Nuclear power plant equipment stress monitoring system and method based on big data

Abstract

The invention provides a nuclear power plant equipment stress monitoring system and method based on big data. The system comprises the steps of obtaining multi-dimensional data generated in the operation process of nuclear power plant equipment; based on the multi-dimensional data, obtaining a stress state of the nuclear power plant equipment by using a big data analysis method; and maintaining and adjusting the nuclear power plant equipment based on the stress state of the nuclear power plant equipment. The safety and the operation efficiency of the nuclear power plant can be improved.

Description

Technical Field

[0001] The present invention relates to the field of nuclear power plant equipment monitoring, and more specifically, to a nuclear power plant equipment stress monitoring system and method based on big data. Background Art

[0002] As a high-energy output power generation facility, the safety and reliability of the equipment in a nuclear power plant are of crucial importance. During the operation of a nuclear power plant, the stress state of the equipment is directly related to the safety and stability of the entire system. Traditional nuclear power plant equipment stress monitoring systems usually rely on a single data source and simple analysis methods, which often fail to comprehensively capture the multi-dimensional operating state of the equipment, resulting in limited accuracy and real-time performance of the monitoring results. In addition, due to the lack of effective data analysis and prediction models, these systems also have obvious limitations in equipment maintenance and adjustment, unable to respond in a timely manner to changes in the equipment state, thus increasing the risk of equipment failure.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: the existing monitoring systems cannot make full use of multi-dimensional data to improve the accuracy of stress monitoring; there is a lack of intelligent analysis and prediction models based on big data and machine learning technologies, resulting in the inability to achieve real-time monitoring and intelligent maintenance of the equipment stress state; and during the equipment maintenance and adjustment process, there is a lack of the ability to dynamically adjust control parameters, making the maintenance work often lag behind the actual needs of the equipment. Summary of the Invention

[0004] The present invention provides a nuclear power plant equipment stress monitoring system and method based on big data.

[0005] In the first aspect of the present invention, a nuclear power plant equipment stress monitoring system based on big data is provided, including: Obtaining multi-dimensional data generated by nuclear power plant equipment during operation; Based on the multi-dimensional data, obtaining the stress state of the nuclear power plant equipment using big data analysis methods; Maintaining and adjusting the nuclear power plant equipment based on the stress state of the nuclear power plant equipment.

[0006] Further, when the nuclear power plant equipment starts to operate, an initialization operation is performed on the nuclear power plant equipment; after the nuclear power plant equipment operates stably, the multi-dimensional data generated by the nuclear power plant equipment is collected.

[0007] Further, the maintaining and adjusting the nuclear power plant equipment based on the stress state of the nuclear power plant equipment includes: Comparing the stress state of the nuclear power plant equipment with a pre-set safety threshold to obtain a stress deviation; Taking the stress deviation as an input parameter of the intelligent controller, the initial control parameters of the intelligent controller are corrected by using the stress deviation and the change rate of the stress deviation to obtain the corrected control parameters; Based on the control parameters, the intelligent controller outputs maintenance and adjustment instructions.

[0008] Further, the step of using the stress deviation and the change rate of the stress deviation to correct the initial control parameters of the intelligent controller to obtain the corrected control parameters includes: According to the deviation level of the stress deviation and the change rate of the stress deviation, the dynamic value of the control parameter is determined according to the preset adaptive control rule; The corrected control parameter is the sum value of the initial control parameter and the dynamic value of the control parameter.

[0009] Further, the step of obtaining the stress state of the nuclear power plant equipment by using the big data analysis method based on the multi-dimensional data includes: Based on the multi-dimensional data, the equipment state characteristics corresponding to each sensor are obtained according to the pre-calibrated data; Based on the equipment state characteristics corresponding to each sensor, the equipment stress evaluation value of each sensor is obtained; Based on the maximum value Tmax in the equipment stress evaluation values of each sensor, the equivalent stress state of each sensor is obtained; Based on the maximum value Tmax and the equivalent stress state of each sensor, the stress state of the nuclear power plant equipment after inversion is obtained by using the machine learning optimization strategy.

[0010] Further, the step of obtaining the stress state of the nuclear power plant equipment after inversion by using the machine learning optimization strategy based on the maximum value and the equivalent stress state of each sensor includes: Taking the maximum value and the equivalent stress state of each sensor as the initial stress state of the first iteration of the machine learning optimization strategy and the initial equipment state characteristics of each sensor; In the iteration step of the machine learning optimization strategy: based on the initial equipment state characteristics of each sensor, the big data analysis method is used as the iteration function of the machine learning optimization strategy to calculate and obtain the optimal stress state as the hidden parameter of the machine learning optimization strategy; In the update step of the machine learning optimization strategy: based on the optimal stress state, the equipment state characteristics of each sensor in this stress state are obtained as the expected value of the equipment state characteristics corresponding to each sensor; Taking the optimal stress state and the expected value of the equipment state characteristics corresponding to each sensor as the initial stress state of the next iteration and the initial equipment state characteristics of each sensor; When the expected value of the device state characteristics corresponding to each of the sensors and the initial device state characteristics of each of the sensors satisfy the convergence condition, the obtained optimal stress state is used as the stress state of the nuclear power plant equipment after inversion, and the iteration is terminated.

