CN119293512A - Real-time evaluation method of UV in-situ curing repair effect of drainage pipes based on machine learning - Google Patents

Real-time evaluation method of UV in-situ curing repair effect of drainage pipes based on machine learning Download PDF

Info

Publication number
CN119293512A
CN119293512A CN202411820618.2A CN202411820618A CN119293512A CN 119293512 A CN119293512 A CN 119293512A CN 202411820618 A CN202411820618 A CN 202411820618A CN 119293512 A CN119293512 A CN 119293512A
Authority
CN
China
Prior art keywords
time
repair
real
formula
crack
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202411820618.2A
Other languages
Chinese (zh)
Other versions
CN119293512B (en
Inventor
范云虎
郑雷
唐文韬
杨袁昊
徐正亚
杨泽均
颜诗其
薛贺
关集俱
高超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Institute Of Technology
Original Assignee
Changshu Institute of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Changshu Institute of Technology filed Critical Changshu Institute of Technology
Priority to CN202411820618.2A priority Critical patent/CN119293512B/en
Publication of CN119293512A publication Critical patent/CN119293512A/en
Application granted granted Critical
Publication of CN119293512B publication Critical patent/CN119293512B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N3/40—Investigating hardness or rebound hardness
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Geometry (AREA)
  • Multimedia (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)

Abstract

本发明公开了一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，本发明涉及修复效果评估技术领域。包括：采集历史参数，包括表面温度、表面湿度、固化时间和紫外光照射强度，以及对应的固化材料硬度值，作为预测模型的输入进行训练，建立固化硬度预测模型。获取修复过程中的紫外光照射强度，结合环境湿度进行修正。采集实时过程参数，输入模型，输出实时的固化材料硬度值。根据光照均匀性对硬度值进行修正后，结合表面平整度、裂缝形状指数及声波信号的参数生成修复效果评估指数。通过与评估阈值对比，输出不同的修复效果评估结果。该方法实现了对排水管道固化修复效果的智能化实时监控与评估，提升了修复质量与效率。

The present invention discloses a real-time evaluation method for the repair effect of ultraviolet light in-situ curing of drainage pipes based on machine learning, and the present invention relates to the technical field of repair effect evaluation. It comprises: collecting historical parameters, including surface temperature, surface humidity, curing time and ultraviolet light irradiation intensity, and the corresponding hardness value of the curing material, as inputs of the prediction model for training, and establishing a curing hardness prediction model. The ultraviolet light irradiation intensity during the repair process is obtained and corrected in combination with the ambient humidity. Real-time process parameters are collected, input into the model, and the real-time hardness value of the curing material is output. After the hardness value is corrected according to the uniformity of the light, a repair effect evaluation index is generated in combination with the parameters of the surface flatness, crack shape index and acoustic wave signal. By comparing with the evaluation threshold, different repair effect evaluation results are output. The method realizes intelligent real-time monitoring and evaluation of the curing repair effect of the drainage pipe, and improves the repair quality and efficiency.

