Special equipment full-life-cycle safety management method based on big data
By assigning unique digital identification to special equipment and building an MGAN-LSTM algorithm model, integrating multi-source data and dynamic updates, the problem of insufficient information islands and risk warning in special equipment management is solved, management efficiency and prediction accuracy are improved, and security guarantees are achieved throughout the life cycle.
Patent Information
- Application Number
- CN202510364273.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-26
- Publication Date
- 2025-07-11
AI Technical Summary
The existing technology has problems such as information islands, insufficient risk warning, loose management processes and inefficient personnel management in the entire life cycle of special equipment, and information technology methods have failed to effectively integrate sensor real-time data and optimize risk models.
By assigning unique digital identifiers to each special device, collecting data in real time with the Internet of Things sensor network, integrating multi-source data using RESTful API and OPC UA protocol, and building a health prediction model based on the MGAN-LSTM algorithm to realize dynamic data updates and risk supervision collaborative decision-making.
It improves the efficiency of equipment information query, significantly improves prediction accuracy, and realizes hierarchical response instructions, providing comprehensive management guarantees for the entire life cycle safety of special equipment.
Smart Images

Figure CN120297943A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of special equipment safety management. Specifically, it relates to a method for the whole-life cycle safety management of special equipment based on big data. Background Art
[0002] In the process of the whole-life cycle safety management of special equipment, timely discovery and handling of potential fault hazards are the key to ensuring the safe and stable operation of the equipment. However, the traditional methods for the whole-life cycle safety management of special equipment often have the following technical defects: (1) Information silo problem: Data such as equipment ledgers, inspection records, and personnel qualifications are scattered in paper archives or independent systems, lacking a unified data platform, resulting in lagging information updates and difficult traceability; (2) Lack of risk warning: Relying on manual inspections and regular inspections, it is impossible to perceive the operating status of the equipment in real time (such as abnormal pressure, temperature, and vibration), and it is difficult to discover potential faults in a timely manner; (3) Loose management process: The hidden danger investigation is not carried out in a closed loop of "investigation - assessment - treatment - acceptance", the file records are incomplete, and the rectification process lacks dynamic tracking; (4) Inefficient personnel management: The verification of the qualifications of operating personnel relies on manual checking, and the training content is single, unable to improve skills targeted. In the prior art, some solutions attempt to introduce information technology means, but they still have the following deficiencies: The data collection only covers the basic ledger and does not integrate the real-time data of sensors; the risk model is static and not dynamically optimized in combination with the historical data of the equipment; the enterprise and government supervision platforms are not connected, and the compliance management cost is high. Summary of the Invention
[0003] The purpose of the present invention is to provide a method for the whole-life cycle safety management of special equipment based on big data, which can improve the management efficiency of special equipment and significantly reduce the probability of accidents.
[0004] The technical solution of the present invention is as follows:
[0005] In a first aspect, the present application provides a method for the whole-life cycle safety management of special equipment based on big data, which includes the following steps:
[0006] S1. Collect historical data of special equipment from multiple dimensions to establish a data set, and generate a unique digital identifier for each special equipment;
[0007] S2. Obtain the whole-life cycle information of special equipment based on the digital identifier of each special equipment through the RESTful API and OPC UA protocols;
[0008] S3. Construct a special equipment health prediction model through the MGAN-LSTM algorithm, and divide a training set from the data set to train the model;
[0009] S4. Input the full life cycle information of special equipment into the trained special equipment health prediction model to obtain the risk level of each special equipment, and conduct corresponding risk supervision collaboration and visualization decision-making based on the risk level.
[0010] Furthermore, in step S1, data preprocessing of the above dataset is also included, and the data preprocessing includes data cleaning, data standardization, and time alignment.
[0011] Furthermore, in step S1, the historical data of the above special equipment includes the service life of each equipment, the number of historical failures, and historical failure data.
[0012] Furthermore, in step S1, the above digital identification includes equipment code, model, factory date, inspection cycle, and safety accessory information.
[0013] Furthermore, in step S2, the full life cycle information of the above special equipment includes static data, dynamic data, and environmental data; among them, the static data includes the service life of the equipment and the number of historical failures, the dynamic data includes real-time pressure, temperature, and vibration amplitude, and the environmental data includes environmental temperature and humidity, operation load rate, inspection cycle, maintenance record, and real-time operation parameters of the equipment.
