Asphalt Pavement Construction Quality Blockchain Traceability System and Its Method

Abstract

The present invention relates to the technical field of road engineering construction, specifically to a blockchain traceability system and method for the construction quality of asphalt pavement, including an intelligent contract layer, a consensus layer, a chain code layer, and a traceability module, an intelligent optimization module, a detection module, a blockchain traceability database, and a server in the application layer. The intelligent contract layer encrypts the data of the entire construction process and automatically executes the functions of intelligent contracts and transaction processing. The consensus layer adopts an improved Practical Byzantine Fault Tolerance (PBFT) algorithm to ensure data consensus. The chain code layer implements the business logic function and uploads the processed data to the access layer. The traceability module, intelligent optimization module, and detection module in the application layer are respectively used to store the working parameters of the equipment, recommend the best modifier addition scheme, and extract the asphalt softening point data. The blockchain traceability database stores the blockchain data, and the server provides system services, realizing the trustworthy storage and anti-tampering of the data in the whole process of asphalt pavement construction.

Description

Technical Field

[0001] The present invention relates to the technical field of road engineering construction, specifically to a blockchain traceability system and method for the construction quality of asphalt pavement, especially a system and method for using blockchain technology to record, trace, and optimize the quality data in the whole process of asphalt pavement construction. Background Art

[0002] As an important form of road paving, the construction quality of asphalt pavement directly affects the service life of the road and driving safety. The traditional construction quality management of asphalt pavement mainly relies on manual inspection and paper records, with problems such as data islands, information opacity, and difficulty in traceability. With the development of Internet of Things and big data technologies, some enterprises have begun to apply information means for quality management, but still face the following key problems:

[0003] Firstly, the traditional construction quality management system of asphalt pavement lacks a credible data storage mechanism, and the data is easily tampered with, making it difficult to achieve full-process traceability. Secondly, there are barriers to data sharing among all participating parties, and it is impossible to form a synergy effect. Thirdly, the quality control during the construction process is mostly experience-driven and lacks intelligent decision-making support. In addition, the traceability analysis of quality problems usually relies on post-event inspection, making it difficult to achieve real-time early warning and proactive intervention.

[0004] Blockchain technology, with its characteristics of decentralization, anti-tampering, and traceability, provides a new technical approach to solve the above problems. However, the existing blockchain traceability systems are mostly applied in the fields of supply chain management and food safety, and there are few specific studies on the construction quality of asphalt pavement. The existing technologies have not fully solved the problems of multi-source heterogeneous data fusion, real-time quality monitoring, and intelligent decision optimization in asphalt pavement construction.

[0005] Therefore, there is an urgent need for a blockchain traceability system for the construction quality of asphalt pavement to achieve credible recording, intelligent analysis, and full-process traceability of quality data in the whole construction process, and improve the construction quality management level of asphalt pavement. Summary of the Invention

[0006] The purpose of the present invention is to provide a blockchain traceability system and method for the construction quality of asphalt pavement, aiming to solve the problems such as poor data credibility, difficult quality traceability, and insufficient decision optimization existing in the traditional construction quality management of asphalt pavement.

[0007] The present invention proposes a blockchain traceability system for the construction quality of asphalt pavement, including:

[0008] The consortium blockchain layer, including the intelligent contract layer, the consensus layer, and the chain code layer; where

[0009] The intelligent contract layer is used to process the whole-process data of asphalt pavement construction by using encryption technology, and process the data information by using the underlying blockchain technology to obtain block data, and automatically execute intelligent contract and transaction processing functions;

[0010] The consensus layer adopts the improved Practical Byzantine Fault Tolerance (PBFT) algorithm to broadcast the block header of the block data, request other nodes to confirm the recording result of the block, achieve consensus on the data, and selectively synchronize the data based on the Byzantine fault tolerance mechanism;

[0011] The chain code layer is used to store the stored block data in the intelligent contract layer, implement the system business logic function, and upload the information after processing the data to the access layer;

[0012] The access layer includes an interface unit; among them, the interface unit is used to provide a data call interface for the interaction between external data and internal system data;

[0013] The application layer includes a traceability module, an intelligent optimization module, a detection module, a blockchain traceability database, and a server; among them,

[0014] The traceability module is used to store the working parameters of the paver equipment during operation, including the processing of paving temperature GPS trajectory data, the processing of paving temperature field thermal images, the extraction of paving data, and three-dimensional construction quality traceability;

[0015] The intelligent optimization module is used to extract image features from the paving temperature field thermal image, the working parameters of the compaction equipment, and the paving GPS trajectory information, recommend the best modifier addition scheme based on reinforcement learning, and upload the data information to the chain code layer, and synchronize the data to other nodes through the consortium chain for recording to achieve multi-party sharing;

[0016] The detection module is used to extract data information related to the softening point of asphalt, record it in the chain code layer, and synchronize the data through the consortium chain to provide a reference for the quality control of paving equipment;

[0017] The blockchain traceability database is used to store blockchain data;

[0018] The server is used to provide system services.

