A method for automatically detecting a protective layer of a wall thickness of a power pole

Abstract

The application discloses a kind of methods for automatically detecting the wall thickness protection layer of electric pole, which comprises: adjusting ultrasonic velocity and detection parameters in combination with environmental data, dynamically adjusting ultrasonic frequency and duty cycle according to electric pole material quality;Multi-channel ultrasonic probe works synchronously, and real-time acquisition electric pole wall thickness and surface defect data;Through FPGA, analog signal is converted into TTL digital signal, and signal anomaly is detected in real time through dynamic threshold method;Intelligent evaluation is carried out on wall thickness data using deep learning model, and defect type is identified according to ultrasonic echo characteristics;Through display screen, electric pole wall thickness and defect risk assessment results are presented in real time, and alarm signal is triggered when abnormality is found;Record task state, and generate wall thickness trend chart based on historical data;Using detection data, generate the historical trend of electric pole wall thickness change, and evaluate potential risk points in the future through prediction algorithm.The application has the characteristics of high precision, high efficiency and intelligence, and can be widely applied in the field of electric power facility detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric pole detection, and in particular to a method for automatically detecting the wall thickness and protective layer of an electric pole. BACKGROUND

[0002] Electric poles are an important part of power facilities, and the integrity of their protective layers and wall thicknesses directly affects the safety and stability of power transmission. However, due to long-term exposure to complex environments, electric poles may experience wall thickness thinning or protective layer shedding due to corrosion, wear, or mechanical damage, which poses a potential threat to the structural strength and service life of the electric poles. Therefore, regular detection of the wall thickness and protective layer state of electric poles is an important measure to ensure the safe operation of the power system.

[0003] Traditional electric pole detection methods mostly rely on manual inspection or single-point detection equipment, which is not only inefficient and has limited coverage, but also prone to insufficient detection accuracy and consistency due to human factors. At the same time, existing detection equipment lacks technology in signal processing, data transmission, and defect identification, resulting in weak intelligent analysis and real-time monitoring capabilities for the state of electric pole protective layers, which cannot meet the needs of modern power systems for high-precision, full-coverage, and intelligent detection.

[0004] To address the above problems, the present application provides a method for automatically detecting the wall thickness and protective layer of an electric pole, which combines a multi-channel ultrasonic probe, an FPGA signal processing unit, and an automated detection system based on deep learning algorithms to achieve efficient and accurate detection of electric poles in complex environments, significantly improving the efficiency and intelligence level of detection. SUMMARY

[0005] The present application provides a method for automatically detecting the wall thickness and protective layer of an electric pole to address the problem of weak intelligent analysis and real-time monitoring capabilities for the state of electric pole protective layers in existing technology, which cannot meet the needs of modern power systems for high-precision, full-coverage, and intelligent detection.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] The present application provides a method for automatically detecting the wall thickness and protective layer of an electric pole, comprising the following steps:

[0008] Step S1, install the detection device and verify its operating state, adjust the ultrasonic sound speed and detection parameters in combination with environmental data, and dynamically adjust the ultrasonic frequency and duty cycle according to the material quality of the electric pole;

[0009] In step S1, the following sub-steps are also included:

[0010] S1-1, Install the detection device onto the pole, ensuring that the sensor module is in complete contact with the pole surface, and activate the device's self-test function to verify the operating status of the sensor module, drive module, and data processing unit;

[0011] S1-2, based on the temperature and humidity parameters of the detection environment, the ultrasonic velocity is dynamically corrected. The number of channels, detection accuracy, and alarm threshold are set through the main control equipment, and the ultrasonic frequency and duty cycle are adjusted according to the pole material, as shown in equations (1)-(2):

[0012] v c =v0(1+α·ΔT) Equation (1)

[0013]

[0014] Among them, v c Let v0 be the speed of sound of the ultrasonic wave, α be the temperature coefficient, ΔT be the temperature difference, f0 be the frequency of the ultrasonic wave, and t be the frequency of the ultrasonic wave. w The width of the excitation pulse.

[0015] In step S2, the sensor module moves along the pole axis and performs a 360° circumferential scan under the control of the drive module. At the same time, the multi-channel ultrasonic probe works synchronously to collect data on the pole wall thickness and surface defects in real time.

[0016] Step S2 further includes the following sub-steps:

[0017] S2-1 After the drive module is started, it controls the sensor module to move smoothly along the axial direction of the pole through the preset path and motion parameters, while performing a 360° surround scan. During the scan, the motion trajectory of the sensor module maintains a constant distance from the surface of the pole, ensuring that the sensor can collect complete data of the pole surface.

[0018] S2-2, multi-channel ultrasonic probes work synchronously, using a distributed layout to collect real-time data on the wall thickness and surface defects of the pole. The probes emit ultrasonic signals at a high frequency, and when the signal encounters different interfaces of the pole, echoes are generated. The ultrasonic propagation time is calculated based on the collected echo signals, as shown in equation (3):

[0019]

[0020] Where d is the pole wall thickness, t is the propagation time, and v is the propagation time. c The corrected speed of sound;

[0021] S2-3, all signals collected by the sensor module are transmitted to the data processing unit through a high-speed data interface, the sound velocity parameter is dynamically corrected according to the environmental data during data transmission, the interference of the environment on the detection result is reduced, the original data is optimized by signal enhancement and denoising algorithm, and possible noise and interference signals are eliminated.

