Accurate prediction algorithm for compaction quality of asphalt pavement of highway reconstruction and extension project

Abstract

The invention discloses a highway reconstruction and extension project asphalt pavement compaction quality accurate prediction algorithm, and the algorithm comprises the steps: collecting the rolling times, speed, track, temperature and vibration data of a road roller in real time according to an on-site intelligent device and a sensor, and carrying out the correlation analysis of the compaction degree data and corresponding information supervision key parameters; and an artificial neural network model is established, real-time prediction of the compaction degree by informatization supervision key parameters is realized, quality problems are found in time, and the construction quality is mastered in real time, so that shoveling and re-paving of completed parts in the later period are avoided, the pavement quality is ensured, and the construction period is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of asphalt pavement compaction, and in particular to an algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project. Background Art

[0002] With the continuous development of social economy, highway transportation occupies an increasingly important position in the national economy. As an important means to improve traffic carrying capacity and road conditions, highway reconstruction and expansion projects are particularly critical in terms of quality control. Compaction is one of the important processes in pavement construction, which directly affects the construction quality and durability of the pavement.

[0003] For a long time, the quality control method of asphalt pavement construction in my country has always adopted the "post-control" mode, and can only test the performance of the asphalt pavement after completion. This makes the feedback time of construction test data longer. The owner, supervisor and construction party cannot grasp the construction quality in time. When quality problems are found, the completed part can only be removed and re-paved, which not only affects the quality of the road surface, but also causes serious waste and delays the construction period. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the problem of the above-mentioned algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide an accurate prediction algorithm for the compaction quality of asphalt pavement in highway reconstruction and expansion projects, which is used to solve the problem that "my country's asphalt pavement construction quality control method has always adopted the "ex post control" mode, and can only test the performance of the asphalt pavement after completion. This makes the feedback time of construction inspection data long. The owner, supervisor and construction party cannot grasp the construction quality situation in time. When quality problems are found, the completed parts can only be removed and repaved, which not only affects the road quality, causes serious waste, but also delays the construction period."

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: an algorithm for accurately predicting the compaction quality of asphalt pavement in highway reconstruction and expansion projects, comprising:

[0008] Step S1, data collection: using sensors and intelligent equipment technology to collect various data related to compaction quality during the construction process in real time;

[0009] Step S2, data preprocessing: cleaning, denoising, and normalization preprocessing operations are performed on the collected raw data;

[0010] Step S3, feature extraction: extracting key features from the preprocessed data according to the factors affecting the compaction quality of the asphalt pavement;

[0011] Step S5, model construction: through the neural network algorithm, key feature data is input, a compaction quality prediction model is constructed, and a multi-dimensional rolling cloud map and quality report are generated;

[0012] Step S6, model training: using historical construction data as a training set to train and optimize the model;

[0013] Step S7, real-time prediction and feedback: During the construction process, various data related to the compaction quality in the current construction are collected in real time and input into the trained prediction model to obtain the predicted value of the current asphalt pavement compaction quality. The predicted results are compared and analyzed with the actual test results to adjust the construction parameters in time;

[0014] Step S8, continuous optimization and iteration: Based on the actual construction situation and prediction results, new data is continuously collected to continuously optimize and iterate the model.

[0015] As a preferred solution of the algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project described in the present invention, the data collected includes the temperature, humidity, number of compaction passes, roller model and parameters, and pavement structure layer thickness of the asphalt mixture.

[0016] As a preferred solution of the algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project described in the present invention, the feature extraction includes the physical properties of the asphalt mixture, the working status of the construction machinery and the environmental conditions.

[0017] As a preferred solution of the algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project described in the present invention, the sensor includes an acceleration sensor, a pressure sensor, a temperature sensor, a high-precision RTK positioning sensor, and an infrared temperature sensor;

[0018] The acceleration sensor is used to monitor and obtain the vibration conditions and data of the roller wheel, and calculate the continuous compaction index ECV through the amplitude and frequency;

[0019] The pressure sensor is used to obtain the pressure of the tire or steel wheel on the ground;

[0020] The temperature sensor is used to monitor the temperature of the roller during operation, including the temperature of the roller itself and the temperature of the compacted material;

[0021] The high-precision RTK positioning sensor is used to provide high-precision GPS data for compaction machinery and accurately record relevant operation data of each point in the operation area, including the number of compaction passes, direction, and speed;

[0022] The infrared temperature sensor is used to monitor the paving temperature and compaction temperature in real time.

