Lateral pressure encoder early warning method for cable laying

Abstract

The invention relates to a side pressure encoder early warning method for cable laying, and the method comprises the steps: deploying a multi-axis pressure sensor array at a bridge corner key point of a cable laying path, and collecting a three-dimensional dynamic side pressure analog signal in real time when a cable passes through; the analog signals are input into an analog-to-digital conversion module, nonlinear correction is carried out through a dynamic calibration algorithm, and a digital real-time side pressure value sequence with the measuring range ranging from 0 N to 500 N and capable of being continuously adjusted is generated; constructing a dynamic pressure-length-speed three-dimensional relation matrix according to the lateral pressure value sequence, the laying length metering value and the speed control instruction through a multi-thread fusion processing module; and performing spectrum feature analysis on the three-dimensional relation matrix, and when it is detected that abnormal frequency component energy exceeds a preset risk threshold, triggering a spatial positioning grading early warning signal and generating a spectrum diagnosis report containing a failure point space coordinate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric digital data processing, in particular to a cable laying side pressure encoder early warning method. BACKGROUND

[0002] In March 2025, in the landscape improvement project of Chongbu Village and Xingang Village in Mingcheng Town, in the cable laying transformation construction technology, it is found that in the existing technology of the control and monitoring system of the cable laying equipment, the incremental encoder is used to indirectly monitor and control the factors related to the cable laying side pressure, mainly reflected in that the control of the cable laying speed is crucial to the control of the side pressure, and the existing technology has the following defects: It cannot directly measure the actual side pressure, only indirectly speculate the pressure through the speed and the bending angle, cannot real-time monitor the dynamic side pressure value of the key position (bridge turning angle), the control precision is insufficient, if the speed is too fast to cause the side pressure to increase suddenly (> 500N), or too slow to increase the friction and indirectly lift the pressure, which is easy to cause the cable wear or equipment failure, and lacks abnormal positioning ability, which is reflected in that it cannot identify the abnormal frequency component of the pressure and its spatial position, and it is difficult to timely early warning and diagnose the failure point. SUMMARY

[0003] In order to solve the problems existing in the above-mentioned prior art, the present application aims to provide a cable laying side pressure encoder early warning method.

[0004] The solution proposed by the present application in view of the above-mentioned prior art defects is: deploying a multi-axis pressure sensing array at the bridge turning angle, real-time collecting three-dimensional dynamic side pressure signals; generating a 0-500N digitized pressure sequence through a dynamic calibration algorithm, combining with the incremental encoder (±0.1%FS accuracy) output laying length; constructing a pressure-length-velocity three-dimensional matrix, performing spectrum analysis; when the abnormal frequency energy exceeds the threshold, triggering spatial positioning hierarchical early warning and generating a spectrum diagnosis report containing the failure point coordinates.

[0005] The cable laying side pressure encoder early warning method provided by the present application comprises the following steps: S101, deploying a multi-axis pressure sensing array at the bridge turning angle key point of the cable laying path, real-time collecting three-dimensional dynamic side pressure analog signals applied when the cable passes through; S102, inputting the analog signal into an analog-to-digital conversion module, adopting a dynamic calibration algorithm for non-linear correction, generating a 0-500N continuously adjustable digitized real-time side pressure value sequence; S103, real-time acquiring cable displacement pulse signals through an incremental encoder, combining with a temperature compensation type calibration algorithm to eliminate jitter error and compensate cumulative error of pulse counting, outputting laying length measurement value accurate to ±0.1%FS; S104, based on the preset time-varying pressure threshold model, the real-time side pressure value sequence is monitored by a sliding window: when the pressure value continuously exceeds the upper threshold, a closed-loop deceleration control instruction is generated to drive the servo motor; when the pressure value continuously drops below the lower threshold, a fuzzy acceleration control instruction is generated to optimize the tension balance; S105, through the multi-thread fusion processing module, the side pressure value sequence, the laying length measurement value and the speed control instruction are constructed into a dynamic pressure-length-speed three-dimensional relationship matrix; S106, the three-dimensional relationship matrix is subjected to frequency spectrum feature analysis, when the energy of the abnormal frequency component detected exceeds the preset risk threshold, a spatial positioning hierarchical early warning signal is triggered and a frequency spectrum diagnosis report containing the spatial coordinates of the failure point is generated.

[0006] Preferably, in step S101, at the cable bridge corner, a multi-axis pressure sensing array is used to collect real-time three-dimensional dynamic side pressure signals generated by the cable passing, forming an original pressure data set, when the signal intensity exceeds the preset threshold, the system immediately performs frequency domain decomposition using fast Fourier transform to obtain a frequency domain feature set, then, the principal component analysis algorithm is used to extract the main pressure distribution pattern from the frequency domain features to generate a reduced feature vector set, if the principal component variance ratio meets the standard, the Kalman filter is used to smooth and optimize the feature vector to establish a reliable pressure distribution model, based on this model, the key dynamic mechanical parameters of the cable passing are calculated to form a mechanical behavior data set, the system further uses time series analysis to predict the pressure change trend to obtain a pressure prediction sequence, and according to this, the pressure distribution abnormal points at the corner are accurately identified, and finally an abnormal detection report is obtained.