[0022] S3, the analog signal is converted into a TTL digital signal by the FPGA, the wall thickness and the defect depth are calculated by the time interval, and the signal anomaly is detected in real time by the dynamic threshold method.

[0023] In step S3, the following sub-steps are further included:

[0024] S3-1, in the data processing unit, the collected ultrasonic wave signal is filtered, amplified and feature extracted, the low-pass filter is used to remove high-frequency noise, and the signal amplification circuit is used to enhance the amplitude of the effective signal, the key feature points in the signal time domain are extracted, including the surface wave arrival time and the first bottom wave arrival time, and the time difference between the two is calculated, specifically as formula (4):

[0025] Δt base =t b1 -t s Formula (4)

[0026] Wherein, t s is the surface wave arrival time, and t b1 is the first bottom wave arrival time.

[0027] S3-2, the ultrasonic wave echo signal is digitized and converted by the FPGA processing unit, the analog signal is converted into a TTL digital signal, and the conversion process is specifically as formula (5):

[0028]

[0029] Wherein, V is the analog signal voltage value collected by the sensor, V threshold is the voltage threshold of signal conversion, V TTL is the digital signal after conversion, 1 represents high level, and 0 represents low level.

[0030] S3-3, the digital signal is processed synchronously by the FPGA, the time interval of the surface wave, the bottom wave and the defect wave is calculated, the wall thickness and the defect depth are calculated according to the ultrasonic wave propagation time, specifically as formula (6)-formula (9):

[0031] Δt base =t b1 -t s Formula (6)

[0032] Δt defect =t defect-t s Formula (7)

[0033]

[0034] where Δt base is the time interval between the surface wave and the bottom wave, Δt defect is the ultrasonic wave round trip time, t defect is the defect echo arrival time, Δt base is the bottom wave arrival time difference, H is the wall thickness, v c is the corrected sound speed, A defect is the defect depth;

[0035] S3-4, combined with the data of the multi-channel signal, the detection results of each channel are integrated through a decision level fusion algorithm, and a dynamic threshold method is used for real-time detection of signal abnormalities, specifically as formula (10):

[0036] Δt threshold = mean(Δt) + k·std(Δt) Formula (10)

[0037] Where mean(Δt) is the mean of the time interval, std(Δt) is the standard deviation of the time interval, and k is the adjustment parameter.

[0038] Step S4, using a deep learning model to intelligently evaluate the wall thickness data, identifying the defect type according to the ultrasonic echo characteristics, and evaluating the risk level combined with the defect depth and classification result;

[0039] Wherein in step S4, further comprising the following sub-steps:

[0040] S4-1, using a deep learning algorithm model to input the wall thickness data to determine whether the wall thickness is within a safe range to evaluate the wall thickness distribution, specifically as formula (11):

[0041] P(y|X) = σ(W·X+b) Formula (11)

[0042] Where X is the input data, W and b are model parameters, σ is the activation function, and P(y|X) is the defect probability;

[0043] S4-2, according to the waveform characteristics of the ultrasonic echo signal, identifying the defect type and evaluating the risk level, using support vector machine (SVM) to classify the defect type, specifically as formula (12) - formula (13):

[0044]

[0045] y = argmax(softmax(Z)) Formula (13)

[0046] Where Adefect is the actual depth of the defect, At defect is the echo time interval of the defect, Z is the classification network output, argmax is used to determine the most likely defect type y, y is the classification result;

[0047] S4-3, based on the data collected by the multi-channel, a three-dimensional wall thickness and defect distribution model of the pole is constructed using spatial coordinates, specifically as formula (14) - formula (15):

[0048]

[0049] wherein x, y are two-dimensional position coordinates, H(x, y) is the wall thickness of the corresponding point, and At(x, y) is the time interval of the corresponding position.

[0050] Step S5, the pole wall thickness and defect risk assessment results are presented in real time through the display screen, and an alarm signal is triggered when an abnormality is found;

[0051] wherein in step S5, the following sub-steps are further included:

[0052] S5-1, after detection, the wall thickness detection results and defect risk assessment report of the pole are displayed in real time through the liquid crystal display screen, and the wall thickness value and defect size are calculated, specifically as formula (16):

[0053] V display (t) = H(t) + A defect (t) formula (16)

[0054] wherein V display (t) is the display value, H(t) is the real-time wall thickness value, A defect (t) is the defect size;

[0055] S5-2, when the wall thickness anomaly or high-risk defect is detected, the buzzer and light alarm are automatically triggered, and the alarm condition is specifically as formula (17):

[0056]

[0057] wherein Alarm is the set minimum wall thickness threshold, A max is the maximum allowable defect depth;

[0058] S5-3, the detection data is transmitted in real time to the remote monitoring center through the wireless communication module for analysis and archiving by the maintenance personnel, and the transmitted data includes: wall thickness value, defect depth and time information.