Description

Machine learning-based real-time evaluation method for ultraviolet light in-situ curing repair effect of drainage pipeline
Technical Field
The invention relates to the technical field of repair effect evaluation, in particular to a real-time evaluation method for ultraviolet light in-situ curing repair effect of a drainage pipeline based on machine learning.
Background
In urban infrastructure, maintenance and repair of drainage pipelines is critical. With the acceleration of the urban process, the pressure of the drainage pipeline is continuously increased, and the pipeline is frequently damaged due to ageing and corrosion of the pipeline and the influence of external environment. Conventional pipeline repair methods, such as excavation and replacement, are generally time consuming, costly, and have a significant impact on the surrounding environment. Therefore, it is particularly important to develop a pipeline repair technology that is efficient, economical and has little impact on the environment. In recent years, in-situ repair methods based on ultraviolet curing technology have been attracting attention. The method can restore the function of the pipeline rapidly under the condition of not damaging the surrounding environment by repairing the ultraviolet light curing material in the pipeline.
However, although the ultraviolet curing technology has many advantages, there are still some technical problems in practical application. First, environmental factors (e.g., temperature, humidity, etc.) and repair parameters (e.g., cure time, uv intensity, etc.) during the curing process have a significant impact on the final hardness of the cured material. Accurate control and assessment of these parameters is critical to ensuring repair effectiveness. Secondly, conventional methods of hardness evaluation of cured materials often rely on manual sampling and laboratory testing, resulting in delayed and inaccurate evaluation results, which are difficult to reflect changes in the repair process in real time. Therefore, an effective method for monitoring parameters of the repair process in real time and evaluating the curing effect in time is lacking.
In order to solve the above technical problems, a real-time evaluation method based on machine learning has been developed. The process parameters in the history repairing process, including surface temperature, humidity, curing time and ultraviolet irradiation intensity, are collected, and the hardness value of the cured material is combined, so that a rich data base can be provided for the machine learning model. A long-short-term memory network (LSTM) is used as a deep learning model suitable for processing time sequence data, can effectively capture nonlinear relations in historical data, and provides support for predicting hardness of a cured material. In addition, through factors such as real-time supervision ultraviolet irradiation intensity, environmental humidity, can improve the accuracy of solidification process, further promote the evaluation precision of restoration effect.
In the prior art, the publication number CN116386789A discloses a method for real-time monitoring of ultraviolet light in-situ curing repair quality of a buried pipeline, which comprises the specific steps of firstly collecting in-situ curing data of a UV-CIPP material, constructing a data set, then establishing a genetic algorithm optimization support vector machine model for predicting the mechanical property of the UV-CIPP material under the influence of multiple factors, namely a GA-SVM model, training and verifying the GA-SVM model through the data set to obtain an optimal GA-SVM model, secondly predicting optimal curing parameters and curing temperature according to the mechanical parameters of the UV-CIPP material required by construction design and the optimal GA-SVM model, finally inputting the predicted optimal curing parameters and curing temperature into an in-situ curing repair trolley comprehensive control system of the buried pipeline, starting pipeline repair construction, and monitoring the ultraviolet light in-situ curing repair quality of the buried pipeline in real time by utilizing the optimal GA-SVM model in the repair process. However, in this solution, all factors affecting the mechanical properties may not be taken into account in the model when building the GA-SVM model. Factors such as the type of soil, the degree of aging of the pipe, the chemical nature of the surrounding environment, etc. may have a significant impact on the results in actual remediation but are not fully represented in the model. Meanwhile, the evaluation model of the GA-SVM may depend on a single mechanical performance index too, other factors which may influence the repairing effect are ignored, and the environmental conditions (such as temperature, humidity, illumination and the like) of a construction site may change in a short time. Failure of the model to accommodate these dynamic changes may result in inaccurate predictions. Thus, only one set of evaluation models may reduce the real-time performance and effectiveness of the evaluation system.
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide a machine learning-based real-time evaluation method for ultraviolet light in-situ curing repair effect of a drainage pipeline, which aims to solve the problems in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a real-time evaluation method for ultraviolet light in-situ curing repair effect of a drainage pipeline based on machine learning comprises the following specific steps:
Collecting process parameters and corresponding hardness values of a curing material at different moments in the ultraviolet light in-situ curing repair process of the historical drainage pipeline, wherein the process parameters comprise surface temperature, surface humidity, curing time and ultraviolet light irradiation intensity of the repair part of the drainage pipeline;
establishing an LSTM prediction model, taking the acquired process parameters at different moments as the input of the model, taking the corresponding hardness value of the cured material as a label, training the LSTM prediction model to obtain the cured hardness prediction model with the input as the process parameters and the output as the corresponding hardness value of the cured material;
calculating to obtain ultraviolet irradiation intensity based on the output power of the ultraviolet light source, the distance between the ultraviolet light source and the pipeline repairing position and the effective emission area of the light source during real-time repairing, and correcting the ultraviolet irradiation intensity through the ambient humidity to obtain accurate ultraviolet irradiation intensity;
Collecting real-time process parameters in the repairing process of the drainage pipeline to be repaired, taking the corresponding accurate ultraviolet irradiation intensity, surface temperature, surface humidity and curing time as input data, inputting the input data into a cured hardness prediction model which is trained, and outputting a real-time cured material hardness value by the model;
Based on the model, outputting a real-time hardness value of the cured material, correcting the real-time hardness value of the cured material through illumination uniformity to obtain an average hardness value of the cured material, generating a repair effect evaluation index by combining the surface evenness, the crack shape index and the resonance frequency and the spectral entropy of the acoustic wave signal of the cured material at corresponding moments, comparing the repair effect evaluation index with an evaluation threshold value, and sending different repair effect evaluation results according to different comparison results.
Further, a prediction model is established by taking an LSTM long-term memory network model as a base, an activation function and an optimization algorithm are selected, wherein a Tanh function is selected as the activation function, adam is selected as the optimization algorithm of the LSTM model, and the Tanh function has the following formula:
;
In the formula, Representing the Tanh function, argumentRepresenting the weighted sum of inputs from the neuron, i.e. the result of the weighted sum of inputs received by the neuron from the previous layer;
setting super parameters of an LSTM model, wherein the super parameters of the LSTM model comprise network layer number, iteration times, learning rate, batch number size, training times, batch processing number and hidden layer neuron number;
The number of network layers is set to be a four-layer network structure, the iteration number is set to be 200, the learning rate is set to be 0.001, the batch number is set to be 64, the training number is set to be 500, the batch processing number is set to be 256, and the number of hidden layer neurons is set to be 32.
Further, the formula based on which the ultraviolet irradiation intensity is calculated based on the output power of the ultraviolet light source, the distance between the ultraviolet light source and the pipeline repair position and the effective emission area of the light source during real-time repair is as follows:
;
In the formula, For the intensity of the ultraviolet light irradiation,For the output power of the uv light source,Is the effective emission area of the light source,Is the shortest distance between the ultraviolet light source and the pipeline repairing part;
Correcting the ultraviolet irradiation intensity according to the ambient humidity to obtain accurate ultraviolet irradiation intensity, wherein the formula for calculating the accurate ultraviolet irradiation intensity is as follows:
;
In the formula, For the purpose of accurate intensity of the ultraviolet light irradiation,For the humidity decay factor, the decay effect of humidity on the ultraviolet intensity is described,Is the real-time ambient humidity, wherein the humidity attenuation coefficientGreater than 0.
Further, outputting a real-time hardness value of the cured material based on the model, and correcting the real-time hardness value of the cured material through illumination uniformity to obtain an average hardness value of the cured material, wherein a formula for calculating the average hardness value of the cured material is as follows:
