Intelligent inspection optimization method for electric power safety production management

Abstract

The invention discloses an electric power safety production management intelligent inspection optimization method, and relates to the technical field of electric power system operation and maintenance, and the method comprises the steps: building an equipment ledger library based on a block chain through collection data, customizing an inspection task, carrying out the uniqueness management of equipment through a radio frequency induction technology, and carrying out the management of the uniqueness of the equipment in the inspection process. The system adopts a self-adaptive control algorithm to dynamically adjust an inspection path, collects equipment operation data, associates the operation data with basic information and feeds back the operation data and the basic information to the system in real time, analyzes whether the equipment meets quality inspection requirements or not according to real-time data and equipment states in the system, adds a temporary inspection task and an emergency inspection task aiming at a fault when the fault occurs, and improves the inspection efficiency. And updating the inspection plan, predicting equipment defects by using a machine learning algorithm, and carrying out equipment maintenance and equipment parameter adjustment. According to the method, the problem that traditional equipment ledger management, inspection task customization and equipment defect prediction are incomplete can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system operation and maintenance, and in particular to an intelligent inspection optimization method for power production safety management. Background Art

[0002] In the field of power production safety management, with the rapid development of information technology, intelligent inspection technology has become an important means to improve the stability and reliability of power systems. Traditional power equipment inspection methods mostly rely on manual operation. Although some automation and intelligent technologies have been applied in recent years, such as using sensors to monitor equipment status and locating inspection paths through GPS, these technologies still have certain limitations in data security, inspection efficiency and adaptability. In particular, in terms of equipment ledger management, inspection task customization and equipment defect prediction, the existing technology has not yet formed a complete solution; the existing intelligent inspection technology for power production safety management has the following shortcomings: First, the data management of the equipment ledger library lacks security and is vulnerable to external attacks, resulting in data leakage or tampering; second, the customization of inspection tasks is often based on preset rules, lacks flexibility and pertinence, and cannot be dynamically adjusted according to the real-time status of the equipment; although the existing technology can collect equipment operation data, the real-time feedback and correlation analysis of the data are not efficient enough, and it is difficult to achieve rapid response; in terms of equipment defect prediction, the existing technology relies on historical data analysis, lacks foresight and accuracy, and cannot effectively predict potential faults. The intelligent inspection optimization method for power production safety management invented by us aims to solve the above-mentioned problems by establishing a blockchain-based equipment ledger library, using radio frequency sensing technology for uniqueness management, and combining adaptive control algorithms and machine learning algorithms. It improves the intelligence level and efficiency of inspections, thereby showing significant advantages in ensuring the safe and stable operation of power systems. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides an intelligent inspection optimization method for power production safety management, which can solve the problems of traditional equipment ledger management, inspection task customization and imperfect equipment defect prediction.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions, a method for optimizing intelligent inspection of power production safety management, comprising:

[0006] By collecting data, a blockchain-based equipment inventory library is established. Users can customize inspection tasks based on the equipment inventory library information and use radio frequency sensing technology to uniquely manage the equipment. During the inspection process, the system uses an adaptive control algorithm to dynamically adjust the inspection path, collect equipment operation data, associate the operation data with basic information, and feed it back to the system in real time. According to the real-time data and equipment status in the system, it analyzes whether the equipment meets the quality inspection requirements. When a fault occurs, temporary inspection tasks and emergency inspection tasks for the fault are added, and the inspection plan is updated. According to the statistical inspection data and the defect categories in the equipment inventory library, the machine learning algorithm is used to perform predictive analysis on equipment defects, detect potential faults in advance, and perform equipment maintenance and equipment parameter adjustments.

[0007] As a preferred solution of the intelligent inspection optimization method for power production safety management described in the present invention, wherein: the collected data includes collecting basic equipment information, technical parameters, maintenance information, defect and fault history, and spare parts information;

[0008] The basic equipment information includes equipment number, equipment name, equipment model, manufacturer, date of manufacture, date of commissioning, service life and installation location; the technical parameters include rated voltage, rated current, rated power, frequency, capacity and efficiency; the maintenance information includes maintenance cycle, last maintenance date and next maintenance date; the defect and fault history includes historical defect records, fault causes and repair measures.

