TTF distribution calculation method and system for nuclear control power supply device based on fusion model

Abstract

The present invention discloses a method and system for calculating the TTF distribution of a nuclear-controlled power supply unit based on a fusion model. The method comprises: obtaining first and second data; the first data being parameters of the nuclear-controlled power supply unit before and after failure, and the second data being historical usage data of the nuclear-controlled power supply unit; constructing a failure physics sub-model and a data-driven sub-model based on the first and second data; fusing the failure physics sub-model and the data-driven sub-model to obtain a data-driven model with an embedded failure mechanism, i.e., a fusion model; constructing and training a TTF distribution calculation model based on the fusion model; and fitting and calculating the TTF probability distribution of the nuclear-controlled power supply unit based on the TTF distribution calculation model. The present invention provides decision support for proactive operation and maintenance systems, reduces reactor operation risks and maintenance costs, and improves safe operation and support capabilities.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear control rod drive power supply and electronic equipment fault prediction, and in particular to a TTF distribution calculation method and system for a nuclear control power supply device based on a fusion model. Background Art

[0002] Nuclear energy is a low-carbon, clean and efficient energy source. The development of nuclear energy has become an important means for my country to ensure energy security and optimize its energy structure. Nuclear safety is the lifeline of nuclear energy development. On the other hand, the technical and economic feasibility of nuclear energy is also receiving more and more attention. The nuclear control power supply device is one of the important equipment for reactor control. It performs normal reactor startup and shutdown functions according to the operator's instructions, and manually operates the control rods to change the core reactivity under various effective working conditions; and performs safe shutdown and power reduction operation functions according to the operator or protection system instructions; when the reactor power is automatically adjusted, the regulating pound group receives the automatic rod speed signal and direction signal sent by the reactor control system through the rod control system, so that the reactor power automatically tracks the load changes and maintains it at the required power level. The external interface between the nuclear control power supply device and the reactor control, protection and other devices is as follows: Figure 1 shown.

[0003] Although nuclear power supply units undergo rigorous inspection during manufacturing, they often experience malfunctions over time, necessitating inspection and repair. The quality of maintenance work on these units directly reflects the overall reactor instrumentation and control system's reliability and is crucial for the reactor's safety and economic viability. Currently, maintenance personnel lack effective specialized tools or technical means to monitor the operating status of nuclear power supply units, identify potential equipment failures, and assess their performance. This limits the targeted, timely, and effective nature of maintenance activities.

[0004] Currently, reliability estimates for reactor instrumentation and control system equipment are still at a preliminary level. They primarily use prototype testing or general physics of failure models for key components to calculate the time to failure (TTF) for individual samples and then integrate data from multiple samples to calculate the mean time to failure (MTTF). This statistical approach, which uses the MTTF derived from individual TTF estimates, ignores the impact of uneven TTF distribution and fails to reflect the true distribution of equipment TTF. The resulting estimates have significant errors, making it difficult to provide accurate decision-making information for proactive operations and maintenance, and insufficient to meet users' urgent needs for equipment O&M assurance.

[0005] In view of this, this application is hereby filed. Summary of the Invention

[0006] The purpose of the present invention is to provide a TTF distribution calculation method and system for nuclear control power supply devices based on a fusion model. By collecting and organizing the failure data of nuclear control power supply devices and analyzing the failure mechanisms of equipment under different operating conditions, a reliability prediction method suitable for reactor instrumentation and control systems is formed. The probability distribution of the time to failure (TTF) of nuclear control power supply devices is calculated with a small prediction error, providing decision support for the active operation and maintenance system, reducing the operating risks and maintenance costs of reactors, and improving the level of safe operation and guarantee capabilities.

[0007] The present invention is achieved through the following technical solutions:

[0008] In a first aspect, the present invention provides a method for calculating TTF distribution of a nuclear-controlled power supply device based on a fusion model, the method comprising:

[0009] Acquire first data and second data; the first data is data parameters of the nuclear-controlled power supply device before and after failure, and the second data is historical usage data of the nuclear-controlled power supply device;

[0010] Based on the first data and the second data, a failure physics sub-model and a data-driven sub-model are constructed; and the failure physics sub-model and the data-driven sub-model are fused to obtain a data-driven model with an embedded fault mechanism, i.e., a fusion model;

[0011] Based on the fusion model, a TTF distribution calculation model is constructed and trained; based on the TTF distribution calculation model, the TTF probability distribution of the nuclear-controlled power supply device is obtained by fitting calculation.

[0012] Furthermore, the method further includes: setting an alarm to provide a repair or replacement time for the nuclear control power supply device according to the TTF probability distribution.

[0013] Furthermore, the data parameters include temperature data, voltage and current data, and control signal data;

[0014] The temperature data is the temperature data measured for the full-bridge IGBT device;

[0015] The voltage and current data include the voltage and current data measured on the bus, the phase voltage and current data measured on the output three-phase AC power supply, and the current and voltage data measured on the optocoupler and electrolytic capacitor;

[0016] The control signal data is the IGBT drive signal phase sequence difference data measured for the full-bridge IGBT control signal.