[0007] Preferably, in step S102, the analog-to-digital conversion module samples the analog signal at a fixed frequency to generate a digitized side pressure sequence, if there is abnormal fluctuation in the sequence, the median filter algorithm is immediately used for smoothing to obtain a smoothed side pressure sequence, then, based on the smoothed sequence, the periodic components are extracted by time series decomposition to form a periodic feature sequence, when the fluctuation amplitude of this sequence exceeds the preset threshold, the system automatically calls the autoregressive model to predict future pressure changes, outputs the pressure change prediction sequence, then, the sliding window method is used to calculate the local pressure change rate of the prediction sequence to generate a pressure change rate sequence, as soon as a mutation point is detected in the change rate sequence, the abnormal detection algorithm immediately locates its position to form an abnormal point distribution sequence, finally, the clustering analysis method is applied to classify the abnormal points in the distribution sequence to obtain an abnormal point classification set.

[0008] Preferably, in step S103, the system acquires the cable displacement pulse signal in real time through the incremental encoder at a fixed sampling frequency, generates a pulse count sequence, and if an abnormal jump is detected in the sequence, immediately applies a median filter algorithm for smoothing processing to obtain a smoothed pulse sequence. Subsequently, based on the smoothed pulse sequence, combined with real-time environmental temperature data, a temperature compensation algorithm is used to correct the count deviation caused by temperature changes, generating a more accurate corrected pulse sequence. Then, the sliding window method is applied to the corrected pulse sequence to calculate the local displacement change rate, forming a displacement change rate sequence. When a mutation point appears in the sequence, the abnormal detection algorithm automatically identifies its position, and outputs a mutation point distribution sequence. Further, the mutation points in the distribution sequence are classified using cluster analysis method to obtain an abnormal classification set. Finally, the system determines the type in the abnormal classification set according to the preset threshold value, and obtains a cable laying length measurement value sequence.

[0009] Preferably, in step S104, the lateral pressure value is acquired in real time at a fixed frequency to form a pressure sequence. Subsequently, the sliding window method is applied to segmentally analyze the sequence to calculate the pressure mean value in the window, generating a pressure mean value sequence. Then, the sequence is compared with a preset time-varying pressure threshold model (including upper and lower threshold values) to determine the triggering condition. When the pressure mean value continuously exceeds the upper threshold value, the system immediately generates a closed-loop deceleration instruction sequence using a proportional-integral-derivative (PID) control algorithm. If the mean value continuously falls below the lower threshold value, a fuzzy control algorithm is automatically applied to generate an acceleration instruction sequence. Finally, the deceleration or acceleration instruction sequence drives the servo motor to adjust the running speed or optimize the tension balance, respectively, to obtain a speed adjustment sequence or a tension adjustment sequence.

[0010] Preferably, in step S105, the sensor array acquires the lateral pressure sequence, laying length measurement value, and speed control instruction in real time, and generates an original data set through multi-thread fusion processing. Subsequently, parallel processing is used to synchronously acquire and denoise to obtain a denoised data sequence. Then, data standardization is performed and statistical features are calculated to form a standardized data sequence. Based on this, a pressure-length-speed three-dimensional relationship matrix is constructed, and principal component analysis is used to extract dynamic correlation features to obtain a feature vector set. If the dynamic feature variance contribution rate of the set exceeds a threshold value, a dynamic control parameter sequence is generated accordingly. Finally, the control parameter drives the servo motor to adjust the running state, and outputs an optimized speed instruction sequence, which synchronously updates the speed component in the three-dimensional matrix.

[0011] Preferably, in the step S106, the time domain conversion is performed on the spectrum feature set by applying the inverse fast Fourier transform to generate a time domain signal sequence, then the periodicity feature of the sequence is calculated to form a periodic feature vector, when the amplitude of the vector exceeds a preset fluctuation threshold, the system immediately performs spatial clustering on the failure point coordinates in the three-dimensional relationship matrix to obtain a clustering center set, then based on the clustering center set, the K-means algorithm is used to divide the failure area to generate a region division result, further, the boundary feature is extracted from the division result and the geometric center of each region is calculated to obtain a center coordinate set, then the center coordinate set is used to update the spatial structure component of the three-dimensional relationship matrix to form an updated matrix, finally, the abnormal pattern matching is performed on the updated matrix, if the preset abnormal pattern is matched, an adjustment signal sequence is generated.