[0014] Furthermore, in step S3, the calculation process of constructing the special equipment health prediction model through the MGAN-LSTM algorithm includes:
[0015] Define a piecewise weight function by combining time decay and data anomaly degree:
[0016]
[0017] Embed the attention mechanism into the LSTM forget gate and design the gated attention unit GAU:
[0018]
[0019]
[0020] Loss function:
[0021]
[0022] Calculate the domain adversarial term:
[0023]
[0024] In the formula, w t represents the piecewise weight function, α represents the benchmark weight coefficient, β represents the time decay coefficient, T represents the service life of the equipment in service, t represents the current moment, λ is the anomaly gain coefficient, and ΔP tis the instantaneous pressure change rate, θ th is the threshold value represents the output of the forget gate of the gated attention unit (GAU), σ represents the forget gate coefficient, W f represents the trainable weight matrix of the input data, h t-1 represents the hidden state at time t-1, x t represents f represents the trainable weight matrix of the linear transformation of the attention value, Q is the attention weight, both represent the historical sensor data matrix, K, K i 、K j are both key vectors, V, V i represents the value vector, L total represents the total loss function, L MSE represents the predicted value of the remaining life of the device, η represents the weight adversarial coefficient, L domain represents the domain adversarial loss, N represents the number of historical failures, d i represents the data source label, x i represents the input data, D(x i ) represents the domain classifier.
[0025] In a second aspect, the present application provides an electronic device, including:
[0026] A memory for storing one or more programs;
[0027] A processor;
[0028] When the above one or more programs are executed by the above processor, a special equipment full-life cycle safety management method based on big data as described in any one of the first aspects above is implemented.
[0029] In a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, a special equipment full-life cycle safety management method based on big data as described in any one of the first aspects above is implemented.
[0030] Compared with the prior art, the present invention has at least the following advantages or beneficial effects:
[0031] (1) A safety management method for the whole life cycle of special equipment based on big data. By assigning a unique digital identifier to each special equipment, embedding the whole life cycle information of the equipment, and combining with the Internet of Things sensor network to collect operation parameters in real time, it realizes the dynamic identification threshold of one machine one code and multi-source data fusion. That is, it can integrate the data of enterprise ERP, inspection agency database and government supervision platform through standardized data interfaces (RESTful API, OPC UA protocol). At the same time, based on the Neo4j graph database, a whole life cycle equipment relationship graph is constructed, which can realize multi-dimensional data traceability and dynamic update, thus improving the query efficiency of equipment information.
[0032] (2) The present invention constructs a health prediction model for special equipment by introducing a multi-stage dynamic weight mechanism and a hybrid gated attention network MGAN-LSTM. Combining with the transfer learning strategy, it can dynamically adjust data according to the actual working conditions of the equipment, significantly improving the prediction accuracy, so as to realize hierarchical response instructions and provide guarantee for the safety of the whole life cycle of special equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.
[0034] Figure 1 It is a safety management method for the whole life cycle of special equipment based on big data of the present invention;
[0035] Figure 2 It is a schematic structural block diagram of an electronic device according to an embodiment of the present invention.
[0036] Icons: 101, memory; 102, processor; 103, communication interface. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0037] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Usually, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.
[0038] Accordingly, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts fall within the scope of protection of the present application.
[0039] It should be noted that like reference numerals and letters denote like items in the following accompanying drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.
[0040] It should be noted that in this text, the term "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article, or device. Without further limitation, elements defined by the statement "including..." "comprising..." do not exclude the presence of additional identical elements in the process, method, article, or device including the said elements.
[0041] The following will describe in detail some embodiments of the present application in conjunction with the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.
[0042] Embodiment 1
[0043] Please refer to Figure 1 , Figure 1 which shows a step diagram of a method for the whole life cycle safety management of special equipment based on big data provided by an embodiment of the present application.
[0044] S1. Collect historical data of special equipment from multiple dimensions to establish a data set, and generate a unique digital identifier for each piece of special equipment;
[0045] S2. Obtain the whole life cycle information of special equipment based on the digital identifier of each piece of special equipment through the RESTful API and OPC UA protocols;
[0046] S3. Construct a special equipment health prediction model through the MGAN-LSTM algorithm, and divide a training set from the data set to train the model;
[0047] S4. Input the whole life cycle information of special equipment into the trained special equipment health prediction model to obtain the risk level of each piece of special equipment, and perform corresponding risk supervision coordination and visualization decision-making according to the risk level.