[0017] Furthermore, a failure physics sub-model and a data-driven sub-model are constructed, including:

[0018] The construction process of the failure physics sub-model is as follows:

[0019] Analyze the failure mechanism of the drive module and key components of the nuclear power supply device, study the aging failure mechanism of the drive module and key components under the optimal characteristic parameter failure mode, and determine the failure symptoms and characteristic parameters;

[0020] Based on the failure mechanism, a multi-failure mechanism physical evolution model of key components and drive modules is established and used as a failure physics sub-model;

[0021] The effectiveness of selecting characteristic parameters for the aging process of each device was verified through simulation, and the effectiveness of failure mechanism analysis of key components was verified through accelerated aging experiments on IGBTs, capacitors, and optocouplers.

[0022] The construction process of the data-driven sub-model is as follows:

[0023] Clarify the aging and failure characteristic parameters of the driving module and its key components, build a database of aging and failure characteristic parameters of the driving module and key components, and analyze the coupling relationship between each key aging characteristic parameter and the aging characteristic parameter of the driving board to obtain a data-driven sub-model.

[0024] Furthermore, a TTF distribution calculation model is constructed and trained, including:

[0025] Integrate the failure mechanism model of IGBT devices and find the operating boundaries and model initial values ​​of the failed devices; construct the boundary residual term, model residual term, and key characteristic data residual term of the fusion model; the key characteristic data residual term includes characteristic parameters such as temperature, current, and voltage of key nodes;

[0026] A multi-input and multi-output neural network is constructed, and the activation function of the neural network is defined as tanh and normal Glorot initialization. After defining the optimization domain of each residual, an overall loss function is constructed, which includes boundary residual terms, model residual terms, and key feature data residual terms. Based on this, the constraint functions of the mathematical model of multiple failure mechanisms, the residual functions of the target value and the actual estimated value, the constraint functions of the initial conditions and boundary conditions, and other relevant physical system information are substituted into the loss function of the neural network through operators.

[0027] Use automatic differentiation technology to construct Jacobi matrix and Hessian matrix modules, and implement high-order differential calculations through nesting; set the optimizer mode, learning rate, number of iterations and loss weight, and compile the fusion model; and train the neural network through gradient descent and minimize the loss function to find the optimal value until the loss drops below the set value, obtaining a trained fusion model.

[0028] Furthermore, based on the TTF distribution calculation model, the TTF probability distribution of the nuclear-controlled power supply device is obtained by fitting and calculation, including:

[0029] Determine failure symptoms and characteristic parameters, and use failure threshold setting and TTF distribution calculation model to perform data trend analysis and Trend function estimation on important parameters and time;

[0030] The remaining life of the nuclear control power supply device is estimated by using the time when the parameter does not exceed the failure threshold; and the TTF distribution calculation model is repeated multiple times to fit the TTF probability distribution of the nuclear control power supply device.

[0031] In a second aspect, the present invention further provides a TTF distributed calculation system for a nuclear-controlled power supply device based on a fusion model, the system comprising:

[0032] an acquisition unit, configured to acquire first data and second data; the first data being data parameters of the nuclear-controlled power supply device before and after failure, and the second data being historical usage data of the nuclear-controlled power supply device;

[0033] a model construction unit for constructing a failure physics sub-model and a data-driven sub-model based on the first data and the second data; fusing the failure physics sub-model and the data-driven sub-model to obtain a data-driven model with an embedded fault mechanism, i.e., a fusion model; and constructing and training a TTF distribution calculation model based on the fusion model;

[0034] The TTF calculation unit is used to obtain the TTF probability distribution of the nuclear control power supply device by fitting calculation based on the TTF distribution calculation model.

[0035] Furthermore, the system also includes:

[0036] The alarm unit is used to set an alarm based on the TTF probability distribution to provide the repair or replacement time of the nuclear control power supply device.

[0037] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned TTF distribution calculation method for a nuclear-controlled power supply device based on a fusion model is implemented.

[0038] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned TTF distribution calculation method for a nuclear-controlled power supply device based on a fusion model.

[0039] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0040] 1. The present invention provides a method and system for calculating the TTF distribution of nuclear power supply devices based on a fusion model. By collecting and organizing failure data of nuclear power supply devices and analyzing the failure mechanisms of the equipment under different operating conditions, a reliability prediction method suitable for reactor instrumentation and control systems is formed. The method calculates the probability distribution of the TTF of the nuclear power supply device before failure, with a small prediction error. This provides decision support for the proactive operation and maintenance system, reduces reactor operation risks and maintenance costs, and improves the level of safe operation and guarantee capabilities.

