Roller screw control rod drive mechanism state online monitoring method, system and medium

Abstract

This invention discloses an online monitoring method, system, and medium for the status of a roller screw control rod drive mechanism; it relates to the field of online monitoring technology; based on traditional control rod drive mechanism status monitoring technology, it improves the method by calculating a first effective value signal and a second effective value signal based on the acceleration signal for the roller screw type control rod drive mechanism, thereby determining the start and end times of the roller screw type control rod drive mechanism, screening out action time periods that meet the action time standard for feature identification, and finally combining all feature identification results to obtain the status of the roller screw control rod drive mechanism; it solves the problem of the inability to monitor the status of roller screw type control rod drive mechanisms online, detects early faults in the roller screw type control rod drive mechanism in advance, and effectively ensures the safety and reliability of the control rod drive mechanism.

Description

Technical Field

[0001] This invention relates to the field of online monitoring technology, specifically to a method, system, and medium for online monitoring of the status of a roller screw control rod drive mechanism. Background Technology

[0002] The control rod drive mechanism is a crucial component for controlling reactor core power and a vital safety facility for safe reactor shutdown. Its safety and reliability directly impact the reactor's functional integrity and overall safety. To achieve core power regulation, the control rod drive mechanism requires rod lifting and lowering actions of varying durations, generating cyclic loads on its components. This can lead to damage, bearing wear, roller jamming, and other malfunctions, affecting the normal operation of the control rods and posing a threat to reactor stability. Past fault monitoring methods for roller screw-type control rod drive mechanisms involved continuous lifting and lowering tests during major overhauls. This "periodic maintenance" approach can lead to over-maintenance, and the additional testing can introduce new faults. Therefore, a method for online fault monitoring of roller screw-type control rod drive mechanisms is needed.

[0003] Because the roller screw type control rod drive mechanism is not in real-time operation during normal reactor operation, and the duration of its real-time operation is uncertain, its operating state cannot be identified when it is static. It can only be identified when the drive mechanism is in operation. Therefore, it is necessary to capture the start and end points of the control rod drive mechanism's actions. However, since there are no other trigger signals to determine the start and end points of the signals, it is necessary to start with the waveform itself. Furthermore, the continuous acquisition duration of the control rod drive mechanism is inconsistent, making it impossible to use stable characteristic quantities to identify its state. Summary of the Invention

[0004] The technical problem this invention aims to solve is that during normal reactor operation, the roller screw type control rod drive mechanism is not in real-time operation, and the duration of its real-time operation is uncertain, making it difficult to accurately identify the operating status of the drive mechanism. This invention aims to provide an online monitoring method, system, and medium for the roller screw type control rod drive mechanism. Based on traditional control rod drive mechanism status monitoring technology, the method is improved. For the roller screw type control rod drive mechanism, a first effective value signal and a second effective value signal are calculated based on the acceleration signal to determine the start and end times of the roller screw type control rod drive mechanism's actions. Action time periods that meet the time criteria are selected for feature identification, and finally, the status of the roller screw type control rod drive mechanism is obtained by combining all feature identification results. This solves the problem of the inability to monitor the status of the roller screw type control rod drive mechanism online, detects early faults in the roller screw type control rod drive mechanism in advance, and effectively ensures the safety and reliability of the control rod drive mechanism.

[0005] This invention is achieved through the following technical solution:

[0006] This solution provides a method for online monitoring of the status of the roller screw control rod drive mechanism, including:

[0007] Acquire the acceleration signal of the roller screw control rod drive mechanism;

[0008] Based on the acceleration signal, a first effective value signal and a second effective value signal are calculated. The first effective value signal and the second effective value signal are analyzed to determine the start time of the roller screw control rod drive mechanism. The second effective value signal is analyzed to determine the end time of the roller screw control rod drive mechanism.

[0009] The start and end times of the roller screw control rod drive mechanism are statistically analyzed to determine the action time period of the roller screw control rod drive mechanism, and the action time period that meets the action time standard is selected.

[0010] Feature identification is performed on the action time period that meets the target, and the state of the roller screw control rod drive mechanism is obtained by combining all feature identification results.