[0012] The cable laying side pressure encoder early warning method has the advantages that for the problems of device failure and low efficiency caused by abnormal side pressure, length measurement error and tension imbalance in the cable laying process, a multi-axis pressure sensing array is deployed at the bridge corner to collect three-dimensional dynamic side pressure signals in real time, high-precision side pressure value sequences are generated through analog-digital conversion and dynamic calibration algorithm, and accurate to ±0.1%FS laying length measurement values are output by using the incremental encoder combined with the temperature compensation calibration algorithm.

[0013] The application optimizes the servo motor driving and tension balance by monitoring the side pressure sequence through the sliding window, generating closed-loop deceleration or fuzzy acceleration control instructions based on the time-varying pressure threshold model, and constructing a pressure-length-speed three-dimensional relationship matrix through multi-thread fusion processing to perform spectrum feature analysis, detect abnormal frequency components and trigger spatial positioning hierarchical early warning to generate a diagnostic report containing failure point coordinates.

[0014] The application realizes dynamic monitoring and intelligent control of the whole cable laying process, and significantly improves the laying accuracy, device stability and operation efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is a flow of the cable laying side pressure encoder early warning method Figure 1 ; Figure 2 is a flow of the cable laying side pressure encoder early warning method Figure 2 . DETAILED DESCRIPTION

[0016] As Figures 1-2 shown, the cable laying side pressure encoder early warning method comprises the following steps: As Figures 1-2As shown, S101, a multi-axis pressure sensing array is deployed at the bridge corner key point of the cable laying path, and real-time collection of three-dimensional dynamic side pressure simulation signals applied when the cable passes.

[0017] Further, in step S101, a three-dimensional dynamic side pressure signal at the cable bridge corner is acquired by the multi-axis pressure sensing array, and an original pressure data set is generated; If the signal strength of the original pressure data set exceeds the preset threshold, the signal is subjected to frequency domain decomposition using the fast Fourier transform algorithm, and a frequency domain feature set is obtained; According to the frequency domain feature set, the main pressure distribution mode is extracted using the principal component analysis algorithm, and a reduced dimension feature vector set is generated; If the principal component variance proportion in the feature vector set is greater than the preset threshold, the feature vector set is subjected to smoothing processing by the Kalman filtering algorithm, and an optimized pressure distribution model is obtained; According to the optimized pressure distribution model, the dynamic mechanical parameters when the cable passes are calculated, and a mechanical behavior data set is generated; Through the mechanical behavior data set, the time series analysis method is used to predict the pressure change trend when the cable passes, and a pressure prediction sequence is obtained; According to the pressure prediction sequence, the pressure distribution abnormal points at the cable bridge corner are determined, and an abnormality detection report is generated.

[0018] Specifically, in step S101, when deploying a multi-axis pressure sensing array at the bridge corner key point of the cable laying path, first, a high-precision three-dimensional modeling software is used to geometrically model the bridge corner, accurately calculate the curvature radius at the corner, for example, set to 0.5 meters, and generate grid data containing corner coordinates (x, y, z) with a resolution of 0.01 meters; Subsequently, a multi-axis pressure sensing array is arranged at the corner key point, a three-axis pressure sensor (model MPU-9250) is selected, each sensor covers an area of 10 cm x 10 cm, the array is arranged in a 5 x 5 matrix, a total of 25 sensors, the sampling frequency is 100 Hz, and the three-dimensional dynamic side pressure simulation signals when the cable passes are collected in real time; The sensor data is transmitted to the edge computing node through the I2C protocol, and the data packet size is 128 bytes / second; The edge node uses an embedded processor (Raspberry Pi 4) to run real-time signal processing algorithms, first denoises the collected original pressure signal, uses the Kalman filtering algorithm, sets the process noise covariance Q=0.01 and the measurement noise covariance R=0.05, and obtains the smooth three-dimensional pressure components (Fx, Fy, Fz) after filtering out high-frequency noise; Next, the total pressure is calculated by vector synthesis algorithm where Fx, Fy, Fz represent the three-axis pressure components (unit: N) respectively, and the peak pressure is extracted, for example, the maximum value is 500 N, which occurs at the maximum point of the corner curvature; The pressure data is analyzed in time series, and the signal is converted into frequency domain by fast Fourier transform (FFT), and the main vibration frequency (10 Hz) is identified to determine whether the cable sliding causes abnormal vibration; If the frequency exceeds the preset threshold (15 Hz), an early warning signal is triggered and sent to the cloud management system through the MQTT protocol; The cloud uses a machine learning model (support vector machine, SVM) to train historical pressure data, input features include pressure peak, frequency and corner curvature, and output cable wear risk level (low, medium, high), with an accuracy of 95%; Finally, the system generates a real-time pressure distribution heat map with a resolution of 0.02 meters, which is stored in the cloud database for subsequent optimization of cable laying path; The entire process is achieved through an automated system, with a data processing delay of less than 50 milliseconds, ensuring real-time and reliability.

