Frequency conversion control method and system for ventilation system of nuclear power plant

Abstract

The present invention relates to the technical field of variable frequency control, and discloses a variable frequency control method and system for a nuclear power plant ventilation system, wherein the method comprises: collecting real-time operating data of multiple areas of the nuclear power plant ventilation system and performing standardization processing to obtain a standardized data set; performing fan performance curve fitting and pressure difference field feature mapping on the standardized data set to obtain pressure difference field mapping features; inputting the pressure difference field mapping features into an active neural pressure difference field network model to perform variable frequency parameter prediction to obtain target variable frequency control parameters; and performing feedforward-feedback combined control of the target variable frequency control parameters through a multi-mode variable frequency controller to obtain fan speed and air valve opening values. The method can adaptively generate target variable frequency control parameters, significantly improve control performance, and achieve a smooth transition of the nuclear power plant ventilation system.

Description

Technical Field

[0001] The present invention relates to the technical field of variable frequency control, and in particular to a variable frequency control method and system for a ventilation system of a nuclear power plant. Background Art

[0002] Traditional nuclear power plant ventilation system control methods primarily rely on a combination of constant-speed operation and valve adjustment. This not only results in high energy consumption but also makes precise control difficult under complex and changing operating conditions. While variable frequency technology has been adopted in ventilation systems in recent years, existing variable frequency control methods still suffer from numerous issues, including insufficient long-term operational stability, irregular sensor data sampling, weak mechanisms for handling missing data, poor control coordination between different ventilation zones, and a lack of effective fault diagnosis and prediction mechanisms. These issues limit their application in safety-critical scenarios such as nuclear power plants.

[0003] Existing variable frequency control solutions for nuclear power plant ventilation systems typically rely on complex PID control algorithms or fuzzy logic control, which perform poorly when dealing with nonlinear, multivariable, and tightly coupled complex systems. In particular, it is often difficult to maintain ideal control results when the system faces sensor failures, sudden operating condition changes, or the need for multi-zone coordinated control. At the same time, existing technical solutions lack an in-depth understanding and modeling of the dynamic characteristics of the ventilation system, and are unable to accurately capture the pressure difference field distribution and its evolution between different ventilation zones. This makes it difficult for control strategies to adapt to the stringent requirements of nuclear power plant ventilation systems, especially in terms of rapid response and stable control capabilities in emergency situations. Summary of the Invention

[0004] The present invention provides a frequency conversion control method and system for a ventilation system of a nuclear power plant. The present invention can adaptively generate target frequency conversion control parameters, significantly improve the control performance, and achieve a smooth transition of the ventilation system of the nuclear power plant.

[0005] In a first aspect, the present invention provides a frequency conversion control method for a ventilation system in a nuclear power plant, the frequency conversion control method for a ventilation system in a nuclear power plant comprising:

[0006] Collect real-time operating data from multiple areas of the nuclear power plant ventilation system and perform standardization processing to obtain a standardized data set;

[0007] Performing fan performance curve fitting and pressure difference field feature mapping on the standardized data set to obtain pressure difference field mapping features;

[0008] Inputting the pressure difference field mapping characteristics into the active neural pressure difference field network model to predict the variable frequency parameters and obtain the target variable frequency control parameters;

[0009] The target frequency conversion control parameters are subjected to feedforward-feedback combined control by a multi-mode frequency conversion controller to obtain the fan speed and air valve opening value.

[0010] In a second aspect, the present invention provides a variable frequency control system for a nuclear power plant ventilation system, the variable frequency control system for the nuclear power plant ventilation system comprising:

[0011] The acquisition module is used to collect real-time operating data from multiple areas of the nuclear power plant ventilation system and perform standardization processing to obtain a standardized data set;

[0012] A feature mapping module, configured to perform fan performance curve fitting and pressure difference field feature mapping on the standardized data set to obtain pressure difference field mapping features;

[0013] A frequency conversion parameter prediction module is used to input the pressure difference field mapping characteristics into the active neural pressure difference field network model to predict the frequency conversion parameters and obtain the target frequency conversion control parameters;

[0014] The combined control module is used to perform feedforward-feedback combined control on the target variable frequency control parameter through a multi-mode variable frequency controller to obtain the fan speed and air valve opening value.

[0015] In the technical solution provided by the present invention, in terms of data quality, a distributed sensor network and a dual-channel redundant acquisition mechanism are used, combined with cubic spline interpolation to repair missing data, and digital filtering technology is used to effectively filter out power grid interference to ensure data integrity and reliability. In terms of system characteristic characterization, a complete mathematical model of ventilation system characteristics is constructed by accurately modeling the fan impedance characteristics and the duct network topology. In terms of dynamic characteristic capture, the finite element method is used to construct the pressure difference field function and the empirical mode decomposition method is combined to extract core features, achieving a comprehensive characterization of the dynamic characteristics of the ventilation system and predicting its future state. In terms of control strategy, an active neural pressure difference field network architecture is used to integrate feature extraction, pressure difference prediction, and parameter generation functions to form an end-to-end intelligent control system and adaptively generate target variable frequency control parameters. In terms of operating mode, intelligent switching between normal operation, emergency response, and maintenance modes is achieved, combining coordinated control of fans and dampers with a multi-zone collaborative mechanism to ensure stable operation of the system under various operating conditions. In terms of fault management, a deep belief network is used to accurately identify common faults. Combined with a hierarchical fault response strategy and fault prediction based on a recurrent neural network, the system reliability and safety are significantly improved.

[0016] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood through implementation of the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of an embodiment of a frequency conversion control method for a ventilation system of a nuclear power plant according to an embodiment of the present invention;

[0019] Figure 2 The figure is a schematic diagram of an embodiment of a variable frequency control system of a nuclear power plant ventilation system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] The terms "including," "having," and any variations thereof, as used in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or device.

[0022] To facilitate understanding of this embodiment, a frequency conversion control method for a nuclear power plant ventilation system disclosed in an embodiment of the present invention is first described in detail. Figure 1 As shown, this method includes the following steps:

[0023] 101. Collect real-time operating data from multiple areas of the nuclear power plant ventilation system and perform standardization processing to obtain a standardized data set;

[0024] It is understandable that the execution subject of the present invention may be a variable frequency control system of a nuclear power plant ventilation system, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0025] Specifically, a multi-zone real-time data acquisition network for the nuclear power plant's ventilation system was constructed. This network covers multiple key building areas within the plant. Within each area, a series of high-precision, multi-parameter environmental monitoring sensors were deployed. These sensors include temperature sensors, humidity sensors, differential pressure sensors, wind speed sensors, and radiation level monitors, distributed throughout ventilation ducts, exhaust outlets, and key measurement locations within the plant. Together, these devices form a distributed data acquisition network, ensuring real-time acquisition of parameters such as temperature, humidity, airflow differential pressure, wind speed, and radiation levels in each area. High-frequency data transmission ensures real-time data and dynamic responsiveness. A dual-channel redundant acquisition and transmission solution is implemented for multi-zone real-time operational data. This solution involves configuring two completely independent acquisition and communication channels at each sensor location to ensure high reliability and fault-tolerance. After data acquisition is complete, these two channels independently transmit data streams to the central processing unit, forming two parallel and independent real-time data streams. Cross-comparison verification is performed on these two parallel data streams to identify data loss points or abnormal data points. By calculating the difference between data collected at the same location across two channels and setting a clear anomaly threshold (e.g., based on multiples of the standard deviation or absolute error threshold), data anomalies or missing locations can be quickly identified. When the data at a timestamp location differs beyond the set threshold, the location is marked as missing. After marking missing or anomalous data points, data reconstruction using a cubic spline interpolation function is performed to correct the missing or anomaly data at these locations. Cubic spline interpolation effectively meets the requirements for curve continuity and smoothness and is highly effective in fitting the fluctuating trends of various operational data related to nuclear power plant ventilation systems, such as temperature, pressure differential, and wind speed. Using the cubic spline interpolation method, the adjacent valid data at the marked location is used as an interpolation reference point. The reconstructed data value at the marked location is interpolated and calculated, resulting in a repaired continuous data stream. This repaired continuous data stream is then digitally filtered to suppress and reduce the effects of random noise and interference from the complex operating environment of nuclear power plants, thereby extracting the true trends and valid features inherent in the data. When performing digital filtering processing, an appropriate cutoff frequency is selected based on the characteristics of the nuclear power plant ventilation system data to ensure that useful change trends are not filtered out while unnecessary interference noise is effectively removed, ultimately generating a standardized data set.