[0019] Preferably, the system further includes a front-end APP and a background management subsystem.

[0020] Preferably, the block data includes a block data header and a block data body. The block data header includes the block height, version, hash value of the previous block, Merkle root, timestamp, difficulty, nonce, and hash value. The block data body includes the paving temperature field thermal image, block ID, timestamp, paver GPS trajectory, paving temperature trajectory coordinates x and y, paving temperature trajectory data z, paving temperature and humidity, infrared spectrum, asphalt gradation, as well as the type of modifier and metering pump frequency.

[0021] Preferably, the working process of the smart contract layer includes: encrypting, compressing the raw materials, construction process data, inspection data, and paver construction trajectory data through the smart contract of blockchain technology, and automatically executing the smart contract and transaction processing functions. The smart contract layer stores the stored block data in the chain code layer, realizes the system business logic function, and uploads the processed data information to the access layer; extracts the features of the paving temperature field thermal image through the smart contract layer, stores it in the blockchain, and calls the data on the chain, and combines the actual construction conditions to perform three-dimensional construction quality traceability, realizing the visualization and traceability of the asphalt pavement construction quality.

[0022] Preferably, the process of the intelligent optimization module includes: extracting the image features of the paving temperature field thermal image, the working parameters of the compaction equipment, and the paving GPS trajectory information; dividing the asphalt pavement construction process into two cases. Case 1: When it is detected by infrared that the current asphalt softening point has reached but not reached the standard, increase the modifier metering pump frequency to the maximum value, continue to stir for 15s, then upload the collected data to the chain code layer, and upload it to the smart contract layer through the interface unit of the access layer. After consensus by the consensus layer, complete the on-chain synchronization; Case 2: When it is detected by infrared that the current asphalt softening point has reached the standard, set the modifier metering pump frequency to the current frequency for normal mixing, and upload the data record to the chain code layer.

[0023] Preferably, the detection module detects the asphalt softening point, including: measuring the temperature using infrared thermal imaging technology, calibrating with a temperature sensor, analyzing the chemical composition change of asphalt using FTIR spectroscopy as an auxiliary basis for softening point judgment, storing the detection data in the chain code layer, encrypting and compressing the data through the smart contract of blockchain technology, calling the on-chain detection data through the chain code layer, and completing the data on-chain based on the blockchain traceability technology.

[0024] Preferably, the process of infrared detection and analysis of detection data in the detection module includes: in the mixing plant laboratory, performing infrared spectrum testing on asphalt raw materials to obtain temperature parameters, and based on neural network technology, establishing an asphalt softening point fitting function; calculating the characteristic values of the temperature curve, including the maximum value of the temperature curve, the area enclosed by the temperature curve and the X-axis, and the number of periods of the temperature curve. Based on the characteristic values of the temperature curve, calculating the difference between the detection data and the asphalt softening point through a convolutional neural network, and uploading the difference calculation result to the chain code layer.

[0025] Preferably, the data storage process during the construction of the paver includes: encrypting and storing the GPS trajectory information during the construction of the paver; encrypting and storing the paving temperature field thermal image, the paving temperature trajectory coordinates x and y, the paving temperature trajectory data z, and the paving temperature and humidity together through the chain code layer to the blockchain, and broadcasting and confirming to all nodes through the consensus layer to ensure the immutability of the data.

[0026] Preferably, the process of tracing the construction quality of the asphalt pavement includes: uploading the paving temperature field thermal image through the interface unit of the access layer to the smart contract layer, and synchronizing the data information to the data tracing module through the link layer; performing coordinate transformation on the GPS device of the paver, correcting the trajectory data after coordinate transformation to obtain the final trajectory points, and using three-dimensional modeling technology to perform three-dimensional modeling on the final trajectory points and the coordinate height together to obtain a three-dimensional tracing map of the construction quality of the asphalt pavement.

[0027] The asphalt pavement construction quality blockchain traceability method based on the system includes:

[0028] Implementing data encryption and consensus for the consortium chain through the smart contract layer, the consensus layer, and the chain code layer;

[0029] Through the access layer, the interface unit effectively interacts external data and internal data;

[0030] Through the application layer, processing the data through the tracing module, the intelligent optimization module, and the detection module. Among them, the tracing module processes the paving temperature GPS trajectory data and the paving temperature field thermal image, the intelligent optimization module extracts the characteristics of the paving temperature field thermal image and recommends the best modifier addition plan, and the detection module extracts the data information related to the asphalt softening point.