;
Wherein, The average hardness value of the cured material at the time t,The real-time hardness value of the solidified material is output for the model,Is illumination uniformity, wherein the illumination uniformityThe formula on which the calculation is based is:
;
In the formula, AndRepresenting the minimum and maximum values of the precise ultraviolet irradiation intensity, respectivelyAndThe specific formula according to the included angle between the incidence direction of the light source and different tangential planes of the pipeline crack is respectively as follows:
;
;
In the formula, Is the included angle between the incident direction of the light source and different tangential planes of the pipeline crack.
Further, the logic on which the surface flatness at the corresponding time is calculated is:
the logic on which the surface flatness at the corresponding moment is calculated is that the absolute difference of the heights of the bottom of the crack and the surface of the pipeline at the corresponding moment is obtained, the flatness of the surface of the pipeline is calculated based on the difference of the heights, and the formula is as follows:
;
In the formula, The flatness of the surface of the pipeline at the time t,Is the crack length at the time t,The absolute difference of the height between the x-th position of the crack and the surface of the pipeline at the t moment is shown, and x is the position index of the point at the crack.
Further, the method for acquiring the shape index of the crack comprises the steps of acquiring image information of the repaired crack in real time, carrying out image enhancement pretreatment on the acquired image of the crack, extracting the contour of the crack through a Canny algorithm based on the enhanced image of the crack to obtain real-time contour feature information of the crack, calculating the geometric feature of the crack according to the real-time contour feature information of the crack, wherein the geometric feature of the crack comprises the area of the crack and the perimeter of the crack, and calculating the shape index of the crack according to the area of the crack and the perimeter of the crack, wherein the formula for calculating the shape index of the crack specifically comprises the following steps:
;
In the formula, Is the crack shape index at the time t,The area of the crack at the time t is defined as the area of the crack at the time t,Is the perimeter of the crack at time t, wherein the area of the crackAnd crack perimeterThe number of the pixels of the crack is calculated, and the specific formula is as follows:
;
;
In the formula, AndThe number of pixels in the crack region and the number of crack contour edge pixels at time t are indicated respectively,Representing the actual area of each pixel,Representing the length of each edge pixel.
Further, the specific acquisition logic of the resonance frequency and the spectral entropy of the acoustic wave signal of the curing material is that the frequency maximum value of the emitted acoustic wave signal is determined, and the sampling frequency is determined based on the frequency maximum value, wherein the specific formula on which the sampling frequency is determined is as follows:
;
In the formula, For the sampling frequency to be the same,For maximum frequency in the emitted acoustic signal, whereAnd is also provided withIs a positive integer;
The method comprises the steps of sending out an acoustic wave signal to a curing material, acquiring the acoustic wave signal transmitted by the curing material by using a sensor, performing fast Fourier transform on the acoustic wave signal of the curing material, converting a time domain signal into a frequency domain signal, and obtaining a frequency spectrum of the signal Based on frequency spectrumThe power spectral density is calculated according to the following formula:
;
In the formula, For frequencyThe power spectral density at which the power spectrum is obtained,Representing the magnitude of the spectrum;
The resonant frequency is identified based on the power spectral density according to the following formula:
;
In the formula, At the frequency of the resonance and,Representing an argument that maximizes the function, i.e. the power spectral densityThe frequency at which the maximum is reached;
the specific formula based on the power spectral density to calculate the spectral entropy of the acoustic wave signal of the curing material is as follows:
;
In the formula, Is the spectral entropy of the acoustic signal of the cured material.
Further, based on the average hardness value of the cured material, combining the surface flatness, the crack shape index and the resonance frequency and the spectral entropy of the acoustic wave signal of the cured material at corresponding moments to generate a repair effect evaluation index, wherein the specific formula on which the repair effect evaluation index is generated is as follows:
;
In the formula, In order to evaluate the index of the healing effect,The average hardness value of the cured material at the time t,The flatness of the surface of the pipeline at the time t,Is the crack shape index at the time t,AndThe average cured material hardness value and the weight index of the resonance frequency, respectively, wherein,And is also provided withAndAre all greater than 0;
Comparing the evaluation index of the repair effect with an evaluation threshold value, and obtaining different evaluation results of the repair effect according to different comparison results, wherein the logic based on the evaluation results of the repair effect is as follows:
When (when) When the pipeline repair is judged to be in an initial stage, an evaluation result with weak repair effect is sent out, and the repair work is continued;
When (when) When the pipeline repairing is judged to be in a process state, an evaluation result with the repairing effect being the same is sent out, and the repairing and perfecting work of the pipeline cracks is continued;
When (when) When the pipeline repair is judged to be in an end state, an evaluation result with excellent repair effect is sent out, and the repair work is ended;
In the formula, To evaluate the threshold.
Compared with the prior art, the invention has the beneficial effects that:
Firstly, an LSTM (long-short term memory network) model is adopted, so that time series data can be dynamically processed, and various parameters such as ultraviolet irradiation intensity, ambient humidity and temperature in the curing process are analyzed in real time. The dynamic monitoring capability enables real-time hardness prediction of the cured material to be obtained in time, reliability and consistency of a repairing effect are improved, and the ultraviolet irradiation intensity is calculated in real time and corrected according to the environmental humidity, so that ultraviolet irradiation conditions can be dynamically monitored and optimized in the repairing process, and the predicted hardness value is ensured to be more accurate. Not only the dynamic monitoring capability is enhanced, the simulation effect of the ultraviolet irradiation intensity in the actual repair process is improved, and the real-time data analysis and the ultraviolet intensity correction can make more scientific decisions according to the current environmental conditions and the repair effect. Finally, the scheme not only pays attention to the hardness of the cured material, but also combines the multidimensional indexes such as surface flatness, crack shape index, acoustic signals and the like to generate a comprehensive repair effect evaluation index, and can provide more comprehensive repair effect evaluation by integrating various evaluation indexes, so that the repair effect evaluation is more comprehensive and scientific.
Drawings
FIG. 1 is a schematic flow chart of the whole method of the invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "up", "down", "left", "right" and the like are used only to indicate a relative positional relationship, and when the absolute position of the object to be described is changed, the relative positional relationship may be changed accordingly.
Examples:
referring to fig. 1, the present invention provides a technical solution:
a real-time evaluation method for ultraviolet light in-situ curing repair effect of a drainage pipeline based on machine learning comprises the following specific steps:
Step 1, collecting process parameters and corresponding hardness values of a cured material at different moments in the ultraviolet light in-situ curing repair process of a historical drainage pipeline, wherein the process parameters comprise surface temperature, surface humidity, curing time and ultraviolet light irradiation intensity of a repair position of the drainage pipeline.
The surface temperature has a direct effect on the rate of chemical reactions. At higher temperatures, the curing reaction is generally accelerated, possibly increasing the hardness of the material. Temperature changes may also affect physical properties of the cured material, such as toughness and brittleness, so monitoring the temperature may help predict material properties after curing.
Surface moisture can affect the moisture content of the cured material and thus the curing process. Sometimes, too high a humidity may result in incomplete curing, causing internal defects in the material, reducing hardness. Changes in humidity may have an effect on the chemical reaction mechanism of the curing agent, especially some curing agents are sensitive to moisture. Thus, collecting humidity data can predict curing effects.
The curing time is one of the important factors affecting the hardness of the cured material. In general, the longer the cure time, the higher the degree of crosslinking within the material and thus the hardness will also increase. By recording the hardness values at different time points, a relationship between cure time and hardness can be established.