[0026] 102. Perform fan performance curve fitting and pressure difference field feature mapping on the standardized data set to obtain pressure difference field mapping features;

[0027] Specifically, dynamic testing and analysis of fan operating parameters within the ventilation system were conducted based on real-time operating data from multiple regions. This dynamic testing and analysis was based on parameters such as fan speed, power, flow rate, and vibration. Using real-time fan operating data, a set of raw performance curve data points was obtained under different load conditions. Least squares fitting was performed on these raw performance curve data points, effectively optimizing the pressure differential-flow relationship, i.e., the fan impedance curve equation, based on the measured fan operating data points. Using the least squares method, a fitting function was constructed with fan flow rate as the independent variable and the pressure differential between the fan outlet and inlet as the dependent variable. The objective function was defined to minimize the sum of squared residuals. By iteratively optimizing the fitting parameters in the function, a fan impedance characteristic function model was derived, revealing the pressure differential characteristics of the fan under variable frequency control. Simultaneously, topological modeling was performed on the pipe network structure information included in the standardized dataset. By clarifying the topological connectivity between ventilation paths within the pipe network and the resistance distribution characteristics along each path, a complete mathematical model of the ventilation system network was formed. In establishing this ventilation network topology model, topological node information, including inlet and outlet ports, branch nodes, fan locations, and valve locations, is identified. Based on the actual ventilation duct length, diameter, shape, and resistance coefficient, the flow resistance characteristic parameters of each duct segment are determined, resulting in a detailed representation of the ventilation system network. Based on the ventilation system network model, a node association matrix and boundary condition vectors are constructed to clearly represent the connectivity and actual operational boundary conditions between nodes in the ventilation network. Together, these two vectors form a ventilation system resistance characteristic matrix equation that describes the flow characteristics of the entire ventilation network. Based on the fan impedance model and the ventilation system resistance characteristic matrix equation, a pressure differential field function is constructed to effectively characterize the dynamic interaction between fan performance and ventilation system structure. By solving the pressure differential field function, the pressure differential distribution at each node in the ventilation network under specific variable frequency control parameters is obtained, providing a quantitative representation of the pressure differential distribution characteristics of the overall system operation. Through numerical solution and analysis of the pressure differential field function, pressure differential field mapping features are extracted that effectively reflect the real-time dynamic operational characteristics of the nuclear power plant ventilation system.

[0028] The control areas involved in the nuclear power plant ventilation system are spatially divided, and the boundary conditions of the control areas are clearly defined to construct a spatial model covering the entire ventilation control system. The construction of this spatial model requires comprehensive consideration of the structural characteristics of the nuclear power plant building and the layout of the ventilation network to ensure that the model accurately reflects the interconnected and independent characteristics of the actual ventilation areas. The entire ventilation control space is divided into p control areas through appropriate spatial mesh refinement to accurately reflect the spatial distribution of pressure differentials in different areas during operation. Based on the spatial model, a set of Laplace equations describing the steady-state pressure differential distribution is established at each grid node. The fan outlet pressure is set as the boundary condition, forming a complete and solvable mathematical boundary value problem. By solving this Laplace boundary value problem, the pressure differential field distribution under initial steady-state conditions is obtained. This step reveals how the fan outlet pressure affects the pressure differential variation at different spatial nodes, thus providing a preliminary spatial pressure differential field state. A time dimension is introduced into the initial pressure differential field distribution, and the empirical mode decomposition algorithm is applied to dynamically analyze and decompose the pressure differential field data. Using empirical mode decomposition (EMD), the complex, nonlinear, and nonstationary pressure differential field time series is decomposed into a set of intrinsic mode functions (IMFs) with clear physical meaning. This IMF set effectively captures the dynamic characteristics of the pressure differential field at different scales and reveals the transient response characteristics of the nuclear power plant ventilation system under actual operating conditions. Hilbert spectrum analysis is performed on the IMF set to obtain key dynamic information, such as the instantaneous frequency and amplitude of the pressure differential field. This results in a pressure differential field spectral feature set that characterizes the dynamic characteristics of the pressure differential field, reflecting the pressure differential fluctuation characteristics, transient processes, and system stability of each control area in the nuclear power plant ventilation system. Based on the pressure differential field spectral feature set, a feature vector is constructed for each control area for subsequent intelligent control decision-making. Each region's feature vector contains multi-dimensional characteristic parameters, such as the mean value, standard deviation, crest factor, pulsation intensity, and autocorrelation function decay rate of the regional pressure differential field, fully expressing the dynamic trend of the regional pressure differential and its stability, periodicity, or random fluctuation characteristics. To accurately map pressure differential field characteristics to fan operating parameters (including fan speed and damper opening), the response surface methodology (RSM) was introduced as a key tool for constructing the relationship between the pressure differential field eigenvectors and fan control parameters. The RSM was used to describe the sensitivity of the pressure differential field's dynamic characteristics to changes in fan operating conditions. Based on this relationship, an autoregressive moving average (ARMA) model was developed to effectively capture the dynamic mapping patterns between the eigenvectors and fan speed and damper opening over time. Through the ARMA model construction and parameter identification process, the pressure differential field mapping characteristics of the nuclear power plant ventilation system under different operating conditions were ultimately obtained, and the precise conversion of the pressure differential field state to fan operating control parameters was achieved.

[0029] 103. Input the pressure difference field mapping characteristics into the active neural pressure difference field network model to predict the variable frequency parameters and obtain the target variable frequency control parameters;

[0030] Specifically, the pressure differential field mapping features are input into the feature extraction network within the active neural pressure differential field network model. This feature extraction network is designed as a deep neural network with a multi-layer, fully connected structure. Through effective nonlinear mapping and dimensionality compression, it reduces the dimensionality of the input high-dimensional pressure differential field mapping features, generating a latent feature representation that efficiently characterizes the pressure differential field state of the nuclear power plant ventilation system. The latent feature representation is then input into the pressure differential field prediction network within the active neural pressure differential field network model, which utilizes a two-layer long short-term memory (LSTM) neural network architecture. Due to the LSTM network's ability to analyze time series data and capture long-term dependencies, it can efficiently and accurately analyze and predict future pressure differential field trends when modeling and predicting highly dynamic, nonlinear, and time-dependent pressure differential field data within the nuclear power plant ventilation system. The LSTM network's gating mechanism effectively mitigates the time delay associated with dynamic changes in the pressure differential field, enabling the network to accurately predict future pressure differential field changes based on the current latent feature representation, thereby obtaining real-time pressure differential field change predictions. The active neural pressure differential network model simultaneously inputs the latent feature representation and predicted pressure differential field changes into the control parameter generation network within the network. This control parameter generation network utilizes a multi-layer, fully connected neural network structure. Through nonlinear mapping of the latent feature representation and predicted pressure differential field values, it efficiently maps from the pressure differential field feature space to the variable frequency control parameter space, generating an initial set of variable frequency control parameters. These parameters include basic operational control variables such as initial fan speed and initial damper opening. The initial parameter determination process considers the current operating conditions of the nuclear power plant's ventilation system and future pressure differential field trends, thereby enabling efficient decision-making for the ventilation system's fan operating parameters. Furthermore, to enhance the accuracy and practical applicability of the variable frequency control parameters, a pattern recognition analysis is performed on the pressure differential field mapping features previously input to the network. Using pattern recognition techniques, the system's current pressure differential field feature data is matched against historical data for similarity, determining the system's current historical operating mode. This process effectively identifies the pattern characteristics of the ventilation system's current operating conditions and incorporates historical experience into the control decision-making process, making subsequent control strategies more environmentally adaptable and reliable. Based on the historical operating mode determination results from the above pattern recognition analysis, mode adaptive adjustment is performed on the initial variable frequency control parameters. By automatically retrieving the optimal control adjustment experience from the historical operating mode database, appropriate gain correction and compensation are applied to the initial variable frequency control parameters based on the historical operating mode determined by the current system, ultimately forming the target variable frequency control parameters suitable for the current operating state.