[0009] As a preferred solution of the intelligent inspection optimization method for power production safety management described in the present invention, wherein: the establishment of a blockchain-based equipment ledger library includes: performing demand analysis on equipment ledger library management, selecting the Hyperledger Fabric blockchain platform and using the Chaincode smart contract development language to write functions, using IPFS to store blockchain data, developing an API interface, and interacting between an external system and a blockchain network;

[0010] The customized inspection task includes the following steps: the user logs in and authenticates on the Web interface, selects the equipment information in the equipment inventory library, selects the equipment to be inspected from the screening results and sets the inspection parameters, selects the inspection personnel and assigns the inspection task, and the user uses the map tool provided by the system to plan the inspection route according to the equipment location;

[0011] The radio frequency sensing technology includes RFID tags, RFID readers and data management systems;

[0012] The RFID tag is attached to the device, each tag has a unique identification code UID, and stores detailed information of the device; the RFID reader / writer includes reading the information on the tag and transmitting the data to the data management system; the data management system includes collecting, processing and storing the data transmitted from the reader / writer, and providing a device management interface and analysis tools;

[0013] Select RFID tags, deploy readers, attach tags to devices and program unique identification codes, establish a device information database and synchronize data, perform inspections and update the database by scanning tags, monitor device status in real time, and manage the uniqueness of devices.

[0014] As a preferred solution of the intelligent inspection optimization method for power production safety management described in the present invention, the adaptive control algorithm includes that during the inspection process, the system uses the adaptive control algorithm to dynamically adjust the inspection path, and the formula for calculating the dynamic inspection path adjustment coefficient is as follows:

[0015]

[0016] Among them, A is the dynamic inspection path adjustment coefficient, t0 is the initial time point, t is the current time point, n is the number of inspection points, x i is the position coordinate of the i-th inspection point, y i is the environmental parameter of the ith inspection point, f i (x i , t) is the position influence function of the i-th inspection point, g i (y i , t) is the environmental impact function of the ith inspection point, λ is the time decay factor, m is the number of parameters of the inspection path, z j is the jth inspection path parameter, h j (z j , t) is the influence function of the jth inspection path parameter, H j is the normalized constant of the jth inspection path parameter;

[0017] The f i (x i , t) The position influence function is:

[0018]

[0019] Among them, d i (t) is the distance from inspection point i to the adjacent inspection point, D max is the maximum permissible distance, e i (t) is the terrain complexity of inspection point i, E max is the maximum allowed terrain complexity, t i(t) is the traffic condition at inspection point i, and R max is the maximum allowable traffic condition. exp is the natural exponential function formula:

[0020] exp(x) = e x

[0021] where x is the input value;

[0022] The said g i (y i , t) environmental impact function is:

[0023]

[0024] where w i (t) is the weather condition at inspection point i, and W max is the maximum allowable weather condition, and s i (t) is the safety risk at inspection point i, and S max is the maximum allowable safety risk. exp is the natural exponential function;

[0025] The said h j (z j , t) inspection path parameter impact function is:

[0026]

[0027] where l j (t) is the length of inspection path j, and L max is the maximum allowable path length, and p j (t) is the slope of inspection path j, and P max is the maximum allowable slope. exp is the natural exponential function;

[0028] The value range of A is (0, ∞). When 0 < A ≤ 3, the inspection path does not need to be adjusted, and the current inspection task continues; when A > 3, the system triggers an adaptive control algorithm to adjust the inspection path, and collects device operation data according to the new path and uploads it to the device ledger database in real time.

[0029] As a preferred solution of the intelligent inspection optimization method for power safety production management described in the present invention, wherein: the association between the operation data and the basic information includes associating the real-time operation data collected from the new path with the basic information in the device ledger database, assigning a unique identifier RFID tag to the devices on the new route, and designing logical rules to associate the operation data with the device ledger information, and feeding back the associated new data to the system for storage in real time;

[0030] The said logical rules include device number matching, timestamp matching, data type matching, and data range matching.