[0011] The working principle of this solution is as follows: During normal reactor operation, the roller screw type control rod drive mechanism is not in real-time operation, and the duration of its real-time operation is uncertain, making it difficult to accurately identify the operating status of the drive mechanism. The purpose of this invention is to provide an online monitoring method, system, and medium for the roller screw type control rod drive mechanism. Based on traditional control rod drive mechanism status monitoring technology, this invention improves upon traditional methods by calculating a first and second effective value signal based on the acceleration signal. This allows for the determination of the start and end times of the roller screw type control rod drive mechanism's actions, filtering out action time periods that meet the time criteria for feature identification, and finally combining all feature identification results to obtain the status of the roller screw type control rod drive mechanism. This solves the problem of the inability to monitor the status of the roller screw type control rod drive mechanism online, enabling early detection of early faults and effectively ensuring the safety and reliability of the control rod drive mechanism.

[0012] Further optimizations include:

[0013] Set an abnormal result threshold, obtain all feature identification results, compare each feature identification result with the abnormal result threshold, and count the number N of feature identification results that exceed the abnormal result threshold. When the proportion of the number N in the total number of feature identification results exceeds 75%, the roller screw control rod drive mechanism is determined to be faulty; otherwise, the roller screw control rod drive mechanism is determined to be normal.

[0014] A further optimized solution involves acquiring the acceleration signal of the roller screw control rod drive mechanism; including the following method:

[0015] An acceleration sensor is installed on the bearing housing of the roller screw control rod drive mechanism to continuously collect acceleration signals. The data length of each collected acceleration signal is L, and the time of each collection of acceleration signals is recorded.

[0016] A further optimized solution is that the calculation of the first effective value signal and the second effective value signal based on the acceleration signal includes the following method:

[0017] Acquire acceleration signals;

[0018] The square of the effective value of the acceleration signal acquired each time is calculated to obtain the first effective value signal;

[0019] Set the number of elements N in storage queue A to store the first valid value signal; when storage queue A is full, update storage queue A: the next element is placed at the end of storage queue A, and the first element enqueued is pushed out.

[0020] The mean is calculated after the storage queue A is full and after the update to obtain the second effective value signal.

[0021] A further optimized scheme is that the analysis of the first effective value signal and the second effective value signal to determine the start action time of the roller screw control rod drive mechanism includes:

[0022] Calculate the quotient of the first RMS signal and the second RMS signal;

[0023] A preset threshold x1 is set, and the quotient is compared with the threshold x1. Among the quotients corresponding to the acceleration signals collected three times consecutively, if the quotients corresponding to the acceleration signals collected twice are both less than the threshold x1, the time of the last acceleration signal collection is determined as the start time of the roller screw control rod drive mechanism.

[0024] A further optimized solution is that the analysis of the second effective value signal to determine the end action time of the roller screw control rod drive mechanism includes:

[0025] A preset threshold x2 is set. The second effective value signal is compared with the preset threshold x2. Among the second effective value signals corresponding to the acceleration signals collected in three consecutive collections, if the second effective value signals corresponding to the acceleration signals collected in two of the collections are less than the threshold x2, the time of the first collection of the acceleration signal is determined as the end action time of the roller screw control rod drive mechanism.

[0026] A further optimized solution involves selecting action time periods that meet the time criteria; including the following methods:

[0027] Get the total data length for all action time periods;

[0028] Set a window length w, compare the total data length in each action time period with the window length w, and determine the action time period whose total data length is greater than the window length w as the action time meets the standard.

[0029] A further optimized solution involves feature identification of the action time intervals that meet the time criteria, and combining all feature identification results to obtain the state of the roller screw control rod drive mechanism, including the following method:

[0030] Configure the number of data segments m, and determine the sliding window step size s based on the window length w and the number of data segments m. Use the sliding window step size s to split the data corresponding to the action time period that meets the action time target into multiple data segments; where In the formula, OL represents the data length between the start and end times of the control rod drive mechanism.

[0031] Calculate the feature values ​​of each data segment and input the feature values ​​into a pre-trained support vector machine model to obtain the feature discrimination results;

[0032] The state of the roller screw control rod drive mechanism is obtained by combining all feature identification results.