[0031] 104. The target frequency conversion control parameters are controlled by feedforward-feedback combination through a multi-mode frequency conversion controller to obtain the fan speed and air valve opening value.

[0032] Specifically, a multi-mode variable frequency controller (VFD) performs real-time scenario analysis and pattern recognition on the target VFD control parameters to determine the current system operating status. This process uses a pattern recognition algorithm to classify the current operating mode, based on real-time data collected by the system and pre-set operating rules, combined with pressure differential field mapping characteristics, fan operating status, and historical operating modes. The current operating mode is primarily categorized into normal operating mode, emergency response mode, and maintenance mode. Normal operating mode corresponds to the stable state of the nuclear power plant ventilation system under standard operating conditions. Its primary goal is to maintain ventilation efficiency and system safety while minimizing energy consumption. Emergency response mode is used to address emergencies such as pipeline leaks, nuclear accident risks, or other abnormal conditions. In this mode, the control strategy focuses on rapidly adjusting fan and damper operating parameters to maximize ventilation efficiency, enhance plant pressure differential control capabilities, and suppress the spread of radioactive materials. Maintenance mode is suitable for equipment maintenance or fan adjustments under specific operating conditions. This mode focuses on fan operation stability and avoiding unnecessary energy waste. The target VFD control parameters are input into the feedforward control unit for initial parameter calculation. The main function of the feedforward control unit is to calculate the initial frequency conversion parameters based on the current operating mode, utilizing a trained fan characteristic model and pressure differential field predictions. This initial calculation preliminarily determines the fan speed and damper opening values appropriate for the current state, thereby forming a preliminary frequency conversion control solution. This calculation takes into account the fan impedance characteristics, ventilation system load conditions, and the optimal solution from historical optimization control strategies to ensure that the initial frequency conversion parameters meet the current ventilation system operating requirements. A feedback control mechanism is introduced to compensate for errors caused by external disturbances, load variations, or system response lag. By comparing the deviation between the system output predicted by the initial frequency conversion parameters and the actual measured pressure differential, the current system control error is calculated. The initial frequency conversion parameters and this error signal are then input into an incremental proportional-integral-derivative (PID) controller for feedback compensation. The incremental PID controller dynamically adjusts the frequency conversion control parameters based on the real-time error signal, gradually converging the system output to the optimal state while preventing excessive disturbances or oscillations during the control process, thereby improving system response speed and stability. The corresponding control increment is obtained through the PID controller's calculations. Based on the operating mode determination and control increment, the mode preset control strategy is executed to optimize the final control instructions. The control increment is adaptively adjusted according to the requirements of different operating modes. For example, in normal operating mode, the optimization strategy focuses on energy-saving control and stable fan operation, while in emergency response mode, priority is given to increasing ventilation rate and enhancing negative pressure control. In maintenance mode, the optimized control logic should appropriately reduce the fan operating intensity to reduce equipment wear and ensure the safety of maintenance work. By applying the mode preset control strategy, the final mode optimization control output can be more closely aligned with actual operating requirements.Based on the mode optimization control output and the actual pressure differential deviation, the coordinated control logic for fans and dampers is executed, generating synergistic control instructions. Due to the strong coupling between the operation of fans and dampers, adjusting either device individually can affect the overall pressure differential distribution of the system. The core goal of the coordinated control logic is to ensure synergy between fan speed adjustment and damper opening changes, ensuring that the entire ventilation system maintains optimal performance under different operating modes. Multi-zone coordinated control and load switching are performed based on the synergistic control instructions and the regional coupling matrix, generating fan speed and damper opening values. The regional coupling matrix is a mathematical model that describes the air flow relationships between ventilation control zones. It quantifies the ventilation impact between different zones and allows the dynamic response characteristics of the entire system to be considered when controlling fans and dampers. By utilizing the regional coupling matrix, the coordinated control logic for fan speed and damper opening is optimized, ensuring that ventilation requirements in each plant area are properly met. Furthermore, under load fluctuations, the system intelligently implements load switching strategies to optimize fan efficiency.

[0033] System performance is evaluated based on fan speed and damper opening to obtain comprehensive performance indicators. A multi-dimensional analysis of fan and damper operating conditions assesses efficiency, safety, and stability under current operating conditions. The calculation of comprehensive performance indicators requires incorporating actual ventilation system operational data, including key factors such as fan energy consumption, damper adjustment response rate, plant pressure differential stability, air flow uniformity, equipment vibration amplitude, and radioactive material control capabilities. A multi-objective weighted evaluation model is established to calculate a comprehensive performance score to quantify the overall system operational quality. Threshold comparison analysis is performed on the comprehensive performance indicators to determine whether parameter optimization or fault diagnosis is necessary. A set of reasonable performance threshold ranges is set and the current comprehensive performance indicators are compared with these preset thresholds. If the comprehensive performance indicators remain within the normal operating range, the system continues to operate according to the existing control strategy. However, if the indicators deviate from the preset thresholds (e.g., abnormally increased fan energy consumption, delayed damper opening adjustment, or excessive system pressure differential fluctuation), parameter optimization or fault diagnosis procedures are triggered, generating a parameter optimization trigger signal. After the parameter optimization trigger signal is activated, multi-dimensional features are extracted from the operating data of fan speed and damper opening to obtain a fault feature vector. This feature extraction process encompasses three aspects: time domain, frequency domain, and state features. Time domain features primarily include parameters such as fan vibration mean, standard deviation, skewness, kurtosis, and pulsation amplitude, reflecting the stability and dynamic fluctuations of fan and damper operation. Frequency domain features utilize fast Fourier transforms to analyze the frequency components of fan and damper operating data to detect the presence of abnormal frequency components. For example, a fan bearing or blade failure may produce an abnormal signal within a specific frequency band. State features are analyzed by comparing historical data based on the ventilation system's operating mode to determine whether the fan's operating state has significantly changed under different modes. For example, abnormal fan current fluctuations under the same load or a slow system response after damper adjustment could indicate a potential system fault. Through this feature extraction process, a fault feature vector is generated, effectively representing the current operational health of the fan and damper. The fault feature vector is then input into a deep belief network consisting of a four-layer restricted Boltzmann mechanism for pattern recognition, determining the fault type and its probability distribution. The Restricted Boltzmann Machine (RBM) is an unsupervised learning algorithm that automatically extracts features and learns fault patterns from massive amounts of operational data. The Deep Belief Network, composed of multiple layers of stacked RBMs, can learn a hierarchical representation of ventilation system faults through layer-by-layer training. During model training, the RBM is pre-trained in an unsupervised manner to learn typical fault characteristics under different fan operating modes. Then, supervised training layers are added to the trained RBMs to enable the network to accurately map input fault feature vectors to different fault categories.During real-time system operation, a deep belief network automatically identifies possible fault types based on input feature vectors and calculates the probability distribution of each fault type, providing accurate fault classification results. After fault pattern identification, a hierarchical fault response strategy analysis is performed based on the fault type and its probability distribution to generate the optimal fault handling solution. These fault response strategies are categorized by fault severity. For example, for minor faults (such as damper adjustment delays or slight increases in fan power consumption), adaptive compensation is achieved by adjusting control parameters or optimizing the PID control strategy. For moderate faults (such as abnormal vibration caused by fan bearing wear or changes in localized pipe network resistance), mitigation measures such as local load adjustment, fan start / stop switching, or maintenance alerts are implemented, and a maintenance plan is scheduled. For severe faults (such as fan blade damage or blockage in critical ventilation system ducts), an emergency mode is immediately triggered, implementing safety measures such as rapid shutdown, switching to backup fans, or emergency pressure relief to prevent serious system accidents. This hierarchical response strategy ensures that potential faults can be identified in real time during ventilation system operation, and optimal optimization and safety measures are implemented to maintain the stability and efficiency of the nuclear power plant's ventilation system.