The intensity of the ultraviolet light directly affects the photopolymerization rate of the cured material. High intensity uv light generally accelerates the curing speed, causing the material to reach the desired hardness faster. Non-uniformity in the intensity of the ultraviolet light exposure may lead to differences in the properties of the cured material in different areas, so monitoring the exposure intensity may help predict the hardness value of the cured material.
And 2, establishing an LSTM prediction model, taking the acquired process parameters at different moments as the input of the model, taking the corresponding hardness value of the cured material as a label, training the LSTM prediction model, obtaining the cured hardness prediction model with the input as the process parameters and the output as the corresponding hardness value of the cured material.
LSTM is specifically designed to process and predict time series data. Because various parameters (such as temperature, humidity, ultraviolet irradiation intensity and the like) in the ultraviolet curing repair process of the drainage pipeline change along with time, the LSTM can effectively capture the time sequence relationship and dynamic interaction between the parameters. This capability makes LSTM excellent in processing time-dependent input data. Traditional Recurrent Neural Networks (RNNs) face the problems of "gradient vanishing" and "gradient explosion" when dealing with longer sequences, resulting in models that are difficult to learn long-term dependencies. LSTM can effectively manage information flow, keep and forget past information through introducing a gating mechanism (input gate, forget gate and output gate), thereby avoiding long dependency problem. This allows the LSTM to better understand and predict the complex time dependence of the curing process.
The method comprises the steps of establishing a prediction model by taking an LSTM long-term memory network model as a base, selecting an activation function and an optimization algorithm, wherein a Tanh function is selected as the activation function, adam is selected as the optimization algorithm of the LSTM model, and the Tanh function has the following formula:
;
In the formula, Representing the Tanh function, argumentRepresenting the weighted sum of inputs from the neuron, i.e. the result of the weighted sum of inputs received by the neuron from the previous layer;
setting super parameters of an LSTM model, wherein the super parameters of the LSTM model comprise network layer number, iteration times, learning rate, batch number size, training times, batch processing number and hidden layer neuron number;
The number of network layers is set to be a four-layer network structure, the iteration number is set to be 200, the learning rate is set to be 0.001, the batch number is set to be 64, the training number is set to be 500, the batch processing number is set to be 256, and the number of hidden layer neurons is set to be 32.
And 3, calculating to obtain ultraviolet irradiation intensity based on the output power of the ultraviolet light source, the distance between the ultraviolet light source and the pipeline repairing position and the effective emission area of the light source during real-time repairing, and correcting the ultraviolet irradiation intensity by using the environment humidity to obtain accurate ultraviolet irradiation intensity.
The formula based on which the ultraviolet irradiation intensity is calculated based on the output power of the ultraviolet light source, the distance between the ultraviolet light source and the pipeline repairing position and the effective emission area of the light source during real-time repairing is as follows:
;
In the formula, For the intensity of the ultraviolet light irradiation,For the output power of the uv light source,Is the effective emission area of the light source,Is the shortest distance between the ultraviolet light source and the pipeline repairing part;
Correcting the ultraviolet irradiation intensity according to the ambient humidity to obtain accurate ultraviolet irradiation intensity, wherein the formula for calculating the accurate ultraviolet irradiation intensity is as follows:
;
In the formula, For the purpose of accurate intensity of the ultraviolet light irradiation,For the humidity decay factor, the decay effect of humidity on the ultraviolet intensity is described,Is the real-time ambient humidity, wherein the humidity attenuation coefficientGreater than 0.
The presence of water vapor also affects the transmittance of ultraviolet light, and the real-time ambient humidity represents the ratio of the actual content of water vapor to the maximum content of air, expressed as a percentage. The change in humidity will directly affectThereby affecting the transmission of ultraviolet light.
Coefficient of humidity decayThis coefficient is used exclusively to describe the effect of humidity on the uv intensity. For quantifying the effect of humidity on Ultraviolet (UV) intensity. As the ambient humidity increases, the water vapor absorbs more uv light, resulting in attenuation of the uv intensity. The higher the humidity, the more pronounced the effect of the water vapor on the absorption of ultraviolet light, the water vapor having an absorption capacity in the ultraviolet wavelength range, in particular in the short-wave ultraviolet (UV-C) and in the partial medium-wave ultraviolet (UV-B) regions. The higher the humidity, the greater the concentration of water vapor, thereby increasing the absorption and scattering of ultraviolet light, resulting in a significant attenuation of the ultraviolet light intensity. Coefficient of humidity decayThe specific acquisition mode is that an ultraviolet light source is arranged in an environment with humidity control, and an optical intensity meter is used for measuring the light intensity under different humidity conditions. The ultraviolet intensity and the ultraviolet intensity under the humidity-free condition are recorded under different relative humidity (for example, 0%, 25%, 50%, 75%, 100%), and the data fitting is performed based on the ultraviolet intensity and the ultraviolet intensity data under the humidity-free condition to obtain the humidity attenuation coefficient.
Step 4, collecting real-time process parameters in the repairing process of the drainage pipeline to be repaired, taking the corresponding accurate ultraviolet irradiation intensity, surface temperature, surface humidity and curing time as input data, inputting the input data into a trained curing hardness prediction model, and outputting a real-time curing material hardness value by the model;
The real-time process parameters comprise accurate ultraviolet irradiation intensity, surface temperature, surface humidity and curing time, wherein the surface temperature and the surface humidity can be obtained specifically by measuring the surface temperature by various methods and instruments, and the infrared thermometer is a non-contact measuring tool and can rapidly measure the temperature of the surface of an object. The working principle is to estimate the temperature by detecting the infrared radiation emitted by the object. Thermistors (RTDs) are also a common temperature sensor with high accuracy and stability. The accuracy is high, and the method is suitable for long-term monitoring.
The measurement of surface humidity may generally be used, i.e. a humidity sensor may directly measure the relative humidity in the air, but may also be used to measure the humidity of the surface of an object, in particular for moisture monitoring during curing. The capacitance type humidity sensor judges humidity by measuring capacitance change, and has higher precision and response speed. Is suitable for the environment with rapid change.
And 5, outputting a real-time hardness value of the cured material based on the model, correcting the real-time hardness value of the cured material through illumination uniformity to obtain an average hardness value of the cured material, generating a repair effect evaluation index by combining the surface evenness, the crack shape index and the resonance frequency and the spectral entropy of the acoustic wave signal of the cured material at corresponding moments, comparing the repair effect evaluation index with an evaluation threshold value, and sending different repair effect evaluation results according to different comparison results.
Outputting a real-time hardness value of the cured material based on the model, and correcting the real-time hardness value of the cured material through illumination uniformity to obtain an average hardness value of the cured material, wherein the formula for calculating the average hardness value of the cured material is as follows:
;
Wherein, The average hardness value of the cured material at the time t,The real-time hardness value of the solidified material is output for the model,For illumination uniformity, a value closer to 1 indicates that the illumination is more uniform, where the illumination uniformityThe formula on which the calculation is based is:
;
In the formula, AndRepresenting the minimum and maximum values of the precise ultraviolet irradiation intensity, respectivelyAndThe specific formula according to the included angle between the incidence direction of the light source and different tangential planes of the pipeline crack is respectively as follows:
;
;
In the formula, Is the included angle between the incident direction of the light source and different tangential planes of the pipeline crack. When the included angle between the incidence direction of the light source and the different tangential surfaces of the pipeline crack is 90 degrees, the ultraviolet irradiation intensity is the largest, namely, the normal direction is aligned to the pipeline crack, because the drainage pipeline is generally circular, the smaller the deviation from the normal incidence direction of the light source is, the smaller the included angle between the incidence direction of the light source and the different tangential surfaces of the pipeline crack is, so the ultraviolet irradiation intensity is higherDescribing the ultraviolet irradiation intensity of the pipeline crack which is not in forward alignment with the light source, and finding out the maximum and minimum accurate ultraviolet irradiation intensities through a formula.