[0048] Among them, risk supervision collaboration and visualization decision-making include hidden danger investigation, emergency drills, personnel qualification and intelligent training, inspection records of evidence-preserving equipment, hidden danger rectification reports, and visualization modules; hidden danger investigation mainly involves inspectors scanning the equipment identification through Android / iOS terminals to retrieve preset inspection checklists (including 50 standardized inspection items, such as "validity period of safety valve calibration" and "wire rope wear rate"); voice input, photo evidence collection, and AI image recognition (such as crack and corrosion recognition) are supported, and a hidden danger report in PDF format is automatically generated; the system assigns rectification responsible persons according to the hidden danger level (Level I / II / III), and if it is not processed beyond the due date, it will be automatically escalated to the higher-level management department; emergency drills mainly include: accessing the emergency plan library, when the equipment triggers a high-risk warning, the system automatically matches the plan (such as "pressure vessel leakage disposal process"), pushes operation guidelines through AR glasses, the whole process of the drill is recorded, and key actions (such as valve closing speed) are scored by AI algorithms to generate a drill evaluation report; personnel qualification and intelligent training include: building an electronic personnel file library, binding the ID number and special operation permit number (real-time verification with the "National Special Equipment Publicity Information Query Platform"), developing a VR training module using the Unity 3D engine to simulate special equipment failure scenarios (such as crane hoisting imbalance and boiler overpressure), uploading the operation data of the trainees (response time, operation sequence) to the cloud to generate a personal ability profile, and 30 days before the qualification expires, triple reminders are sent through text messages, enterprise WeChat, and pop-up windows on the data center large screen; inspection records of evidence-preserving equipment mainly use blockchain technology to preserve inspection records of evidence-preserving equipment and hidden danger rectification reports to ensure that the data cannot be tampered with and synchronize them to the government supervision platform; the visualization module provides an equipment health heat map, a hidden danger rectification dashboard, and a personnel ability matrix by the data cockpit. The equipment health heat map is used to mark the distribution of high-risk equipment based on the GIS map, the hidden danger rectification dashboard is used to count the number of hidden dangers not processed beyond the due date by department, and the personnel ability matrix is used to display the training pass rate and qualification effectiveness of each team.
[0049] It should be noted that in this embodiment, the risk levels and response mechanisms of special equipment include: low risk level, triggering the response mechanism: automatically generating a maintenance suggestion work order and pushing it to the mobile terminal of the operation and maintenance personnel; medium risk level, triggering the response mechanism: restricting the equipment usage load and starting a re-inspection process within 48 hours; high risk level, triggering the response mechanism: automatically cutting off the power source of the equipment, simultaneously triggering an audible and visual alarm, and reporting to the local supervision department.
[0050] As a preferred implementation method, in step S1, data preprocessing of the data set is also included, and the data preprocessing includes data cleaning, data standardization, and time alignment.
[0051] As a preferred implementation method, in step S1, the historical data of special equipment includes the equipment service life, historical failure times, and historical failure data of each piece of equipment.
[0052] As a preferred implementation, in step S1, the digital identifier includes device code, model, factory date, inspection period, and safety accessory information.
[0053] It should be noted that the digital identifier can be an encrypted QR code or a UHF RFID tag.
[0054] As a preferred implementation, in step S2, the whole life cycle information of special equipment includes static data, dynamic data, and environmental data; among them, the static data includes the service life of the equipment and the number of historical failures, the dynamic data includes real-time pressure, temperature, and vibration amplitude, and the environmental data includes environmental temperature and humidity, operation load rate, inspection period, maintenance records, and real-time operation parameters of the equipment.
[0055] As a preferred implementation, in step S3, the calculation process of constructing a health prediction model for special equipment by the MGAN-LSTM algorithm includes:
[0056] Combining time decay and data anomaly degree to define a piecewise weight function:
[0057]
[0058] Embedding the attention mechanism into the LSTM forget gate to design a gated attention unit GAU:
[0059]
[0060]
[0061] Loss function:
[0062]
[0063] Calculating the domain adversarial term:
[0064]
[0065] In the formula, w t represents the piecewise weight function, α represents the benchmark weight coefficient, β represents the time decay coefficient, T represents the service life of the equipment, t represents the current moment, λ is the anomaly gain coefficient, ΔP t is the instantaneous pressure change rate, θ th is the threshold value, represents the output of the forget gate of the gated attention unit (GAU), σ represents the forget gate coefficient, W f represents the trainable weight matrix of the input data, h t-1 represents the hidden state at time t-1, x t represents, U fA trainable weight matrix representing the linear transformation of the attention value, Q is the attention weight, both representing the historical sensor data matrix, K, K i 、K j are all key vectors, V, V i represent value vectors, L total represents the total loss function, L MSE represents the predicted value of the remaining life of the device, η represents the weight adversarial coefficient, L domain represents the domain adversarial loss, N represents the number of historical failures, d i represents the data source label, x i represents the input data, D(x i ) represents the domain classifier.
[0066] Embodiment 2
[0067] Please refer to Figure 2 , Figure 2 which is a schematic structural block diagram of an electronic device provided by an embodiment of the present application.
[0068] An electronic device includes a memory 101, a processor 102, and a communication interface 103. The memory 101, the processor 102, and the communication interface 103 are electrically connected directly or indirectly to each other to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules. The processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used to communicate signaling or data with other node devices.
[0069] Among them, the memory 101 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.