[0034] In an embodiment of the present invention, data quality is improved by employing a distributed sensor network and a dual-channel redundant acquisition mechanism, combined with cubic spline interpolation to repair missing data. Digital filtering technology is also used to effectively filter out grid interference, ensuring data integrity and reliability. System characterization is achieved by accurately modeling fan impedance characteristics and duct network topology to construct a complete mathematical model of ventilation system characteristics. Dynamic characteristic capture is achieved by constructing a pressure differential field function using the finite element method and extracting core features using the empirical mode decomposition method, enabling comprehensive characterization of the ventilation system's dynamic characteristics and future state prediction. Control strategy integrates feature extraction, pressure differential prediction, and parameter generation using an active neural pressure differential field network architecture to form an end-to-end intelligent control system that adaptively generates target variable frequency control parameters. Operational modes are achieved by intelligently switching between normal operation, emergency response, and maintenance modes. Coordinated control of fans and dampers, combined with a multi-zone collaborative mechanism, ensures stable system operation under various operating conditions. Fault management uses a deep belief network to accurately identify common faults. This, combined with a hierarchical fault response strategy and recurrent neural network-based fault prediction, significantly improves system reliability and safety.

[0035] In a specific embodiment, the process of executing step 101 may specifically include the following steps:

[0036] A ventilation system monitoring network is constructed using distributed airflow sensors, differential pressure sensors, temperature sensors, and humidity sensors. This network collects real-time operating data from multiple areas of the nuclear power plant's ventilation system.

[0037] Perform dual-channel redundant collection and transmission of real-time operating data from multiple regions to obtain dual-verified data streams, and perform anomaly detection on the dual-verified data streams to obtain the locations of data missing markers;

[0038] The cubic spline interpolation function is applied to reconstruct the data at the data missing mark position to obtain the repaired continuous data stream, and the repaired continuous data stream is digitally filtered to obtain a standardized data set.

[0039] Specifically, a distributed sensor network is deployed throughout key areas of the nuclear power plant. This network, comprised of a variety of measurement devices, including airflow sensors, differential pressure sensors, temperature sensors, and humidity sensors, ensures real-time monitoring of key operating parameters such as air flow, differential pressure distribution, and temperature and humidity changes across the plant. Given the complexity of the plant's internal ventilation system, sensors should be deployed across multiple typical areas, such as the main ventilation ducts, air exchange openings within each building, areas surrounding key equipment, and emergency exhaust systems. Sensor density is dynamically adjusted based on the importance of each area, ensuring higher spatial resolution in high-risk areas and lower sampling density in low-impact areas to optimize data acquisition costs and system response speed. To enhance data acquisition reliability and interference resistance, the ventilation system monitoring network utilizes a dual-channel redundant acquisition and transmission mechanism. Data from each monitoring point is collected simultaneously by two independent data acquisition channels and transmitted to the central data processing unit via two independent communication paths, creating a dual-verified data stream. This dual-channel redundant design effectively reduces the risk of data loss or anomalies due to sensor failure, network transmission interference, or external environmental influences, and ensures real-time verification and error correction during data transmission. Set the sensor measurement values of the two channels to be and , if the error between the two satisfies the following conditions:

[0040]

[0041] in, If the error threshold is greater than the set allowable error threshold, the data at that time point is considered to be abnormal or missing, and the data is marked as missing. For the data points that have been marked as missing or abnormal, data reconstruction is performed to complete the missing information and ensure the continuity of the data. Since the operating parameters of the ventilation system have a strong time correlation, it is suitable to use the cubic spline interpolation function for data reconstruction. The core idea of cubic spline interpolation is to construct a smooth cubic polynomial curve at the missing point so that the interpolated data maintains the continuity of the second-order derivative within the fitting interval, thereby ensuring the physical rationality of the data. Assume that in a certain time interval If there is data missing, the cubic spline interpolation function is expressed as:

[0042]

[0043] in, Indicates that in the interval The interpolation function inside is the interpolation coefficient to be determined. In order to ensure the smoothness of the interpolation curve and the rationality of the data, the following conditions need to be met:

[0044] Continuity of interpolation points:

[0045]

[0046] Continuity of the first-order derivative:

[0047] ;

[0048] Continuity of the second-order derivative:

[0049]

[0050] By solving the above constraint equations, we can obtain the interpolation coefficients , and then calculate the interpolated values of missing data points , generating a repaired continuous data stream. After data reconstruction, the repaired data stream is digitally filtered to remove high-frequency noise and retain the true physical signal characteristics. Considering that the data changes of the ventilation system have low-frequency characteristics, and high-frequency signals are often the result of measurement noise or environmental interference, a low-pass filter is used for processing. Assuming that the reconstructed data stream is , then the filtered signal Expressed as:

[0051]

[0052] in, is the impulse response function of the filter, and a Butterworth filter or a Kalman filter is selected for signal smoothing. For example, if a second-order Butterworth filter is used, its transfer function is expressed as:

[0053]

[0054] in, The cutoff frequency is set to an appropriate value according to the data characteristics to ensure that the true dynamic characteristics of the system are retained as much as possible while removing high-frequency noise. After completing the digital filtering process, a standardized data set is finally obtained.

[0055] In a specific embodiment, the process of executing step 102 may specifically include the following steps:

[0056] Perform dynamic test analysis on the fan operating parameters in the standardized data set to obtain the fan original performance curve data point set;

[0057] The original performance curve data point set is fitted and calculated using the least squares method to obtain the fan impedance model. At the same time, the pipe network structure information in the standardized data set is topologically modeled to obtain the ventilation system network model.

[0058] Based on the ventilation system network model, the node correlation matrix and boundary condition vector are constructed to obtain the ventilation system resistance characteristic matrix equation;

[0059] The pressure difference field function is constructed based on the fan impedance model and the ventilation system resistance characteristic matrix equation, and the pressure difference field mapping characteristics that characterize the dynamic characteristics of the ventilation system are calculated.