The logic on which the surface flatness at the corresponding moment is calculated is that the absolute difference of the heights of the bottom of the crack and the surface of the pipeline at the corresponding moment is obtained, the flatness of the surface of the pipeline is calculated based on the difference of the heights, and the formula is as follows:
;
In the formula, The flatness of the surface of the pipeline at the time t,Is the crack length at the time t,The absolute difference of the height between the x-th position of the crack and the surface of the pipeline at the t moment is shown, and x is the position index of the point at the crack.
The absolute difference between the x-th position of the crack at the t moment and the surface of the pipeline is represented, and the specific acquisition mode can be measured by using a surface roughness meter (such as a profilometer, a laser scanner and the like).
The method for acquiring the crack shape index comprises the steps of acquiring image information of a repaired crack in real time, carrying out image enhancement pretreatment on the acquired crack image, extracting the contour of the crack through a Canny algorithm based on the enhanced crack image to obtain real-time contour feature information of the crack, calculating the geometric feature of the crack according to the real-time contour feature information of the crack, wherein the geometric feature of the crack comprises the area of the crack and the perimeter of the crack, and calculating the crack shape index according to the area of the crack and the perimeter of the crack, wherein the formula for calculating the crack shape index specifically comprises the following steps:
;
In the formula, Is the crack shape index at the time t,The area of the crack at the time t is defined as the area of the crack at the time t,Is the perimeter of the crack at time t, wherein the area of the crackAnd crack perimeterThe number of the pixels of the crack is calculated, and the specific formula is as follows:
;
;
In the formula, AndThe number of pixels in the crack region and the number of crack contour edge pixels at time t are indicated respectively,Representing the actual area of each pixel,Representing the length of each edge pixel, wherein the actual area of each pixel and the length of the pixel are identical.
The specific acquisition logic of the resonance frequency and the spectral entropy of the acoustic wave signal of the curing material is that the frequency maximum value of the emitted acoustic wave signal is determined, and the sampling frequency is determined based on the frequency maximum value, wherein the specific formula on which the sampling frequency is determined is as follows:
;
In the formula, For the sampling frequency to be the same,For maximum frequency in the emitted acoustic signal, whereAnd is also provided withIs a positive integer;
The method comprises the steps of sending out an acoustic wave signal to a curing material, acquiring the acoustic wave signal transmitted by the curing material by using a sensor, performing fast Fourier transform on the acoustic wave signal of the curing material, converting a time domain signal into a frequency domain signal, and obtaining a frequency spectrum of the signal By analyzing the frequency spectrum, finding out the frequency corresponding to the maximum value in the amplitude spectrum, namely the maximum value of the frequency in the sound wave signal. Based on frequency spectrumThe power spectral density is calculated according to the following formula:
;
In the formula, For frequencyThe power spectral density at which the power spectrum is obtained,Representing the magnitude of the spectrum;
The resonant frequency is identified based on the power spectral density according to the following formula:
;
In the formula, At the frequency of the resonance and,Representing an argument that maximizes the function, i.e. the power spectral densityThe frequency at which the maximum is reached;
the specific formula based on the power spectral density to calculate the spectral entropy of the acoustic wave signal of the curing material is as follows:
;
In the formula, Is the spectral entropy of the acoustic signal of the cured material.
Based on the average hardness value of the cured material, combining the surface flatness, the crack shape index and the resonance frequency and the spectral entropy of the acoustic wave signal of the cured material at corresponding moments to generate a repair effect evaluation index, wherein the specific formula on which the repair effect evaluation index is generated is as follows:
;
In the formula, In order to evaluate the index of the healing effect,The average hardness value of the cured material at the time t,The flatness of the surface of the pipeline at the time t,Is the crack shape index at the time t,AndThe average cured material hardness value and the weight index of the resonance frequency, respectively.
Wherein a higher hardness generally means a higher material strength, which is better able to withstand external pressure. Thus, the hardnessThe larger the index, the better the repair result, and the repair effect evaluation indexThe larger the average hardness value of the cured material, the better the repair effect, and the evaluation index of the repair effectIs a positive correlation. And the exponential function can reflect the gradual enhancement effect of the curing strength on the repairing effect. For example, whenWhen a certain value is reached, its contribution to the healing effect increases significantly, while below this value its contribution may be relatively small.
Pipeline surface flatnessThe surface flatness affects the contact and adhesion ability of the material. A better flatness means a better healing effect, so the surface flatness and the index of evaluation of the healing effectIs a positive correlation. For surface flatness, square root transformation can reduce its impact on the model, especially at higher flatness values. Meanwhile, the transformation can improve the sensitivity of the model to smaller flatness values, and reflects that even slight improvement can have important influence on the overall repairing effect.
Crack shape indexThe fracture shape index affects the propagation characteristics of the fracture and the difficulty of repair. In general, a lower fracture shape index means that the fracture is easier to repair, while as the repair proceeds, the area and perimeter of the fracture decrease, smaller fracture means better repair results, and thus the fracture shape index and the evaluation index for the repair effectIs a negative correlation. Natural logarithmic transformationSuch a transformation can reduce the effect of extreme values (particularly high crack shape index values) on the model and make the data more focused, facilitating the model to capture general trends. Furthermore, the fracture shape typically exhibits an exponentially growing characteristic, so that such growth characteristics can be better handled using logarithmic transformation.
During curing, the acoustic signal will exhibit a specific resonant frequency, which is closely related to the physical properties of the material. The fully cured material generally exhibits a higher resonant frequency because the elastic modulus of the material increases, and therefore the resonant frequency and the repair effect evaluation indexIs a positive correlation.
The dominant frequency is the highest energy frequency in the acoustic signal spectrum and generally represents the main vibration characteristic of the material, in the cured material, the dominant frequency changes due to the uniformity and the overall rigidity of the material, the higher dominant frequency and the energy concentration are represented, the concentration of the dominant frequency is described by the spectral entropy, the spectral entropy is used for quantifying the complexity and the concentration of the signal, the lower the spectral entropy is, the more concentrated the frequency components are, and therefore, the spectral entropy repairing effect evaluation indexIs a negative correlation. Spectral entropy is a measure of the complexity of a signal, and generally higher spectral entropy values represent an increase in the complexity of the signal. By means of the exponential decay form, high complexity can be mapped to low values, so that the influence of spectral entropy on the repair effect can be smoother, and meanwhile, the positive influence of the low complexity on the repair effect can be emphasized.
AndWeight indexes of an average hardness value of the cured material and a resonance frequency are respectively set, wherein, the influence of the average hardness value of the cured material on the repairing result is larger than the resonance frequencyAnd is also provided withAndAre all greater than 0;
Comparing the evaluation index of the repair effect with an evaluation threshold value, and obtaining different evaluation results of the repair effect according to different comparison results, wherein the logic based on the evaluation results of the repair effect is as follows:
When (when) When the pipeline repair is judged to be in an initial stage, an evaluation result with weak repair effect is sent out, and the repair work is continued;
When (when) When the pipeline repairing is judged to be in a process state, an evaluation result with the repairing effect being the same is sent out, and the repairing and perfecting work of the pipeline cracks is continued;
When (when) When the pipeline repair is judged to be in an end state, an evaluation result with excellent repair effect is sent out, and the repair work is ended;
In the formula, To evaluate the threshold. The specific acquired formula is as follows:
;
In the formula, For the evaluation threshold value set in advance according to the expert experience,Is the pressure loss of the drainage pipeline, whereinThe formula on which the calculation is based is:
;
In the formula, AndThe pressures at the inlet and outlet, respectively, are small values of pressure loss generally indicate good repair. Thus, during repair, the threshold is evaluatedCan be dynamically adjusted according to the pressure loss of the drainage pipeline.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.