[0019] In one embodiment, the Kalman filter state equation can be represented as: State equation: ; Measurement equation: ; The character physical meaning of the above calculation formula is: xk: state (displacement) at time k, v: cable speed (unit: m / s), Δt: sampling interval (unit: s, in the embodiment Δt=0.01 s), n: measurement noise.

[0020] As shown in Figures 1-2 S102, the analog signal is input into an analog-to-digital conversion module, and a dynamic calibration algorithm is used for non-linear correction to generate a digital real-time side pressure value sequence with a range of 0-500 N continuously adjustable.

[0021] Further, in step S102, the analog signal is sampled by the analog-to-digital conversion module using a fixed sampling frequency to obtain a digital side pressure sequence; According to the digital side pressure sequence, if there is abnormal fluctuation in the sequence, the sequence is smoothed by a median filter algorithm to obtain a smoothed side pressure sequence; Using the smoothed side pressure sequence, the periodic component is extracted by a time series decomposition method to obtain a periodic characteristic sequence; According to the periodic characteristic sequence, if the fluctuation amplitude of the periodic characteristic sequence exceeds a preset threshold, the sequence is predicted by an autoregressive model to obtain a pressure change prediction sequence; The pressure change rate sequence is calculated by using a sliding window method to calculate the local pressure change rate, and the pressure change rate sequence is obtained; According to the pressure change rate sequence, if there is a mutation point in the change rate sequence, the mutation point position is identified by an anomaly detection algorithm, and an abnormal point distribution sequence is obtained; Through the abnormal point distribution sequence, the clustering analysis method is used to classify the abnormal points, and the abnormal point classification set is obtained.

[0022] Specifically, in step S102, the analog signals collected at the bridge corner of the cable laying path are processed by an analog-to-digital conversion module. A high-precision analog-to-digital converter (ADS1256, 24-bit resolution) is selected to convert the analog voltage signals (range 0-5V) of the three-axis pressure sensor into digital signals. The sampling rate is 200Hz, and the range is set to 0-500N; To ensure data accuracy, a dynamic calibration algorithm is used to correct the analog-to-digital conversion results. The algorithm is based on a polynomial fitting model, assuming that the correction function is y=ax³+bx²+cx+d, where the coefficients a=0.0001, b=0.02, c=1.5, d=0.1, y: corrected pressure value (unit: N), x: original analog-to-digital conversion value; The sensor output is fitted by the least squares method to correct the non-linear error, and the error range is controlled within ±0.5N; The corrected digital signal is transmitted to the edge computing unit (NVIDIA Jetson Nano) through the SPI protocol, and the data packet size is 256 bytes / second; The edge computing unit runs a real-time processing program to smooth the corrected pressure data sequence. A sliding window average algorithm is used with a window size of 10 samples to reduce random noise interference and obtain a continuous pressure value sequence (e.g. peak pressure of 480N, occurring when the cable sliding speed at the corner is 0.2m / s); Subsequently, the system extracts features from the pressure sequence and calculates the pressure change rate, with the formula ΔP / Δt, where Δt=0.01 seconds, and extracts the maximum change rate (50N / s) as the dynamic load feature; The feature data is uploaded to the cloud analysis platform through the LoRa protocol. The cloud runs a time series analysis algorithm, using an autoregressive model (ARIMA, p=2, d=1, q=1) to predict the short-term trend of the pressure sequence. The prediction window is 1 second, and the prediction error is less than 5N; The analysis results are stored in a distributed database (MongoDB) with time stamp and location coordinates (resolution 0.02 meters) as indexes, facilitating subsequent dynamic adjustment of the cable laying path; The entire processing flow is implemented through an automated script, with a data processing delay controlled within 30 milliseconds to ensure real-time performance.

[0023] like Figures 1-2 As shown in Figure S103, the cable displacement pulse signal is acquired in real time through an incremental encoder, and the pulse counting is eliminated by a temperature-compensated calibration algorithm to compensate for jitter error and cumulative error, and the laying length measurement value is output with an accuracy of ±0.1%FS.

[0024] Furthermore, in step S103, the cable displacement pulse signal is acquired in real time by an incremental encoder, and a pulse counting sequence is obtained by using a fixed sampling frequency; If there are abnormal jumps in the pulse counting sequence, the sequence is smoothed by the median filtering algorithm to obtain a smooth pulse sequence; Based on the smoothed pulse sequence, a temperature compensation algorithm is used in conjunction with ambient temperature data to correct the counting deviation caused by temperature, resulting in a corrected pulse sequence. By correcting the pulse sequence, the local displacement change rate is calculated using the sliding window method to obtain the displacement change rate sequence. If there are abrupt changes in the displacement change rate sequence, the location of the abrupt changes is identified by an anomaly detection algorithm to obtain the abrupt change point distribution sequence. Based on the distribution sequence of mutation points, cluster analysis is used to classify the mutation points and obtain an anomaly classification set; By using an anomaly classification set and a preset threshold to determine the anomaly type, a sequence of laying length measurement values ​​is generated.