[0060] Specifically, the key parameters of the fan under different operating conditions are collected for a long time and at a high frequency. These parameters include the fan speed, air volume, power consumption, inlet and outlet pressure difference and environmental conditions (temperature, humidity, etc.). The fan performance curve is obtained by experimentally measuring the flow rate of the fan under different operating conditions. and pressure Since the fan is affected by complex pipe network resistance and variable operating conditions during operation, its performance curve is not a single fixed one. Therefore, multiple data points under different operating conditions are dynamically collected to form the fan's original performance data set. The original performance curve data point set is fitted and calculated using the least squares method to establish the fan's impedance model. The core of the fan impedance model is to describe the nonlinear relationship between the fan's flow rate and pressure difference, and a quadratic polynomial or cubic polynomial is used for fitting:

[0061]

[0062] in, represents the pressure difference of the fan, is the fan flow rate, are the fitting coefficients to be determined. To determine these coefficients, construct the least squares error function:

[0063]

[0064] in, Represents the number of sampled data points, and is the fan flow rate and pressure difference value measured in the experiment. about The optimal fitting parameters of the fan impedance model are obtained by solving the set of equations with zero partial derivatives, thereby accurately describing the flow-pressure difference characteristics of the fan. At the same time, in order to establish a complete ventilation system network model, the pipe network structure information in the standardized data set is topologically modeled. The ventilation pipe network is abstracted as a graph structure consisting of several nodes and connecting edges, where the nodes represent key positions in the pipe network, such as fan inlets, outlets, branch intersections and exhaust vents, and the edges represent ventilation ducts or local resistance elements (such as valves, filters, etc.). Based on the topological relationship, the node association matrix of the ventilation system is constructed. , where the elements Representation node and In addition, the boundary condition vectors of the ventilation system are defined. , which includes the inlet and outlet pressure conditions of the fan, environmental factors (such as external wind pressure), etc., and describes the state of the system under external influences. After the topology modeling is completed, based on the node association matrix and the boundary condition vector Construct the resistance characteristic matrix equation of the ventilation system. Assume that the airflow in the ventilation duct obeys the Darcy-Weisbach equation:

[0065]

[0066] in, is the coefficient of friction, is the pipe length, is the pipe diameter, is the air density, is the air velocity. Combining the fan pressure difference formula and the pipe network topology model, the resistance characteristic matrix equation is established:

[0067]

[0068] in, is the resistance matrix of the ventilation system, which describes the flow resistance characteristics of components such as pipes, valves, and fans. is the air volume vector, which represents the air volume distribution of each pipe in the system. is the boundary condition vector, which includes factors such as the fan outlet pressure and the external wind pressure. After obtaining the fan impedance model and the ventilation system resistance characteristic matrix equation, a pressure difference field function is constructed to characterize the overall dynamic characteristics of the ventilation system. The pressure difference field function establishes a continuous mathematical model, allowing the pressure difference distribution at each spatial location in the ventilation system to be calculated using analytical or numerical methods. It is assumed that the spatial area of the ventilation system is discretized into a finite number of grid cells, and the air flow within each grid cell is assumed to satisfy the Poisson equation:

[0069]

[0070] in, The Laplace operator representing the pressure field, is the air flow rate per unit volume, is the aerodynamic viscosity coefficient. By solving this equation and combining the boundary condition vector , obtain the pressure difference field distribution of the entire ventilation system. In order to more specifically describe the dynamic characteristics of the ventilation system, the pressure difference field mapping characteristics are calculated. These characteristics are used to evaluate the operating status and stability of the system. For example, the energy distribution function of the pressure difference field is defined as:

[0071]

[0072] in, Represents the pressure difference energy of the entire system, For the space area of the ventilation system. If it is too large, it means that the system has high wind resistance loss, and it is necessary to optimize the fan operation strategy or adjust the air valve opening.

[0073] In a specific embodiment, the process of executing the step of constructing a pressure difference field function based on the fan impedance model and the ventilation system resistance characteristic matrix equation, and calculating the pressure difference field mapping characteristics that characterize the dynamic characteristics of the ventilation system may specifically include the following steps:

[0074] Perform spatial division and boundary definition on the ventilation system control area to obtain a spatial model containing p control areas;

[0075] Based on the spatial model, the Laplace equation and the fan outlet pressure boundary conditions are established at each grid node to obtain the initial pressure difference field distribution;

[0076] The time dimension is introduced into the initial pressure difference field distribution and the empirical mode decomposition algorithm is applied to obtain the set of intrinsic mode functions representing the time series of the pressure difference field.

[0077] Perform Hilbert spectrum analysis on the intrinsic mode function set to obtain the pressure difference field spectrum feature set consisting of instantaneous frequency and instantaneous amplitude information;

[0078] Based on the pressure difference field spectrum feature set, a feature vector is constructed for each control area. The feature vector includes the pressure difference average value, standard deviation, peak factor, pulsation intensity and autocorrelation function decay rate.

[0079] The response surface methodology is used to establish the mapping relationship between the characteristic vector and the fan speed and air valve opening, and an autoregressive moving average model is constructed to obtain the pressure difference field mapping characteristics.

[0080] Specifically, the entire ventilation system area is divided into blocks. Each control area corresponds to a functional unit in the ventilation system of a nuclear power plant, such as the main ventilation duct, auxiliary ventilation outlet, fuel storage room, reactor building exhaust system, etc. The division criteria are based on the fan layout, damper adjustment capacity, air flow distribution characteristics and boundary constraints to ensure that the flow characteristics of each area can be analyzed independently and can be coupled with each other during the overall modeling. For the entire ventilation system space, For the control areas, there are:

[0081]

[0082] The union of all regions covers the entire ventilation system and they do not overlap with each other. The boundary of each region It is a physical boundary (such as a plant wall), a fan outlet, a damper control port, or a shared boundary of an adjacent area. Based on this spatial model, the Laplace equation is established at each grid node to solve the static pressure difference field distribution. is the pressure difference distribution function in the ventilation system. In the absence of an external pressure source, the pressure difference field satisfies the Poisson equation:

[0083]

[0084] in, is the Laplace operator of the pressure field, is the air flow rate per unit volume, is the aerodynamic viscosity coefficient. For the boundary conditions of the fan outlet, the pressure at the fan outlet is , then it is necessary to meet the following requirements:

[0085]

[0086] in is the fan outlet boundary. This set of equations is solved by the finite difference method or the finite element method to obtain the initial pressure difference field distribution. After obtaining the static pressure difference field, in order to describe the dynamic characteristics of the ventilation system, the time dimension is introduced, making the pressure difference field a time dimension. The function of The empirical mode decomposition method is applied to decompose the pressure difference field time series into a set of intrinsic mode functions (IMFs), namely:

[0087]

[0088] in, It is An intrinsic modal function, is the residual term, which represents the trend term that has not been decomposed. Each modal function corresponds to a pressure difference oscillation component of different scales, which can reflect the dynamic characteristics of ventilation on different time scales. Hilbert spectrum analysis is performed on the set of intrinsic modal functions to extract the instantaneous frequency and instantaneous amplitude information to form the spectral feature set of the pressure difference field. Assume The Hilbert transform of is:

[0089]

[0090] Then the instantaneous amplitude and instantaneous frequency are:

[0091]

[0092]

[0093] in, represents the instantaneous intensity of the pressure difference fluctuation, Represents the local pressure difference fluctuation frequency. By analyzing the instantaneous spectrum characteristics of different areas, the pressure change pattern of different areas of the ventilation system is identified. Based on the extracted pressure difference field spectrum feature set, a feature vector is constructed for each control area. The eigenvectors of are:

[0094]

[0095] in, It is a region The average pressure difference, is the standard deviation, is the crest factor, a measure of extreme pressure fluctuations:

[0096]

[0097] is the pulsation intensity:

[0098]

[0099] is the decay rate of the autocorrelation function:

[0100]

[0101] This eigenvector can fully characterize the dynamic characteristics of the pressure difference in the control area. In order to establish the mapping relationship between the eigenvector and the fan speed and the air valve opening, the response surface method is used. Assuming that the fan speed Air valve opening Influencing the pressure difference eigenvector, the second-order response surface equation is constructed:

[0102]

[0103] in, is an undetermined parameter obtained by fitting experimental data. In order to establish a dynamic pressure difference field prediction model, an autoregressive moving average model is constructed, and the pressure difference characteristic vector is assumed to evolve over time as follows:

[0104]

[0105] in, and are the autoregressive coefficient and the moving average coefficient, is a white noise term. The model can predict the pressure difference field characteristics of different control areas and optimize the fan control strategy to achieve efficient and intelligent management of the nuclear power plant ventilation system.

