Real-time monitoring method for reverse installation of laser displacement sensor, medium and system

Abstract

The invention discloses a laser displacement sensor reverse installation real-time monitoring method, medium and system, and the method comprises the steps: S1, obtaining output data of a laser displacement sensor, detecting the integrity of key variables of the output data, and screening effective data meeting a preset power threshold value; s2, based on the effective data in the step S1, extracting displacement data of a zero channel and each sampling channel, and calculating a differential signal sequence; s3, extracting the main frequency of each differential signal in the differential signal sequence, and calculating an adaptive period parameter according to the main frequency and the sampling frequency; s4, peak detection parameters are set based on the self-adaptive period parameters, a multi-channel peak sequence is obtained, and the matching degree of the multi-channel peak sequence and a preset peak sequence template is calculated; if the matching degree is lower than a preset threshold value, it is judged that the laser displacement sensor is installed abnormally. The system has the advantages of high automation degree, high monitoring precision and the like.

Description

Technical Field

[0001] This invention mainly relates to the field of wind power technology, specifically to a method, medium, and system for real-time monitoring of a laser displacement sensor mounted in reverse. Background Technology

[0002] Laser displacement sensors are widely used in wind turbines to accurately measure parameters such as object displacement. Misalignment of the sensor installation position directly affects the accuracy of data acquisition. If the sensor is installed backwards, it may cause distorted measurement data, leading to errors in the wind turbine control logic or safety accidents. Traditional monitoring methods rely on periodic manual inspections, which suffer from problems such as high latency, low efficiency, and high cost. Specifically, this manifests in the following aspects: 1. Traditional sensor monitoring systems can only detect whether data exceeds a threshold, but cannot distinguish whether "data anomalies" are due to sensor malfunction or position swapping. When multiple sensors are swapped in installation position, single-channel data may still be within the normal range, but the correlation between multi-channel data is disrupted, leading to misjudgments in the wind turbine control logic. Existing algorithms lack the ability to identify this kind of "hidden installation error" in real time. 2. Currently, the installation positions of sensors in wind turbine units need to be manually calibrated one by one. After the wind turbine is debugged, maintained or the sensors are replaced, the positions need to be recalibrated, which takes up to several hours and cannot meet the needs of rapid changeover in the production line. 3. Replacing sensor positions will lead to the long-term collection of invalid correlation data. Existing systems need to accumulate a large amount of abnormal data and then manually review and analyze it to locate the problem. The average response cycle exceeds 24 hours. Delayed anomaly handling may increase the difficulty of troubleshooting and economic losses. Summary of the Invention

[0003] To address the technical problems existing in the prior art, this invention provides a highly automated and highly accurate real-time monitoring method, medium, and system for reverse mounting of a laser displacement sensor.

[0004] To solve the above-mentioned technical problems, the technical solution proposed by this invention is as follows: A method for real-time monitoring of a laser displacement sensor in reverse mounting includes the following steps: S1. Obtain the output data of the laser displacement sensor, detect the integrity of key variables in the output data, and filter valid data that meet the preset power threshold. S2. Based on the valid data from step S1, extract the displacement data of the zero channel and each sampling channel, and calculate the differential signal sequence; S3. Extract the main frequency of each differential signal in the differential signal sequence, and calculate the adaptive period parameter based on the main frequency and the sampling frequency; S4. Based on the adaptive period parameter setting, the peak detection parameters are set to obtain the multi-channel peak sequence, and the matching degree between the multi-channel peak sequence and the preset peak sequence template is calculated. If the matching degree is lower than the preset threshold, the laser displacement sensor is judged to be installed abnormally.

[0005] Preferably, in step S3, power spectral density analysis is used to extract the main frequency of the differential signal.

[0006] Preferably, in step S3, the formula for calculating the adaptive periodic parameter is: Number of periodic sampling points = sampling frequency / main frequency.