[0033] This solution also provides an online monitoring system for the status of the roller screw control rod drive mechanism, used to implement the above-mentioned online monitoring method for the status of the roller screw control rod drive mechanism. The system includes:

[0034] The acquisition module is used to acquire the acceleration signal of the roller screw control rod drive mechanism;

[0035] The analysis module is used to calculate a first effective value signal and a second effective value signal based on the acceleration signal, analyze the first effective value signal and the second effective value signal to determine the start time of the roller screw control rod drive mechanism, and analyze the second effective value signal to determine the end time of the roller screw control rod drive mechanism.

[0036] The statistical filtering module is used to statistically analyze the start and end times of the roller screw control rod drive mechanism, determine the action time period of the roller screw control rod drive mechanism, and filter out the action time periods that meet the action time standard.

[0037] The identification module is used to identify features of the action time period that meets the target, and to obtain the state of the roller screw control rod drive mechanism by combining all feature identification results.

[0038] This solution also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, can realize the online monitoring method for the status of the roller screw control rod drive mechanism as described above.

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

[0040] 1. The present invention provides an online monitoring method, system, and medium for the status of a roller screw control rod drive mechanism. Based on traditional control rod drive mechanism status monitoring technology, the method is improved. For roller screw type control rod drive mechanisms, a first effective value signal and a second effective value signal are calculated based on the acceleration signal to determine the start and end times of the roller screw type control rod drive mechanism. Action time periods that meet the time standard are selected for feature identification. Finally, the status of the roller screw control rod drive mechanism is obtained by combining all feature identification results. This solves the problem of the inability to monitor the status of roller screw type control rod drive mechanisms online, detects early faults in roller screw type control rod drive mechanisms in advance, and effectively ensures the safety and reliability of the control rod drive mechanism.

[0041] 2. The present invention provides an online monitoring method, system, and medium for the status of a roller screw control rod drive mechanism. Addressing the issue of inconsistent operating times in the roller screw control rod drive mechanism, this invention uses a sliding window approach to filter out data from action time periods that meet the specified time thresholds. This data is then divided into sub-segments, and the feature values ​​of each sub-segment are calculated. These feature values ​​are then input into a pre-trained support vector machine model to obtain feature discrimination results. Filtering out data from action time periods that meet the specified time thresholds ensures the stability of the feature values ​​and improves discrimination accuracy. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0043] Figure 1 A schematic diagram of the online monitoring method for the status of the roller screw control rod drive mechanism;

[0044] Figure 2 A schematic diagram of the online monitoring system for the status of the roller screw control rod drive mechanism;

[0045] Figure 3 This is a schematic diagram of the roller screw control rod drive mechanism.

[0046] In the attached diagram:

[0047] 1-Rotor component; 2-Pressure housing; 3-Counterweight; 4-Acceleration sensor. Detailed Implementation

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0049] Because the roller screw type control rod drive mechanism is not in real-time operation during normal reactor operation, and the duration of its real-time operation is uncertain, its operating state cannot be identified when it is static. Only when the drive mechanism is in operation can its state be identified. Therefore, it is necessary to capture the start and end points of the roller screw type control rod drive mechanism's actions. However, since there are no other trigger signals to determine the start and end points of the signal, it is necessary to start from the waveform itself. Furthermore, the continuous acquisition time of the roller screw type control rod drive mechanism is inconsistent, making it impossible to identify its state using stable characteristic quantities. In view of this, the present invention provides the following embodiments to solve the above-mentioned technical problems:

[0050] Example 1

[0051] This embodiment provides a method for online monitoring of the status of a roller screw control rod drive mechanism, such as... Figure 1 Shown, including:

[0052] Step 1: Acquire the acceleration signal of the roller screw control rod drive mechanism; specifically, the method includes:

[0053] An acceleration sensor is installed on the bearing housing of the roller screw control rod drive mechanism to continuously collect acceleration signals. The data length of each collected acceleration signal is L, and the time of each collection of acceleration signals is recorded.