[0106] Among them, the finite element method is used to construct the pressure difference field function based on the impedance model and the ventilation system resistance characteristic matrix equation, and the pressure difference field mapping characteristics that characterize the dynamic characteristics of the ventilation system are obtained. Before the pressure difference field mapping characteristics are input into the active neural pressure difference field network architecture for variable frequency parameter prediction, the following steps are also included: based on the pressure difference field mapping characteristics, the basic dynamic equations of the ventilation system are constructed to obtain a group of partial differential equations that describe the evolution of the pressure difference field. The equation group includes the mass conservation equation, the momentum conservation equation and the energy conservation equation, and introduces vortex and turbulence correction terms; the partial differential equation group is parameterized using a physical constraint neural network to obtain a neural network model embedded with physical knowledge. The forward propagation part of the neural network model represents the equation solving process, and the loss function contains a measure of violation of physical laws; the neural network model is deployed at the boundary points of each key area of the nuclear power plant ventilation system to obtain a distributed environmental perception network. The distributed network consists of multiple active perception nodes, and each node has local computing and communication capabilities; based on the distributed environmental perception network, the environmental parameters of the nuclear power plant ventilation system are actively detected to obtain real-time environmental information. Environmental disturbance data is collected and actively detected, and controllable small disturbances are generated by fine-tuning the fan speed or air valve opening, and the system response is recorded. The spatiotemporal attention mechanism is applied to the real-time environmental disturbance data for multi-scale analysis to obtain the environmental change feature map. The attention mechanism highlights the environmental change pattern of key time points and spatial locations through adaptive weighting. The environmental change feature map is used to model the inter-regional impact propagation through a graph neural network guided by physical knowledge to obtain the dynamic pressure difference field topology structure. The nodes in the graph neural network represent pressure measurement points and the edges represent airflow propagation paths. The dynamic pressure difference field topology structure is compared with the traditional CFD simulation results for verification and error correction to obtain a corrected high-precision pressure difference field dynamic model. The correction process uses the Bayesian optimization algorithm to minimize the deviation between the measured value and the predicted value. Based on the high-precision pressure difference field dynamic model, an active adaptive pressure difference control strategy library is constructed to obtain the optimal control parameter combination for different environmental changes. The control strategy library adopts a hierarchical structure, which includes three levels: steady-state control, transition state control and emergency response control, and continuously optimizes the control strategy through reinforcement learning methods.

[0107] In a specific embodiment, the process of executing step 103 may specifically include the following steps:

[0108] The pressure difference field mapping features are input into the feature extraction network in the active neural pressure difference field network model for dimensionality reduction to obtain the potential feature representation;

[0109] The pressure difference field prediction network with a double-layer LSTM structure in the active neural pressure difference field network model is used to perform time series analysis on the potential feature representation to obtain the predicted value of the pressure difference field change.

[0110] The potential feature representation and the predicted value of the pressure difference field change are input into the control parameter generation network in the active neural pressure difference field network model for mapping conversion to obtain the initial variable frequency control parameters;

[0111] Perform pattern recognition analysis on the pressure difference field mapping characteristics to obtain historical working mode determination results;

[0112] Based on the historical working mode determination results, the initial frequency conversion control parameters are adaptively adjusted to obtain the target frequency conversion control parameters.

[0113] Specifically, the pressure difference field mapping features are processed with dimensionality reduction to reduce data redundancy, improve subsequent computational efficiency, and extract the most representative potential feature representation. Since the pressure difference field mapping features contain multidimensional feature vectors of multiple control regions, such as pressure difference average value, standard deviation, peak factor, pulsation intensity, and autocorrelation function decay rate, a nonlinear dimensionality reduction method is used to construct a feature extraction network. Suppose the original pressure difference field feature vector is ,in represents the number of samples, Represents the feature dimension of each sample, and uses a dimensionality reduction method based on an autoencoder to map high-dimensional data to a low-dimensional potential feature space. The encoder network is defined as:

[0114]

[0115] in, is the potential feature representation after dimensionality reduction, and are the weight matrix and bias vector of the encoder respectively, represents a nonlinear activation function, such as ReLU or Sigmoid, is the feature dimension after dimensionality reduction The dimensionality reduction network minimizes the reconstruction error:

[0116]

[0117] in, is the decoder network. The trained encoder can extract the main dynamic features of the ventilation system and reduce redundant information, making the subsequent time series analysis more stable and efficient. The potential features after dimensionality reduction are represented as The pressure differential field prediction network with a two-layer long short-term memory (LSTM) structure is input into the active neural pressure differential field network model to perform time series analysis and predict future pressure differential field change trends. Since the pressure differential field characteristic of the ventilation system is a dynamic time series signal, its changes are affected by historical states. The LSTM structure can effectively model the long-term dependencies in time series data. Assume that the input of the LSTM network is , the output is the predicted value of the pressure difference field at the next moment , then the LSTM recursive calculation is as follows:

[0118]

[0119]

[0120]

[0121] in, is the hidden state vector, is the memory unit state, are the weight matrices of the LSTM network, is the bias term. The network minimizes the prediction error:

[0122]

[0123] Optimize it to accurately predict the future changes in the pressure difference field characteristics. The pressure difference field change value predicted by LSTM With the current latent feature representation The control parameter generation network is input to the active neural pressure difference field network to perform mapping conversion of variable frequency control parameters. The control parameter generation network uses a fully connected neural network, and its input is , the output is the initial frequency conversion control parameters:

[0124]

[0125] in, Represents the preliminary control parameters of fan speed and air valve opening, is the weight matrix, is the bias vector. The optimization goal of this network is:

[0126]

[0127] in, is the optimal variable frequency control parameter. After obtaining the initial variable frequency control parameter, the pressure difference field mapping characteristics are subjected to pattern recognition analysis to determine the historical working mode of the current system. Assume that the historical mode database of the system is , where each mode It consists of the past pressure difference characteristics and the corresponding control strategies. The similarity between the current characteristics and the historical patterns is calculated:

[0128]

[0129] Determine the current best matching historical pattern :

[0130]

[0131] Then determine what operating state the current system is in. According to the historical working mode judgment results, the initial frequency conversion control parameters are adaptively adjusted to obtain the final target frequency conversion control parameters. Let the adjustment function be , then the target frequency conversion control parameters are:

[0132]

[0133] in, Optimize the initial parameters based on historical data. For example, if the current mode matches a high load condition and the initial control parameters suggest reducing the fan speed, then The fan speed will be appropriately increased based on the historical best strategy to avoid system overload.

[0134] In a specific embodiment, the process of executing step 104 may specifically include the following steps:

[0135] Performing work scenario analysis and pattern recognition on the target frequency conversion control parameters through a multi-mode frequency conversion controller to obtain the current operation mode, where the current operation mode includes normal operation mode, emergency response mode, and maintenance mode;

[0136] According to the current operation mode, the target frequency conversion control parameters are input into the feedforward control unit to perform initial parameter calculation to obtain the initial frequency conversion parameters;

[0137] The initial frequency conversion parameters and the actual pressure difference deviation value are input into the incremental PID controller for feedback compensation calculation to obtain the control increment;

[0138] Based on the operation mode determination and control increment, the mode preset control strategy is executed to obtain the mode optimized control output;

[0139] Execute the fan and air valve coordinated control logic according to the mode optimization control output and the pressure difference deviation value to obtain the coordinated control instructions;

[0140] Based on the synergistic control instructions and regional coupling matrix, multi-region coordinated control and load switching processing are carried out to obtain the fan speed and air valve opening values.