[0023] As a preferred solution of the algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project described in the present invention, wherein: the intelligent equipment includes a beta ray dust monitor, a noise monitoring device, a nuclear humidity meter and an ultrasonic anemometer;

[0024] The beta ray dust monitor is used to monitor the concentration values ​​of TSP, PM10 and PM2.5 particles in real time, and feed the data back to the construction personnel or environmental protection department through the data transmission system;

[0025] The noise monitoring equipment is used to collect noise data in real time and evaluate and warn the noise level through data analysis software;

[0026] The nuclear humidity meter is used to detect the humidity of the material in real time;

[0027] The ultrasonic anemometer is used to monitor wind speed changes in real time.

[0028] As a preferred solution of the algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project described in the present invention, the neural network comprises an input layer, a hidden layer and an output layer, the input layer is various data related to the compaction quality, the output layer is the estimated value of the compaction quality, the hidden layer is the historical construction data, and the neural network training algorithm comprises a forward stage, a backward stage, and an iteration and termination stage;

[0029] The forward phase algorithm is specifically as follows:

[0030]

[0031] Where W ij is the weight between input layer neuron i and hidden layer neuron j, θ j is the bias, u j and h j are the input and output signal labels of each neuron in the hidden layer;

[0032]

[0033] Among them, l k and c k are the input signal and output signal of the output layer neurons, V jk is the weight between hidden layer neuron j and output layer neuron k, γk is bias.

[0034] As a preferred solution of the algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project described in the present invention, the backward phase algorithm is specifically as follows:

[0035] d k =(y k -c k )c k (1-c k ),k=1,2,

[0036]

[0037] V jk (N+1)=V jk (N)+α1d k (N)h j

[0038] γ k (N+1)=γ k (N)+α1d k (N)

[0039] W ij (N+1)=W ij (N)+α2e j (N)h j

[0040] θ j (N+1)=θ j (N)+α2e j (N)

[0041] Where i = 1, 2, ..., m; j = 1, 2, ..., q; k = 1, 2, ..., n; α1 and α2 are learning rates ranging from 0 to 1; N represents the number of the current training round.

[0042] As a preferred solution of the algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project described in the present invention, the calculation formula of the continuous compaction index ECV is specifically as follows:

[0043] EVC=C×A×f

[0044] Among them, A is the amplitude, f is the frequency, and C is the material property obtained from the experiment;

[0045] The regression analysis model established between the continuous compaction index ECV and compaction is:

[0046] y=ax+b, y is the compaction degree, and x is the continuous compaction index ECV value.

[0047] Beneficial effects of the present invention:

[0048] This application collects the roller's rolling times, speed, trajectory, temperature and vibration data in real time based on on-site intelligent equipment and sensors, and conducts correlation analysis on the compaction data with the corresponding key parameters of information-based supervision, establishes an artificial neural network model, and realizes real-time prediction of the compaction degree by key parameters of information-based supervision, so as to promptly discover quality problems and grasp the construction quality in real time, thereby avoiding the need to remove and repave the completed parts at a later stage, which not only ensures the road quality but also speeds up the construction period. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0050] Figure 1 The present invention is a flow chart of an algorithm for accurately predicting the compaction quality of asphalt pavement in a highway reconstruction and expansion project. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0055] Embodiment 1

[0056] Reference Figure 1 , which is an embodiment of the present invention, provides an accurate prediction algorithm for the compaction quality of asphalt pavement in highway reconstruction and expansion projects, which includes:

[0057] Step S1, data collection: using sensors and intelligent equipment technology to collect various data related to compaction quality during the construction process in real time;

[0058] Step S2, data preprocessing: cleaning, denoising, and normalization of the collected raw data to improve the accuracy and efficiency of subsequent analysis;

[0059] Step S3, feature extraction: extracting key features from the preprocessed data according to the factors affecting the compaction quality of the asphalt pavement;

[0060] Step S5, model construction: through the neural network algorithm, key feature data is input, a compaction quality prediction model is constructed, and a multi-dimensional rolling cloud map and quality report are generated;

[0061] Step S6, model training: using historical construction data as a training set, the model is trained and optimized to improve the prediction accuracy and generalization ability of the model;

[0062] Step S7, real-time prediction and feedback: During the construction process, various data related to the compaction quality in the current construction are collected in real time and input into the trained prediction model to obtain the predicted value of the current asphalt pavement compaction quality. The predicted results are compared and analyzed with the actual test results, and the construction parameters are adjusted in time to ensure that the compaction quality meets the design requirements;

[0063] Step S8, continuous optimization and iteration: Based on the actual construction situation and prediction results, new data is continuously collected, and the model is continuously optimized and iterated to improve the accuracy and stability of the prediction algorithm.