[0031] As a preferred solution of the intelligent inspection optimization method for power production safety management described in the present invention, wherein: the quality inspection requirements include analyzing whether the equipment meets the requirements of completeness, accuracy, compliance, timeliness, problem handling and data analysis based on real-time data and equipment status in the system;

[0032] The completeness refers to whether all inspection items have been checked and recorded without omission; the accuracy refers to whether the inspection data reflects the actual status of the equipment, including operating parameters and fault conditions; the compliance refers to whether the inspection process complies with safety regulations, operating procedures and quality standards; the timeliness refers to whether the inspection tasks are completed within the specified time and whether emergency situations can be responded to in a timely manner; the problem handling refers to whether the problems found are correctly classified, recorded and handled, and whether the handling measures are effective; the data analysis refers to the trend analysis and failure rate analysis of the inspection data, and then the overall health status of the equipment is evaluated;

[0033] When the quality inspection requirements are met, the current operating status and equipment parameters of the equipment are maintained, and inspections continue along the current inspection route. When the quality inspection requirements are not met, the equipment is determined to be faulty, a temporary inspection task is added, and emergency inspections are performed on the faulty equipment. The inspection route is updated, and the operation, status, and equipment parameters of the faulty equipment are adjusted until the quality inspection requirements are met.

[0034] As a preferred solution of the intelligent inspection optimization method for power production safety management described in the present invention, the machine learning algorithm includes predictive analysis of equipment defects using a machine learning algorithm based on statistical inspection data and defect categories in the equipment ledger library. The algorithm formula is as follows:

[0035]

[0036] in, is the comprehensive score of equipment defect prediction, is the input feature vector, M is the machine learning model parameter set, T is the inspection cycle, v is the number of devices, is the defect probability, is the defect characteristic function of the oth device, is the normal operating characteristic function of the oth device, k is the time decay coefficient, t o is the inspection time of the oth device, V(τ) is the time-related influence function, r is the number of features, is the weight function of the qth feature, a is the feature weight adjustment coefficient, b q is the standard value of the qth feature, is the current value of the qth feature, p is the normalized index, and τ is the time;

[0037] Said The defect characteristic function is:

[0038]

[0039] Among them, B qo is the weight of the qth feature in the oth device, f qo (x qo ) is the eigenvalue conversion function of the qth feature in the oth device;

[0040] Said The normal operation characteristic function is:

[0041]

[0042] Among them, C qo is the normal weight of the qth feature in the oth device, g qo (x qo ) is the normal eigenvalue transfer function of the qth feature in the oth device;

[0043] in, The weight function is:

[0044]

[0045] Among them, α q is the weight adjustment coefficient of feature q, x q is the current value of feature q, μ q is the standard value of characteristic q;

[0046] The V(τ) time-dependent influence function is:

[0047] V(τ)=e -λτ

[0048] Among them, λ is the decay rate and τ is the time;

[0049] The value range of is (0, 1], when When , it is predicted that the device will not have any problems.

[0050] As a preferred solution of the intelligent inspection optimization method for power production safety management described in the present invention, the equipment maintenance and equipment parameter adjustment include predicting the defect status of the equipment through a machine learning algorithm, discovering potential faults in advance according to the comprehensive scores of different equipment defect predictions, and performing equipment maintenance and equipment parameter adjustment; when When the device is predicted to have defects and be in an abnormal operating state, the system issues instructions to adjust the device state and device parameters, and re-predicts the device defects until it is adjusted to a normal operating state; when When the device is predicted to be in normal operation without any defects, the system issues instructions to continue to maintain the current device status and parameters.

[0051] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of an intelligent inspection optimization method for power production safety management are implemented.

[0052] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of an intelligent inspection optimization method for power production safety management are implemented.