[0141] Specifically, the target variable frequency control parameters are analyzed for working scenarios and pattern recognition to determine the current operating mode. In the ventilation system of a nuclear power plant, the operating modes include normal operating mode, emergency response mode, and maintenance mode. The key to determining the current mode is to monitor the fan speed in real time. , air valve opening , Plant pressure difference and its deviation , and combined with the system's historical status, use pattern recognition algorithms for classification. Define the pattern classification function at the current moment as:

[0142]

[0143] in, Represents the current best matching pattern, is the pattern similarity, is the current system state vector, For mode Historical state vector, pattern library The typical operating characteristics of different modes are stored. After confirmation, the system identifies the current operating mode and enters the corresponding control process. After the mode recognition is completed, the target frequency conversion control parameters are adjusted according to the current operating mode. Input the feedforward control unit to calculate the initial frequency conversion parameters. The function of the feedforward control unit is to use the pressure difference field dynamic model to predict the optimal fan speed and air valve opening, thereby providing a near-optimal control initial value. Assume that the state variables of the ventilation system are , the fan characteristic function is , then the feedforward control model is expressed as:

[0144]

[0145] in, is the initial frequency conversion parameter, Represents the feedforward control mapping relationship obtained by fitting historical data. This function is established through neural networks or response surface methods and minimizes the prediction error:

[0146]

[0147] Train it so that its output is as close as possible to the optimal frequency conversion control parameters. Use the feedback control mechanism to compensate for the error. Assume that the current pressure difference deviation is ,in is the target pressure difference, is the currently measured pressure difference, then the initial frequency conversion parameters and Enter the incremental PID controller to calculate the control increment:

[0148]

[0149] in, is the PID control increment, are the proportional, integral and differential gain coefficients respectively, is the sampling period. The goal of PID control is to minimize the steady-state error and improve the dynamic response capability of the system. Based on the operation mode determination and control increment, the mode preset control strategy is executed to obtain the mode optimized control output. Different operation modes correspond to different control strategies: in normal operation mode, the system maintains optimal energy consumption, while in emergency response mode, the system prioritizes ensuring the stability of the plant negative pressure, that is:

[0150]

[0151] in, Represents a mode-based optimization function. For example, in emergency mode with high pressure differential demand, the fan speed should be increased appropriately, while in maintenance mode with low load, the damper should be partially closed to reduce energy consumption. Optimize control output according to the mode and pressure difference deviation , execute the coordinated control logic of the fan and the damper to obtain the synergistic control instructions. Due to the nonlinear coupling between the operation of the fan and the damper, the control strategy is solved through collaborative optimization:

[0152] ;

[0153] in, For control instructions, For the optimized fan speed and air valve opening, is the weight coefficient to balance the pressure difference control, energy consumption and system response rate. and the regional coupling matrix , perform multi-zone coordinated control and load switching processing to optimize fan speed and air valve opening. regions, and the coupling relationship between regions is represented by the matrix express:

[0154]

[0155] in, represents the pressure difference field distribution after adjustment, Describes the airflow coupling relationship between zones. By solving this equation, the load demand of each zone is determined and, if necessary, the fan operating mode is adjusted, such as shutting down some auxiliary fans or increasing fan speed in high-load areas.

[0156] In a specific embodiment, the method for executing the variable frequency control of the ventilation system of a nuclear power plant further includes the following steps:

[0157] Perform system performance evaluation based on fan speed and air valve opening value to obtain comprehensive performance indicators;

[0158] Perform threshold comparison analysis on comprehensive performance indicators to obtain parameter optimization trigger signals;

[0159] Based on the parameter optimization trigger signal, the time domain, frequency domain and state features are extracted from the operating data of the fan speed and air valve opening value to obtain the fault feature vector;

[0160] The fault feature vector is input into a deep belief network composed of four layers of restricted Boltzmann mechanism for pattern recognition to obtain the fault type and its probability distribution;

[0161] Perform hierarchical fault response strategy analysis based on fault types and their probability distribution to generate fault handling plans.

[0162] Specifically, the comprehensive performance indicators of the system are defined to quantify the current operating status of the ventilation system. These comprehensive performance indicators are composed of multiple key parameters including fan energy consumption , fan efficiency , System pressure difference stability , Air valve adjustment sensitivity and air flow uniformity In order to form a unified comprehensive performance index, a weighted scoring function is defined:

[0163]

[0164] in, is the weight coefficient, which is obtained through historical data optimization, so that the comprehensive performance index Can effectively evaluate the current operating status of the system. Perform threshold comparison analysis to determine whether parameter optimization or fault detection is required. Set the normal operation threshold range , then the generation rule of parameter optimization trigger signal is:

[0165]

[0166] when When the parameter optimization trigger signal is activated, the fan speed is based on the fan speed. Air valve opening The operating data is used to extract the time domain, frequency domain and state features to form the fault feature vector The time domain features include the mean , standard deviation , skewness and crest factor :

[0167]

[0168]

[0169] in, Represents the time series of fan speed or air valve opening, is the observation window length. Frequency domain features are obtained through Fourier transform, including the main frequency and spectrum energy :

[0170]

[0171] in, is the spectral component after Fourier transformation. The state characteristics are described by the autoregressive model, such as the ARMA model of wind turbine operation:

[0172]

[0173] in, and are the autoregressive and moving average coefficients, is the noise term. By fitting the ARMA model, the dynamic stability of the fan and the damper is detected and the potential failure mode is identified. After extracting the fault features, the feature vector The input is a deep belief network (DBN) composed of four layers of restricted Boltzmann machines (RBM) for pattern recognition to obtain the fault type and its probability distribution. The energy function of RBM is defined as:

[0174]

[0175] in, is the input feature vector, is the hidden layer neuron state, is the connection weight. The DBN is composed of multiple RBM stacks, which are trained layer by layer to learn fault feature representations. The output layer uses the Sottmax classifier to calculate the probability distribution of different fault types:

[0176]

[0177] in, Representative fault type The probability of is the parameter of the Softmax classifier. After identifying the fault type and its probability distribution, a hierarchical fault response strategy analysis is performed to generate a fault handling plan. According to the severity of the fault, it is divided into minor faults, moderate faults and major faults. Minor faults (such as air valve adjustment lag) can be handled by adjusting the control parameters Perform adaptive correction:

[0178]

[0179] in, is the adjustment factor. Moderate faults (such as fan bearing wear) require load switching, and the fan operation is adjusted through the regional coupling matrix:

[0180]

[0181] in, is the fan speed distribution after adjustment, is the fan speed distribution before adjustment, A load distribution matrix is created. A serious fault (such as a damaged fan blade) requires an emergency shutdown and activation of the backup system. This triggers emergency mode, allowing the backup fan to take over the load of the primary fan and rapidly adjust the system pressure differential through boost exhaust mode.

[0182] The frequency conversion control method of the ventilation system of a nuclear power plant according to the embodiment of the present invention is described above. The frequency conversion control system of the ventilation system of a nuclear power plant according to the embodiment of the present invention is described below. Figure 2 In one embodiment of the present invention, a variable frequency control system for a ventilation system of a nuclear power plant includes:

[0183] The acquisition module 201 is used to collect real-time operating data of multiple areas of the nuclear power plant ventilation system and perform standardization processing to obtain a standardized data set;

[0184] A feature mapping module 202 is used to perform fan performance curve fitting and pressure difference field feature mapping on the standardized data set to obtain pressure difference field mapping features;

[0185] The frequency conversion parameter prediction module 203 is used to input the pressure difference field mapping characteristics into the active neural pressure difference field network model to predict the frequency conversion parameters and obtain the target frequency conversion control parameters;

[0186] The combined control module 204 is used to perform feedforward-feedback combined control on the target variable frequency control parameters through the multi-mode variable frequency controller to obtain the fan speed and the air valve opening value.