[0025] Specifically, in step S103, during the cable laying process, a high-resolution incremental encoder (HEDL-5540, 1000 pulses / revolution) is used to collect the cable displacement pulse signal in real time. The encoder is installed on the traction wheel axle, the wheel circumference is 0.314 meters, and 1000 pulses are generated per revolution. When the cable moving speed is 0.5 meters / second, the pulse frequency is 1592Hz. The pulse signal is acquired by a high-speed counting module (based on an STM32F4 microcontroller). The counter records the number of pulses at a sampling rate of 100kHz to generate the original displacement data. To eliminate jitter error, a Kalman filter algorithm is used to smooth the pulse count. The filter state equation is x(k)=x(k-1)+v*Δt, and the measurement equation is z(k)=x(k)+n, where v is the cable speed, Δt=0.01 seconds, noise covariance Q=0.01, R=0.1. After filtering, the pulse count jitter error is reduced to ±2 pulses. To compensate for the cumulative error caused by temperature, a temperature-compensated calibration algorithm is introduced. The temperature at the traction wheel (25℃ to 40℃) is measured based on an ambient temperature sensor (DS18B20, resolution 0.0625℃). The linear correction model L=Lo*(1+α*ΔT) is used, where L is the corrected length, Lo is the original count length, α=0.000011 / ℃ is the coefficient of thermal expansion, and ΔT is the temperature change. The corrected length error is controlled within ±0.1%FS (full scale 100 meters). The corrected displacement data is transmitted to the edge computing unit (Raspberry Pi 4) via the MQTT protocol. The data packet size is 128 bytes and the transmission frequency is 100Hz. The algorithm for accumulating edge cell running length is as follows: Wherein, S: cumulative laying length (unit: m), n: pulse count, C: circumference of traction wheel (unit: m, C=0.314 m in the example), N: number of encoder pulses per revolution (N=1000 in the example). The formula is S=∑(n*0.314 / 1000), which calculates the real-time laying length (50.125 meters). To ensure data reliability, the edge unit performs anomaly detection on the length sequence using the Z-score method with a threshold of 3σ, and removes abnormal pulses (count jumps caused by sudden noise). The processed length data is uploaded to a cloud database (InfluxDB), indexed by timestamp (1 millisecond resolution) and laying location (0.05 meter resolution), for use by the path planning system. The entire process is automated using Python scripts, with data processing latency controlled to within 20 milliseconds.

[0026] like Figures 1-2 As shown in S104, based on a preset time-varying pressure threshold model, a sliding window is used to monitor the real-time side pressure value sequence: When the pressure value continuously exceeds the upper limit threshold, a closed-loop deceleration control command is generated to drive the servo motor. When the pressure value remains below the lower threshold, a fuzzy acceleration control command is generated to optimize the tension balance.

[0027] Further, in step S104, the side pressure value sequence is collected in real time by the sensor, and a pressure sequence is obtained by using a fixed sampling frequency; The pressure sequence is segmented using the sliding window method, and the average pressure within the window is calculated to obtain the average pressure sequence. Based on the average pressure sequence and combined with the preset time-varying pressure threshold model, the average value is compared with the upper and lower thresholds to determine the triggering conditions. If the mean value continuously exceeds the upper limit threshold, the proportional-integral-derivative control algorithm is used to generate closed-loop deceleration control commands, resulting in a deceleration command sequence. By using a deceleration command sequence, the servo motor is driven to adjust its operating speed, resulting in an adjusted speed sequence. If the mean value remains below the lower threshold, a fuzzy control algorithm is used to generate acceleration control commands, resulting in an acceleration command sequence. Based on the acceleration command sequence, the servo motor is driven to optimize the tension balance, resulting in a tension adjustment sequence.