[0053] Beneficial effects of the present invention: The method of the present invention realizes the secure storage and rapid identification of equipment information by establishing a blockchain-based equipment ledger library and adopting radio frequency sensing technology for uniqueness management. The adaptive control algorithm dynamically adjusts the inspection path and provides real-time feedback of equipment operation data, thereby ensuring the flexibility and real-time nature of the inspection. By adding temporary and emergency inspection tasks and using machine learning algorithms for predictive analysis, the emergency handling capability of the inspection and the preventive maintenance level of the equipment are improved, thereby effectively improving the safety, stability and operation efficiency of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0055] Figure 1 A flowchart of an intelligent inspection optimization method for power production safety management provided by an embodiment of the present invention.

[0056] Figure 2 A schematic diagram of management software for an intelligent inspection optimization method for power production safety management provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0060] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0061] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0062] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0063] Example 1, reference Figure 1-Figure 2 , which is the first embodiment of the present invention, and provides an intelligent inspection optimization method for power production safety management, comprising:

[0064] S1: By collecting data, a blockchain-based equipment ledger database is established. Users customize inspection tasks based on the equipment ledger database information and use radio frequency sensing technology to manage the uniqueness of the equipment.

[0065] Furthermore, the data collection includes collecting basic equipment information, technical parameters, maintenance information, defect and failure history, and spare parts information;

[0066] It should be noted that the basic information of the equipment includes the equipment number, equipment name, equipment model, manufacturer, date of manufacture, date of commissioning, service life and installation location; the technical parameters include rated voltage, rated current, rated power, frequency, capacity and efficiency; the maintenance information includes maintenance cycle, last maintenance date and next maintenance date; the defect and fault history includes historical defect records, fault causes and repair measures; and the collected data is used to establish a blockchain-based equipment ledger library.

[0067] Furthermore, the establishment of the equipment ledger library based on blockchain includes conducting a demand analysis on the equipment ledger library management, selecting the Hyperledger Fabric blockchain platform and using the Chaincode smart contract development language to write functions, using IPFS to store blockchain data, developing an API interface, and interacting with the blockchain network through external systems;

[0068] The establishment of a blockchain-based equipment ledger library includes conducting a demand analysis on equipment ledger library management, selecting a Hyperledger Fabric blockchain platform and using the Chaincode smart contract development language to write functions, using IPFS to store blockchain data, developing an API interface, and interacting between external systems and the blockchain network;

[0069] The customized inspection task includes the following steps: the user logs in and authenticates on the Web interface, selects the equipment information in the equipment inventory library, selects the equipment to be inspected from the screening results and sets the inspection parameters, selects the inspection personnel and assigns the inspection task, and the user uses the map tool provided by the system to plan the inspection route according to the equipment location;

[0070] The radio frequency sensing technology includes RFID tags, RFID readers and data management systems;

[0071] The RFID tag is attached to the device, each tag has a unique identification code UID, and stores detailed information of the device; the RFID reader / writer includes reading the information on the tag and transmitting the data to the data management system; the data management system includes collecting, processing and storing the data transmitted from the reader / writer, and providing a device management interface and analysis tools;

[0072] Select RFID tags, deploy readers, attach tags to devices and program unique identification codes, establish a device information database and synchronize data, perform inspections and update the database by scanning tags, monitor device status in real time, and manage the uniqueness of devices.

[0073] S2: During the inspection process, the system uses an adaptive control algorithm to dynamically adjust the inspection path, collect equipment operation data, associate the operation data with basic information, and feed it back to the system in real time;

[0074] Furthermore, the adaptive control algorithm includes that during the inspection process, the system uses the adaptive control algorithm to dynamically adjust the inspection path, and the formula for calculating the dynamic inspection path adjustment coefficient is as follows:

[0075]

[0076] Among them, A is the dynamic inspection path adjustment coefficient, t0 is the initial time point, t is the current time point, n is the number of inspection points, x i is the position coordinate of the i-th inspection point, y i is the environmental parameter of the ith inspection point, f i (x i , t) is the position influence function of the i-th inspection point, g i (y i , t) is the environmental impact function of the ith inspection point, λ is the time decay factor, m is the number of parameters of the inspection path, z j is the jth inspection path parameter, h j (z j , t) is the influence function of the jth inspection path parameter, H j is the normalized constant of the jth inspection path parameter;

[0077] in, It is a summation expression that multiplies the influence functions and reflects the influence of the specific attributes of the inspection point on the inspection path selection. is an exponential decay function, indicating that as time goes by, the influence of past information on current decisions gradually weakens. λ is the time decay factor, which determines the speed of information decay.