[0054] Step 2: Calculate the first effective value signal and the second effective value signal based on the acceleration signal; analyze the first effective value signal and the second effective value signal to determine the start time of the roller screw control rod drive mechanism; analyze the second effective value signal to determine the end time of the roller screw control rod drive mechanism.

[0055] The method for calculating the first effective value signal and the second effective value signal based on the acceleration signal includes:

[0056] Acquire acceleration signals;

[0057] The square of the effective value of the acceleration signal acquired each time is calculated to obtain the first effective value signal;

[0058] Set the number of elements N in storage queue A to store the first valid value signal; when storage queue A is full, update storage queue A: the next element is placed at the end of storage queue A, and the first element enqueued is pushed out.

[0059] The mean is calculated after the storage queue A is full and after the update to obtain the second effective value signal.

[0060] The acceleration signal acquired in the nth time is used to calculate a first effective value signal q1n (when the storage queue A is full, the elements are q11, q12, q13, ..., q1n). A second effective value signal q2n is calculated based on the storage queue A. The acceleration signal acquired in the (n+1)th time is used to calculate a first effective value signal q1(n+1) (when the storage queue A is full, the elements are q12, q13, q14, ..., q1(n+1)). A second effective value signal q2n will be calculated accordingly.

[0061] Since the roller screw type control rod drive mechanism does not produce any action during normal reactor operation, the signal measured by the accelerometer located in the drive mechanism is a background noise signal with a low amplitude. When the reactor requires power regulation, the control rod drive mechanism motor actuates, forcing the drive mechanism to vibrate. The accelerometer captures a signal with a higher vibration amplitude. At this time, the second effective value of the signal changes little, while the first effective value changes greatly. The start time of the signal can be determined by the ratio. Therefore, analyzing the first and second effective value signals determines the start time of the roller screw control rod drive mechanism, including:

[0062] Calculate the quotient of the first RMS signal and the second RMS signal;

[0063] A preset threshold x1 is set, and the quotient is compared with the threshold x1. Among the quotients corresponding to the acceleration signals collected three times consecutively, if the quotients corresponding to the acceleration signals collected twice are both less than the threshold x1, the time of the last acceleration signal collection is determined as the start time of the roller screw control rod drive mechanism.

[0064] Similarly, when the control rod drive mechanism ends its operation, the acceleration measurement amplitude decreases significantly. The more robust second effective value is selected as the evaluation standard. The smaller the signal, the more likely the control rod drive mechanism has ended its operation.

[0065] Therefore, the final action time of the roller screw control rod drive mechanism is determined by analyzing the second effective value signal, including:

[0066] A preset threshold x2 is set. The second effective value signal is compared with the preset threshold x2. Among the second effective value signals corresponding to the acceleration signals collected in three consecutive collections, if the second effective value signals corresponding to the acceleration signals collected in two of the collections are less than the threshold x2, the time of the first collection of the acceleration signal is determined as the end action time of the roller screw control rod drive mechanism.

[0067] Step 3: Calculate the start and end times of the roller screw control rod drive mechanism, determine the action time period of the roller screw control rod drive mechanism, and select the action time periods that meet the action time standard.

[0068] The method for filtering out action time periods that meet the time criteria includes:

[0069] Get the total data length for all action time periods;

[0070] Set a window length w, compare the total data length in each action time period with the window length w, and determine the action time period whose total data length is greater than the window length w as the action time meets the standard.

[0071] Step four: Feature identification is performed on the action time period that meets the action time standard, and the state of the roller screw control rod drive mechanism is obtained by combining all feature identification results.

[0072] Including methods:

[0073] Configure the number of data segments m, and determine the sliding window step size s based on the window length w and the number of data segments m. Use the sliding window step size s to split the data corresponding to the action time period that meets the action time target into multiple data segments; where In the formula, OL represents the data length between the start and end times of the control rod drive mechanism.

[0074] Calculate the feature values ​​of each data segment and input the feature values ​​into a pre-trained support vector machine model to obtain the feature discrimination results;

[0075] The state of the roller screw control rod drive mechanism is obtained by combining all feature identification results.