[0011] Further, the optimal stress state Topt is calculated using a big data analysis method, and its formula is as follows: where Topt is the optimal stress state; is the device state characteristic corresponding to the sensor i ; is the sensor i under the stress state T the ideal device state characteristic; n is the total number of sensors.

[0012] Further, based on the optimal stress state, the device state characteristics of each of the sensors under this stress state are obtained using the following formula: where is the device state characteristic of sensor i; is the device state characteristic corresponding to sensor i; is the ideal device state characteristic of sensor i under the optimal stress state Topt.

[0013] Further, based on the device state characteristics corresponding to each of the sensors, a statistical analysis method is used to obtain the device stress evaluation values of each of the sensors, and based on the maximum value Tmax among these evaluation values, a statistical analysis method is used to obtain the equivalent stress state of each of the sensors. Its calculation formula is as follows: where is the equivalent stress state, is the stress evaluation value of sensor i, is the average value of the stress evaluation values of all sensors, is the standard deviation of the stress evaluation values of all sensors, and n is the total number of sensors.

[0014] In the second aspect of the present invention, a method for monitoring the stress of nuclear power plant equipment based on big data is provided, including: Obtaining multi-dimensional data generated during the operation of the nuclear power plant equipment; Based on the multi-dimensional data, using a big data analysis method to obtain the stress state of the nuclear power plant equipment; Maintaining and adjusting the nuclear power plant equipment based on the stress state of the nuclear power plant equipment.

[0015] The above embodiments of the present invention have at least the following beneficial effects: By adopting the big data analysis method and the machine learning optimization strategy, the big data-based stress monitoring system for nuclear power plant equipment of the present invention can comprehensively capture multi-dimensional data generated during the operation of nuclear power plant equipment, so as to obtain a more accurate stress state assessment. This comprehensive analysis method can not only improve the accuracy of stress monitoring, but also, through real-time monitoring and intelligent analysis, timely discover potential risk points, and thus take measures in advance for prevention, which can effectively improve the safety and reliability of nuclear power plant equipment.

[0016] In addition, by comparing the stress state with a preset safety threshold and dynamically adjusting the control parameters of the intelligent controller using the stress deviation and its change rate, the system can achieve real-time maintenance and adjustment of nuclear power plant equipment. This dynamic maintenance strategy can not only reduce unnecessary maintenance work and lower maintenance costs, but also ensure that the equipment always operates in the best state, thereby improving the overall operation efficiency and economic benefits of the nuclear power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown by way of example and not limitation, wherein: Figure 1 is a schematic flow chart of a big data-based stress monitoring system for nuclear power plant equipment provided by an embodiment of the present invention; Figure 2 is a schematic flow chart of a big data-based stress monitoring method for nuclear power plant equipment provided by an embodiment of the present invention; Figure 3 schematically shows a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The principles and spirit of the present invention will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and then implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to be able to fully convey the scope of the present invention to those skilled in the art.

[0019] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, apparatus, device, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms: completely hardware, completely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0020] It should be noted that the number of any elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0021] The following refers to Figure 1 , Figure 1 , which is a schematic flow diagram of a nuclear power plant equipment stress monitoring system based on big data provided by an embodiment of the present invention. As Figure 1 shown, a nuclear power plant equipment stress monitoring system 100 based on big data includes: Step 101, obtaining multi-dimensional data generated by nuclear power plant equipment during operation; Step 102, based on the multi-dimensional data, using big data analysis methods to obtain the stress state of the nuclear power plant equipment; Step 103, maintaining and adjusting the nuclear power plant equipment based on the stress state of the nuclear power plant equipment.

[0022] It should be noted that this system monitors the stress state of nuclear power plant equipment by performing a series of steps, where the multi-dimensional data refers to various types of data generated by nuclear power plant equipment during operation, such as temperature, pressure, vibration, etc. These data can be obtained from multiple sensors and can be used to analyze the health status of the equipment. The stress state can specifically be an external load; through the external load, the loading capacity of the nuclear power plant equipment or the bearing capacity of the material and structure can be evaluated.