[0078] in, It represents the cumulative amount of impact from t0 to t;

[0079] in, Represents the influencing factor of the normalized inspection path parameters;

[0080] in, It reflects the sum of squares of the influence of each parameter on the inspection path adjustment;

[0081] in, It reflects the average value of the total impact of all inspection path parameters on inspection path adjustment, and represents the comprehensive impact of inspection path adjustment;

[0082] It should be noted that the f i (x i , t) The position influence function is:

[0083]

[0084] Among them, d i (t) is the distance from inspection point i to the adjacent inspection point, D max is the maximum permissible distance, e i (t) is the terrain complexity of inspection point i, E max is the maximum allowed terrain complexity, t i (t) is the traffic condition at inspection point i, R max is the maximum permissible traffic condition, and exp is the natural exponential function formula:

[0085] exp(x) = e x

[0086] Where x is the input value;

[0087] in, The closer it is to zero, the smaller the influence of distance factor on inspection path selection; The closer it is to zero, the smaller the impact of terrain complexity on inspection path selection; The closer it is to zero, the less impact the traffic conditions at the inspection point have on the inspection route selection;

[0088] Among them, traffic conditions are to assign different weights to different traffic states by considering the influence of traffic flow, road conditions, traffic congestion and weather on inspection path selection, and then apply the weights to the location influence function;

[0089] The g i (y i , t) The environmental impact function is:

[0090]

[0091] Among them, w i (t) is the weather condition at inspection point i, W max is the maximum permissible weather condition, s i (t) is the safety risk of inspection point i, S maxis the maximum allowable safety risk, and exp is the natural exponential function;

[0092] Among them, the weather conditions are to assign weights to temperature, humidity, wind force, precipitation, and visibility and incorporate them into the environmental impact function. The safety risk is to assign weights to flammable and explosive substances, high-voltage areas, mechanical hazards, and biological hazards and incorporate them into the environmental impact function;

[0093] The described h j (z j , t) inspection path parameter influence function is:

[0094]

[0095] Among them, l j (t) is the length of the inspection path j, L max is the maximum allowable path length, p j (t) is the slope of the inspection path j, P max is the maximum allowable slope, and exp is the natural exponential function;

[0096] Furthermore, the value range of A is (0, ∞). When 0 < A ≤ 3, the inspection path does not need to be adjusted, and the current inspection task continues; when A > 3, the system triggers an adaptive control algorithm to adjust the inspection path, and collects device operation data according to the new path and uploads it to the device ledger database in real time;

[0097] The association of the operation data with the basic information includes associating the real-time operation data collected from the new path with the basic information in the device ledger database, assigning a unique identifier RFID tag to the devices on the new route, and designing logical rules to associate the operation data with the device ledger information, and feeding back the associated new data to the system in real time for storage;

[0098] The logical rules include device number matching, timestamp matching, data type matching, and data range matching.

[0099] S3: Analyze whether the device meets the quality inspection requirements according to the real-time data and device status in the system. When a fault occurs, add temporary inspection tasks and emergency inspection tasks for the fault, and update the inspection plan;

[0100] Further, the quality inspection requirements include analyzing whether the device meets the requirements of integrity, accuracy, compliance, timeliness, problem handling, and data analysis according to the real-time data and device status in the system;

[0101] It should be noted that the integrity refers to whether all inspection items have been checked and recorded without omission; the accuracy refers to whether the inspection data reflects the actual status of the equipment, including operating parameters and fault conditions; the compliance refers to whether the inspection process complies with safety regulations, operating procedures and quality standards; the timeliness refers to whether the inspection tasks are completed within the specified time and whether emergency situations can be responded to in a timely manner; the problem handling refers to whether the problems found are correctly classified, recorded and handled, and whether the handling measures are effective; the data analysis refers to the trend analysis and failure rate analysis of the inspection data, and then the overall health status of the equipment is evaluated;