[0076] It also includes step five:

[0077] Set an abnormal result threshold, obtain all feature identification results, compare each feature identification result with the abnormal result threshold, and count the number N of feature identification results that exceed the abnormal result threshold. When the proportion of the number N in the total number of feature identification results exceeds 75%, the roller screw control rod drive mechanism is determined to be faulty; otherwise, the roller screw control rod drive mechanism is determined to be normal.

[0078] This embodiment provides an online monitoring method for the status of a roller screw control rod drive mechanism. Based on traditional control rod drive mechanism status monitoring technology, the method improves upon traditional methods. For roller screw type control rod drive mechanisms, it calculates a first effective value signal and a second effective value signal based on the acceleration signal, thereby determining the start and end times of the roller screw type control rod drive mechanism's actions. It then filters out action time periods that meet the time criteria for feature identification, and finally combines all feature identification results to obtain the status of the roller screw control rod drive mechanism. This solves the problem of the inability to monitor the status of roller screw type control rod drive mechanisms online, allowing for early detection of early faults in the roller screw type control rod drive mechanism and effectively ensuring the safety and reliability of the control rod drive mechanism.

[0079] Meanwhile, to address the issue of inconsistent running times in the roller screw control rod drive mechanism, a sliding window method is used to filter out data from action time periods that meet the standard, break them down into data segments, calculate the feature values ​​of each data segment, and input the feature values ​​into a pre-trained support vector machine model to obtain feature discrimination results. By filtering out data from action time periods that meet the standard for discrimination, the stability of feature values ​​is ensured and the discrimination accuracy is improved.

[0080] Example 2

[0081] This embodiment provides an online monitoring system for the status of a roller screw control rod drive mechanism, used to implement the online monitoring method for the status of the roller screw control rod drive mechanism described in Embodiment 1, such as... Figure 2 As shown, the system includes:

[0082] The acquisition module is used to acquire the acceleration signal of the roller screw control rod drive mechanism; the acquisition module includes an acceleration sensor, which is mounted on the rotor of the roller screw control rod drive mechanism to acquire the acceleration signal.

[0083] The analysis module is used to calculate a first effective value signal and a second effective value signal based on the acceleration signal, analyze the first effective value signal and the second effective value signal to determine the start time of the roller screw control rod drive mechanism, and analyze the second effective value signal to determine the end time of the roller screw control rod drive mechanism.

[0084] The statistical filtering module is used to statistically analyze the start and end times of the roller screw control rod drive mechanism, determine the action time period of the roller screw control rod drive mechanism, and filter out the action time periods that meet the action time standard.

[0085] The identification module is used to identify features of the action time period that meets the target, and to obtain the state of the roller screw control rod drive mechanism by combining all feature identification results.

[0086] Example 3

[0087] This embodiment provides a computer-readable medium having a computer program stored thereon. The computer program is executed by a processor to realize the online monitoring method for the status of the roller screw control rod drive mechanism as described in Embodiment 1.

[0088] Step 1: Acquire the acceleration signal of the roller screw control rod drive mechanism;

[0089] Step 2: Calculate the first effective value signal and the second effective value signal based on the acceleration signal; analyze the first effective value signal and the second effective value signal to determine the start time of the roller screw control rod drive mechanism; analyze the second effective value signal to determine the end time of the roller screw control rod drive mechanism.

[0090] Step 3: Calculate the start and end times of the roller screw control rod drive mechanism, determine the action time period of the roller screw control rod drive mechanism, and select the action time periods that meet the action time standard.

[0091] Step four: Feature identification is performed on the action time period that meets the action time standard, and the state of the roller screw control rod drive mechanism is obtained by combining all feature identification results.

[0092] Step 5: Set an abnormal result threshold, obtain all feature identification results, compare each feature identification result with the abnormal result threshold, and count the number N of feature identification results that exceed the abnormal result threshold. When the proportion of the number N in the total number of feature identification results exceeds 75%, the roller screw control rod drive mechanism is determined to be faulty; otherwise, the roller screw control rod drive mechanism is determined to be normal.