[0007] Preferably, the specific process of step S4 is as follows: S401. Based on the adaptive period parameter setting, the minimum distance and significance threshold for peak detection are set to perform peak detection on the differential signal and obtain the peak time point of each channel. S402. Perform peak detection on the differential signal of each sampling channel, record the order of peak occurrence of each channel in time sequence, and generate the actual peak sequence sequence. S403. Calculate the matching degree between the actual peak sequence and the preset peak sequence template; if the matching degree is lower than the threshold M, it is determined that "sensor positions are interchanged" and an abnormal result is output; otherwise, it is determined that the position is normal.

[0008] Preferably, the minimum distance for peak detection in step S401 is the number of sampling points in half a cycle.

[0009] Preferably, the key variables in step S1 include displacement and sampling time.

[0010] The present invention also discloses a computer program product, comprising a computer program that, when executed by a processor, performs the steps of the method described above.

[0011] The present invention further provides a computer-readable storage medium having a computer program stored thereon, the computer program performing the steps of the method described above when run by a processor.

[0012] The present invention also discloses a laser displacement sensor reverse mounting real-time monitoring system, including a memory and a processor connected to each other, wherein the memory stores a computer program, and the computer program executes the steps of the method described above when run by the processor.

[0013] Compared with the prior art, the advantages of the present invention are as follows: This invention achieves real-time and accurate identification of interchangeable installation positions of laser displacement sensors by constructing an automated monitoring process that combines data verification, differential denoising, frequency analysis, and peak order matching. It effectively overcomes the shortcomings of traditional methods, such as reliance on manual labor, slow response, and high misjudgment rate, and significantly improves the reliability and operational safety of wind turbine displacement monitoring. At the same time, it has good versatility and engineering applicability.

[0014] The laser displacement sensor reverse installation real-time monitoring method of the present invention realizes automatic and real-time detection of the sensor installation status, ensuring the real-time and accuracy of the collected data, reducing manual intervention, and improving the operational safety of wind turbine units. This invention combines multiple conditions such as variable integrity and power threshold to screen effective data, improving the robustness of anomaly detection; based on the extraction of the main frequency and peak order statistics, it achieves quantitative judgment of the sensor reverse installation status, rather than traditional qualitative analysis.

[0015] This invention requires no manual intervention throughout the entire process, automatically completing data verification, analysis, and anomaly marking, achieving a high degree of automation. By jointly judging multiple parameters (power, frequency, peak order), it reduces the false judgment rate and achieves high accuracy. This invention is applicable to different models of laser displacement sensors and can be adapted to different application scenarios by adjusting thresholds (such as power threshold and peak ratio). Attached Figure Description

[0016] Figure 1 The flowchart is shown in an embodiment of the laser displacement sensor reverse mounting real-time monitoring method of the present invention.

[0017] Figure 2 This is a flowchart illustrating the analysis of the frequency components of the differential signal in this invention.

[0018] Figure 3 This is a flowchart of the peak order detection method in this invention.

[0019] Figure 4 This is a diagram showing the signal vertex order in this invention. Detailed Implementation

[0020] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0021] like Figure 1 As shown, the laser displacement sensor reverse-mounted real-time monitoring method provided in this embodiment of the invention includes the following steps: S1. Check whether the input data contains key variables of the laser displacement sensor (such as displacement value, sampling time, etc.), filter valid operating condition data that meet the power requirements, and perform data cleaning; specifically including: S101. Data validity verification: Automatically detect the completeness of key variables of laser displacement sensor in the input data; if any variable is missing, mark it as "no displacement sensor data variable" and output an invalid result to avoid misjudgment due to incomplete data; S102. Operating condition data screening: Screen operating condition data that meet the normal operating conditions of the wind turbine based on a preset power threshold (such as 10%-90% of the rated power), and remove low power or invalid samples; if the data is empty after screening, mark it as "data that does not meet the power requirements" to ensure that only data under valid operating conditions are analyzed.