[0059] Step S6, after the detection task is completed, the task state is recorded and the data is stored to the local and cloud databases, and a wall thickness change trend chart is generated based on the historical data;

[0060] Wherein in step S6, further comprising the following sub-steps:

[0061] S6-1, after detecting the task, the host system stops the movement of the sensor module and the operation of the driving module through the termination instruction, and ensures that the equipment is in a safe shutdown state;

[0062] The stop operation includes: recording the final detected state parameters; stopping all data acquisition and processing work, and simultaneously disconnecting the communication connection with the remote monitoring center; and returning the equipment to the initial standby position for the next task;

[0063] S6-2, store the detection data to the local storage unit of the equipment, and simultaneously upload the data to the cloud database through the wireless communication module, generate the wall thickness change trend of the electric pole based on the stored data, specifically as formula (18):

[0064]

[0065] Wherein, H trend (t) is the wall thickness change trend, H baseline is the reference wall thickness, ΔH i is the thickness change of each detection;

[0066] S6-3, after the detection is finished, check the surface cleanliness of the sensor module, remove the possible attached dust and foreign matters; lubricate and test the performance of the slide rail and motor of the driving module; according to the running time and maintenance record of the equipment, judge whether the key components need to be replaced or repaired.

[0067] Step S7, generate the historical trend of the wall thickness change of the electric pole by using the detection data, evaluate the potential risk points in the future by using the prediction algorithm, and propose the targeted maintenance suggestions.

[0068] Wherein in step S7, further comprising the following sub-steps:

[0069] S7-1, based on the multiple wall thickness data stored in the detection task, generate the historical change trend graph of the wall thickness of the electric pole, intuitively show the wall thickness change of the electric pole in the long-term operation through the historical trend graph, and the trend calculation is specifically as formula (19):

[0070]

[0071] Wherein, H baseline is the initial wall thickness at the beginning of detection, ΔH i is the wall thickness change amount of the i-th detection, and n is the detection number;

[0072] S7-2, combine the trend analysis and the current detection data, evaluate the potential risk points of the electric pole by using the prediction algorithm, the prediction model is based on the time series algorithm, calculate the future wall thickness change, specifically as formula (20):

[0073] H future (t+Δt)=H(t)-R decay ·Δt Equation (20)

[0074] Among them, H future (t+Δt) represents the projected wall thickness at a future time point, R decay The wall thickness reduction rate is given by Δt, which is the predicted time interval. This occurs when the predicted wall thickness falls below a set safety threshold H. threshold Maintenance recommendations will be generated, including specific plans for reinforcing or replacing poles, and areas of poles with high priority will be marked.

[0075] S7-3 involves in-depth analysis of all historical testing data to identify variations in wall thickness under different materials, pole types, and environmental conditions. Through multi-dimensional data correlation, it generates material performance optimization suggestions or testing method improvement plans, as detailed below:

[0076] Material optimization: Based on the corrosion rate in different environments, it is recommended to use more durable protective layer materials; Detection method improvement: Add filtering algorithms in high-noise environments and increase the detection frequency in severely worn areas.

[0077] Compared with the prior art, the beneficial effects of the present invention are:

[0078] This invention introduces a deep learning algorithm to intelligently analyze the detection data, which can determine in real time whether the pole wall thickness is within the safe range, and accurately identify the defect type through a classification algorithm, effectively improving the accuracy and reliability of defect identification.

[0079] This invention reduces the impact of environmental factors on detection results by dynamically adjusting the ultrasonic velocity and signal processing parameters, thereby ensuring detection accuracy even in complex environments.

[0080] This invention generates a three-dimensional wall thickness and defect distribution model, which helps users quickly understand the health status of the pole through intuitive graphical display. At the same time, the detection data is transmitted to the cloud for storage in real time, realizing remote monitoring and historical data management, and providing a scientific basis for subsequent maintenance.

[0081] This invention combines historical data and trend analysis, uses time series prediction algorithms to assess potential risks to utility poles, generates maintenance plans, and proposes suggestions for material optimization and improved testing methods, significantly improving the scientific rigor and foresight of utility pole maintenance work. Attached Figure Description

[0082] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments, and understand that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor based on these drawings.

[0083] Figure 1 is a method flowchart of the present application. DETAILED DESCRIPTION

[0084] In order to make the objects, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only for selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0085] Please refer to Figure 1 is a method flowchart of the present application provided by an embodiment of automatically detecting the wall thickness protection layer of the electric pole, including the following steps:

[0086] Step S1, install the detection device and check its running state, adjust the ultrasonic sound velocity and detection parameters combined with environmental data, dynamically adjust the ultrasonic frequency and duty cycle according to the electric pole material;

[0087] In step S1, the following sub-steps are further included:

[0088] S1-1, install the detection device on the electric pole, make the sensor module fully contact with the surface of the electric pole, start the self-checking function of the equipment, check the running state of the sensor module, the driving module and the data processing unit;

[0089] S1-2, dynamically correct the ultrasonic sound velocity according to the temperature and humidity parameters of the detection environment, set the channel number, detection accuracy and alarm threshold through the main control equipment, and adjust the ultrasonic frequency and duty cycle according to the electric pole material, specifically as formula (1)-(2):

[0090] v c = v0(1+α·ΔT) formula (1)

[0091]

[0092] wherein v c is the ultrasonic wave speed, v0 is the reference speed, a is the temperature coefficient, AT is the temperature difference, f0 is the ultrasonic wave frequency, t w is the excitation pulse width.

[0093] It should be noted that the running state includes: the sensor module confirms whether its signal acquisition capability and contact state are normal, the driving module verifies its working capability of moving along the axial direction of the pole and rotating 360° around, and the data processing unit checks whether its signal processing, storage and transmission functions are normal.

