (e.g., [2,3]);

[0099] NextAction: The system recommends subsequent processing steps, such as "Enter Approval", "Initiate Re-inspection", and "Mark for Review".

[0100] This structure can be used directly as a system interface to return results, or it can be inserted into a task queue to be synchronized to mobile terminals.

[0101] In one or more embodiments, such as Figure 2 As shown, a smart management system for the entire lifecycle of ultra-high voltage metering equipment is disclosed, the system comprising:

[0102] The data acquisition module is used to construct a device lifecycle structure, which includes a unique device number and a sequence of operation behaviors arranged in chronological order. Each operation behavior record includes operation type, normalized time position, operator number, operation location number, and system status snapshot.

[0103] The legality verification module is used to perform dual-channel legality verification on each operation, including the consistency verification between the image recognition result and the system registration information, and the compliance verification of whether the operation path conforms to the preset lifecycle rules. It generates a compliance score for each operation and marks it as legal to obtain a legality mark sequence.

[0104] The status scoring module is used to perform dual-channel legality verification on each operation, including consistency verification between image recognition results and system registration information, and compliance verification of whether the operation path conforms to preset lifecycle rules. It generates a compliance score for each operation and marks its legality to obtain a legality mark sequence.

[0105] The work order generation module is used to automatically generate and output structured processing work orders based on the equipment status score and abnormal operation records. The processing work orders include scrapping suggestion work orders, re-inspection suggestion work orders, and abnormal review work orders.

[0106] It is worth noting that the specific workflow of the intelligent management system for the entire life cycle of ultra-high voltage metering equipment provided in this embodiment of the invention is the same as that of the intelligent management method for the entire life cycle of ultra-high voltage metering equipment described in the above embodiment, and will not be repeated here.

[0107] This invention also provides an intelligent management device for the entire lifecycle of ultra-high voltage metering equipment, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps described in the above embodiment of an intelligent management method for the entire lifecycle of ultra-high voltage metering equipment. Figure 1 The steps S1 to S4 described above; or, when the processor executes the computer program, it implements the functions of each module in the above system embodiments.

[0108] For example, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the intelligent lifecycle management device for ultra-high voltage metering equipment.

[0109] The aforementioned intelligent management device for the entire lifecycle of ultra-high voltage metering equipment can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. This intelligent management device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the intelligent management device may also include input / output devices, network access devices, buses, etc.

[0110] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the intelligent management device for the entire lifecycle of ultra-high voltage metering equipment, connecting all parts of the intelligent management device for the entire lifecycle of ultra-high voltage metering equipment through various interfaces and lines.

[0111] The memory can be used to store the computer programs and / or modules. The processor, by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory, realizes various functions of the intelligent management device for the entire life cycle of ultra-high voltage metering equipment. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the operation of the air conditioning controller, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart memory card (SmartMedaCard, SMC), secure digital card (SecureDagatal, SD), flash memory card, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0112] The integrated module of the intelligent management device for the entire lifecycle of ultra-high voltage metering equipment, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0113] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0114] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for intelligent management of the entire lifecycle of ultra-high voltage metering equipment, characterized in that, The method includes: Construct a device lifecycle structure, which includes a unique device number and a sequence of operation behaviors arranged in chronological order. Each operation behavior record includes operation type, normalized time location, operator number, operation location number, and system status snapshot. For each operation, a dual-channel legality check is performed, including the consistency check between the image recognition result and the system registration information, and the compliance check of whether the operation path conforms to the preset lifecycle rules. A compliance score is generated for each operation and the legality is marked to obtain a legality mark sequence. Based on the legality marker sequence and the operation behavior sequence, the equipment status score is calculated. The equipment status score integrates three factors: abnormal operation density, early abnormal behavior penalty, and operation rhythm change penalty, and outputs an equipment status score in the range of 0 to 1. Based on the equipment status score and abnormal operation records, a structured processing work order is automatically generated and output. The processing work order includes a scrapping suggestion work order, a re-inspection suggestion work order, and an anomaly review work order.

2. The intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to claim 1, characterized in that, The steps for constructing the device lifecycle structure include: Collect device operation data from at least one subsystem, including device number, operation timestamp, operation type, operator, operation location, and system status snapshot; Sort all operations on the same device by time and normalize the operation time so that it falls within the range of 0 to 1; encapsulate each operation into a 5-tuple and arrange them in ascending order of normalized time to form a behavior sequence. Combine the device number with the behavior sequence to form a device lifecycle structure.

3. The intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to claim 1, characterized in that, The dual-channel validity verification includes: The first channel uses image recognition technology to extract device information from images uploaded on-site, compares it with the system registration information, and detects whether the seal number is used repeatedly, generating an image inconsistency score. The second channel determines whether the current operation conforms to the process logic based on preset lifecycle path rules and generates a path violation score; The two scores are combined into a compliance score, which is then compared with a preset threshold to determine whether the operation is legal.

4. The intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to claim 3, characterized in that, The image recognition technology includes using a convolutional neural network to extract image features, and combining a gated recurrent unit and a CTC decoder to recognize character sequences in the image.

5. The intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to claim 1, characterized in that, The calculation of the equipment status score includes: The proportion of abnormal operations to the total number of operations is used as the anomaly density. Apply higher weight to early-occurring abnormal operations as an early penalty; Apply a rhythmic mutation penalty term to operation sequences that frequently switch between legal and illegal states with short time intervals; The final score is obtained by weighted fusion of abnormal density, early penalty term, and rhythm mutation penalty term.

6. The intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to claim 5, characterized in that, In the calculation of the early penalty term, the closer the normalized time of the abnormal operation is to 0, the higher the penalty weight.

7. The intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to claim 5, characterized in that, In the rhythm mutation penalty term, the greater the change in the legality state of adjacent operations and the shorter the time interval, the higher the penalty value.

8. The intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to claim 1, characterized in that, The logic for generating the processing work order includes: If the equipment score is lower than the first threshold and the number of abnormal operations exceeds the set value, a scrapping recommendation work order will be generated. If the equipment score is between the first and second thresholds and the number of abnormal operations is within the set range, a re-inspection suggestion work order will be generated. If there are two consecutive abnormal operations and the time interval is less than the set threshold, an abnormal review work order will be generated.

9. The intelligent management method for the entire life cycle of ultra-high voltage metering equipment according to claim 1, characterized in that, The processing work order includes the equipment number, work order generation time, work order type, equipment score, number of abnormal operations, a list of key operation numbers that triggered the work order, and the system's recommended follow-up processing actions.

10. A smart management system for the entire lifecycle of ultra-high voltage metering equipment, characterized in that, The system includes: The data acquisition module is used to construct a device lifecycle structure, which includes a unique device number and a sequence of operation behaviors arranged in chronological order. Each operation behavior record includes operation type, normalized time position, operator number, operation location number, and system status snapshot. The legality verification module is used to perform dual-channel legality verification on each operation, including the consistency verification between the image recognition result and the system registration information, and the compliance verification of whether the operation path conforms to the preset lifecycle rules. It generates a compliance score for each operation and marks it as legal to obtain a legality mark sequence. The status scoring module is used to perform dual-channel legality verification on each operation, including consistency verification between image recognition results and system registration information, and compliance verification of whether the operation path conforms to preset lifecycle rules. It generates a compliance score for each operation and marks its legality to obtain a legality mark sequence. The work order generation module is used to automatically generate and output structured processing work orders based on the equipment status score and abnormal operation records. The processing work orders include scrapping suggestion work orders, re-inspection suggestion work orders, and abnormal review work orders.

Images