[0022] S2. Calculate the differential signal: such as Figure 2 As shown, based on the valid operating condition data output in step S1, the displacement data of the zero channel (reference channel) and each sampling channel are extracted, and the differential signal sequence is calculated to eliminate environmental noise (such as temperature drift and mechanical vibration) interference and highlight the characteristic signal of displacement change. Where the differential signal = sampling channel data - zero channel data; S3. Power spectral density (PSD) analysis is used to extract the main frequency of each differential signal, and adaptive period parameters are calculated based on the main frequency and sampling frequency. Specifically: S301. Power spectral density (PSD) analysis is used to analyze the frequency components of the differential signal, identify the dominant frequency of energy concentration, and characterize the periodicity of the sensor-acquired signal. S302, Adaptive Period Parameter Calculation: The adaptive period parameter is dynamically adjusted according to the main frequency and sampling frequency to ensure that the time window for subsequent peak detection matches the signal period and improves the peak recognition accuracy. The formula for calculating the adaptive period parameter is as follows: Number of periodic sampling points = Sampling frequency / Main frequency; S4. Peak Order Detection: The peak order sequence of the signal is obtained using a peak detection algorithm (with a minimum distance set to the number of sampling points in half a cycle). The matching degree between the actual peak order sequence and the preset peak order template is calculated. If the matching degree is lower than a threshold M, the sensor position is determined to be abnormal; otherwise, it is marked as normal. Specifically... Figure 3 As shown: S401, Peak detection parameter configuration: Based on the adaptive period parameter setting, the minimum distance for peak detection (such as the number of sampling points in half a period) and the significance threshold are set to perform peak detection on the differential signal and obtain the peak time points of each channel; Setting a minimum distance for peak detection can avoid interference from false peaks caused by signal fluctuations; setting a peak significance threshold can ensure that only valid signal peaks are detected. S402, Multi-channel peak sequence acquisition: Perform peak detection on the differential signals of multiple sensor channels, record the order of peak occurrence of each channel in time sequence, and generate a peak sequence sequence; S403, Template Matching and Anomaly Judgment: Preset peak sequence template under normal sensor installation position, calculate the matching degree between the actual peak sequence and the preset peak sequence template; if the matching degree is lower than the threshold M, it is judged as "sensor position interchanged" and an abnormal result is output; otherwise, it is judged as normal position.

[0023] Specifically, the corresponding matching degree = number of correct sequence sets / total number of sets. For example... Figure 4 As shown, the preset peak order template is [4, 3, 2, 1]. Each group of four is matched with the predicted peak order template. Figure 4 The calculated actual peak order sequence is [4, 1, 2, 3, ... 4, 1, 2, 3]. There is no peak order sequence [4, 3, 2, 1], so its matching degree is 0.

[0024] For example, given a peak sequence [4, 3, 2, 1, 4, 3, 2, 1], if its length is 8, there are 2 sequences (each with a length of 4). Counting from the beginning, there are 2 occurrences of [4, 3, 2, 1]. Therefore, the wiring is correct, and the accuracy (matching degree) is 2 / 2. Alternatively, given a peak sequence [3, 4, 1, 2, 3, 4, 1, 2, 3, 4], with a length of 10, there are 2 sequences. Counting from the beginning, there are 0 occurrences of [4, 3, 2, 1], resulting in an accuracy of 0 / 2 = 0. In actual test data with noise, occasionally [4, 3, 2, 1, 2, 4, 3, 2, 1, 3, 4, 3] may appear. If this length is 12, there are 3 sequences. Counting from the beginning, there are 2 occurrences of [4, 3, 2, 1], resulting in an accuracy of 2 / 3.

[0025] This invention achieves real-time and accurate identification of interchangeable installation positions of laser displacement sensors by constructing an automated monitoring process that combines data verification, differential denoising, frequency analysis, and peak order matching. It effectively overcomes the shortcomings of traditional methods, such as reliance on manual labor, slow response, and high misjudgment rate, and significantly improves the reliability and operational safety of wind turbine displacement monitoring. At the same time, it has good versatility and engineering applicability.

[0026] The laser displacement sensor reverse installation real-time monitoring method of the present invention realizes automatic and real-time detection of the sensor installation status, ensuring the real-time and accuracy of the collected data, reducing manual intervention, and improving the operational safety of wind turbine units. This invention combines multiple conditions such as variable integrity and power threshold to screen effective data, improving the robustness of anomaly detection; based on the extraction of the main frequency and peak order statistics, it achieves quantitative judgment of the sensor reverse installation status, rather than traditional qualitative analysis.