[0094] The number of channels determines the number of ultrasonic probes participating in detection at the same time, directly affecting the detection coverage and efficiency. According to the diameter and length of the pole, a proper number of probes are selected, and the main control device provides options to allow users to switch between single-channel mode and multi-channel mode according to needs.

[0095] The setting of detection accuracy determines the signal sampling rate and the resolution of data processing, affecting the level of detail and reliability of the detection results. According to the pole material and detection target, adjust: for thicker protective layer, select lower accuracy to speed up detection; for thin layer or vulnerable area, increase sampling rate to improve accuracy.

[0096] The alarm threshold is used to determine whether the wall thickness or defect depth reaches a dangerous level, triggering the corresponding alarm mechanism. The settings are as follows: the wall thickness threshold is set according to the pole design specification, setting the minimum safe wall thickness value; the defect depth threshold is set according to the pole bearing capacity, setting the maximum allowable defect depth.

[0097] Step S2, the sensor module moves along the axial direction of the pole under the control of the driving module and performs 360° around scanning, while the multi-channel ultrasonic probes work synchronously, real-time collecting the pole wall thickness and surface defect data;

[0098] In step S2, the following sub-steps are further included:

[0099] S2-1, after the driving module is started, the sensor module is controlled to move smoothly along the axial direction of the pole through the preset path and motion parameters, and 360° around scanning is performed. During the scanning process, the motion trajectory of the sensor module maintains a constant distance from the surface of the pole, ensuring that the sensor can collect complete pole surface data;

[0100] S2-2, the multi-channel ultrasonic probes work synchronously, and real-time collect the pole wall thickness and surface defect data using distributed layout. The probes emit ultrasonic wave signals at a high frequency, and when the signals encounter different interfaces of the pole, they produce echoes. The ultrasonic wave propagation time is calculated according to the collected echo signals, specifically as formula (3):

[0101]

[0102] wherein d is the pole wall thickness, t is the propagation time, v c is the corrected sound velocity;

[0103] S2-3, all signals collected by the sensor module are transmitted to the data processing unit through a high-speed data interface, the sound velocity parameter is dynamically corrected according to the environmental data during data transmission, the interference of the environment on the detection result is reduced, the original data is optimized by signal enhancement and denoising algorithm, and possible noise and interference signals are eliminated.

[0104] It should be noted that the multi-channel probe refers to arranging multiple ultrasonic probes on the device, each probe being responsible for a different detection area, the probes being arranged in an equidistant manner around the pole, covering the circumferential and axial areas of the pole, and the positions and spacings of the probes being dynamically adjusted according to the diameter and material properties of the pole.

[0105] The probes of each channel are periodically and synchronously triggered by the control system to emit ultrasonic signals, the excitation signals of multiple probes are generated by a PWM signal generator to avoid interference between signals of each channel, the echo signals received by each probe are independently collected, and filtering and feature extraction are performed by the data processing unit, multi-channel data are simultaneously transmitted to the FPGA for real-time processing, and the time difference error between the probes is minimized.

[0106] The driving module shell is made of IP68 grade protection, and is internally provided with a position sensor for real-time monitoring of its position on the pole to ensure the accuracy of the detection path; high-precision guide rails and ball slides are provided to ensure the stability of the driving module when moving on the surface of the pole; and the moving speed can be automatically adjusted according to the complexity of the detection area to improve the efficiency.

[0107] Step S3, converting the analog signal into a TTL digital signal by the FPGA, calculating the wall thickness and defect depth by time interval, and detecting signal abnormalities in real time by a dynamic threshold method;

[0108] In step S3, the following sub-steps are further included:

[0109] S3-1, in the data processing unit, filtering, amplification and feature extraction are performed on the collected ultrasonic signals, a low-pass filter is used to remove high-frequency noise, and a signal amplification circuit is used to enhance the amplitude of the effective signal, key feature points are extracted in the signal time domain, including the surface wave arrival time and the first bottom wave arrival time, the time difference between the two is calculated, and the specific formula (4) is as follows:

[0110] Δt base = t b1 -t s Formula (4)

[0111] wherein t s is the surface wave arrival time, t b1 is the primary bottom wave arrival time;

[0112] S3-2, the FPGA processing unit is used to digitize the ultrasonic echo signal, and the analog signal is converted into a TTL digital signal. The conversion process is specifically as formula (5):

[0113]

[0114] wherein V is the analog signal voltage value collected by the sensor, V threshold is the signal conversion voltage threshold, V TTL is the converted digital signal, 1 represents high level, and 0 represents low level;

[0115] S3-3, the FPGA is used to synchronously process the digital signal, calculate the time interval of the surface wave and the bottom wave and the defect wave, and calculate the wall thickness and the defect depth according to the ultrasonic wave propagation time, which is specifically as formula (6)-(9):

[0116] Δt base = t b1 -t s Formula (6)

[0117] Δt defect = t defect -t s Formula (7)

[0118]

[0119] wherein Δt base is the time interval between the surface wave and the bottom wave, Δt defect is the ultrasonic wave round trip time, t defect is the defect echo arrival time, Δt base is the bottom wave arrival time difference, H is the wall thickness, v c is the corrected sound speed, A defect is the defect depth;

[0120] S3-4, the detection results of each channel are integrated through a decision-level fusion algorithm combined with the data of the multi-channel signal, and the dynamic threshold method is used for real-time detection for signal abnormalities, which is specifically as formula (10):

[0121] Δt threshold = mean(Δt) + k·std(Δt) Formula (10)

[0122] wherein mean(At) is the mean of the time interval, std(At) is the standard deviation of the time interval, and k is an adjustment parameter.