[0041] 2. The present invention's fusion-model-based TTF distribution calculation method and system for nuclear-controlled power supply devices demonstrates a high degree of fit between physical test data and historical operation and maintenance data during equipment operation and maintenance activities, resulting in superior prediction results. This eliminates the need for a fuzzy fixed-value estimate of the TTF reliability prediction index for this type of equipment. Based on specific data and model inputs, multiple sets of characteristic parameter degradation curves and the equipment's TTF life distribution can be derived. This facilitates user access to equipment failure information throughout its lifecycle, enabling understanding and prediction of equipment failures and proactive equipment operation and maintenance. Unexpected failures trigger a simple maintenance activity, enabling autonomous maintenance and reducing usage and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0043] Figure 1 A schematic diagram of the external interface between the nuclear control power supply device and the reactor control and protection devices;

[0044] Figure 2 Schematic diagram of the TTF distribution calculation process based on PIML of the present invention;

[0045] Figure 3 This is a flow chart of the TTF distribution calculation method for a nuclear-controlled power supply device based on a fusion model of the present invention;

[0046] Figure 4 This is a schematic diagram of the PINN principle of the present invention;

[0047] Figure 5 This is a schematic diagram of the Deep Operator Net principle of the present invention;

[0048] Figure 6 This is a schematic diagram of the process of Example 1 of the present invention;

[0049] Figure 7 This is a system framework diagram of the failure data acquisition device of the present invention;

[0050] Figure 8This is a technical flow chart for analyzing the aging failure mechanism of key components based on the failure physics sub-model of the present invention;

[0051] Figure 9 A technical roadmap for selecting aging characteristic parameters of driver modules based on the data-driven sub-model of the present invention;

[0052] Figure 10 This is a structural block diagram of the TTF distributed calculation system of the nuclear-controlled power supply device based on the fusion model of the present invention. DETAILED DESCRIPTION

[0053] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0054] Currently, the most sophisticated TTF calculation techniques all employ a "fusion" approach that combines the aforementioned two approaches. This approach integrates failure prediction monitoring and reasoning with the physics of failure (PoF) modeling approach to achieve the full goals of the calculation system, leveraging the strengths of each approach to overcome the limitations of each approach alone. Failure prediction monitoring and reasoning can provide a certain level of equipment lifecycle status assessment when sufficient data is available; while the PoF modeling approach helps identify the root cause of failure and provides thresholds for system parameters and failure definitions, thereby supporting TTF assessment. Ultimately, the two prediction results are combined in a weakly competitive decision-making process to produce a comprehensive TTF assessment report. This "fusion" approach leverages the strengths of both approaches, complementing their weaknesses and providing a comprehensive decision-making process. While it possesses considerable technical sophistication and engineering application value, its reliability prediction results are low in accuracy and generally overly conservative. This fundamental reason stems from a failure to effectively integrate the industry's historical experience and modeling with existing historical failure data and real-time monitoring data. Instead, the two prediction approaches operate largely independently, with significant overlap and coupling between their inputs.

[0055] Ultimately, all our knowledge stems from empirical data. In the past, humans developed vast knowledge model systems through methods like analysis, deduction, fitting, and induction. Later, the development of machine learning fully explored information previously considered useless and chaotic, allowing for further learning and understanding of these systems. We now need a more comprehensive learning machine to comprehensively re-integrate and cognitively learn from both sources of knowledge. From the outset, we should imbue learning models with valuable prior knowledge, laws, and connotations derived from human society. This will enable a true fusion of knowledge-based model methods and data-driven technologies, enabling TTF computing technology to address complex nonlinear systems, coupled failure mechanisms, and even chaotic systems.

[0056] To ensure that nuclear power supply units can perform their specific functions within their expected lifespan, guarantee safe and reliable operation, and reduce reactor operational risks and maintenance costs, while also meeting the urgent needs of equipment users to improve safety and support capabilities, it is imperative to conduct reliability analysis and prediction of reactor instrumentation and control system equipment, particularly nuclear power supply units. By collecting and organizing failure data on nuclear power supply units and analyzing their failure mechanisms under different operating conditions, a reliability prediction method suitable for reactor instrumentation and control systems is developed. The probability distribution of the time to failure (TTF) of nuclear power supply units is calculated, providing decision support for proactive operation and maintenance systems, reducing reactor operational risks and maintenance costs, and improving safe operation and support capabilities.

[0057] The technical route of the present invention is:

[0058] First, the data parameters of the nuclear power supply unit before and after failure, as well as the historical usage data of the nuclear power supply unit, must be fully monitored, collected, and recorded. Furthermore, a thorough understanding of the physical model laws of electronic components, printed circuit boards, through-holes, connecting wires, and other components at all levels within the system must be acquired to provide the necessary information for the establishment of models and algorithms for detecting and predicting equipment status.

[0059] Secondly, the sensor system processes and stores the collected data, provides a processing method, and performs real-time analysis and feature extraction on the sensor data by integrating the data-driven method and the PoF method.

[0060] Then, through data monitoring and analysis, when abnormal performance is detected, the parameters causing the abnormality are isolated. Correlated parameters that reflect or cause changes in equipment performance are identified. Established Point of Failure (PoF) modeling methods can be used to identify failures and isolate parameters. Based on the extracted features, the fault baseline is then compared with the features of the monitoring data to detect anomalies.