[0023] Specifically, when the nuclear power plant equipment starts to operate, the system will perform initialization operations, which include setting sensors, calibrating equipment, and starting the data acquisition program. After the equipment operates stably, the system will regularly collect multi-dimensional data.

[0024] Furthermore, the collected data will be transmitted to the central processing unit, where big data analysis methods will be applied to these data to calculate and evaluate the stress state of the equipment. These methods include statistical analysis, machine learning algorithms, and pattern recognition techniques.

[0025] Preferably, the system can be configured with adaptive control rules, which can dynamically adjust control parameters according to real-time data. For example, the system will use a preset algorithm to determine the optimal control strategy under specific stress deviations and change rates.

[0026] Even further, the system can also include a user interface that allows operators to monitor data, receive alerts, and manually adjust control parameters. To improve the accuracy and reliability of the system, redundant sensors and data verification techniques can be adopted to ensure the integrity and accuracy of the data.

[0027] In some embodiments, when the nuclear power plant equipment starts to operate, an initialization operation is performed on the nuclear power plant equipment; after the nuclear power plant equipment operates stably, multi-dimensional data generated by the nuclear power plant equipment is collected.

[0028] It should be noted that this embodiment relates to the initialization operation and multi-dimensional data collection of nuclear power plant equipment during operation. The initialization operation mentioned here refers to a series of preset actions performed before the equipment starts, to ensure that the equipment can operate normally and start data collection. And multi-dimensional data collection refers to collecting various parameter data generated by the equipment during operation, such as temperature, pressure, vibration, etc. These data are crucial for subsequent stress state analysis.

[0029] Specifically, the initialization operation includes, but is not limited to, calibrating sensors, setting initial parameters, starting a data recording system, etc. After the equipment operates stably, the system will automatically collect multi-dimensional data according to a preset time interval or trigger condition.

[0030] More specifically, these data include readings from different sensors, such as temperature sensors, pressure sensors, and vibration sensors, etc. They jointly constitute the multi-dimensional data set of the equipment. The collected data will be stored in a database for subsequent analysis and processing.

[0031] Preferably, the collected multi-dimensional data can include more sensor types, such as humidity sensors, radiation monitoring sensors, etc., to provide more comprehensive equipment operation status information. In addition, the system can be provided with an intelligent trigger mechanism. When an abnormal signal is detected or the equipment operation status changes, the data collection frequency is automatically increased or additional diagnostic programs are started.

[0032] Furthermore, in order to improve the accuracy of the data, data cleaning and preprocessing techniques can be adopted to ensure the quality of the collected data and provide reliable data support for subsequent stress state analysis.

[0033] In some embodiments, maintaining and adjusting the nuclear power plant equipment based on the stress state of the nuclear power plant equipment includes: Comparing the stress state of the nuclear power plant equipment with a pre-set safety threshold to obtain a stress deviation; Taking the stress deviation as an input parameter of an intelligent controller, and using the stress deviation and the change rate of the stress deviation to correct the initial control parameters of the intelligent controller to obtain corrected control parameters; Based on the control parameters, the intelligent controller outputs maintenance and adjustment instructions.

[0034] It should be noted that this embodiment details how to perform maintenance and adjustment based on the stress state of nuclear power plant equipment. The stress state mentioned here refers to the distribution and magnitude of internal forces borne by the equipment during operation, while maintenance and adjustment involve a series of operations on the equipment based on this stress data to ensure its safe and efficient operation. The safety threshold refers to the pre-set upper limit of stress, and exceeding this value will cause damage to the equipment.

[0035] Specifically, the embodiment includes comparing the actual stress state of the equipment with the pre-set safety threshold to determine whether there is a stress deviation. This comparison process can be completed by an automated control system that can monitor the stress state of the equipment in real time and compare it with the safety threshold.

[0036] More specifically, the stress deviation refers to the difference between the actual stress and the safety threshold, and this deviation will be used as an input parameter for the intelligent controller. The intelligent controller will use this stress deviation and its rate of change to correct its initial control parameters to obtain the corrected control parameters for more precisely adjusting the equipment operation state.

[0037] Preferably, the correction process of the intelligent controller can include multiple steps. For example, the controller will dynamically adjust the operation parameters of the equipment, such as temperature, pressure, etc., according to the magnitude and rate of change of the stress deviation.

[0038] Furthermore, the controller can also automatically learn and optimize its control strategy based on the operation history and maintenance records of the equipment. To further improve the accuracy of control, advanced algorithms, such as neural networks or genetic algorithms, can be used to predict the stress change trend of the equipment and adjust the control parameters accordingly.