[0064] This application collects the roller's rolling times, speed, trajectory, temperature and vibration data in real time based on on-site intelligent equipment and sensors, and conducts correlation analysis on the compaction data and the corresponding key parameters of information-based supervision, establishes an artificial neural network model, and realizes real-time prediction of the compaction degree by key parameters of information-based supervision, so as to promptly discover quality problems and grasp the construction quality in real time, thereby avoiding the need to remove and repave the completed parts at a later stage, which not only ensures the road quality but also speeds up the construction period.

[0065] The data collected includes the temperature, humidity, compaction times, roller model and parameters, and pavement structure layer thickness of the asphalt mixture.

[0066] The feature extraction includes the physical properties of the asphalt mixture, the working status of the construction machinery and the environmental conditions.

[0067] Wherein, the sensors include acceleration sensors, pressure sensors, temperature sensors, high-precision RTK positioning sensors, and infrared temperature sensors;

[0068] The acceleration sensor is used to monitor and obtain the vibration conditions and data of the roller wheel, and calculate the continuous compaction index ECV through the amplitude and frequency;

[0069] The pressure sensor is used to obtain the pressure of the tire or steel wheel on the ground;

[0070] The temperature sensor is used to monitor the temperature of the roller during operation, including the temperature of the roller itself and the temperature of the compacted material;

[0071] The high-precision RTK positioning sensor is used to provide high-precision GPS data for compaction machinery and accurately record relevant operation data of each point in the operation area, including the number of compaction passes, direction, and speed;

[0072] The infrared temperature sensor is used to monitor the paving temperature and compaction temperature in real time to ensure that the temperature control during the construction process meets the design requirements.

[0073] Among them, the intelligent equipment includes a beta ray dust monitor, a noise monitoring device, a nuclear humidity meter and an ultrasonic anemometer;

[0074] The beta ray dust monitor is used to monitor the concentration values ​​of TSP, PM10 and PM2.5 particles in real time, and feed the data back to the construction personnel or environmental protection department through the data transmission system;

[0075] The noise monitoring equipment is used to collect noise data in real time and evaluate and warn the noise level through data analysis software;

[0076] The nuclear humidity meter is used to detect the humidity of materials in real time and adjust the construction plan in time according to the construction;

[0077] The ultrasonic anemometer is used to monitor wind speed changes in real time to ensure construction safety.

[0078] The neural network comprises an input layer, a hidden layer and an output layer, the input layer is various data related to compaction quality, the output layer is the compaction quality estimation, the hidden layer is the historical construction data, and the neural network training algorithm comprises a forward stage, a backward stage, and an iteration and termination stage;

[0079] The forward phase algorithm is specifically as follows:

[0080]

[0081] Where W ijis the weight between input layer neuron i and hidden layer neuron j, θ j is the bias, u j and h j are the input and output signal labels of each neuron in the hidden layer;

[0082]

[0083] Among them, l k and c k are the input signal and output signal of the output layer neurons, V jk is the weight between hidden layer neuron j and output layer neuron k, γ k is bias.

[0084] The backward phase algorithm is specifically as follows:

[0085] d k =(y k -c k )c k (1-c k ),k=1,2,

[0086]

[0087] V jk (N+1)=V jk (N)+α1d k (N)h j

[0088] γ k (N+1)=γ k (N)+α1d k (N)

[0089] W ij (N+1)=W ij (N)+α2e j (N)h j

[0090] θ j (N+1)=θ j (N)+α2e j (N)

[0091] Where i = 1, 2, ..., m; j = 1, 2, ..., q; k = 1, 2, ..., n; α1 and α2 are learning rates ranging from 0 to 1; N represents the number of the current training round.

[0092] The calculation formula of the continuous compaction index ECV is as follows:

[0093] EVC=C×A×f

[0094] Among them, A is the amplitude, f is the frequency, and C is the material property obtained from the experiment;

[0095] The regression analysis model established between the continuous compaction index ECV and compaction is:

[0096] y=ax+b, y is the compaction degree, and x is the continuous compaction index ECV value.