[0031] Storing the processed data to the blockchain traceability database through the chain code layer, and providing system services through the server to achieve the visualization and traceability of the construction quality of the asphalt pavement.

[0032] The beneficial effects of the present invention include:

[0033] 1. The credible storage and anti-tampering of data throughout the asphalt pavement construction process are realized, ensuring the authenticity and integrity of quality data;

[0034] 2. Through the fusion and intelligent analysis of multi-source heterogeneous data, the accuracy and real-time performance of asphalt pavement construction quality monitoring are improved;

[0035] 3. Based on reinforcement learning technology, the intelligent optimization of modifier addition schemes is realized, enhancing material properties and pavement quality;

[0036] 4. A three-dimensional construction quality traceability model is constructed, realizing the intuitive and visual traceability of construction quality, facilitating problem positioning and responsibility identification;

[0037] 5. Through blockchain technology, multi-party data sharing and collaboration are realized, breaking information silos and improving construction efficiency and quality management levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is the overall architecture diagram of the blockchain traceability system for asphalt pavement construction quality of the present invention;

[0039] Figure 2 It is the structural schematic diagram of the consortium chain layer of the present invention;

[0040] Figure 3 It is the schematic diagram of the block data structure of the present invention;

[0041] Figure 4 It is the working flow chart of the intelligent optimization module of the present invention;

[0042] Figure 5 It is the infrared detection and analysis flow chart of the detection module of the present invention;

[0043] Figure 6 It is the schematic diagram of three-dimensional construction quality traceability of the present invention;

[0044] Figure 7 It is the flow chart of the blockchain traceability method for asphalt pavement construction quality of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0045] Please refer to the attached Figures 1-7 , and the following will describe in detail the specific implementation manners of the present invention in conjunction with the attached drawings. It should be noted that the following implementation manners are only used to illustrate the present invention and are not intended to limit the present invention.

[0046] Referring to Figure 1 , the blockchain traceability system for asphalt pavement construction quality provided by the present invention includes a consortium chain layer 1, an access layer 2, and an application layer 3.

[0047] The consortium blockchain layer 1 includes the smart contract layer 11, the consensus layer 12, and the chain code layer 13. The smart contract layer 11 is used to process the whole-process data of asphalt pavement construction using encryption technology, and process the data information using the underlying blockchain technology to obtain block data, and automatically execute the smart contract and transaction processing functions. The consensus layer 12 adopts the improved Practical Byzantine Fault Tolerance (PBFT) algorithm to broadcast the block header of the block data, request other nodes to confirm the recording result of the block, achieve consensus on the data, and selectively synchronize the data based on the Byzantine fault tolerance mechanism. The chain code layer 13 is used to store the stored block data in the smart contract layer 11, implement the system business logic function, and upload the information after processing the data to the access layer 2.

[0048] The access layer 2 includes an interface unit 21, which is used to provide a data call interface for the interaction between external data and internal system data.

[0049] The application layer 3 includes a traceability module 31, an intelligent optimization module 32, a detection module 33, a blockchain traceability database 34, and a server 35. The traceability module 31 is used to store the working parameters of the paver equipment during operation, including the processing of paving temperature GPS trajectory data, the processing of paving temperature field thermal images, the extraction of paving data, and the three-dimensional construction quality traceability. The intelligent optimization module 32 is used to extract the image features of the paving temperature field thermal images, the working parameters of the compaction equipment, and the paving GPS trajectory information, recommend the best modifier addition plan based on reinforcement learning, and upload the data information to the chain code layer 13, and synchronize the data to other nodes through the consortium blockchain layer 1 for recording to achieve multi-party sharing. The detection module 33 is used to extract the data information related to the asphalt softening point, record it in the chain code layer 13, and synchronize the data through the consortium blockchain layer 1 to provide a reference for the quality control of the paving equipment. The blockchain traceability database 34 is used to store blockchain data. The server 35 is used to provide system services.

[0050] In addition, the asphalt pavement construction quality blockchain traceability system of the present invention further includes a front-end APP 4 and a background management subsystem 5. The front-end APP 4 is mainly used for on-site data collection and query, and supports the access of various terminal devices. The background management subsystem 5 is mainly used for functions such as system configuration, user permission management, and data statistical analysis. This design makes the system easy to operate and has perfect functions, meeting the usage requirements of different users.