Claims (8)

1.一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，其特征在于，具体步骤包括：1. A real-time evaluation method for the repair effect of UV in-situ curing of drainage pipes based on machine learning, characterized in that the specific steps include: 采集历史排水管道紫外光原位固化修复过程中，不同时刻下的过程参数以及对应的固化材料硬度值，所述过程参数包括排水管道修复处表面温度、表面湿度、固化时间和紫外光照射强度；Collect the process parameters and corresponding hardness values of the cured materials at different times during the UV in-situ curing repair process of the historical drainage pipes. The process parameters include the surface temperature, surface humidity, curing time and UV irradiation intensity of the drainage pipe repair site; 建立LSTM预测模型，将获取的不同时刻的过程参数作为模型的输入，并以对应的固化材料硬度值作为标签，对LSTM预测模型进行训练，得到输入为过程参数，输出为对应固化材料硬度值的固化硬度预测模型；An LSTM prediction model is established, the process parameters obtained at different times are used as the input of the model, and the corresponding hardness value of the solidified material is used as the label. The LSTM prediction model is trained to obtain a solidification hardness prediction model with the input as the process parameter and the output as the corresponding hardness value of the solidified material. 基于实时修复时的紫外光源输出功率、紫外光源与管道修复处之间的距离和光源的有效发射面积计算得到紫外光照射强度，并通过环境湿度对紫外光照射强度进行修正，得到精确紫外光照射强度；The UV light intensity is calculated based on the output power of the UV light source during real-time repair, the distance between the UV light source and the pipeline repair location, and the effective emission area of the light source. The UV light intensity is corrected by the ambient humidity to obtain the accurate UV light intensity. 采集待修复排水管道修复过程中的实时过程参数，将对应的精确紫外光照射强度、表面温度、表面湿度和固化时间作为输入数据，输入完成训练的固化硬度预测模型中，模型输出实时的固化材料硬度值；Collect the real-time process parameters of the drainage pipe to be repaired during the repair process, and use the corresponding precise UV light intensity, surface temperature, surface humidity and curing time as input data, and input them into the trained curing hardness prediction model. The model outputs the real-time hardness value of the curing material. 基于模型输出实时的固化材料硬度值，通过光照均匀性对实时的固化材料硬度值进行修正，得到平均固化材料硬度值，结合对应时刻的表面平整度、裂缝形状指数和固化材料声波信号的共振频率和谱熵，生成修复效果评估指数，根据修复效果评估指数与评估阈值进行对比，根据不同对比结果，发出不同的修复效果评估结果。Based on the real-time hardness value of the solidified material output by the model, the real-time hardness value of the solidified material is corrected by the uniformity of light illumination to obtain the average hardness value of the solidified material. The repair effect evaluation index is generated by combining the surface flatness, crack shape index and the resonance frequency and spectral entropy of the sound wave signal of the solidified material at the corresponding moment. The repair effect evaluation index is compared with the evaluation threshold, and different repair effect evaluation results are issued according to different comparison results. 2.根据权利要求1所述的一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，其特征在于：以LSTM长短期记忆网络模型为基底建立预测模型，选取激活函数和优化算法，其中选择Tanh函数作为激活函数，选择Adam作为LSTM模型的优化算法；Tanh函数其公式为：2. According to a method for real-time evaluation of the repair effect of ultraviolet in-situ curing of drainage pipes based on machine learning in claim 1, it is characterized by: establishing a prediction model based on the LSTM long short-term memory network model, selecting an activation function and an optimization algorithm, wherein the Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is: ； ; 式中，表示Tanh函数，自变量表示神经元的输入加权和，即神经元接收到的来自上一层的输入经过加权求和后的结果；In the formula, Represents the Tanh function, independent variable Represents the weighted sum of the neuron's input, that is, the result of weighted summation of the input received by the neuron from the previous layer; 同时设定LSTM模型的超参数，所述LSTM模型的超参数包括：网络层数、迭代次数、学习率、批量数大小、训练次数、批处理数量和隐藏层神经元个数；At the same time, the hyperparameters of the LSTM model are set, and the hyperparameters of the LSTM model include: the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing number, and the number of hidden layer neurons; 其中网络层数设置为四层网络结构，迭代次数设定为200，学习率设置为0.001，批量数大小设为64，训练次数设为500，批处理数量设为256，隐藏层神经元个数为32。The number of network layers is set to a four-layer network structure, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 64, the number of training times is set to 500, the batch size is set to 256, and the number of hidden layer neurons is 32. 3.根据权利要求1所述的一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，其特征在于：基于实时修复时的紫外光源输出功率、紫外光源与管道修复处之间的距离和光源的有效发射面积计算得到紫外光照射强度所依据的公式为：3. According to the method for real-time evaluation of the repair effect of drainage pipe UV in-situ curing based on machine learning in claim 1, it is characterized in that: the formula for calculating the UV irradiation intensity based on the output power of the UV light source during real-time repair, the distance between the UV light source and the pipe repair location, and the effective emission area of the light source is: ； ; 式中，为紫外光照射强度，为紫外光源输出功率，为光源的有效发射面积，为紫外光源与管道修复处之间的最短距离；In the formula, is the UV irradiation intensity, is the output power of the UV light source, is the effective emitting area of the light source, is the shortest distance between the UV light source and the pipeline repair location; 根据环境湿度对紫外光照射强度进行修正，得到精确紫外光照射强度，其中计算精确紫外光照射强度所依据的公式为：The UV light intensity is corrected according to the ambient humidity to obtain the precise UV light intensity, wherein the formula for calculating the precise UV light intensity is: ； ; 式中，为精确紫外光照射强度，为湿度衰减系数，用于描述湿度对紫外线强度的衰减影响，为实时环境湿度，其中湿度衰减系数大于0。In the formula, To accurately measure the intensity of UV light, is the humidity attenuation coefficient, which is used to describe the attenuation effect of humidity on ultraviolet intensity. is the real-time ambient humidity, where the humidity attenuation coefficient Greater than 0. 4.根据权利要求1所述的一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，其特征在于：基于模型输出实时的固化材料硬度值，通过光照均匀性对实时的固化材料硬度值进行修正，得到平均固化材料硬度值，其中计算平均固化材料硬度值所依据的公式为：4. According to the method for real-time evaluation of the UV in-situ curing repair effect of drainage pipes based on machine learning in claim 1, it is characterized in that: based on the real-time hardness value of the solidified material output by the model, the real-time hardness value of the solidified material is corrected by the uniformity of light illumination to obtain the average hardness value of the solidified material, wherein the formula for calculating the average hardness value of the solidified material is: ； ; 其中，为t时刻的平均固化材料硬度值，为模型输出实时的固化材料硬度值，为光照均匀性，其中光照均匀性计算所依据的公式为：in, is the average hardness value of the solidified material at time t, Output real-time cured material hardness values for the model, is the uniformity of illumination, where The calculation is based on the formula: ； ; 式中，和分别表示精确紫外光照射强度的最小值和最大值，其中精确紫外光照射强度的最小值和最大值和通过光源入射方向与管道裂缝不同切面间的夹角计算，具体所依据的公式分别为：In the formula, and Respectively represent the minimum and maximum values of the precise UV light intensity, where the minimum and maximum values of the precise UV light intensity and The angle between the incident direction of the light source and different sections of the pipe crack is calculated, and the specific formulas are: ； ; ； ; 式中，为光源入射方向与管道裂缝不同切面间的夹角。In the formula, It is the angle between the incident direction of the light source and different sections of the pipe crack. 5.