[0187] Through the collaborative efforts of the aforementioned components, the present invention improves data quality by employing a distributed sensor network and a dual-channel redundant acquisition mechanism, combined with cubic spline interpolation to repair missing data, while applying digital filtering technology to effectively filter out grid interference, ensuring data integrity and reliability. In terms of system characterization, a complete mathematical model of ventilation system characteristics is constructed by accurately modeling the fan impedance characteristics and the duct network topology. In terms of dynamic characteristic capture, the finite element method is used to construct the pressure difference field function, combined with the empirical mode decomposition method to extract core features, achieving a comprehensive characterization of the ventilation system's dynamic characteristics and predicting its future state. In terms of control strategy, an active neural pressure difference field network architecture integrates feature extraction, pressure difference prediction, and parameter generation to form an end-to-end intelligent control system that adaptively generates target variable frequency control parameters. In terms of operating mode, intelligent switching between normal operation, emergency response, and maintenance modes is achieved, combining coordinated fan and damper control with a multi-zone collaborative mechanism to ensure stable system operation under various operating conditions. In terms of fault management, a deep belief network is used to accurately identify common faults. Combined with a hierarchical fault response strategy and recurrent neural network-based fault prediction, this significantly improves system reliability and safety.

[0188] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0189] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0190] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A frequency conversion control method for a ventilation system of a nuclear power plant, characterized in that: include: Collect real-time operating data from multiple areas of the nuclear power plant ventilation system and perform standardization processing to obtain a standardized data set; Performing fan performance curve fitting and pressure difference field feature mapping on the standardized data set to obtain pressure difference field mapping features; Input the pressure difference field mapping features into the active neural pressure difference field network model to predict the frequency conversion parameters and obtain the target frequency conversion control parameters; specifically including: inputting the pressure difference field mapping features into the feature extraction network in the active neural pressure difference field network model to perform dimensionality reduction processing to obtain potential feature representation; performing time series analysis on the potential feature representation through the pressure difference field prediction network with a double-layer LSTM structure in the active neural pressure difference field network model to obtain the pressure difference field change prediction value; inputting the potential feature representation and the pressure difference field change prediction value into the control parameter generation network in the active neural pressure difference field network model for mapping conversion to obtain the initial frequency conversion control parameters; performing pattern recognition analysis on the pressure difference field mapping features to obtain the historical working mode determination result; performing mode adaptive adjustment on the initial frequency conversion control parameters based on the historical working mode determination result to obtain the target frequency conversion control parameters; The target frequency conversion control parameters are subjected to feedforward-feedback combined control by a multi-mode frequency conversion controller to obtain the fan speed and air valve opening value.

2. The frequency conversion control method for a nuclear power plant ventilation system according to claim 1, characterized in that: The method collects real-time operating data of multiple areas of the nuclear power plant ventilation system and performs standardization processing to obtain a standardized data set, including: A ventilation system monitoring network is constructed using distributed airflow sensors, differential pressure sensors, temperature sensors, and humidity sensors, and real-time operating data of multiple areas of the nuclear power plant ventilation system is collected through the ventilation system monitoring network; Performing dual-channel redundant collection and transmission on the multi-region real-time operation data to obtain a double-verified data stream, and performing anomaly detection on the double-verified data stream to obtain a data missing mark position; A cubic spline interpolation function is applied to reconstruct data at the data missing mark position to obtain a repaired continuous data stream, and the repaired continuous data stream is digitally filtered to obtain a standardized data set.

3. The frequency conversion control method for a nuclear power plant ventilation system according to claim 1, characterized in that: The performing of fan performance curve fitting and pressure difference field feature mapping on the standardized data set to obtain pressure difference field mapping features includes: Performing dynamic testing and analysis on the fan operating parameters in the standardized data set to obtain a set of original performance curve data points of the fan; The original performance curve data point set is fitted and calculated using the least squares method to obtain a fan impedance model, and the pipe network structure information in the standardized data set is topologically modeled to obtain a ventilation system network model; Based on the ventilation system network model, a node association matrix and boundary condition vectors are constructed to obtain a ventilation system resistance characteristic matrix equation; A pressure difference field function is constructed based on the fan impedance model and the ventilation system resistance characteristic matrix equation, and a pressure difference field mapping feature characterizing the dynamic characteristics of the ventilation system is calculated.

4. The frequency conversion control method for a nuclear power plant ventilation system according to claim 3, characterized in that: The step of constructing a pressure difference field function based on the fan impedance model and the ventilation system resistance characteristic matrix equation, and calculating a pressure difference field mapping feature that characterizes the dynamic characteristics of the ventilation system, includes: Perform spatial division and boundary definition on the ventilation system control area to obtain a spatial model containing p control areas; Based on the spatial model, a Laplace equation and a fan outlet pressure boundary condition are established at each grid node to obtain an initial pressure difference field distribution; Introducing a time dimension into the initial pressure difference field distribution and applying an empirical mode decomposition algorithm to obtain a set of intrinsic mode functions representing a time series of the pressure difference field; Performing Hilbert spectrum analysis on the intrinsic modal function set to obtain a pressure difference field spectrum feature set consisting of instantaneous frequency and instantaneous amplitude information; Constructing a feature vector for each control area based on the pressure difference field spectrum feature set, wherein the feature vector includes the pressure difference average value, standard deviation, peak factor, pulsation intensity and autocorrelation function decay rate; The response surface method is used to establish the mapping relationship between the characteristic vector and the fan speed and the air valve opening, and an autoregressive moving average model is constructed to obtain the pressure difference field mapping characteristics.

5. The frequency conversion control method for a nuclear power plant ventilation system according to claim 1, characterized in that: The method of performing feedforward-feedback combined control on the target variable frequency control parameter by the multi-mode variable frequency controller to obtain the fan speed and the air valve opening value includes: Performing a working scenario analysis and mode recognition on the target frequency conversion control parameter by a multi-mode frequency conversion controller to obtain a current operating mode, wherein the current operating mode includes a normal operating mode, an emergency response mode, and a maintenance mode; Inputting the target frequency conversion control parameter into a feedforward control unit according to the current operation mode to perform initial parameter calculation to obtain an initial frequency conversion parameter; Inputting the initial frequency conversion parameter and the actual pressure difference deviation value into the incremental PID controller for feedback compensation calculation to obtain a control increment; Based on the operation mode determination and the control increment, a mode preset control strategy is executed to obtain a mode optimization control output; Execute the coordinated control logic of the fan and the air valve according to the optimized control output and the pressure difference deviation value of the mode to obtain a coordinated control instruction; Based on the synergistic control instruction and the regional coupling matrix, multi-region coordinated control and load switching processing are performed to obtain the fan speed and air valve opening value.

6. The frequency conversion control method for a nuclear power plant ventilation system according to claim 1, characterized in that: The frequency conversion control method of the nuclear power plant ventilation system also includes: Performing system performance evaluation based on the fan speed and the air valve opening value to obtain a comprehensive performance index; Performing threshold comparison analysis on the comprehensive performance indicators to obtain a parameter optimization trigger signal; Based on the parameter optimization trigger signal, extracting time domain, frequency domain and state features from the operating data of the fan speed and the air valve opening value to obtain a fault feature vector; Inputting the fault feature vector into a deep belief network composed of four layers of restricted Boltzmann machines for pattern recognition to obtain the fault type and its probability distribution; Perform hierarchical fault response strategy analysis based on the fault type and its probability distribution to generate a fault handling plan.

7. A variable frequency control system for a nuclear power plant ventilation system, characterized in that: A method for executing a variable frequency control method for a nuclear power plant ventilation system according to any one of claims 1 to 6, wherein the variable frequency control system for the nuclear power plant ventilation system comprises: The acquisition module is used to collect real-time operating data from multiple areas of the nuclear power plant ventilation system and perform standardization processing to obtain a standardized data set; A feature mapping module, configured to perform fan performance curve fitting and pressure difference field feature mapping on the standardized data set to obtain pressure difference field mapping features; A frequency conversion parameter prediction module is used to input the pressure difference field mapping characteristics into the active neural pressure difference field network model to predict the frequency conversion parameters and obtain the target frequency conversion control parameters; The combined control module is used to perform feedforward-feedback combined control on the target variable frequency control parameter through a multi-mode variable frequency controller to obtain the fan speed and air valve opening value.

Images