[0039] In some embodiments, the correction of the initial control parameters of the intelligent controller using the stress deviation and the rate of change of the stress deviation to obtain the corrected control parameters includes: Obtain the actual stress state of the equipment and the pre-set equipment safety threshold, and take the difference to obtain the stress deviation value; Obtain the stress deviation values at t time points, subtract the stress deviation value at the (t - 1)th moment from the stress deviation value at the tth moment, and then divide by the time interval to obtain the rate of change of the stress deviation; Based on the stress deviation value and the change rate of the stress deviation, set the deviation level; construct a corresponding deviation level table with the stress deviation value and the change rate of the stress deviation. Taking each stress deviation value as the main body and each change rate of the stress deviation as the object, generate deviation level tables with the same number as the stress deviation values. One main body can correspond to multiple objects and multiple deviation levels; the setting of the deviation level can be set by those skilled in the art in combination with the technical knowledge in the professional field. Exemplarily, when the stress deviation value is a, there is a deviation level table a corresponding to multiple change rates b, c, d of the stress deviation. When the stress deviation is a and the change rate of the stress deviation is b, the corresponding deviation level is the first level. When the stress deviation is a and the change rate of the stress deviation is c, the corresponding deviation level is the second level. When the stress deviation is a and the change rate of the stress deviation is d, the corresponding deviation level is the third level; the same stress deviation value can correspond to multiple change rates of the stress deviation and the same deviation level. Exemplarily, when the stress deviation is a and the change rates of the stress deviation are e and f, the corresponding deviation levels can both be the third level; the higher the deviation level, the greater the stress deviation or the faster the change rate. According to the deviation level of the stress deviation and the change rate of the stress deviation, determine the dynamic value of the control parameter according to the preset adaptive control rule. The corrected control parameter is the sum of the initial control parameter and the dynamic value of the control parameter.

[0040] It should be noted that this embodiment involves how to dynamically adjust the control parameters of the intelligent controller by using the stress deviation and the change rate of the stress deviation. The stress deviation mentioned here refers to the difference between the actual stress state of the device and the preset safety threshold, and the change rate refers to the change speed of this deviation over time. The adaptive control rule is a method of dynamically adjusting the control strategy according to real-time data, which can ensure that the response of the controller is more accurate and timely.

[0041] Specifically, the embodiment includes determining the dynamic value of the control parameter according to the deviation level of the stress deviation and the change rate of the stress deviation, based on the preset adaptive control rule. This involves real-time analysis of the stress deviation data to determine its level and adjust the control parameter accordingly. For example, if the stress deviation is large or the change rate is fast, that is, the deviation level is higher, the controller will increase the intensity or frequency of the output signal to adjust the device stress to the safe range faster. The dynamic value of the control parameter refers to the parameter value adjusted according to real-time data, which is combined with the initial control parameter to form the corrected control parameter.

[0042] Preferably, the adaptive control rules can be implemented using a variety of algorithms, such as fuzzy logic control, PID control, or model predictive control, etc. These algorithms can be selected and adjusted according to the actual application scenarios and requirements. For example, fuzzy logic control is suitable for dealing with systems with high uncertainty, while PID control is applicable to systems that require precise regulation.

[0043] Furthermore, through machine learning methods, the controller can be made to self-optimize based on historical data, further improving the control accuracy and response speed. To improve the robustness of the system, multiple sensors can be set up to monitor the stress state, and a redundant control strategy can be adopted to ensure that the system can still operate normally when a certain sensor fails.

[0044] In some embodiments, obtaining the stress state of the nuclear power plant equipment using big data analysis methods based on the multi-dimensional data includes: Based on the multi-dimensional data, obtaining the equipment state characteristics corresponding to each sensor according to pre-calibrated data; Based on the equipment state characteristics corresponding to each of the sensors, obtaining the equipment stress evaluation values of each of the sensors; Based on the maximum value Tmax among the equipment stress evaluation values of each of the sensors, obtaining the equivalent stress state of each of the sensors; Based on the maximum value Tmax and the equivalent stress state of each of the sensors, using a machine learning optimization strategy to obtain the inverted stress state of the nuclear power plant equipment.

[0045] It should be noted that this embodiment describes how to obtain the stress state of nuclear power plant equipment using big data analysis methods based on multi-dimensional data. The multi-dimensional data here refers to different types of data collected from nuclear power plant equipment, such as temperature, pressure, vibration, etc., which together constitute the comprehensive operating state of the equipment. The big data analysis method refers to using advanced data processing technologies, such as machine learning, statistical analysis, etc., to analyze this data and obtain the stress state of the equipment.