[0027] This invention requires no manual intervention throughout the entire process, automatically completing data verification, analysis, and anomaly marking, achieving a high degree of automation. By jointly judging multiple parameters (power, frequency, peak order), it reduces the false judgment rate and achieves high accuracy. This invention is applicable to different models of laser displacement sensors and can be adapted to different application scenarios by adjusting thresholds (such as power threshold and peak ratio).

[0028] The present invention also discloses a computer program product, comprising a computer program that, when executed by a processor, performs the steps of the method described above.

[0029] The present invention further provides a computer-readable storage medium having a computer program stored thereon, the computer program performing the steps of the method described above when run by a processor.

[0030] The present invention also discloses a laser displacement sensor reverse mounting real-time monitoring system, including a memory and a processor connected to each other, wherein the memory stores a computer program, and the computer program executes the steps of the method described above when run by the processor.

[0031] The products, media, and systems of the present invention, corresponding to the methods described above, also possess the advantages described above.

[0032] The present invention can implement all or part of the processes in the methods of the above embodiments, or it can be implemented by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium includes: any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. The memory is used to store computer programs and / or modules. The processor implements various functions by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may include high-speed random access memory, as well as non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital (SD) cards, flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0033] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principle of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A method for real-time monitoring of a laser displacement sensor in reverse mounting, characterized in that, Including the following steps: S1. Obtain the output data of the laser displacement sensor, detect the integrity of key variables in the output data, and filter valid data that meet the preset power threshold. S2. Based on the valid data from step S1, extract the displacement data of the zero channel and each sampling channel, and calculate the differential signal sequence; S3. Extract the main frequency of each differential signal in the differential signal sequence, and calculate the adaptive period parameter based on the main frequency and the sampling frequency; S4. Based on the adaptive period parameter setting, the peak detection parameters are set to obtain the multi-channel peak sequence and the matching degree between the multi-channel peak sequence and the preset peak sequence template is calculated. If the matching degree is lower than the preset threshold, it is determined that the laser displacement sensor is installed abnormally.

2. The laser displacement sensor reverse-mounted real-time monitoring method according to claim 1, characterized in that, In step S3, power spectral density analysis is used to extract the main frequency of the differential signal.

3. The laser displacement sensor reverse-mounted real-time monitoring method according to claim 2, characterized in that, In step S3, the formula for calculating the adaptive periodic parameter is: Number of periodic sampling points = sampling frequency / main frequency.

4. The real-time monitoring method for reverse-mounted laser displacement sensor according to claim 1, 2, or 3, characterized in that, The specific process of step S4 is as follows: S401. Based on the adaptive period parameter setting, the minimum distance and significance threshold for peak detection are set to perform peak detection on the differential signal and obtain the peak time point of each channel. S402. Perform peak detection on the differential signal of each sampling channel, record the order of peak occurrence of each channel in time sequence, and generate the actual peak sequence sequence. S403. Calculate the matching degree between the actual peak sequence and the preset peak sequence template; If the matching degree is lower than the threshold M, it is determined as "sensor position swap" and an abnormal result is output; otherwise, it is determined as normal position.

5. The real-time monitoring method for reverse-mounted laser displacement sensor according to claim 4, characterized in that, The minimum distance for peak detection in step S401 is the number of sampling points in half a cycle.

6. The real-time monitoring method for reverse-mounted laser displacement sensor according to claim 1, 2, or 3, characterized in that, The key variables in step S1 include displacement and sampling time.

7. A computer program product, comprising a computer program, characterized in that, The computer program is executed by a processor to perform the steps of the method as described in any one of claims 1-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when run by a processor, performs the steps of the method as described in any one of claims 1-6.

9. A real-time monitoring system for reverse mounting of a laser displacement sensor, comprising a memory and a processor interconnected, wherein the memory stores a computer program, characterized in that, The computer program, when run by a processor, performs the steps of the method as described in any one of claims 1-6.

Images