[0123] It should be noted that the FPGA is a data processing unit, mainly used for receiving and processing the echo signals transmitted by the ultrasonic probe, realizing high-speed and high-precision real-time signal processing, and its functions include: analog signal conversion to digital signal, filtering, feature extraction and time difference calculation, multi-channel signal synchronous processing and fusion, and logic control of data storage and transmission.

[0124] The FPGA simultaneously collects and processes signals of multiple channels, ensures that the time synchronization error between channels is less than 1 microsecond, integrates multi-channel results using a data fusion algorithm to improve detection accuracy, and directly stores the processed data in the cache of the device, and transmits it to the host device or the cloud through a gigabit Ethernet interface or a wireless module.

[0125] The data processing unit is usually integrated in the host device as the core part of the entire detection system, responsible for receiving signals from the sensor module and the multi-channel probe, performing preliminary data processing, connecting high-speed data interfaces and sensor modules, communicating with the drive module, and coordinating the detection tasks and position states of the sensor.

[0126] The data processing unit receives the original analog signals transmitted from the sensor module, performs preliminary calibration on the signals according to environmental parameters, removes high-frequency noise through a low-pass filter, and enhances the signal amplitude using an amplification circuit to ensure that key signal points stand out.

[0127] The preprocessed signals are transmitted to the FPGA processing unit through a high-speed data interface for further processing. The FPGA processing unit is usually integrated on the hardware mainboard close to the data processing unit to ensure efficient data transmission and real-time processing capability. It is connected to the data processing unit through a high-speed interface and directly interacts with the display module, alarm system, and storage module.

[0128] Step S4, using a deep learning model to intelligently evaluate the wall thickness data, identifying the defect type according to the ultrasonic echo characteristics, and evaluating the risk level in combination with the defect depth and classification result;

[0129] In step S4, the following sub-steps are further included:

[0130] S4-1, using a deep learning algorithm model to input the wall thickness data to determine whether the wall thickness is within a safe range and evaluate the wall thickness distribution, specifically as formula (11):

[0131] P(y|X) = σ(W·X + b) formula (11)

[0132] Wherein, X is input data, W and b are model parameters, sigma is an activation function, and P(y|X) is a defect probability.

[0133] S4-2, according to the waveform characteristics of the ultrasonic echo signal, the defect type is identified and the risk level is evaluated, and a support vector machine (SVM) is used to classify the defect type, specifically as formula (12) to formula (13):

[0134]

[0135] y = argmax (softmax (Z)) Formula (13)

[0136] Wherein, A defect is the actual depth of the defect, Delta t defect is the echo time interval of the defect, Z is the output of the classification network, argmax is used to determine the most likely defect type y, and y is the classification result.

[0137] S4-3, based on the data collected by the multi-channel, a three-dimensional wall thickness and defect distribution model of the pole is constructed using spatial coordinates, specifically as formula (14) to formula (15):

[0138]

[0139] Wherein, x, y are two-dimensional position coordinates, H(x, y) is the wall thickness of the corresponding point, and Delta t(x, y) is the time interval of the corresponding position.

[0140] It should be noted that the defect type recognition is achieved by analyzing the waveform characteristics of the ultrasonic echo, including amplitude, frequency, duration and energy, extracting feature values for defect classification, and the support vector machine model classifies the defects based on a high-dimensional feature space. The defect types are as follows:

[0141] Surface defects are usually manifested as high-frequency short-time signals, such as cracks and peeling; internal defects are manifested as low-frequency long-time signals, such as bubbles and cavities; boundary abnormalities are manifested as signal amplitude mutation, such as delamination and edge damage.

[0142] Using a three-dimensional graphics processing tool, the data is converted into an interactive distribution model, and the defect distribution is color-coded and superimposed on the three-dimensional wall thickness model:

[0143] Normal areas are green, medium defect areas are yellow, and severe defect areas are red.

[0144] Step S5, the pole wall thickness and defect risk assessment results are presented in real time through the display screen, and an alarm signal is triggered when an abnormality is found;

[0145] Wherein, in step S5, the following sub-steps are further included:

[0146] S5-1, after detection, the wall thickness detection results and defect risk assessment report of the electric pole are displayed in real time through the liquid crystal display screen, the wall thickness value and defect size are calculated, and the specific formula (16) is as follows:

[0147] V display (t) = H(t) + A defect (t) formula (16)

[0148] Wherein, V display (t) is the display value, H(t) is the real-time wall thickness value, A defect (t) is the defect size;

[0149] S5-2, when the wall thickness anomaly or high risk defect is detected, the buzzer and light alarm are automatically triggered, and the alarm condition is specifically as formula (17):

[0150]

[0151] Wherein, Alarm is the set minimum wall thickness threshold, A max is the maximum allowable defect depth;

[0152] S5-3, the detection data is transmitted to the remote monitoring center in real time through the wireless communication module, which is analyzed and archived by the maintenance personnel, and the transmitted data includes: wall thickness value, defect depth and time information.