[0046] Specifically, the embodiment includes first obtaining the equipment state characteristics corresponding to each sensor according to pre-calibrated data. This involves using historical data and known equipment states to train an analysis model so as to be able to identify and predict the characteristic performance of the equipment under different operating conditions. Then, based on these equipment state characteristics, the system will calculate the equipment stress evaluation value of each sensor. This involves statistical analysis, such as calculating the average value, standard deviation, etc., to evaluate the stress level of the equipment under the current operating conditions.

[0047] Preferably, the system can further refine the operation steps. For example, by setting weights to adjust the importance of different sensor data in stress assessment. In addition, advanced machine learning algorithms such as deep learning or support vector machines can be adopted to improve the accuracy of stress assessment.

[0048] Furthermore, to ensure the robustness of the system, regular data calibration and model retraining can be implemented to adapt to the changes that occur in the equipment. Additionally, the system can also include a feedback mechanism that allows the operator to adjust the parameters of the analysis model based on the actual observed performance of the equipment, thereby improving the adaptability and accuracy of the system.

[0049] In some embodiments, using the machine learning optimization strategy based on the maximum value and the equivalent stress states of each of the sensors to obtain the stress state of the nuclear power plant equipment after inversion includes: Taking the maximum value and the equivalent stress states of each of the sensors as the initial stress state and the initial equipment state features of each of the sensors for the first iteration of the machine learning optimization strategy; In the iteration step of the machine learning optimization strategy: using the big data analysis method based on the initial equipment state features of each of the sensors as the iteration function of the machine learning optimization strategy to calculate the optimal stress state as the hidden parameter of the machine learning optimization strategy; In the update step of the machine learning optimization strategy: obtaining the equipment state features of each of the sensors under this stress state based on the optimal stress state as the expected values of the equipment state features corresponding to each sensor; Taking the optimal stress state and the expected values of the equipment state features corresponding to each of the sensors as the initial stress state and the initial equipment state features of each of the sensors for the next iteration; When the expected values of the equipment state features corresponding to each of the sensors satisfy the convergence condition with the initial equipment state features of each of the sensors, the obtained optimal stress state is used as the stress state of the nuclear power plant equipment after inversion, and the iteration ends.

[0050] It should be noted that this embodiment details how to use the machine learning optimization strategy to invert the stress state of the nuclear power plant equipment. The machine learning optimization strategy mentioned here refers to the process of iteratively optimizing the equipment stress state using machine learning algorithms to improve the accuracy of stress assessment. The iteration function refers to the function used to calculate the optimal stress state in the machine learning algorithm, and the hidden parameter refers to the internal parameter used to guide the algorithm to find the optimal solution during the iteration process.

[0051] Specifically, the implementation includes using the maximum value and the equivalent stress state of each sensor as the initial stress state for the first iteration of the machine learning optimization strategy and the initial device state features of each sensor. This means that in the first round of iteration of the algorithm, the system will use these initial values to calculate the optimal stress state.

[0052] More specifically, in the iteration step, the system will use the big data analysis method as the iteration function based on the initial device state features of each sensor to calculate the optimal stress state as the hidden parameter.

[0053] Furthermore, in the update step, the system will obtain the device state features of each sensor under this stress state as the expected values based on the optimal stress state, and use these expected values as the initial conditions for the next iteration.

[0054] Preferably, various machine learning algorithms such as the gradient descent method, genetic algorithm, or simulated annealing algorithm can be used during the iteration process to optimize the evaluation of the stress state. These algorithms can be customized and adjusted according to the actual device data and system requirements. For example, the number of iterations, learning rate, or other parameters of the algorithm can be set to ensure that the algorithm can converge to the optimal solution within a reasonable time.

[0055] Even further, the system can also include an early stopping mechanism to prevent overfitting and ensure the generalization ability of the model. To further improve the performance of the algorithm, parallel computing or distributed computing technologies can be adopted to accelerate the iteration process.

[0056] In some embodiments, the optimal stress state Topt is calculated using the big data analysis method, and the formula is as follows: Where Topt is the optimal stress state; is the device state feature corresponding to sensor i; is the ideal device state feature of sensor i under the stress state T; n is the total number of sensors.

[0057] It should be noted that this embodiment describes how to calculate the optimal stress state using a specific formula . The optimal stress state here refers to the stress level at which the device operates most ideally under the given multi-dimensional data conditions. In the formula, represents the total number of sensors, and is obtained by minimizing the sum of the squares of the differences between the actual state features and the ideal state features of the sensors.

[0058] Specifically, the process of calculating the optimal stress state involves for each sensor 's actual state feature and at a specific stress state The ideal state characteristics under This comparison is done by calculating the square of the difference between the two and summing this across all sensors.

[0059] More specifically, the summation symbol in the formula For all sensors The values ​​from 1 to n are accumulated. In this way, the system can find the stress state that minimizes the total difference , that is, the ideal state of equipment operation.