[0061] Furthermore, a database is established by combining isolation parameters, monitoring data, and historical data to provide data support for the subsequent DeepONet and embedded physical mechanism neural network (PINN) learning models. Furthermore, knowledge such as the physical model rules at each level is integrated and collected to establish a PoF-based knowledge base, providing physical information embedding for the subsequent embedded physical mechanism machine learning (PIML) model. The DeepONet-based learning model can supplement the PoF knowledge base with models or parameters based on database input. This approach can be used to fill gaps or remodel for different failure mechanisms or situations that exceed the failure threshold defined by the selected PoF model.

[0062] Finally, comprehensively determine the failure signs and characteristic parameters, use the failure threshold setting and the two aforementioned methods (rich PoF knowledge base and PINN model) to estimate the trend function of important parameters and time, and use the time (TTF) when the parameters do not exceed the failure threshold to estimate the remaining life of the equipment. Repeat the above evaluation method multiple times to fit the TTF probability distribution of the equipment. Set an alarm based on the calculated TTF distribution to provide a reasonable repair or replacement time for the equipment. The schematic diagram of the TTF distribution calculation process based on PIML is shown as follows: Figure 2 shown.

[0063] The technology of the present invention combines the latest research results in artificial intelligence and data science for solving partial differential equation problems. It is a deep fusion of two major technical routes in the existing TTF calculation field. It has the potential to develop into a complete solution to this type of TTF calculation problem, and has significant research value and field development connotations. Currently, the research direction of deeply integrating physical models and data science is relatively blank in the field of TTF prediction and calculation of electronic products in China. It introduces the physical information of existing knowledge models accumulated in the industry into the architectural design of the learning model. It can improve the algorithm prediction performance of TTF calculation technology in situations such as insufficient data volume or poor data quality, traditional methods of physical model laws are difficult to analyze, there are multiple failure mechanism models in the system, and the interaction between them is difficult to decouple, and existing models for complex systems are not applicable. It can also expand the existing knowledge model library, improve the ability to fill gaps in existing knowledge models, and improve the ability to establish analytical degradation models for complex coupled systems such as board-level and system-level. Currently, the difficulties in the practical application of the above-mentioned TTF calculation technology exist not only in the field of reactor instrumentation and control equipment, but also in various industries.

[0064] In equipment operation and maintenance support activities, this calculation method achieves a high degree of fit between physical test data and historical operation and maintenance data, resulting in excellent prediction results. This eliminates the need for a fuzzy fixed-value estimate of the TTF reliability prediction index for this type of equipment. Based on specific data and model inputs, multiple sets of characteristic parameter degradation curves and the equipment's TTF life distribution can be derived. This helps users understand failure information throughout the equipment's lifecycle, understand and predict when equipment failure will occur, and conduct proactive equipment operation and maintenance. When an unexpected failure occurs, a simple maintenance activity is triggered, enabling autonomous support and reducing usage and support costs.

[0065] Example 1

[0066] like Figure 3 and Figure 6 As shown, the present invention provides a method for calculating TTF distribution of a nuclear-controlled power supply device based on a fusion model, the method comprising:

[0067] Step 1: Acquire first data and second data; the first data is the data parameters of the nuclear-controlled power supply device before and after failure, and the second data is the historical usage data of the nuclear-controlled power supply device;

[0068] Step 2: constructing a failure physics sub-model and a data-driven sub-model based on the first data and the second data; and fusing the failure physics sub-model and the data-driven sub-model to obtain a data-driven model with an embedded fault mechanism, i.e., a fusion model;

[0069] Step 3: Based on the fusion model, a TTF distribution calculation model is constructed and trained; based on the TTF distribution calculation model, a TTF probability distribution of the nuclear-controlled power supply device is obtained by fitting and calculation.

[0070] Step 4: Based on the TTF probability distribution, set an alarm to provide the repair or replacement time of the nuclear control power supply device.

[0071] The present invention is designed based on key equipment such as nuclear control power supply devices in the reactor instrumentation and control system, collects data from the system instrumentation and control equipment testing and operation and maintenance processes, develops a failure data acquisition device, uses data-driven and failure physical models as analysis inputs, constructs a dynamic, closed-loop instrumentation and control product reliability index prediction technology, grasps the failure laws of nuclear control power supply devices and their key components, and provides technical support for the proactive operation and maintenance and reliability improvement of nuclear control power supply devices.