[0093] Example 4

[0094] This embodiment describes the invention in detail with reference to the accompanying drawings and an embodiment of online monitoring of the roller screw type control rod drive mechanism.

[0095] This embodiment utilizes an accelerometer to conduct online monitoring and evaluation of the status of a roller screw-type control rod drive mechanism. The specific methods include:

[0096] First, determine the start and end times of the roller screw-type control rod drive mechanism, based on the acceleration sensor data of the roller screw-type control rod drive mechanism. The acceleration sensor placement is shown in the attached figure. Figure 3 As shown, the roller screw type control rod drive mechanism includes a rotor component 1, a pressure-resistant shell 2, and a counterweight 3. In this embodiment, an acceleration sensor 4 is installed on the rotor component 1 to collect acceleration data in real time. The data length L is set to 100 points, and the square of the effective value of the 100 data points is calculated as the first effective value signal q1. j :

[0097]

[0098] Where a ij Let i represent the data point i collected in the j-th time, where i = 1, 2, 3, ..., 100;

[0099] The calculated first effective value signal is sent to storage queue A, which adopts a first-in-first-out strategy. The maximum capacity N of storage queue A is 10. The mean of all elements in the queue is calculated to obtain the second effective value signal q2.

[0100]

[0101] The acceleration signal acquired in the nth time is used to calculate a first effective value signal q1n (when the storage queue A is full, the elements are q11, q12, q13, ..., q1n). A second effective value signal q2n is calculated based on the storage queue A. The acceleration signal acquired in the (n+1)th time is used to calculate a first effective value signal q1(n+1) (when the storage queue A is full, the elements are q12, q13, q14, ..., q1(n+1)). A second effective value signal q2n will be calculated accordingly.

[0102] The quotient of the second effective value signal and the first effective value signal is calculated and compared with the threshold x1. If the quotient is less than the threshold twice out of three consecutive times, it is determined that this is the start time of the control rod drive mechanism.

[0103] Simultaneously, the second effective value signal and the first effective value signal are calculated. The second effective value signal is compared with the threshold x2. If the second effective value signal is less than the threshold x2 in two out of three consecutive calculations, the start time of the first long effective value calculation is determined to be the end time of the control rod drive mechanism.

[0104] Secondly, the data is split using a sliding window method. Assuming the total data length OL acquired from the start to the end of the control rod drive mechanism is 5300 points, and the length w of a single data line used for state identification calculation is 3000, then 10 data lines need to be split. Therefore, the sliding window step size s can be calculated as follows:

[0105]

[0106] Third, each data point after splitting is individually screened to obtain the screening results. Feature values ​​are calculated for each data point, including acceleration level, kurtosis, spectral peak values ​​in low-frequency bands such as the first, second, fourth, and eighth harmonics of the signal, and frequency band energy in high-frequency bands such as 800–1000Hz and 1000Hz–2000Hz. These calculated feature values ​​are then used in a pre-trained support vector machine model to perform binary classification and obtain the screening results.

[0107] Finally, the analysis results of each data point are combined to determine the final status of the equipment. The identification results of each data point obtained in step 3 are summarized. To consider a certain margin against false alarms, if the number of identified abnormalities accounts for more than 75% of the total, it is judged as an abnormal status; otherwise, it is judged as normal.