[0060] Preferably, the calculation process can be further refined, for example, weight factors can be introduced to consider the importance or reliability of different sensors. In addition, in order to improve the stability and accuracy of the calculation, numerical optimization techniques, such as Newton's method or quasi-Newton's method, can be used to solve this minimization problem.

[0061] Furthermore, in practical applications, it is also possible to consider introducing regularization terms to avoid overfitting, or using parallel computing technology to speed up the processing of large-scale data sets. In addition, the system can be designed to adaptively adjust the number of iterations or learning rate to adapt to different data characteristics and computing resources.

[0062] In some embodiments, based on the optimal stress state, the device state characteristics of each sensor in the stress state are obtained using the following formula: in, For sensor i Device status characteristics; For sensor i The corresponding device status characteristics; For sensor i Ideal device state characteristics under the optimal stress state Topt.

[0063] It should be noted that this embodiment describes how to The device state characteristics of each sensor under the stress state are calculated. The optimal stress state here refers to the ideal stress level of the device operation determined by the above method, and the device state characteristics refer to various parameters that can reflect the operating status of the device, such as temperature, pressure, etc.

[0064] Specifically, the embodiment involves using a formula to determine the optimal stress state for each sensor The ideal equipment state characteristics under this formula. Indicates sensor i In the optimal stress state The ideal equipment state characteristics under Represents a sensor The current actual device state characteristics. Through this formula, the system can calculate the device state characteristics that each sensor should have under the optimal stress state, thereby providing a basis for device maintenance and adjustment.

[0065] Preferably, the calculation process can be further refined. For example, an error correction mechanism can be introduced to improve the calculation accuracy. In addition, the system can be designed to dynamically update the optimal stress state to adapt to changes in device operating conditions.

[0066] Furthermore, in practical applications, a prediction model can also be considered to predict the state characteristics of the device at a certain future moment, so as to perform maintenance and adjustment in advance. In addition, the system can be designed to automatically record and analyze the historical data of the device state characteristics, so as to identify the long-term trends and potential problems of device performance.

[0067] In some embodiments, based on the device state characteristics corresponding to each of the sensors, a statistical analysis method is used to obtain the device stress evaluation values of each of the sensors, and based on the maximum value among these evaluation values , a statistical analysis method is used to obtain the equivalent stress state of each of the sensors. The calculation formula is as follows: Wherein,[[]]END]] is the equivalent stress state,[[]]END]] is the stress evaluation value of the sensor i ,[[]]END]] is the average value of the stress evaluation values of all sensors,[[]]END]] is the standard deviation of the stress evaluation values of all sensors, and n is the total number of sensors.

[0068] It should be noted that this embodiment describes how to use a statistical analysis method to evaluate the device stress of each sensor, and based on the maximum value among these evaluation values to determine the equivalent stress state of each sensor. The equivalent stress state here refers to a parameter that comprehensively reflects the overall stress level of the device after considering the stress evaluation values of all sensors.

[0069] Specifically, the embodiment involves performing a statistical analysis on the stress evaluation values of each sensor, and calculating the average value and standard deviation of the stress evaluation values of all sensors. These statistical parameters will be used to evaluate the equivalent stress state of each sensor.

[0070] More specifically, in the formula represents the equivalent stress state,[[]]END]] represents the stress evaluation value of the sensor ,[[]]END]] TRepresents the average value of all sensor stress evaluation values, Represents the standard deviation of all sensor stress evaluation values, n Is the total number of sensors.

[0071] Preferably, the process of calculating the equivalent stress state can be further refined. For example, a weighted average can be introduced to consider the importance or reliability of different sensors. In addition, the system can be designed to dynamically adjust the weight of the standard deviation to adapt to changes in the operating conditions of the equipment. In practical applications, an outlier detection mechanism can also be considered to identify and process abnormal data points that affect the accuracy of stress evaluation.

[0072] Furthermore, to improve the robustness of the system, various statistical analysis methods, such as robust statistical methods, can be adopted to reduce the impact of outliers on stress evaluation. In addition, the system can also be designed to automatically record and analyze the historical data of stress evaluation to facilitate the identification of long-term trends and potential problems in equipment performance.

[0073] The above-mentioned various embodiments of the present invention have the following beneficial effects: The nuclear power plant equipment stress monitoring system based on big data according to the present invention can accurately master the stress state of the equipment by obtaining multi-dimensional data generated during the operation of the nuclear power plant equipment in real time and applying big data analysis methods, and then perform effective maintenance and adjustment. This method can ensure the safe operation of the nuclear power plant equipment because the system can timely detect stress anomalies and take corresponding maintenance measures to prevent the equipment from failing due to excessive stress, thus ensuring the safe and stable operation of the entire nuclear power plant.