[0153] It should be noted that the buzzer alarm emits high frequency sound to remind the operator to pay attention to the detection results immediately, and the alarm mode includes: continuous sound indicates that multiple high risk areas exist, intermittent sound indicates single high risk area or medium risk, and the alarm volume can be adjusted according to the environmental noise of the detection site.

[0154] The light alarm provides intuitive alarm information through color change and flashing mode, and the color coding includes: green normal state without exception; yellow medium risk needs attention; red high risk needs to be handled immediately; the flashing mode, i.e. the flashing frequency increases with the risk level, and the red light frequency is the highest.

[0155] The display screen is linked, and when the alarm is triggered, the display screen automatically locates the abnormal point, highlights the specific value of the wall thickness or defect depth, and generates real-time alarm log.

[0156] Graded alarm, providing graded alarm according to risk level:

[0157] First level alarm (low risk): only display screen marking, no sound and light alarm;

[0158] Second level alarm (medium risk): yellow light flashing, display screen highlighting;

[0159] Third level alarm (high risk): red light flashing + buzzer alarm.

[0160] Step S6, record the task state after the detection task is completed and store the data to the local and cloud databases, and generate a wall thickness change trend graph based on historical data;

[0161] In step S6, the following sub-steps are further included:

[0162] S6-1, after the detection task is completed, the main control system stops the movement of the sensor module and the operation of the driving module through a termination instruction, to ensure that the equipment is in a safe shutdown state;

[0163] The stop operation includes: recording the final detected state parameters; stopping all data acquisition and processing work, and simultaneously disconnecting the communication connection with the remote monitoring center; and returning the equipment to the initial standby position for the next task;

[0164] S6-2, store the detection data to the local storage unit of the equipment, and simultaneously upload the data to the cloud database through the wireless communication module, generate a pole wall thickness change trend based on the stored data, specifically as formula (18):

[0165]

[0166] Wherein, H trend (t) is the wall thickness change trend, H baseline is the reference wall thickness, and ΔH i is the thickness change of each detection;

[0167] S6-3, after the detection is completed, check the surface cleanliness of the sensor module, remove possible dust and foreign matter; lubricate and test the performance of the sliding rail and motor of the driving module; according to the running time and maintenance record of the equipment, determine whether the key components need to be replaced or repaired.

[0168] It should be noted that the pole wall thickness change trend analysis reveals the change law of the wall thickness with time by comparing multiple detection data, and is used for: corrosion or wear monitoring: identifying the long-term degradation of the pole protection layer and material; risk warning: predicting possible future wall thickness deficiency or defect expansion problems; maintenance optimization: providing basis for developing a scientific maintenance plan and material improvement.

[0169] Data visualization includes trend graph generation and heat map and three-dimensional model, trend graph generation uses line chart or column chart to intuitively display the wall thickness change, x-axis represents time (detection period), y-axis represents wall thickness or change rate, and key points are labeled as time nodes when the threshold is first reached.

[0170] The thermal map and the three-dimensional model are combined to intuitively display the area and severity of the change in the wall thickness of the electric pole surface, and the time dimension is added to the three-dimensional wall thickness model to dynamically display the wall thickness degradation.

[0171] The local storage unit is integrated in the main control device inside the hardware platform of the main control device, is directly connected with the data processing unit and the FPGA processing unit, is connected with the data processing unit and the FPGA unit through a high-speed bus SPI interface, ensures fast writing and reading of data, is equipped with a non-volatile memory (such as NAND flash or EEPROM), ensures that data will not be lost in the case of power failure, backs up key data through a RAID configuration or a dual-partition structure, further improves storage security, supports regular cleaning of expired data to release storage space, or allows manual export or deletion of historical data through a user interface.

[0172] Step S7, using the detection data to generate a historical trend of the wall thickness change of the electric pole, evaluating potential risk points in the future through a prediction algorithm, and proposing targeted maintenance suggestions.

[0173] In step S7, the following sub-steps are further included:

[0174] S7-1, based on the multiple wall thickness data stored in the detection task, a historical change trend graph of the wall thickness of the electric pole is generated, and the wall thickness change of the electric pole in long-term operation is intuitively displayed through the historical trend graph, and the trend calculation is specifically as formula (19):

[0175]

[0176] H baseline is the initial wall thickness at the start of detection, H i is the wall thickness change amount of the i-th detection, and n is the number of detections;

[0177] S7-2, combining trend analysis and current detection data, using a prediction algorithm to evaluate potential risk points of the electric pole, the prediction model is based on a time series algorithm, and the future wall thickness change is calculated, specifically as formula (20):

[0178] H future (t+Δt)=H(t)-R decay ·Δt formula (20)

[0179] H future (t+Δt) is the predicted wall thickness at the future time point, R decay is the wall thickness reduction rate, and Δt is the prediction time interval, when the predicted wall thickness is lower than the set safety threshold H threshold , a maintenance suggestion is generated, including a specific scheme of reinforcing or replacing the electric pole, and marking the electric pole area with high priority processing;

[0180] S7-3, deep mining of all historical detection data, analyzing the wall thickness change law under different materials, pole types and environmental conditions, generating material performance optimization suggestions or detection method improvement schemes through multi-dimensional data association, as follows:

[0181] Material optimization, according to the corrosion rate in different environments, it is suggested to use more durable protective layer materials; detection method improvement, increase filtering algorithm in high noise environment, enhance detection frequency in severe wear area.