[0072] In this embodiment, the present invention is based on a set of data acquisition devices for nuclear control power supply devices to carry out the collection of fault data. Considering both software and hardware aspects, the acquisition device automatically collects and records according to the preset configuration, judges the correctness of the test results, and can generate corresponding analysis tables for the test results. The data stored in the data acquisition device can be exported through storage media or communication networks, which can meet the requirements of application scenarios such as factory, on-site, and portable testing. Failure data of equipment during operation and maintenance is collected, and accelerated life tests of equipment, boards and devices are carried out. The acquisition device is used to monitor and record the failure and aging process of key nodes of the equipment in real time, including failure data measurement of key components. The current front-end acquisition is realized by the Hall sensor, the voltage signal front-end acquisition is realized by the precision resistor voltage divider method, and the temperature signal acquisition is realized by the NTC temperature sensor. The system framework of the data acquisition device is as follows: Figure 7 shown.

[0073] The data acquisition device realizes the following functions: (1) temperature measurement and real-time monitoring of full-bridge IGBT devices; (2) bus voltage and current measurement; (3) phase voltage and current measurement of output three-phase AC power supply; (4) full-bridge IGBT control signal measurement and IGBT drive signal phase sequence difference measurement; (5) current and voltage measurement of optocouplers and electrolytic capacitors; (6) temperature, voltage, current and control signal waveform generation, and the waveform status can be recorded through the host computer software.

[0074] Based on the above, we can know that:

[0075] The data parameters of the present invention include temperature data, voltage and current data, and control signal data; wherein the temperature data is the temperature data measured for the full-bridge IGBT device; the voltage and current data include the voltage and current data measured for the bus, the phase voltage and current data measured for the output three-phase AC power supply, and the current and voltage data measured for the optocoupler and electrolytic capacitor; and the control signal data is the phase sequence difference data of the IGBT drive signal measured for the full-bridge IGBT control signal.

[0076] The historical usage data of the present invention includes environmental parameters and parameters of the nuclear-controlled power supply device under various working conditions.

[0077] In this embodiment, a system functional principle model is established based on the hierarchical composition of the nuclear power supply system, including the entire system, various functional subsystems, key circuit components, and core elements. Based on this model, reliability analysis is conducted based on the system-level model, searching for potential failure modes of the system based on multiple failure cues. The functional relationships between various units are analyzed, and the key components and failure modes that have a significant impact on system reliability are identified. This allows the establishment of a system-level reliability analysis model for the nuclear power supply system.

[0078] Based on the typical mission environment of a nuclear power control unit, the hierarchical structure of subsystems and circuit components, including the functional control chassis, low-frequency power supply chassis, main transformer chassis, low-frequency signal unit, isolation drive unit, protection unit, DC unit, D automatic unit, rod speed unit, reverse insertion unit, shutdown unit, and main circuit, was analyzed. The potential operating loads during the mission were analyzed. Using the material / information / energy modeling approach, a functional principle model of the nuclear power control unit was established based on system structure, functional principles, inputs, and outputs.

[0079] Based on the system functional principle model, using the failure mode search method that considers working loads, according to different working loads and mission scenarios, and based on failure clues such as function loss, function discontinuity, and function incompleteness, the potential failure modes of each level of the system are sorted out.

[0080] Based on the results of the system's failure mode analysis, according to the functions of the nuclear control power supply device itself and external influences, the severity categories of failure modes at each level are defined, the list of Class I and Class II failure modes and the list of key components and key parts that have a significant impact on system reliability are determined, and a system-level fault evolution model of the nuclear control power supply device is established.

[0081] Based on the above system-level fault modeling analysis, a failure physics sub-model and a data-driven sub-model are constructed. Specifically, starting from the current state of the equipment, combined with current environmental conditions, relevant parameters, and historical data, relevant algorithms are used to predict, analyze, and judge the failure and operation of the equipment, determine the nature, category, degree, and cause of the failure, and based on the functional principles and reliability relationships derived from the above system-level reliability analysis, a method based on failure physics models and failure data drive is used to predict the development trend of the equipment status in the next period of time. Various existing failure physics models or methods such as DeepONet are used to establish a device-level life analysis model. A data-driven method is used to select the aging characteristic parameters of key components and set the fault threshold. Experiments are designed to verify the accuracy of the corresponding models.

[0082] Specifically, the construction process of the failure physics sub-model is as follows:

[0083] Analyze the failure mechanism of the drive module and key components of the nuclear power supply device, study the aging failure mechanism of the drive module and key components under the optimal characteristic parameter failure mode, and determine the failure symptoms and characteristic parameters;

[0084] Based on the failure mechanism, a multi-failure mechanism physical evolution model of key components and driver modules (including the Coffin-Manson model, LESIT model, Bayerer model, capacitor degradation model, etc.) is established and used as a failure physics sub-model;

[0085] The effectiveness of selecting characteristic parameters for the aging process of each device was verified through simulation, and the effectiveness of failure mechanism analysis of key components was verified through accelerated aging experiments on IGBTs, capacitors, and optocouplers.

[0086] Among them, the technical process of aging failure mechanism analysis of key components based on failure physics sub-model is as follows: Figure 8 shown.

[0087] Specifically, the construction process of the data-driven sub-model is as follows:

[0088] The aging and failure characteristic parameters of the driver module and its key components are clarified. Based on artificial intelligence and data screening, a database of these parameters is constructed. The coupling relationship between each key aging characteristic parameter and the driver board aging characteristic parameter is analyzed to develop a data-driven sub-model. Based on this data-driven sub-model, the driver board aging and failure characteristic parameters and fault thresholds are selected.