[0028] Specifically, in step S104, during the cable laying process, in order to monitor the side pressure of the traction system in real time and dynamically adjust the traction speed, a high-precision pressure sensor (MPX5700AP, range 0-700kPa, resolution 0.1kPa) is used to collect the side pressure value. The sensor is installed on the side wall of the traction wheel, the sampling frequency is 200Hz, and a real-time pressure sequence is generated. For example, the cable laying speed is 0.8 meters per second, and the lateral pressure fluctuation during normal operation is 200-300 kPa; The pressure data is converted into a digital signal at a sampling rate of 100kHz through an analog-to-digital conversion module (based on ADS1256, 24-bit resolution) and stored as a time series. To achieve sliding window monitoring, a sliding window of length 50 (time span 0.25 seconds) was used to calculate the mean of the pressure sequence, using the formula P. avg =∑P i / 50, where P i The pressure value within the window; If the average value exceeds the preset upper limit threshold of 350 kPa for 5 consecutive times (based on historical data analysis), the system generates a closed-loop deceleration command. The servo motor (model SGM7J, rated speed 3000 rpm) is adjusted through a PID controller (proportional coefficient Kp=0.5, integral coefficient Ki=0.1, derivative coefficient Kd=0.05) to reduce the target speed to 0.6 m / s. The calculation formula is: u(t)=Kp*e(t)+Ki*∫e(t)dt+Kd*de(t) / dt, where, u(t): control output (speed command), e(t) is the pressure deviation, Kp, Ki, Kd: PID coefficients (in this example, Kp=0.5, Ki=0.1, Kd=0.05); Conversely, if the mean value is below the lower limit threshold of 150 kPa for 5 consecutive times, the system triggers fuzzy acceleration control based on fuzzy logic rules (input is pressure deviation and deviation change rate, output is speed increment). For example, when the deviation is -50 kPa and the change rate is -10 kPa / s, the speed increment is +0.1 m / s to optimize tension balance. The fuzzy rule table is designed based on experience and contains 25 rules. It uses triangular membership functions and defuzzifies the rules by weighted average method after inference. The processed instructions are transmitted to the motor driver via the CAN bus (speed 1Mbps), with a data packet size of 64 bytes and a delay controlled within 10 milliseconds; The stress sequence was simultaneously uploaded to the edge computing unit (Jetson Nano), and anomaly detection was performed using a Python script. An anomaly removal algorithm based on mean and standard deviation was used, with a threshold of 2.5σ, to remove mutation data (instantaneous jump to 500kPa). The final data is stored in a local SQLite database with timestamps (1 millisecond resolution) for subsequent analysis.

[0029] like Figures 1-2 As shown in S105, the multi-threaded fusion processing module constructs a dynamic pressure-length-speed three-dimensional relationship matrix by combining the side pressure value sequence, laying length measurement value, and speed control command.

[0030] Furthermore, in step S105, the side pressure value sequence, laying length measurement value and speed control command are collected in real time by the sensor array, and the original data set is obtained by using a multi-threaded fusion processing module; Parallel processing methods are used to synchronously acquire and denoise the original dataset, generating a denoised data sequence. Based on the denoised data sequence, perform data standardization, calculate the statistical characteristics of each sequence, and obtain the standardized data sequence; By standardizing the data sequence, a three-dimensional relationship matrix of pressure-length-velocity is constructed, and the dynamic correlation features are extracted using the principal component analysis algorithm to obtain a set of feature vectors. If the variance contribution rate of the dynamically associated features in the feature vector set exceeds a preset threshold, then dynamic control parameters are generated based on the feature vector set to obtain a control parameter sequence. Based on the control parameter sequence, the operating state of the servo motor is adjusted to generate an optimized speed command sequence; By optimizing the velocity command sequence, the velocity components in the three-dimensional relation matrix are updated, resulting in the updated three-dimensional relation matrix.

[0031] Specifically, in step S105, during the cable laying process, in order to construct a dynamic pressure-length-speed three-dimensional relationship matrix, a multi-threaded fusion processing module is used to process the side pressure value sequence, laying length measurement value and speed control command. First, the lateral pressure data is collected by a high-precision pressure sensor (range 0-600kPa, resolution 0.05kPa) at a sampling frequency of 250Hz to generate a time series. During normal operation, the pressure fluctuation is between 180-280kPa. The laying length is measured in real time by an encoder (resolution 0.01 meters), with a sampling frequency of 100 Hz, and the cable advance distance is recorded. For example, when the current laying speed is 0.9 meters / second, the length sequence is updated every 0.01 seconds. Speed ​​control commands are generated by the servo motor driver and are based on voltage signals (range 0-10V). The multi-threaded processing module uses three threads to process in parallel: Thread 1 performs a Fast Fourier Transform (FFT) on the stress sequence to extract frequency features, as shown in the formula. N: Number of sampling points (N=64 in the example), x(n): Time-domain pressure sequence, X(k): Frequency-domain component, calculate the dominant frequency component (e.g., 10Hz) to analyze the periodicity of pressure fluctuations; Thread 2 applies a Kalman filter to the length sequence, with the state equation being x. k =x (k-1) +v k *Δt, noise covariance Q=0.01, smooths length data, eliminates measurement jitter, for example, reduces noise interference from 0.03 meters to 0.01 meters; Thread 3 processes instructions using a weighted moving average algorithm, with the formula V. avg =0.6*V k +0.3*V (k-1) +0.1*V (k-2) Smooth speed fluctuations, for example, adjust the speed from 0.92 m / s to 0.90 m / s; The fusion module maps the three data points to a three-dimensional matrix with dimensions [100, 100, 50], corresponding to pressure (0-600 kPa), length (0-1000 m), and speed (0-2 m / s), respectively. The matrix elements are calculated using a three-dimensional interpolation algorithm (linear interpolation). For example, the interpolation result for the point (250 kPa, 500 m, 0.9 m / s) is a control weight of 0.85. Anomaly detection was performed using K-means clustering with K=3, and data that deviated from the cluster center by two standard deviations (pressure sudden change to 450 kPa) were removed. The processing results are transmitted to the cloud via the MQTT protocol (2Mbps rate), with a data packet size of 128 bytes and a latency controlled within 5 milliseconds. The data is then stored in a MongoDB database with a timestamp resolution of 0.5 milliseconds.