[0102] When the quality inspection requirements are met, the current operating status and equipment parameters of the equipment are maintained, and inspections continue along the current inspection route. When the quality inspection requirements are not met, the equipment is determined to be faulty, a temporary inspection task is added, and emergency inspections are performed on the faulty equipment. The inspection route is updated, and the operation, status, and equipment parameters of the faulty equipment are adjusted until the quality inspection requirements are met.

[0103] S4: Based on the statistical inspection data and defect categories in the equipment ledger database, use machine learning algorithms to perform predictive analysis on equipment defects, discover potential faults in advance, and perform equipment maintenance and equipment parameter adjustments;

[0104] The machine learning algorithm includes predictive analysis of equipment defects using a machine learning algorithm based on statistical inspection data and defect categories in the equipment ledger library. The algorithm formula is as follows:

[0105]

[0106] in, is the comprehensive score of equipment defect prediction, is the input feature vector, M is the machine learning model parameter set, T is the inspection cycle, v is the number of devices, is the defect probability, is the defect characteristic function of the oth device, is the normal operating characteristic function of the oth device, k is the time decay coefficient, t o is the inspection time of the oth device, V(τ) is the time-related influence function, r is the number of features, is the weight function of the qth feature, a is the feature weight adjustment coefficient, b q is the standard value of the qth feature, is the current value of the qth feature, p is the normalized index, and τ is the time;

[0107] in, It is used to evaluate the abnormality of the equipment under specific characteristics. The ratio result is proportional to the possibility of equipment defects.

[0108] in, is the sum of the defect probability functions for each device;

[0109] in, is an exponential decay function, representing the effect of time on the function;

[0110] in, is the difference between the current value and the standard value;

[0111] in, It represents the use of weight function to normalize the data;

[0112] Among them, the normalized sum It helps to adjust the feature weights so that the sum is 1, thus balancing the relative importance of the features;

[0113] in, The entire summation expression is raised to the pth power and further normalized. The exponent p can be any positive number to further adjust the sum of feature weights.

[0114] Said The defect characteristic function is:

[0115]

[0116] Among them, B qo is the weight of the qth feature in the oth device, f qo (x qo ) is the eigenvalue conversion function of the qth feature in the oth device;

[0117] Said The normal operation characteristic function is:

[0118]

[0119] Among them, C qo is the normal weight of the qth feature in the oth device, g qo (x qo ) is the normal eigenvalue transfer function of the qth feature in the oth device;

[0120] in, The weight function is:

[0121]

[0122] Among them, α q is the weight adjustment coefficient of feature q, x q is the current value of feature q, μ q is the standard value of characteristic q;

[0123] The V(τ) time-dependent influence function is:

[0124] V(τ)=e -λτ

[0125] Among them, λ is the decay rate and τ is the time;

[0126] The value range of is (0, 1], when When When the device is predicted to have no problems;

[0127] The equipment maintenance and equipment parameter adjustment include predicting the defect status of the equipment through machine learning algorithms, discovering potential faults in advance according to the comprehensive scores of different equipment defect predictions, and performing equipment maintenance and equipment parameter adjustment; When the device is predicted to have defects and be in an abnormal operating state, the system issues instructions to adjust the device state and device parameters, and re-predicts the device defects until it is adjusted to a normal operating state; when When the device is predicted to be in normal operation without any defects, the system issues instructions to continue to maintain the current device status and parameters.