[0097] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. An accurate prediction algorithm for the compaction quality of asphalt pavement in highway reconstruction and expansion projects, characterized in that: include: Step S1, data collection: using sensors and intelligent equipment technology to collect various data related to compaction quality during the construction process in real time; Step S2, data preprocessing: cleaning, denoising, and normalization preprocessing operations are performed on the collected raw data; Step S3, feature extraction: extracting key features from the preprocessed data according to the factors affecting the compaction quality of the asphalt pavement; Step S5, model construction: through the neural network algorithm, key feature data is input, a compaction quality prediction model is constructed, and a multi-dimensional rolling cloud map and quality report are generated; Step S6, model training: using historical construction data as a training set to train and optimize the model; Step S7, real-time prediction and feedback: During the construction process, various data related to the compaction quality in the current construction are collected in real time and input into the trained prediction model to obtain the predicted value of the current asphalt pavement compaction quality. The predicted results are compared and analyzed with the actual test results to adjust the construction parameters in time; Step S8, continuous optimization and iteration: Based on the actual construction situation and prediction results, new data is continuously collected to continuously optimize and iterate the model.

2. According to claim 1, the algorithm for accurately predicting the compaction quality of asphalt pavement in highway reconstruction and expansion projects is characterized by: The data collected includes the temperature, humidity, compaction times, roller model and parameters, and pavement structure layer thickness of the asphalt mixture.

3. According to claim 1, the algorithm for accurately predicting the compaction quality of asphalt pavement in highway reconstruction and expansion projects is characterized by: The feature extraction includes the physical properties of the asphalt mixture, the working status of the construction machinery and the environmental conditions.

4. According to claim 1, the algorithm for accurately predicting the compaction quality of asphalt pavement in highway reconstruction and expansion projects is characterized by: The sensors include acceleration sensors, pressure sensors, temperature sensors, high-precision RTK positioning sensors and infrared temperature sensors; The acceleration sensor is used to monitor and obtain the vibration conditions and data of the roller wheel, and calculate the continuous compaction index ECV through the amplitude and frequency; The pressure sensor is used to obtain the pressure of the tire or steel wheel on the ground; The temperature sensor is used to monitor the temperature of the roller during operation, including the temperature of the roller itself and the temperature of the compacted material; The high-precision RTK positioning sensor is used to provide high-precision GPS data for compaction machinery and accurately record relevant operation data of each point in the operation area, including the number of compaction passes, direction, and speed; The infrared temperature sensor is used to monitor the paving temperature and compaction temperature in real time.

5. According to claim 1, the algorithm for accurately predicting the compaction quality of asphalt pavement in highway reconstruction and expansion projects is characterized by: The intelligent equipment includes a beta ray dust monitor, a noise monitoring device, a nuclear humidity meter and an ultrasonic anemometer; The beta ray dust monitor is used to monitor the concentration values ​​of TSP, PM10 and PM2.5 particles in real time, and feed the data back to the construction personnel and environmental protection department through the data transmission system; The noise monitoring equipment is used to collect noise data in real time and evaluate and warn the noise level through data analysis software; The nuclear humidity meter is used to detect the humidity of the material in real time; The ultrasonic anemometer is used to monitor wind speed changes in real time.

6. The algorithm for accurately predicting the compaction quality of asphalt pavement in highway reconstruction and expansion projects according to claim 1 is characterized by: The neural network comprises an input layer, a hidden layer and an output layer, the input layer is various data related to compaction quality, the output layer is the compaction quality estimation, the hidden layer is the historical construction data, and the neural network training algorithm comprises a forward stage, a backward stage, and an iteration and termination stage; The forward phase algorithm is specifically as follows: Where W ij is the weight between input layer neuron i and hidden layer neuron j, θ j is the bias, u j and h j are the input and output signal labels of each neuron in the hidden layer; Among them, l k and c k are the input signal and output signal of the output layer neurons, V jk is the weight between hidden layer neuron j and output layer neuron k, γ k is bias.

7. The algorithm for accurately predicting the compaction quality of asphalt pavement in highway reconstruction and expansion projects according to claim 6 is characterized by: The backward phase algorithm is specifically as follows: d k =(y k -c k )c k (1-c k ),k=1,2, V jk (N+1)=V jk (N)+α1d k (N)h j c k (N+1)=γ k (N)+α1d k (N) W ij (N+1)=W ij (N)+α2e j (N)h j i j (N+1)=θ j (N)+α2e j (N) Where i = 1, 2, ..., m; j = 1, 2, ..., q; k = 1, 2, ..., n; α1 and α2 are learning rates ranging from 0 to 1; N is the number of the current training round.

8. The algorithm for accurately predicting the compaction quality of asphalt pavement in highway reconstruction and expansion projects according to claim 4 is characterized by: The calculation formula of the continuous compaction index ECV is specifically: EVC=C×A×f Among them, A is the amplitude, f is the frequency, and C is the material property obtained from the experiment; The regression analysis model established between the continuous compaction index ECV and compaction is: y=ax+b, y is the compaction degree, and x is the continuous compaction index ECV value.

Images