[0032] like Figures 1-2 As shown in step S106, spectral feature analysis is performed on the three-dimensional relationship matrix. When the energy of an abnormal frequency component exceeds a preset risk threshold, a spatial positioning graded early warning signal is triggered and a spectral diagnostic report containing the spatial coordinates of the failure point is generated.

[0033] Furthermore, in step S106, the spectral feature set is transformed in the time domain by using the Fast Fourier Transform algorithm to obtain the time domain signal sequence; The periodic characteristics of the signal are calculated from the time-domain signal sequence, and a periodic feature vector is generated. If the amplitude of the periodic eigenvector exceeds the preset fluctuation threshold, spatial clustering is performed on the coordinates of the failure points of the three-dimensional relation matrix to obtain the cluster center set. Based on the cluster center set, the K-means algorithm is used to divide the failure point region and generate the region division result; Extract boundary features from the region division results, calculate the geometric center of each region, and obtain the center coordinate set; By using the central coordinate set, the spatial dimension components of the three-dimensional relation matrix are updated to generate an update matrix; Perform anomaly pattern matching on the update matrix. If a preset anomaly pattern is matched, generate an adjustment signal sequence.

[0034] Specifically, in step S106, during cable laying, to perform spectral feature analysis of the three-dimensional relationship matrix and generate a spectral diagnostic report containing the spatial coordinates of the failure point, the three-dimensional matrix (dimensions [100, 100, 50], corresponding to pressure 0-600 kPa, length 0-1000 meters, and speed 0-2 m / s) is first subjected to spectral analysis. Discrete wavelet transform (DWT) is used to decompose the signal in the pressure dimension. Daubechies wavelet (db4) is selected, decomposed into 4 levels, extract frequency components, and calculate the energy of each level. The formula is as follows: , where c j (k) represents the wavelet coefficients of the j-th layer, E j The energy of the j-th wavelet layer, for example, the wavelet coefficients of the 4th layer are calculated for a pressure sequence (sampling frequency 200Hz, length 1024 points). The main frequency energy is concentrated in 2-8Hz, and the normal energy range is 500-800 units. If the energy in a certain frequency band (12Hz) reaches 1200 units, exceeding the preset risk threshold of 1000 units, an anomaly detection will be triggered. Anomaly detection uses the Support Vector Machine (SVM) algorithm with a radial basis function (RBF) kernel function, parameters C=1.0, γ=0.01. The pressure, length, and velocity data in the three-dimensional matrix are projected into a high-dimensional space to classify anomaly points. For example, if the coordinates (300kPa, 600m, 1.2m / s) deviate from the normal cluster, it is marked as a failure point. Spatial positioning is achieved through a 3D grid search algorithm with a grid resolution of [0.5 kPa, 0.1 m, 0.01 m / s]. The coordinates of the location failure point are determined, for example (300.2 kPa, 600.1 m, 1.21 m / s), and the Euclidean distance between it and the normal data is calculated using the following formula: Where d is the distance between the failure point and the normal cluster, p,l,v are the pressure (kPa), length (m), and velocity (m / s) of the failure point, and p0,l0,v0 are the coordinates of the center of the normal cluster. The distance value is 15.3, which exceeds the threshold of 10, triggering a graded early warning signal. The warning signal is divided into three levels: 10-15 is low level, 15-20 is medium level, and >20 is high level. This example is a medium level warning. The spectrum diagnostic report is generated in JSON format, including the coordinates of the failure point, the spectrum energy (12Hz, 1200 units), and the warning level (medium). It is transmitted to the cloud analysis platform via the Kafka protocol (throughput 5Mbps, data packet 256 bytes) and stored in the Elasticsearch database. The index timestamp accuracy is 1 millisecond to ensure real-time performance and traceability.

[0035] For those skilled in the art, various other corresponding changes and modifications can be made based on the technical solutions and concepts described above, and all such changes and modifications should fall within the protection scope of the claims of this application.