[0128] Embodiment 2, the second embodiment of the present invention, is different from the previous embodiment in that:

[0129] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0130] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0133] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0134] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent inspection optimization method for power production safety management, characterized by: include, By collecting data, a blockchain-based equipment ledger database is established. Users can customize inspection tasks based on the equipment ledger database information and use radio frequency sensing technology to manage the uniqueness of the equipment. During the inspection process, the system uses an adaptive control algorithm to dynamically adjust the inspection path, collect equipment operation data, associate the operation data with basic information, and feed it back to the system in real time; Analyze whether the equipment meets the quality inspection requirements based on the real-time data and equipment status in the system. When a fault occurs, add temporary inspection tasks and emergency inspection tasks for the fault, and update the inspection plan. Based on the statistical inspection data and defect categories in the equipment inventory database, machine learning algorithms are used to conduct predictive analysis of equipment defects, detect potential failures in advance, and perform equipment maintenance and equipment parameter adjustments.

2. The intelligent inspection optimization method for power production safety management according to claim 1, characterized in that: The collected data includes collecting basic equipment information, technical parameters, maintenance information, defect and failure history, and spare parts information; The basic equipment information includes equipment number, equipment name, equipment model, manufacturer, date of manufacture, date of commissioning, service life and installation location; the technical parameters include rated voltage, rated current, rated power, frequency, capacity and efficiency; the maintenance information includes maintenance cycle, last maintenance date and next maintenance date; the defect and fault history includes historical defect records, fault causes and repair measures.

3. The intelligent inspection optimization method for power production safety management according to claim 2, characterized in that: The establishment of a blockchain-based equipment ledger library includes conducting a demand analysis on equipment ledger library management, selecting the Hyperledger Fabric blockchain platform and using the Chaincode smart contract development language to write functions, using IPFS to store blockchain data, developing an API interface, and interacting between external systems and the blockchain network; The customized inspection task includes the following steps: the user logs in and authenticates on the Web interface, selects the equipment information in the equipment inventory library, selects the equipment to be inspected from the screening results and sets the inspection parameters, selects the inspection personnel and assigns the inspection task, and the user uses the map tool provided by the system to plan the inspection route according to the equipment location; The radio frequency sensing technology includes RFID tags, RFID readers and data management systems; The RFID tag is attached to the device, each tag has a unique identification code UID, and stores detailed information of the device; the RFID reader / writer includes reading the information on the tag and transmitting the data to the data management system; the data management system includes collecting, processing and storing the data transmitted from the reader / writer, and providing a device management interface and analysis tools; Select RFID tags, deploy readers, attach tags to devices and program unique identification codes, establish a device information database and synchronize data, perform inspections and update the database by scanning tags, monitor device status in real time, and manage the uniqueness of devices.

4. The intelligent inspection optimization method for power production safety management according to claim 3, characterized in that: The adaptive control algorithm includes that during the inspection process, the system uses the adaptive control algorithm to dynamically adjust the inspection path, and the formula for calculating the dynamic inspection path adjustment coefficient is as follows: Among them, A is the dynamic inspection path adjustment coefficient, t0 is the initial time point, t is the current time point, n is the number of inspection points, x i is the position coordinate of the i-th inspection point, y i is the environmental parameter of the ith inspection point, f i (x i , t) is the position influence function of the ith inspection point, g i (y i , t) is the environmental impact function of the ith inspection point, λ is the time decay factor, m is the number of parameters of the inspection path, z j is the jth inspection path parameter, h j (z j , t) is the influence function of the jth inspection path parameter, H j is the normalized constant of the jth inspection path parameter; The f i (x i , t) The position influence function is: Among them, d i (t) is the distance from inspection point i to the adjacent inspection point, D max is the maximum permissible distance, e i (t) is the terrain complexity of inspection point i, E max is the maximum allowed terrain complexity, t i (t) is the traffic condition at inspection point i, R max is the maximum permissible traffic condition, and exp is the natural exponential function formula: exp(x)=e x Where x is the input value; The g i (y i , t) The environmental impact function is: Among them, w i (t) is the weather condition at inspection point i, W max is the maximum permissible weather condition, s i (t) is the safety risk of inspection point i, S max is the maximum allowable safety risk, exp is the natural exponential function; The h j (z j , t) The inspection path parameter influence function is: Among them, l j (t) is the length of inspection path j, L max is the maximum allowed path length, p j (t) is the slope of inspection path j, P max is the maximum allowable slope, exp is the natural exponential function; The value range of A is (0, ∞). When 0 < A ≤ 3, the inspection path does not need to be adjusted, and the current inspection task continues; when A > 3, the system triggers an adaptive control algorithm to adjust the inspection path, and collects device operation data according to the new path and uploads it to the device ledger database in real time.