[0074] In addition, the system uses a machine learning optimization strategy, combines sensor data and pre-calibrated data, and can inversely obtain the accurate stress state of the nuclear power plant equipment. This strategy can improve the accuracy of stress evaluation and dynamically adjust control parameters through an intelligent controller to achieve real-time monitoring and maintenance of the equipment stress state. This method can not only reduce manual intervention, lower maintenance costs, but also improve the efficiency and accuracy of maintenance work, thereby enhancing the overall operation efficiency of the nuclear power plant.

[0075] Exemplarily, if stress monitoring is performed on the gantry crane equipment of a nuclear power plant, the specific method is as follows: Obtain multi-dimensional data generated during the operation of the gantry crane equipment, including voltage, temperature, no-load, light-load, static load, rated load, and dynamic load, etc.; Based on multi-dimensional data, obtain the external load A of the ring crane equipment as the stress state of the ring crane equipment; compare the obtained external load A with the pre-set safety threshold of the external load to obtain the deviation value AP and the change rate AB of the deviation; the change rate of the deviation is obtained by subtracting the previous deviation value from the current deviation value and then dividing by the previous deviation value; input it as an input parameter into the intelligent controller, and the intelligent controller corrects the initial control parameters to generate maintenance and adjustment instructions; Use the big data analysis method to calculate the optimal stress state of the ring crane equipment, that is, the external load when the ring crane equipment reaches the best state: Among them, Topt is the optimal stress state; is the sensor i corresponding to the state characteristics of the ring crane equipment; is the sensor i at the stress state T that is, when the external load is T the ideal equipment state characteristics; n is the total number of sensors; the ring crane equipment includes a trolley, a crab, a main hook, a sub-hook, and a maintenance hoist, etc. Therefore, corresponding sensors are set at different positions to obtain the overall state characteristics of the ring crane equipment, improving the accuracy of analysis; the state characteristics of the ring crane equipment can be expressed as an aging state, a fault state, a maintenance state, and a normal state, etc.; Based on the optimal stress state, obtain the equipment state characteristics of each sensor: Among them, is the evaluation value of the state characteristics of the ring crane equipment of the sensor i ; is the sensor i corresponding equipment state characteristics; is the sensor at the optimal stress state Topt of the ideal equipment state characteristics; Obtain the maximum value in the evaluation value of the state characteristics of the ring crane equipment to obtain the equivalent stress state, and use the machine learning optimization strategy to obtain the stress state of the ring crane equipment after anomaly, that is, the external load; Based on the obtained external load of the ring crane equipment and the maintenance and adjustment instructions generated by the intelligent controller, perform corresponding maintenance on the ring crane equipment.

[0076] Such as Figure 2 shown, a method 200 for monitoring the stress of nuclear power plant equipment based on big data in some embodiments, the method 200 includes: Step 201, obtain multi-dimensional data generated during the operation of the nuclear power plant equipment; Step 202: Based on the multi-dimensional data, use big data analysis methods to obtain the stress state of the nuclear power plant equipment; Step 203: Maintain and adjust the nuclear power plant equipment based on the stress state of the nuclear power plant equipment.

[0077] It can be understood that the steps described in the big data-based nuclear power plant equipment stress monitoring method 200 correspond to the respective steps in the big data-based nuclear power plant equipment stress monitoring system described in the reference Figure 1 Therefore, the operations, features, and beneficial effects described above for the big data-based nuclear power plant equipment stress monitoring system also apply to the big data-based nuclear power plant equipment stress monitoring method 200 and the operations included therein, and will not be elaborated herein.

[0078] Next, refer to Figure 3 , which shows a schematic structural diagram of a structure 300 of an electronic device suitable for implementing some embodiments of the present invention. The electronic device in some embodiments of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0079] As Figure 3 shown, the electronic device 300 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage device 308 into the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0080] Generally, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 3An electronic device 300 with various devices is shown, but it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices can be implemented or had. Figure 3 Each block shown in can represent a device or, as needed, multiple devices.

[0081] Furthermore, the storage medium of the embodiments of the present application stores program instructions capable of implementing all the above methods. Among them, the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in the various embodiments of the present application. And the aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0082] The above description is only some preferred embodiments of the present invention and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, technical solutions formed by mutually replacing the above features with technical features having similar functions (but not limited to) disclosed in the embodiments of the present invention.

Claims

1. A nuclear power plant equipment stress monitoring system based on big data, characterized in that: The system performs the following steps: Obtain multi-dimensional data generated by nuclear power plant equipment during operation; Based on the multidimensional data, using a big data analysis method to obtain the stress state of the nuclear power plant equipment; The nuclear power plant equipment is maintained and adjusted based on the stress state of the nuclear power plant equipment.