[0182] It should be noted that the multi-dimensional data sources include:

[0183] Wall thickness change data, wall thickness trend and change rate in different time periods;

[0184] Defect feature data, defect type, depth, distribution and expansion law;

[0185] Environmental condition data, temperature, humidity, corrosive gas concentration and other environmental factors;

[0186] Material attribute data, composition, density and durability characteristics of pole protective layer materials.

[0187] Material performance optimization suggestions, the optimization direction is to improve the corrosion resistance, for high corrosion environment, it is suggested to select more corrosion-resistant protective layer materials, such as using acid and alkali-resistant composite materials; increase mechanical strength, for crack-prone areas, it is suggested to use high-strength fiber reinforced materials to improve crack resistance; reduce the influence of thermal expansion and contraction, in areas with large temperature difference, it is recommended to use materials with higher thermal stability.

[0188] It should be noted that the sensor module is fixed on the surface of the pole by the mounting device, for poles of different diameters, telescopic fixing supports are used, equipped with elastic clamps to ensure that the sensor module is tightly attached to the surface of the pole; a universal adjusting base is added at the connection between the support and the sensor module, allowing the sensor to be adjusted in angle after installation; avoid signal interference or data distortion caused by improper installation, ensure the flatness of the contact surface of the sensor module during installation, use adjustable clamps or soft gaskets to adapt to the curvature of the pole surface, prevent loose installation.

[0189] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application has various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for automatically detecting the protective layer thickness of utility pole walls, characterized in that, Includes the following steps: Step S1: Install the detection device and verify its operating status. Adjust the ultrasonic velocity and detection parameters based on environmental data. Dynamically adjust the ultrasonic frequency and duty cycle according to the pole material. In step S2, the sensor module moves along the pole axis and performs a 360° circumferential scan under the control of the drive module. At the same time, the multi-channel ultrasonic probe works synchronously to collect data on the pole wall thickness and surface defects in real time. Step S3: The analog signal is converted into a TTL digital signal by the FPGA, the wall thickness and defect depth are calculated by time interval, and the signal anomaly is detected in real time by the dynamic threshold method. Step S4: Use a deep learning model to intelligently evaluate the wall thickness data, identify the defect type based on the ultrasonic echo characteristics, and assess the risk level by combining the defect depth and classification results. Step S5: Display the pole wall thickness and defect risk assessment results on the screen in real time, and trigger an alarm signal when an abnormality is detected; Step S6: After the detection task is completed, record the task status and store the data in the local and cloud databases, and generate a wall thickness change trend chart based on historical data; Step S7: Use the detection data to generate historical trends of pole wall thickness changes, use prediction algorithms to assess potential future risks, and propose targeted maintenance recommendations. Step S1 further includes the following sub-steps: S1-1, Install the detection device onto the pole, ensuring that the sensor module is in complete contact with the pole surface, and activate the device's self-test function to verify the operating status of the sensor module, drive module, and data processing unit; S1-2, based on the temperature and humidity parameters of the detection environment, dynamically correct the ultrasonic velocity, set the number of channels, detection accuracy and alarm threshold through the main control equipment, and adjust the ultrasonic frequency and duty cycle according to the pole material, as shown in equations (1)-(2): Equation (1) Equation (2) in, The speed of sound in ultrasound. For reference speed of sound, For temperature coefficient, For temperature difference, This refers to the ultrasonic frequency. To determine the excitation pulse width; Step S2 further includes the following sub-steps: S2-1 After the drive module is started, it controls the sensor module to move smoothly along the axial direction of the pole through the preset path and motion parameters, while performing a 360° surround scan. During the scan, the motion trajectory of the sensor module maintains a constant distance from the surface of the pole, ensuring that the sensor can collect complete data of the pole surface. S2-2, multi-channel ultrasonic probes work synchronously, and a distributed layout is used to collect data on the wall thickness and surface defects of the pole in real time. The probes emit ultrasonic signals at a high frequency. When the signal encounters different interfaces of the pole, echoes are generated. The ultrasonic propagation time is calculated based on the collected echo signals, as shown in equation (3): Equation (3) in, For pole wall thickness, For the time of dissemination, The corrected speed of sound; S2-3, All signals collected by the sensor module are transmitted to the data processing unit through a high-speed data interface. During the data transmission process, the sound velocity parameter is dynamically corrected according to the environmental data to reduce the interference of the environment on the detection results. The original data is optimized through signal enhancement and denoising algorithms to eliminate possible noise and interference signals. Step S3 further includes the following sub-steps: S3-1, in the data processing unit, the acquired ultrasonic signal is filtered, amplified and feature extracted. A low-pass filter is used to remove high-frequency noise and the amplitude of the effective signal is enhanced by a signal amplification circuit. Key feature points are extracted in the signal time domain, including the arrival time of the surface wave and the arrival time of the first bottom wave. The time difference between the two is calculated, as shown in equation (4). Equation (4) in, For the arrival time of the surface wave, This is the arrival time of one bottom wave; S3-2, the FPGA processing unit is used to digitally convert the ultrasonic echo signal into a TTL digital signal. The conversion process is as follows (5): Equation (5) in, It is the analog signal voltage value collected by the sensor. It is the voltage threshold for signal conversion. It is the converted digital signal, where 1 represents a high level and 0 represents a low level; S3-3, using FPGA to synchronously process digital signals, calculate the time interval between surface wave, bottom wave and defect wave, and calculate the wall thickness and defect depth based on the ultrasonic wave propagation time, as shown in equations (6)-(9): Equation (6) Equation (7) Equation (8) Equation (9) in, The time interval between surface waves and bottom waves. This represents the round-trip time of the ultrasound. For the arrival time of the defect echo, The time difference of arrival of the bottom wave. For wall thickness, This is the corrected speed of sound. For the depth of the defect; S3-4, combining the data of multi-channel signals, the detection results of each channel are integrated through a decision-level fusion algorithm. For signal anomalies, a dynamic threshold method is used for real-time detection, as shown in equation (10): Equation (10) in, The mean of the time intervals. The standard deviation of the time interval. To adjust the parameters; Step S4 further includes the following sub-steps: S4-1, using a deep learning algorithm model with wall thickness data as input, determines whether the wall thickness is within a safe range and evaluates the wall thickness distribution, as shown in equation (11): Equation (11) in, For input data, and For model parameters, For activation function, This represents the defect probability. S4-2, Based on the waveform characteristics of the ultrasonic echo signal, identify the defect type and assess the risk level. Use support vector machine to classify the defect type, as shown in equations (12)-(13): Equation (12) Equation (13) in, The actual depth of the defect. For the defect echo time interval, For the output of the classification network, To determine the most likely type of defect , The classification results; S4-3, Based on the data acquired from multiple channels, a three-dimensional model of the pole's wall thickness and defect distribution is constructed using spatial coordinates, as shown in equations (14)-(15): Equation (14) Equation (15) in, Two-dimensional position coordinates, The wall thickness at the corresponding point. This represents the time interval for the corresponding position.