[0108] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for online monitoring of the status of a roller screw control rod drive mechanism, characterized in that, include: Acquire the acceleration signal of the roller screw control rod drive mechanism; Based on the acceleration signal, a first effective value signal and a second effective value signal are calculated. The first effective value signal and the second effective value signal are analyzed to determine the start time of the roller screw control rod drive mechanism. The second effective value signal is analyzed to determine the end time of the roller screw control rod drive mechanism. The method for calculating the first effective value signal and the second effective value signal based on the acceleration signal includes: Acquire acceleration signals; The square of the effective value of the acceleration signal acquired each time is calculated to obtain the first effective value signal; Set the number of elements N in storage queue A to store the first valid value signal; when storage queue A is full, update storage queue A: the next element is placed at the end of storage queue A, and the first element enqueued is pushed out. The mean is calculated after storage queue A is full and after the update to obtain the second effective value signal; The analysis of the first and second effective value signals determines the start time of the roller screw control rod drive mechanism, including: Calculate the quotient of the first RMS signal and the second RMS signal; A preset threshold x1 is set, and the quotient is compared with the threshold x1. Among the quotients corresponding to the acceleration signals collected three times in a row, if the quotients corresponding to the acceleration signals collected twice are less than the threshold x1, the time of the last acceleration signal collection is determined as the start time of the roller screw control rod drive mechanism. The analysis of the second effective value signal determines the end action time of the roller screw control rod drive mechanism, including: A preset threshold x2 is set. The second effective value signal is compared with the preset threshold x2. In the three consecutive acquisitions of the second effective value signal corresponding to the acceleration signal, if the second effective value signal corresponding to the acceleration signal is less than the threshold x2 in two of the acquisitions, the time of the first acquisition of the acceleration signal is determined as the end action time of the roller screw control rod drive mechanism. The start and end times of the roller screw control rod drive mechanism are statistically analyzed to determine the action time period of the roller screw control rod drive mechanism, and the action time period that meets the action time standard is selected. Feature identification is performed on the action time period that meets the target, and the state of the roller screw control rod drive mechanism is obtained by combining all feature identification results.

2. The online monitoring method for the status of the roller screw control rod drive mechanism according to claim 1, characterized in that, Also includes: Set an abnormal result threshold, obtain all feature identification results, compare each feature identification result with the abnormal result threshold, and count the number N of feature identification results that exceed the abnormal result threshold. When the proportion of the number N in the total number of feature identification results exceeds 75%, the roller screw control rod drive mechanism is determined to be faulty; otherwise, the roller screw control rod drive mechanism is determined to be normal.

3. The online monitoring method for the status of the roller screw control rod drive mechanism according to claim 1, characterized in that, The acceleration signal of the roller screw control rod drive mechanism is collected; Including methods: An acceleration sensor is installed on the bearing housing of the roller screw control rod drive mechanism to continuously collect acceleration signals. The data length of each collected acceleration signal is L, and the time of each collection of acceleration signals is recorded.

4. The online monitoring method for the status of the roller screw control rod drive mechanism according to claim 1, characterized in that, The method for filtering out action time periods that meet the time criteria includes: Get the total data length for all action time periods; Set a window length w, compare the total data length in each action time period with the window length w, and determine the action time period whose total data length is greater than the window length w as the action time meets the standard.

5. The online monitoring method for the status of the roller screw control rod drive mechanism according to claim 4, characterized in that, The method involves identifying features of the action time interval that meets the target, and combining all feature identification results to obtain the state of the roller screw control rod drive mechanism, including: Configure the number of data segments m, and determine the sliding window step size s based on the window length w and the number of data segments m. Use the sliding window step size s to split the data corresponding to the action time period that meets the action time standard into multiple data segments. Calculate the feature values ​​of each data segment and input the feature values ​​into a pre-trained support vector machine model to obtain the feature discrimination results; The state of the roller screw control rod drive mechanism is obtained by combining all feature identification results.

6. An online monitoring system for the status of a roller screw control rod drive mechanism, characterized in that, The system is used to implement the online monitoring method for the state of the roller screw control rod drive mechanism according to any one of claims 1-5, the system comprising: The acquisition module is used to acquire the acceleration signal of the roller screw control rod drive mechanism; The analysis module is used to calculate a first effective value signal and a second effective value signal based on the acceleration signal, analyze the first effective value signal and the second effective value signal to determine the start time of the roller screw control rod drive mechanism, and analyze the second effective value signal to determine the end time of the roller screw control rod drive mechanism. The statistical filtering module is used to statistically analyze the start and end times of the roller screw control rod drive mechanism, determine the action time period of the roller screw control rod drive mechanism, and filter out the action time periods that meet the action time standard. The identification module is used to identify features of the action time period that meets the target, and to obtain the state of the roller screw control rod drive mechanism by combining all feature identification results.

7. A computer-readable medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, can implement the online monitoring method for the status of the roller screw control rod drive mechanism as described in any one of claims 1-5.

Images