[0089] Among them, the technical route for selecting the aging characteristic parameters of the driving module based on the data-driven sub-model is as follows: Figure 9 shown.

[0090] In this embodiment, in view of the fact that the interaction between the failure mechanism models of multiple IGBTs, electrolytic capacitors and other devices in the nuclear control power supply device is difficult to decouple, the existing models of complex systems are difficult to characterize, or the model parameters have characteristics of evolving over time, a PINN model with an embedded fault mechanism is established based on the established PoF model of the corresponding device module and physical laws such as electrothermal force and empirical formulas, and the known physical laws and mathematical characteristics of the model are introduced into the design of the neural network architecture.

[0091] Specifically, a TTF distribution calculation model is constructed and trained, including:

[0092] First, the Coffin-Manson model, LESIT model, Bayerer model, capacitor capacitance degradation model and other fault mechanism models of IGBT devices are integrated, and the operating boundaries and model initial values ​​of these complex failure devices are found; based on this, the boundary residual terms and model residual terms of the fusion model are constructed; then, based on the results of the above data selection and collection, the key feature data residual terms are constructed, including characteristic parameters such as temperature, current, and voltage of key nodes.

[0093] Then, a multi-input and multi-output neural network is constructed, and the activation function of the neural network is defined as tanh and normal Glorot initialization. After defining the optimization domain of each residual, an overall loss function is constructed, which includes boundary residual terms, model residual terms, and key feature data residual terms. Based on this, the constraint functions of the mathematical model of multiple failure mechanisms, the residual functions of the target value and the actual estimated value, the constraint functions of the initial conditions and boundary conditions, and other relevant physical system information are substituted into the loss function of the neural network through operators.

[0094] Then, automatic differentiation technology is used to construct Jacobi matrix and Hessian matrix modules, and high-order differential calculations are achieved through nesting; the optimizer mode, learning rate, number of iterations and loss weight are set for each item, and the fusion model is compiled; and the neural network is trained by gradient descent method and the loss function is minimized to find the optimal value until the loss drops below the set value, resulting in a trained fusion model.

[0095] The neural network trained to convergence is a near-optimal solution for the prediction of the comprehensive data model information. The final TTF calculation value is obtained by inputting the characteristic parameters in the domain. In this way, a dedicated neural network is obtained that embeds the existing failure physics sub-model, empirical formula rules and constraints. This type of embedding method has strong versatility and can basically realize the embedding of any physical model with an analytical expression. The training process of the neural network is adjusted to make it learn and master the embedded physical laws. The schematic diagram of the latter general PINN model principle is shown in the figure. Figure 4 shown.

[0096] In order to solve the problem of missing failure mechanism models for components such as transformers and optocouplers, or the difficulty in establishing a failure physics model for a certain mechanism, a deep operator network (Deep Operator Net) is established to identify the system (parameters) of the model. The temperature, voltage ratio, current ratio and other data related to the unknown domain are used for training. The empirical physical formulas such as the optocoupler CTR degradation with known related mechanisms are input into the discretized Branch net (branch network), and the desired but unknown mechanism information (initial or boundary conditions in the computational domain) is input into the Trunk net (base network) that ensures continuity. This avoids the discretization of the output of the traditional neural network. Finally, the output of the two parts of the neural network is dot-producted (or other operations) to obtain the basis function expansion of the estimated model, and a continuous analytical model of the failure physics (PoF) is established at a higher system level (such as the board-level system level) or that is difficult to establish with traditional methods, thereby enriching and supplementing the existing incomplete PoF knowledge base. In the case of interactive coupling of multi-level physical laws, DeepM&Mnet can be further established based on this method to solve the difficult problem of modeling multi-physics complex systems. The schematic diagram of the Deep Operator Net model principle is shown in the figure. Figure 5 shown.

[0097] In this embodiment, based on the TTF distribution calculation model, the TTF probability distribution of the nuclear-controlled power supply device is obtained by fitting and calculation, including:

[0098] Determine failure symptoms and characteristic parameters, and use failure threshold setting and TTF distribution calculation model to perform data trend analysis and Trend function estimation on important parameters and time;

[0099] The remaining life of the nuclear control power supply device is estimated by using the time when the parameter does not exceed the failure threshold; and the TTF distribution calculation model is repeated multiple times to fit the TTF probability distribution of the nuclear control power supply device.