2. The method for automatically detecting the protective layer thickness of utility poles according to claim 1, characterized in that: Step S5 further includes the following sub-steps: S5-1, After the inspection is completed, the wall thickness test results and defect risk assessment report of the pole are displayed in real time on the LCD screen, and the wall thickness value and defect size are calculated, as shown in formula (16): Equation (16) in, To display the value, This is the real-time wall thickness value. Defect size; S5-2, When an abnormal wall thickness or a high-risk defect is detected, the buzzer and light alarm are automatically triggered. The alarm conditions are as shown in equation (17): Alarm Equation (17) Where Alarm is the set minimum wall thickness threshold. The maximum allowable defect depth; The S5-3 transmits detection data to a remote monitoring center in real time via a wireless communication module for maintenance personnel to analyze and archive. The transmitted data includes wall thickness, defect depth, and time information.

3. The method for automatically detecting the protective layer thickness of utility poles according to claim 1, characterized in that: Step S6 further includes the following sub-steps: S6-1, After the detection task is completed, the main control system stops the movement of the sensor module and the operation of the drive module by the termination command to ensure that the equipment is in a safe shutdown state; The shutdown procedure includes: recording the final test status parameters; stopping all data acquisition and processing, and disconnecting the communication connection with the remote monitoring center; and restoring the device to its initial standby position in preparation for the next task. S6-2, the detected data is stored in the local storage unit of the device, and at the same time, the data is uploaded to the cloud database through the wireless communication module. Based on the stored data, the trend of pole wall thickness change is generated, as shown in equation (18): ； in, This shows the trend of wall thickness variation. Based on the reference wall thickness, This represents the thickness change in each test. S6-3 After the test is completed, check the surface cleanliness of the sensor module and remove any dust and foreign objects that may be attached; lubricate and test the performance of the slide rail and motor of the drive module; and determine whether key components need to be replaced or repaired based on the equipment's operating time and maintenance records.

4. The method for automatically detecting the protective layer thickness of utility poles according to claim 1, characterized in that: Step S7 further includes the following sub-steps: S7-1, Based on the multiple wall thickness data stored in the detection task, a historical trend chart of the pole wall thickness is generated. The historical trend chart visually displays the wall thickness change of the pole during long-term operation. The trend calculation is as shown in equation (19): Equation (19) in, To detect the initial wall thickness at the start. For the first The change in wall thickness detected in each test. Number of tests; S7-2, combining trend analysis and current inspection data, uses a prediction algorithm to assess potential risk points of the pole. The prediction model is based on a time series algorithm to calculate future wall thickness changes, as shown in equation (20): Equation (20) in, The projected wall thickness at a future point in time. For the rate of wall thickness reduction, The time interval for prediction is when the predicted wall thickness is below a set safety threshold. Maintenance recommendations will be generated, including specific plans for reinforcing or replacing poles, and areas of poles with high priority will be marked. S7-3 involves in-depth analysis of all historical testing data to identify wall thickness variation patterns under different materials, pole types, and environmental conditions. Through multi-dimensional data correlation, it generates material performance optimization suggestions or testing method improvement plans, as detailed below: Material optimization: Based on the corrosion rate in different environments, it is recommended to use more durable protective layer materials; Detection method improvement: Add filtering algorithms in high-noise environments and increase the detection frequency in severely worn areas.

Images