5. The intelligent inspection optimization method for power production safety management according to claim 4, characterized in that: The association between the operation data and the basic information includes associating the real-time operation data collected from the new path with the basic information in the device ledger database, assigning a unique identifier RFID tag to the devices on the new route, and designing logical rules to associate the operation data with the device ledger information, and feeding the associated new data back to the system for storage in real time; The logical rules include device number matching, timestamp matching, data type matching, and data range matching.

6. The intelligent inspection optimization method for power production safety management according to claim 5, characterized in that: The quality inspection requirements include analyzing whether the device meets the requirements of integrity, accuracy, compliance, timeliness, problem handling, and data analysis based on the real-time data and device status in the system; The integrity refers to whether all inspection items have been inspected and recorded without omission; the accuracy refers to whether the inspection data reflects the actual state of the device, including operation parameters and fault conditions; the compliance refers to whether the inspection process follows safety specifications, operating procedures, and quality standards; the timeliness refers to whether the inspection task is completed within the specified time and whether it can respond in a timely manner to emergencies; the problem handling refers to whether the problems found have been correctly classified, recorded, and processed, and whether the handling measures are effective; the data analysis refers to performing trend analysis and failure rate analysis on the inspection data to evaluate the overall health status of the device; When the quality inspection requirements are met, the current operating state and device parameters of the device are maintained, and the inspection continues along the current inspection route; When the quality inspection requirements are not met, it is determined that the device has a fault, a temporary inspection task is added, an emergency inspection is carried out on the faulty device, the inspection path is updated, and the operation, status, and device parameters of the faulty device are adjusted until the quality inspection requirements are met.

7. The intelligent inspection optimization method for power production safety management according to claim 6, characterized in that: The machine learning algorithm includes using the machine learning algorithm to perform predictive analysis on device defects according to the statistically collected inspection data and defect categories in the device ledger database. The algorithm formula is as follows: in, is the comprehensive score of equipment defect prediction, is the input feature vector, M is the machine learning model parameter set, T is the inspection cycle, v is the number of devices, is the defect probability, is the defect characteristic function of the oth device, is the normal operating characteristic function of the oth device, k is the time decay coefficient, t o is the inspection time of the oth device, V(τ) is the time-related influence function, r is the number of features, is the weight function of the qth feature, a is the feature weight adjustment coefficient, b q is the standard value of the qth feature, is the current value of the qth feature, p is the normalized index, and τ is the time; Said The defect characteristic function is: Among them, B qo is the weight of the qth feature in the oth device, f qo (x qo ) is the eigenvalue conversion function of the qth feature in the oth device; Said The normal operation characteristic function is: Among them, C qo is the normal weight of the qth feature in the oth device, g qo (x qo ) is the normal eigenvalue transfer function of the qth feature in the oth device; in, The weight function is: Among them, α q is the weight adjustment coefficient of feature q, x q is the current value of feature q, μ q is the standard value of characteristic q; The V(τ) time-related influence function is: V(τ)=e -λτ Where λ is the decay rate and τ is time; The value range of is (0, 1], when When , it is predicted that the device will not have any problems.

8. The intelligent inspection optimization method for power production safety management according to claim 7, characterized in that: The equipment maintenance and equipment parameter adjustment include predicting the defect status of the equipment through machine learning algorithms, discovering potential faults in advance according to the comprehensive scores of different equipment defect predictions, and performing equipment maintenance and equipment parameter adjustment; When the device is predicted to have defects and be in an abnormal operating state, the system issues instructions to adjust the device state and device parameters, and re-predicts the device defects until it is adjusted to a normal operating state; when When the device is predicted to be in normal operation without any defects, the system issues instructions to continue to maintain the current device status and parameters.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method described in any one of claims 1 to 8.

Images