[0100] During the calculation of the TTF probability distribution, a system failure threshold is set based on the system-level fault evolution model, failure symptoms, and characteristic parameters of the nuclear power supply unit. Based on the established database, model library, and device-level data model fusion-driven model, a PINN model that incorporates failure mechanisms is used to estimate trend functions for key parameters and time. The remaining life (RTF) of the device is estimated using the time it takes for a parameter to not exceed the failure threshold. The aforementioned embedding method incorporates the principles of the random process of device failure, including equations such as Markov processes and martingale processes, to output a device-level TTF probability distribution. Alternatively, the aforementioned evaluation method can be repeated multiple times to directly obtain the device TTF probability distribution using a constrained fitting algorithm. Finally, the device-level calculation results are input into the system-level fault evolution model, outputting a system-level TTF distribution. Operations and maintenance personnel use this calculated TTF distribution for the nuclear power supply unit to set reasonable expected repair times and maintenance opportunities.

[0101] The PIML method fully utilizes the industry's knowledge accumulation over long time scales in the past and the data processing capabilities of the learning model. It still has good predictive performance when the data volume is insufficient or the data quality is poor, and the physical model or law is difficult to analyze. This achieves a deep integration of the two major technical routes in this field - failure physics models and data-driven technologies, which helps us to deeply grasp and understand the degradation and aging process of equipment objects.

[0102] This study focuses on nuclear power control devices for reactors, targeting engineering applications. Integrating feedback from equipment operation and maintenance experience and ongoing technical service tracking, this study analyzes methods related to nuclear power control device reliability model data acquisition, data analysis and evaluation, and physical model verification. The study then develops a failure data acquisition device, proposes a device-level reliability analysis method, and designs and researches techniques for calculating the probability distribution of the device-level reliability prediction indicator, TTF. This method achieves a high-fitting estimate of the TTF probability distribution for nuclear power control devices. Through analysis and research on the calculation of TTF probability distribution curves, a theoretical framework for reliability prediction methods with potential for widespread adoption has been established.

[0103] Example 2

[0104] like Figure 10 As shown, the difference between this embodiment and embodiment 1 is that this embodiment provides a TTF distribution calculation system for a nuclear-controlled power supply device based on a fusion model, which includes:

[0105] an acquisition unit, configured to acquire first data and second data; the first data being data parameters of the nuclear-controlled power supply device before and after failure, and the second data being historical usage data of the nuclear-controlled power supply device;

[0106] a model construction unit for constructing a failure physics sub-model and a data-driven sub-model based on the first data and the second data; fusing the failure physics sub-model and the data-driven sub-model to obtain a data-driven model with an embedded fault mechanism, i.e., a fusion model; and constructing and training a TTF distribution calculation model based on the fusion model;

[0107] The TTF calculation unit is used to obtain the TTF probability distribution of the nuclear control power supply device by fitting calculation based on the TTF distribution calculation model.

[0108] As a further implementation, the system further includes:

[0109] The alarm unit is used to set an alarm based on the TTF probability distribution to provide the repair or replacement time of the nuclear control power supply device.

[0110] Among them, the execution process of each unit can be executed according to the process steps of the TTF distribution calculation method of the nuclear-controlled power supply device based on the fusion model in Example 1, and will not be repeated one by one in this embodiment.

[0111] At the same time, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the above-mentioned TTF distribution calculation method of the nuclear-controlled power supply device based on the fusion model is implemented.

[0112] At the same time, the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned TTF distribution calculation method of the nuclear-controlled power supply device based on the fusion model.

[0113] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0114] 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. 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.

[0115] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0117] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A TTF distribution calculation method for nuclear-controlled power supply devices based on a fusion model is characterized by: The method includes: Acquire first data and second data; the first data is data parameters of the nuclear-controlled power supply device before and after failure, and the second data is historical usage data of the nuclear-controlled power supply device; constructing a failure physics sub-model and a data-driven sub-model based on the first data and the second data; and fusing the failure physics sub-model and the data-driven sub-model to obtain a data-driven model with an embedded fault mechanism, i.e., a fusion model; Based on the fusion model, a TTF distribution calculation model is constructed and trained; based on the TTF distribution calculation model, a TTF probability distribution of the nuclear control power supply device is obtained by fitting and calculation; Build and train the TTF distribution calculation model, including: Integrate the failure mechanism model of IGBT devices and find the operating boundaries and model initial values ​​of the failed devices; construct the boundary residual term, model residual term, and key feature data residual term of the fusion model; the key feature data residual term includes the temperature, current, and voltage characteristic parameters of key nodes; A multi-input and multi-output neural network is constructed, and the activation function of the neural network is defined as tanh and normal Glorot initialization; after defining the optimization domain of each residual, an overall loss function is constructed including the boundary residual term, the model residual term, and the key feature data residual term; accordingly, the constraint function of the mathematical model of multiple failure mechanisms, the residual function of the target value and the actual estimated value, the constraint function of the initial condition and boundary condition, or the physical system information of the deep operator network are substituted into the loss function of the neural network through the operator; The Jacobi matrix and Hessian matrix modules are constructed using automatic differentiation technology, and high-order differential calculations are achieved through nesting. The optimizer mode, learning rate, number of iterations, and loss weight are set, and the fusion model is compiled. The neural network is trained by the gradient descent method and the loss function is minimized to find the optimal value until the loss drops below the set value, thereby obtaining a trained fusion model.