2. The system according to claim 1, characterized in that: When the nuclear power plant equipment starts to operate, the nuclear power plant equipment is initialized; after the nuclear power plant equipment operates stably, the multi-dimensional data generated by the nuclear power plant equipment is collected.

3. The system according to claim 2, characterized in that: The maintaining and adjusting the nuclear power plant equipment based on the stress state of the nuclear power plant equipment includes: Comparing the stress state of the nuclear power plant equipment with a preset safety threshold to obtain a stress deviation; The stress deviation is used as an input parameter of an intelligent controller, and the initial control parameters of the intelligent controller are corrected using the stress deviation and the change rate of the stress deviation to obtain corrected control parameters; Based on the control parameters, the intelligent controller outputs maintenance and adjustment instructions.

4. The system according to claim 3, characterized in that: The method of using the stress deviation and the change rate of the stress deviation to correct the initial control parameters of the intelligent controller to obtain the corrected control parameters includes: Determining the dynamic value of the control parameter according to a preset adaptive control rule based on the deviation level of the stress deviation and the rate of change of the stress deviation; The modified control parameter is a total value of the initial control parameter and the dynamic value of the control parameter.

5. The system according to claim 2, characterized in that: The method of obtaining the stress state of the nuclear power plant equipment based on the multi-dimensional data using a big data analysis method includes: Based on the multidimensional data, obtaining device status characteristics corresponding to each sensor according to pre-calibrated data; Based on the equipment state characteristics corresponding to each of the sensors, an equipment stress assessment value of each of the sensors is obtained; Based on the maximum value Tmax of the device stress evaluation value of each sensor, the equivalent stress state of each sensor is obtained; Based on the maximum value Tmax and the equivalent stress state of each of the sensors, a machine learning optimization strategy is used to obtain the inverted stress state of the nuclear power plant equipment.

6. The system according to claim 5, characterized in that: The method of obtaining the inverted stress state of the nuclear power plant equipment using a machine learning optimization strategy based on the maximum value and the equivalent stress state of each sensor includes: Using the maximum value and the equivalent stress state of each of the sensors as the initial stress state of the first iteration of the machine learning optimization strategy and the initial device state characteristics of each of the sensors; In the iterative step of the machine learning optimization strategy: based on the initial device state characteristics of each of the sensors, a big data analysis method is used as an iterative function of the machine learning optimization strategy to calculate the optimal stress state as a hidden parameter of the machine learning optimization strategy; In the updating step of the machine learning optimization strategy: based on the optimal stress state, the device state characteristics of each of the sensors under the stress state are obtained as the expected values ​​of the device state characteristics corresponding to each sensor; Taking the optimal stress state and the expected value of the device state characteristic corresponding to each of the sensors as the initial stress state and the initial device state characteristic of each of the sensors for the next iteration; When the expected value of the equipment state characteristic corresponding to each of the sensors and the initial equipment state characteristic of each of the sensors meet the convergence condition, the obtained optimal stress state is used as the stress state of the nuclear power plant equipment after inversion, and the iteration ends.

7. The system according to claim 6, characterized in that: The optimal stress state Topt is calculated using the big data analysis method, and the formula is as follows: ； Among them, Topt is the optimal stress state; For sensor i The corresponding device status characteristics; For sensor i In a state of stress T Ideal equipment state characteristics under ; n is the total number of sensors.

8. The system according to claim 7, characterized in that: Based on the optimal stress state, the device state characteristics of each sensor under the stress state are obtained using the following formula: ； in, is the device status feature of sensor i; For sensor i The corresponding device status characteristics; For sensor i In the optimal stress state Topt The ideal equipment state characteristics under .

9. The system according to claim 5, characterized in that: Based on the equipment state characteristics corresponding to each of the sensors, a statistical analysis method is used to obtain an equipment stress evaluation value of each of the sensors, and based on a maximum value Tmax among the evaluation values, an equivalent stress state of each of the sensors is obtained using a statistical analysis method; The calculation formula is as follows: ； in, is the equivalent stress state, For sensor i The stress evaluation value of is the average value of all sensor stress evaluation values, is the standard deviation of all sensor stress evaluation values, n is the total number of sensors.

10. A method for monitoring stress of nuclear power plant equipment based on big data, characterized in that: include: Obtain multi-dimensional data generated by nuclear power plant equipment during operation; Based on the multidimensional data, using a big data analysis method to obtain the stress state of the nuclear power plant equipment; The nuclear power plant equipment is maintained and adjusted based on the stress state of the nuclear power plant equipment.

Images