根据权利要求4所述的一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，其特征在于：计算对应时刻的表面平整度所依据的逻辑为：获取对应时刻时裂缝底部与管道表面的高度绝对差值，基于高度差计算管道表面平整度，所依据的公式为：5. According to the method of real-time evaluation of the repair effect of UV in-situ curing of drainage pipes based on machine learning in claim 4, it is characterized in that: the logic for calculating the surface flatness at the corresponding time is: obtaining the absolute difference in height between the bottom of the crack and the surface of the pipe at the corresponding time, and calculating the surface flatness of the pipe based on the height difference, and the formula based on which is: ； ; 式中，为t时刻的管道表面平整度，为t时刻时的裂缝长度，表示t时刻裂缝第x处与管道表面的高度绝对差值，x表示裂缝处点的位置索引。In the formula, is the surface flatness of the pipeline at time t, is the crack length at time t, It represents the absolute difference between the height of the crack at the xth point and the pipe surface at time t, and x represents the position index of the crack point. 6.根据权利要求1所述的一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，其特征在于：所述裂缝形状指数的获取方法为：实时采集修复过程中，修复裂缝的图像信息，对采集的裂缝图像进行图像增强预处理，基于增强后的裂缝图像，通过Canny算法进行裂缝轮廓提取，得到裂缝实时的轮廓特征信息，根据裂缝实时的轮廓特征信息计算裂缝的几何特征，所述裂缝的几何特征包括裂缝的面积和裂缝的周长，根据裂缝的面积和裂缝周长计算裂缝形状指数，其中计算裂缝形状指数具体所依据的公式为：6. According to a method for real-time evaluation of the repair effect of ultraviolet in-situ curing of drainage pipes based on machine learning as described in claim 1, it is characterized in that: the method for obtaining the crack shape index is: real-time acquisition of image information of the repaired cracks during the repair process, image enhancement preprocessing of the acquired crack images, based on the enhanced crack images, crack contour extraction by the Canny algorithm to obtain real-time contour feature information of the cracks, and calculate the geometric features of the cracks according to the real-time contour feature information of the cracks, the geometric features of the cracks include the area of the cracks and the circumference of the cracks, and the crack shape index is calculated according to the area of the cracks and the circumference of the cracks, wherein the specific formula for calculating the crack shape index is: ； ; 式中，为t时刻的裂缝形状指数，为t时刻裂缝的面积，为t时刻的裂缝周长，其中裂缝的面积和裂缝周长通过裂缝像素的数量进行计算，具体所依据的公式为：In the formula, is the crack shape index at time t, is the area of the crack at time t, is the crack perimeter at time t, where the crack area and crack perimeter The calculation is based on the number of crack pixels, and the specific formula is: ； ; ； ; 式中，和分别表示t时刻裂缝区域内的像素数和裂缝轮廓边缘像素的数量，表示像素的实际面积，表示边缘像素的长度。In the formula, and They represent the number of pixels in the crack area and the number of pixels on the edge of the crack contour at time t, respectively. Represents the actual area of the pixel, Indicates the length of edge pixels. 7.根据权利要求1所述的一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，其特征在于：所述固化材料声波信号的共振频率和谱熵具体的获取逻辑为：确定发出的声波信号的频率最大值，基于该频率最大值确定采样频率，其中采样频率确定所依据的具体公式为：7. According to a method for real-time evaluation of the repair effect of UV in-situ curing of drainage pipes based on machine learning in claim 1, it is characterized in that: the specific acquisition logic of the resonance frequency and spectral entropy of the sound wave signal of the curing material is: determine the maximum frequency of the emitted sound wave signal, and determine the sampling frequency based on the maximum frequency, wherein the specific formula for determining the sampling frequency is: ； ; 式中，为采样频率，为发出的声波信号中频率最大值，其中且为正整数；In the formula, is the sampling frequency, is the maximum frequency of the emitted sound wave signal, where and is a positive integer; 通过对固化材料发出声波信号，利用传感器获取固化材料传递的声波信号，对固化材料的声波信号进行快速傅里叶变换，将时域信号转换为频域信号，得到信号的频谱，基于频谱计算功率谱密度，具体所依据的公式为：By sending an acoustic wave signal to the curing material, using a sensor to obtain the acoustic wave signal transmitted by the curing material, performing a fast Fourier transform on the acoustic wave signal of the curing material, converting the time domain signal into a frequency domain signal, and obtaining the spectrum of the signal , based on the spectrum The power spectral density is calculated based on the following formula: ； ; 式中，为频率处的功率谱密度，表示频谱的幅度；In the formula, For frequency The power spectral density at Indicates the amplitude of the spectrum; 基于功率谱密度识别共振频率，具体所依据的公式为：The resonant frequency is identified based on the power spectral density, and the specific formula is: ； ; 式中，为共振频率，表示使得函数达到最大值的自变量，即为使得功率谱密度达到最大值的频率；In the formula, is the resonant frequency, represents the independent variable that makes the function reach the maximum value, that is, the power spectral density The frequency at which the maximum value is reached; 基于功率谱密度计算固化材料声波信号的谱熵所依据的具体公式为：The specific formula for calculating the spectral entropy of the sound wave signal of the solidified material based on the power spectral density is: ； ; 式中，为固化材料声波信号的谱熵。In the formula, is the spectral entropy of the acoustic wave signal of the solidifying material. 8.根据权利要求7所述的一种基于机器学习的排水管道紫外光原位固化修复效果实时评估方法，其特征在于：基于平均固化材料硬度值，结合对应时刻的表面平整度、裂缝形状指数和固化材料声波信号的共振频率和谱熵，生成修复效果评估指数，其中生成修复效果评估指数所依据的具体公式为：8. A real-time evaluation method for the repair effect of UV in-situ curing of drainage pipes based on machine learning according to claim 7, characterized in that: based on the average hardness value of the cured material, combined with the surface flatness, crack shape index and the resonance frequency and spectral entropy of the sound wave signal of the cured material at the corresponding moment, a repair effect evaluation index is generated, wherein the specific formula for generating the repair effect evaluation index is: ； ; 式中，为修复效果评估指数，为t时刻的平均固化材料硬度值，为t时刻的管道表面平整度，为t时刻的裂缝形状指数，和分别为平均固化材料硬度值和共振频率的权重指数，其中，且和均大于0；In the formula, is the restoration effect evaluation index, is the average hardness value of the solidified material at time t, is the surface flatness of the pipeline at time t, is the crack shape index at time t, and are the weight indexes of the average cured material hardness value and the resonance frequency, respectively, where and and All are greater than 0; 根据修复效果评估指数与评估阈值进行对比，根据不同对比结果，得出不同的修复效果评估结果所依据的逻辑为：According to the comparison between the restoration effect evaluation index and the evaluation threshold, different restoration effect evaluation results are obtained according to different comparison results. The logic is as follows: 当时，判断管道修复处于初期阶段，发出修复效果为弱的评估结果，继续进行修复工作；when When the pipeline repair is judged to be in the early stage, an assessment result of weak repair effect is issued, and the repair work continues; 当时，判断管道修复处于过程状态，发出修复效果为中的评估结果，继续对管道裂缝进行修补完善工作；when When the pipeline is repaired, it is judged that the pipeline repair is in the process state, and the evaluation result of the repair effect is medium is issued, and the repair and improvement work of the pipeline cracks continues; 当时，判断管道修复处于结束状态，发出修复效果为优的评估结果，结束修复工作；when When the pipeline repair is completed, it is judged that the pipeline repair is in the final state, and an evaluation result that the repair effect is excellent is issued, and the repair work is completed; 式中，为评估阈值。In the formula, is the evaluation threshold.
CN202411820618.2A 2024-12-11 2024-12-11 Machine learning-based real-time evaluation method for ultraviolet light in-situ curing repair effect of drainage pipeline Active CN119293512B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411820618.2A CN119293512B (en) 2024-12-11 2024-12-11 Machine learning-based real-time evaluation method for ultraviolet light in-situ curing repair effect of drainage pipeline