2. The TTF distribution calculation method for a nuclear-controlled power supply device based on a fusion model according to claim 1 is characterized in that: The method further includes: setting an alarm to provide a repair or replacement time for the nuclear-controlled power supply device according to the TTF probability distribution.

3. The TTF distribution calculation method for a nuclear-controlled power supply device based on a fusion model according to claim 1 is characterized in that: The data parameters include temperature data, voltage and current data, and control signal data; The temperature data is the temperature data measured on the full-bridge IGBT device; The voltage and current data include the voltage and current data measured on the bus, the phase voltage and current data measured on the output three-phase AC power supply, and the current and voltage data measured on the optocoupler and electrolytic capacitor; The control signal data is IGBT drive signal phase sequence difference data measured for the full-bridge IGBT control signal.

4. The TTF distribution calculation method for a nuclear-controlled power supply device based on a fusion model according to claim 1 is characterized in that: Construct failure physics sub-model and data-driven sub-model, including: The construction process of the failure physics sub-model is as follows: Analyze the failure mechanism of the drive module and key components of the nuclear power supply device, study the aging failure mechanism of the drive module and key components under the optimal characteristic parameter failure mode, and determine the failure symptoms and characteristic parameters; Based on the failure mechanism, a multi-failure mechanism physical evolution model of key components and drive modules is established and used as a failure physics sub-model; The effectiveness of selecting characteristic parameters for the aging process of each device was verified through simulation, and the effectiveness of failure mechanism analysis of key components was verified through accelerated aging experiments on IGBTs, capacitors, and optocouplers. The construction process of the data-driven sub-model is as follows: Clarify the aging and failure characteristic parameters of the driving module and its key components, build a database of aging and failure characteristic parameters of the driving module and key components, and analyze the coupling relationship between each key aging characteristic parameter and the aging characteristic parameter of the driving board to obtain a data-driven sub-model.

5. The TTF distribution calculation method for a nuclear-controlled power supply device based on a fusion model according to claim 1 is characterized in that: Based on the TTF distribution calculation model, the TTF probability distribution of the nuclear-controlled power supply device is obtained by fitting and calculating, including: Determine failure symptoms and characteristic parameters, and use failure threshold settings and the TTF distribution calculation model to perform data trend analysis function estimation on important parameters and time; The remaining life of the nuclear-controlled power supply device is estimated by using the time when the parameter does not exceed the failure threshold; and the TTF distribution calculation model is repeated multiple times to fit the TTF probability distribution of the nuclear-controlled power supply device.

6. The TTF distributed calculation system of nuclear power supply device based on fusion model is characterized by: The system includes: an acquiring unit, configured to acquire first data and second data; the first data being data parameters of the nuclear-controlled power supply device before and after failure, and the second data being historical usage data of the nuclear-controlled power supply device; a model construction unit, configured to construct a failure physics sub-model and a data-driven sub-model based on the first data and the second data; and to fuse the failure physics sub-model and the data-driven sub-model to obtain a data-driven model with an embedded fault mechanism, i.e., a fusion model; and to construct and train a TTF distribution calculation model based on the fusion model; A TTF calculation unit is used to obtain the TTF probability distribution of the nuclear-controlled power supply device by fitting and calculating based on the TTF distribution calculation model; Build and train the TTF distribution calculation model, including: Integrate the failure mechanism model of IGBT devices and find the operating boundaries and model initial values ​​of the failed devices; construct the boundary residual term, model residual term, and key feature data residual term of the fusion model; the key feature data residual term includes the temperature, current, and voltage characteristic parameters of key nodes; A multi-input and multi-output neural network is constructed, and the activation function of the neural network is defined as tanh and normal Glorot initialization; after defining the optimization domain of each residual, an overall loss function is constructed including the boundary residual term, the model residual term, and the key feature data residual term; accordingly, the constraint function of the mathematical model of multiple failure mechanisms, the residual function of the target value and the actual estimated value, the constraint function of the initial condition and boundary condition, or the physical system information of the deep operator network are substituted into the loss function of the neural network through the operator; The Jacobi matrix and Hessian matrix modules are constructed using automatic differentiation technology, and high-order differential calculations are achieved through nesting. The optimizer mode, learning rate, number of iterations, and loss weight are set, and the fusion model is compiled. The neural network is trained by the gradient descent method and the loss function is minimized to find the optimal value until the loss drops below the set value, thereby obtaining a trained fusion model.

7. The TTF distributed calculation system for nuclear-controlled power supply device based on fusion model according to claim 6 is characterized in that: The system also includes: An alarm unit is used to set an alarm to provide a repair or replacement time for the nuclear control power supply device according to the TTF probability distribution.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the TTF distribution calculation method of the nuclear-controlled power supply device based on the fusion model is implemented as described in any one of claims 1 to 5.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for calculating TTF distribution of a nuclear-controlled power supply device based on a fusion model according to any one of claims 1 to 5 is implemented.

Images