Claims

1. A method for early warning of cable laying using a side pressure encoder, characterized in that, Includes the following steps: S101. Deploy a multi-axis pressure sensor array at key points of the cable tray corners along the cable laying path to collect real-time three-dimensional dynamic lateral pressure simulation signals applied when the cable passes through. S102. Input the analog signal into the analog-to-digital conversion module, use the dynamic calibration algorithm to perform nonlinear correction, and generate a digital real-time side pressure value sequence with a range of 0-500N that is continuously adjustable. S103. The cable displacement pulse signal is acquired in real time by an incremental encoder. Combined with a temperature-compensated calibration algorithm, the pulse counting is jittered and the cumulative error is compensated, and the laying length measurement value of ±0.1%FS is output. S104. Based on the preset time-varying pressure threshold model, a sliding window is used to monitor the real-time side pressure value sequence: when the pressure value continuously exceeds the upper limit threshold, a closed-loop deceleration control command is generated to drive the servo motor; when the pressure value continues to be lower than the lower limit threshold, a fuzzy acceleration control command is generated to optimize the tension balance. S105. The multi-threaded fusion processing module combines the side pressure value sequence, laying length measurement value and speed control command to construct a dynamic pressure-length-speed three-dimensional relationship matrix. S106. Perform spectral feature analysis on the three-dimensional relationship matrix. When the energy of abnormal frequency components exceeds the preset risk threshold, trigger a spatial positioning graded early warning signal and generate a spectral diagnostic report containing the spatial coordinates of the failure point.

2. The method for early warning of cable laying using a side pressure encoder according to claim 1, characterized in that, Step S101 includes: The original pressure dataset is generated using a multi-axis pressure sensor array. If the signal strength of the original pressure dataset exceeds a preset threshold, then frequency domain decomposition is performed to obtain a frequency domain feature set. Pressure distribution patterns are extracted based on frequency domain feature sets to generate a dimensionality-reduced feature vector set. If the proportion of the principal component variance in the feature vector set is greater than a preset threshold, then smoothing is performed to obtain an optimized pressure distribution model; A dataset of mechanical behavior is generated by calculating dynamic mechanical parameters based on an optimized pressure distribution model. A pressure prediction sequence is obtained by using time series analysis to predict pressure change trends. Anomaly points in pressure distribution are identified based on the pressure prediction sequence, and anomaly detection reports are generated.

3. The method for early warning of cable laying using a side pressure encoder according to claim 1, characterized in that, Step S102 includes: A digital side pressure sequence is obtained by sampling the analog signal through an analog-to-digital conversion module; If the sequence has abnormal fluctuations, smoothing is performed to obtain a smoothed lateral pressure sequence; Periodic feature sequences are obtained by extracting periodic components from smoothed lateral pressure sequences; If the fluctuation range of the periodic characteristic sequence exceeds the preset threshold, the pressure change prediction sequence is obtained by predicting through the autoregressive model. The local pressure change rate sequence was obtained by calculating the local pressure change rate using the sliding window method. If there are abrupt changes in the rate of change sequence, the location of the abrupt changes is identified by an anomaly detection algorithm to obtain the anomaly distribution sequence. The outliers are classified to obtain an outlier classification set.

4. The method for early warning of cable laying using a side pressure encoder according to claim 1, characterized in that, Step S103 includes: A pulse counting sequence is obtained by acquiring cable displacement pulse signals using an incremental encoder; If there are abnormal jumps in the sequence, smoothing is performed to obtain a smooth pulse sequence; A corrected pulse sequence is obtained by combining a smooth pulse sequence with ambient temperature data and using a temperature compensation algorithm to correct the counting deviation. The displacement change rate sequence is obtained by calculating the local displacement change rate of the correction pulse sequence. If there are abrupt changes in the displacement change rate sequence, the location of the abrupt changes is identified by an anomaly detection algorithm to obtain the abrupt change point distribution sequence. The mutation points are classified to obtain an anomaly classification set; The type of the abnormal classification set is determined based on the preset threshold, and the sequence of laying length measurement values ​​is obtained.

5. The method for early warning of cable laying using a side pressure encoder according to claim 1, characterized in that, Step S105 includes: The side pressure sequence, laying length measurement value and speed control command are collected in real time by sensor array, and the raw data set is generated through multi-threaded fusion processing. Parallel processing methods are used to synchronously acquire and denoise the original dataset to obtain a denoised data sequence.

6. The method for early warning of cable laying using a side pressure encoder according to claim 1, characterized in that, Step S106 includes: A time-domain signal sequence is obtained by performing a time-domain transformation on the spectral feature set; Calculate the periodic characteristics of the signal to generate a periodic feature vector; If the amplitude of the periodic eigenvector exceeds the preset fluctuation threshold, spatial clustering is performed on the coordinates of the failure points of the three-dimensional relation matrix to obtain the cluster center set.

Images