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411820618.2A CN119293512B (en) 2024-12-11 2024-12-11 Machine learning-based real-time evaluation method for ultraviolet light in-situ curing repair effect of drainage pipeline

Publications (2)

Publication Number Publication Date
CN119293512A true CN119293512A (en) 2025-01-10
CN119293512B CN119293512B (en) 2025-05-16

Family

ID=94149618

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411820618.2A Active CN119293512B (en) 2024-12-11 2024-12-11 Machine learning-based real-time evaluation method for ultraviolet light in-situ curing repair effect of drainage pipeline

Country Status (1)

Country Link
CN (1) CN119293512B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119878982A (en) * 2025-03-26 2025-04-25 福建巨联环境科技股份有限公司 Method for performing ultraviolet light curing non-excavation repair on pipeline by combining robot
CN120830302A (en) * 2025-09-19 2025-10-24 中国电建集团华东勘测设计研究院有限公司 Ecological revetment system, self-repair method and device for ecological revetment system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN219510573U (en) * 2023-03-29 2023-08-11 常熟理工学院 Novel device for collecting image of inner wall of pipeline
CN117212602A (en) * 2023-09-25 2023-12-12 广州开发区市政工程有限公司 An overall UV curing technology for repairing water supply and drainage pipelines
CN117469607A (en) * 2023-10-26 2024-01-30 江苏长三角智慧水务研究院有限公司 A water supply and drainage pipeline detection system and method
CN117553192A (en) * 2023-12-26 2024-02-13 常熟理工学院 A crawler for non-destructive testing of the inner wall of spiral pipes

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN219510573U (en) * 2023-03-29 2023-08-11 常熟理工学院 Novel device for collecting image of inner wall of pipeline
CN117212602A (en) * 2023-09-25 2023-12-12 广州开发区市政工程有限公司 An overall UV curing technology for repairing water supply and drainage pipelines
CN117469607A (en) * 2023-10-26 2024-01-30 江苏长三角智慧水务研究院有限公司 A water supply and drainage pipeline detection system and method
CN117553192A (en) * 2023-12-26 2024-02-13 常熟理工学院 A crawler for non-destructive testing of the inner wall of spiral pipes

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119878982A (en) * 2025-03-26 2025-04-25 福建巨联环境科技股份有限公司 Method for performing ultraviolet light curing non-excavation repair on pipeline by combining robot
CN120830302A (en) * 2025-09-19 2025-10-24 中国电建集团华东勘测设计研究院有限公司 Ecological revetment system, self-repair method and device for ecological revetment system

Also Published As

Publication number Publication date
CN119293512B (en) 2025-05-16

Similar Documents

Publication Publication Date Title
CN119293512B (en) Machine learning-based real-time evaluation method for ultraviolet light in-situ curing repair effect of drainage pipeline
Laxman et al. Automated crack detection and crack depth prediction for reinforced concrete structures using deep learning
CN114282709A (en) Prediction method of fatigue crack growth of structural parts based on digital twin
CN115392124B (en) A method for inversion and reproduction of multi-scale fracture three-dimensional morphology
CN113096088B (en) Concrete structure detection method based on deep learning
CN116825243B (en) A method and system for predicting the service life of thermal barrier coatings based on multi-source data
Fu et al. Automatic bolt tightness detection using acoustic emission and deep learning
CN117436355B (en) Method for establishing optical film thickness model and related equipment
Frusque et al. Non-contact sensing for anomaly detection in wind turbine blades: A focus-SVDD with complex-valued auto-encoder approach
CN118730946A (en) Sewage composition monitoring and detection method and system
CN119395150B (en) Differential pressure flowmeter weld joint nondestructive testing system and method based on ultrasonic phased array
Zhao et al. Smart prediction of rock crack opening displacement from noisy data recorded by distributed fiber optic sensing
CN119475189A (en) A concrete surface crack detection method and system based on machine learning algorithm
CN120952349B (en) A Big Data-Based Assessment System for the Conservation of Historical Rural Buildings
CN119222510B (en) Method, device and product for monitoring leakage position of underground pipe network
CN119480676B (en) Wafer film thickness calibration library construction method, measurement method and polishing equipment
CN118585963B (en) Tunnel guniting intelligent detection method and system based on multi-mode information fusion
CN118224552A (en) Outdoor pipeline heat preservation effect monitoring system in job site
CN119936050A (en) A UAV-assisted bridge structure health monitoring method and system
CN120163012A (en) A system and method for monitoring the degradation degree of arrester resistors in an extremely cold environment
CN117554185B (en) Method and system for monitoring mechanical properties of film material
Su et al. Deep transfer learning method for detection of internal cavities in concrete-filled steel tube structural elements
CN119474795A (en) A method for selecting demodulation model of fiber Bragg grating stress sensor based on calibration data
CN118688300A (en) A nondestructive testing method and system for pipeline quality of reservoir water delivery
CN117309999A (en) Method and system for detecting compactness performance of concrete in arch bridge tubes based on complementary fusion of multi-source acoustic parameter models

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: 215500 Suzhou, Changshou City Province, South Ring Road No. 99, No., No. three

Patentee after: Suzhou Institute of Technology

Country or region after: China

Address before: 215500 Suzhou, Changshou City Province, South Ring Road No. 99, No., No. three

Patentee before: CHANGSHU INSTITUTE OF TECHNOLOGY

Country or region before: China

CP03 Change of name, title or address