[0070] The processor 102 can be an integrated circuit chip with signal processing capabilities. The processor 102 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0071] It can be understood that the structure shown in the figure is only schematic. A special equipment full-life-cycle safety management method based on big data may also include more or fewer components than those shown in the figure, or have a different configuration from that shown in the figure. Each component shown in the figure can be implemented by hardware, software, or a combination thereof.
[0072] In the embodiments provided in this application, it should be understood that the disclosed method can also be implemented in other ways. The above-described embodiments are merely illustrative. For example, the flowcharts or block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the methods and computer program products according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.
[0073] In addition, in each embodiment of this application, the functional modules can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.
[0074] When the above-mentioned functions are implemented in the form of software function modules 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 this application, in essence, or the part that contributes to the prior art or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.
[0075] The above are only the preferred embodiments of this application and are not used to limit this application. For those skilled in the art, this application can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.
[0076] For those skilled in the art, it is obvious that this application is not limited to the details of the above-mentioned exemplary embodiments, and without departing from the spirit or basic characteristics of this application, this application can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of this application is defined by the appended claims rather than the above description. Therefore, it is intended to embrace all changes that fall within the meaning and scope of the equivalent elements of the claims in this application. Any reference signs in the claims should not be regarded as limiting the claimed rights.
Claims
1. A safety management method for the whole life cycle of special equipment based on big data, characterized in that, It includes the following steps: S1. Collect historical data of special equipment from multiple dimensions to establish a data set, and generate a unique digital identifier for each special equipment; S2. Obtain the full life cycle information of special equipment through the RESTful API and OPC UA protocols based on the digital identifier of each special equipment; S3. Construct a health prediction model for special equipment through the MGAN-LSTM algorithm, and divide a training set from the data set to train the model; S4. Input the full life cycle information of special equipment into the trained health prediction model of special equipment to obtain the risk level of each special equipment, and perform corresponding risk supervision coordination and visualization decision-making according to the risk level.
2. The safety management method for the whole life cycle of special equipment based on big data according to claim 1, characterized in that, In step S1, data preprocessing of the data set is further included, and the data preprocessing includes data cleaning, data standardization and time alignment.
3. The safety management method for the whole life cycle of special equipment based on big data according to claim 1, characterized in that In step S1, the historical data of the special equipment includes the service life of each equipment, the number of historical failures and historical failure data.
4. The safety management method for the whole life cycle of special equipment based on big data according to claim 1, characterized in that In step S1, the digital identifier includes equipment code, model, factory date, inspection cycle and safety accessory information.
5. The safety management method for the whole life cycle of special equipment based on big data according to claim 1, characterized in that, In step S2, the full life cycle information of the special equipment includes static data, dynamic data and environmental data; among them, the static data includes the service life of the equipment and the number of historical failures, the dynamic data includes real-time pressure, temperature and vibration amplitude, and the environmental data includes environmental temperature and humidity, operation load rate, inspection cycle, maintenance record and real-time operation parameters of the equipment.
6. The safety management method for the whole life cycle of special equipment based on big data according to claim 1, characterized in that, In step S3, the calculation process of constructing a health prediction model for special equipment through the MGAN-LSTM algorithm includes: Define a piecewise weight function by combining time decay and data anomaly degree: Embed the attention mechanism into the LSTM forget gate and design a gated attention unit GAU: Loss function: Calculate the domain adversarial term: where, w t represents a piecewise weight function, α represents a reference weight coefficient, β represents a time decay coefficient, T represents the service life of the equipment, t represents the current moment, λ is an abnormal gain coefficient, and ΔP t is the instantaneous pressure change rate, and θ th is the threshold value, represents the output of the forget gate of the gated attention unit (GAU), σ represents the forget gate coefficient, W f represents the trainable weight matrix of the input data, h t-1 represents the hidden state at time t-1, x t represents, U f represents the trainable weight matrix of the linear transformation of the attention value, Q is the attention weight, both represent the historical sensor data matrix, K, K i 、K j are both key vectors, V, V i represent value vectors, L total represents the total loss function, L MSE represents the predicted value of the remaining life of the equipment, η represents the weight adversarial coefficient, L domain represents the domain adversarial loss, N represents the number of historical failures, d i represents the data source label, x i represents the input data, and D(x i ) represents the domain classifier.
7. An electronic device, characterized in that, Include: A memory for storing one or more programs; A processor; When the one or more programs are executed by the processor, a safety management method for the full life cycle of special equipment based on big data as described in any one of claims 1-6 is implemented.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, a safety management method for the full life cycle of special equipment based on big data as described in any one of claims 1-6 is implemented.
Citation Information
Cited By
Electronic equipment dynamic management method and system based on risk grading
CN120952562A
A special equipment whole life cycle digital management system and method
CN122509836A