[0051] Refer to Figure 3, the block data in the system of the present invention includes a block data header and a block data body. The block data header includes a block height, a version, a hash value of the previous block, a Merkle root, a timestamp, a difficulty, a nonce, and a hash value. The block data body includes a thermal image of the paving temperature field, a block ID, a timestamp, a GPS trajectory of the paver, paving temperature trajectory coordinates x and y, paving temperature trajectory data z, paving temperature and humidity, an infrared spectrum, an asphalt gradation, as well as the type of modifier and the metering pump frequency.

[0052] Preferably, the block height represents the position of the block in the entire blockchain, the version represents the blockchain protocol version number, the hash value of the previous block is used to ensure the continuity of the blockchain, the Merkle root is the root hash of the hash values of all transactions in the block, the timestamp records the time when the block is generated, the difficulty and the nonce are used for the consensus mechanism, and the hash value is the unique identifier of the entire block.

[0053] In a specific embodiment of the present invention, the thermal image of the paving temperature field in the block data body is obtained by using infrared imaging technology, with a resolution of 640×480 pixels and a temperature accuracy of ±0.5°C; the GPS trajectory of the paver uses centimeter-level positioning technology, and the positioning accuracy is better than 5 centimeters; the paving temperature trajectory coordinates x, y, and data z constitute a three-dimensional temperature distribution map, realizing the visual representation of the construction quality.

[0054] This design of the block data structure realizes the complete recording and effective storage of construction data, providing a data basis for subsequent quality traceability and analysis. At the same time, the blockchain technology ensures the immutability and traceability of the data.

[0055] Refer to Figure 2 , the working process of the intelligent contract layer 11 of the present invention includes encrypting and compressing the raw material, construction process data, inspection data, and paver construction trajectory data. The intelligent contract layer 11 uses the AES-256 encryption algorithm to encrypt sensitive data and the gzip algorithm to compress a large amount of data, reducing the storage space and transmission burden. The encrypted and compressed data automatically executes the transaction processing function through the intelligent contract, ensuring the automation and security of the data processing process.

[0056] The intelligent contract layer 11 stores the storage block data in the chain code layer 13, realizes the system business logic function, and uploads the information after processing the data to the access layer 2. At the same time, the intelligent contract layer 11 also extracts features from the thermal image of the paving temperature field, and the extracted features include temperature distribution features, temperature gradient features, and temperature anomaly point features. These feature data are stored in the blockchain as an important basis for quality assessment.

[0057] In addition, the smart contract layer 11 can also call on-chain data, combine it with the actual construction conditions, and conduct three-dimensional construction quality traceability for the asphalt pavement construction, realizing the visualization and traceability of the construction quality. This traceability function can help users quickly locate quality problems during the construction process and provide a basis for quality improvement.

[0058] In a preferred embodiment of the present invention, the smart contract is written in Solidity language and supports the implementation of complex business logics. The execution process of the smart contract is completely transparent and can be verified by all participating parties, ensuring the fairness and transparency of the system processing.

[0059] Referring to Figure 4 , the working process of the intelligent optimization module 32 of the present invention mainly includes the following steps:

[0060] First, image feature extraction is performed on the paving temperature field thermal image, the working parameters of the compaction equipment, and the paving GPS trajectory information. The temperature field thermal image is collected by an infrared camera with a resolution of 640×480 pixels and a collection frequency of 1 time per second. The working parameters of the compaction equipment include compaction speed, amplitude, and frequency, etc., with a sampling frequency of 5 times per second. The collection frequency of the paving GPS trajectory information is 1 time per second, and the positioning accuracy is better than 5 cm.

[0061] During the feature extraction process, the convolutional neural network is used to process the temperature field thermal image to extract temperature distribution features, temperature gradient features, and temperature anomaly point features. The GPS trajectory data is filtered and interpolated to ensure the continuity and accuracy of the trajectory data. The working parameters of the compaction equipment are normalized so that different parameters can be analyzed uniformly.

[0062] Secondly, the asphalt pavement construction process is divided into two situations:

[0063] Situation 1: When it is detected by infrared that the current asphalt softening point has reached but does not meet the standard (for example, the softening point is 48°C while the standard requirement is 53°C), the frequency of the modifier metering pump is increased to the maximum value (usually 50 Hz), and after continuous stirring for 15 s, the collected data is uploaded to the chain code layer 13 and then uploaded to the smart contract layer 11 through the interface unit 21 of the access layer 2. After consensus by the consensus layer 12, the data is synchronized to the blockchain.

[0064] Situation 2: When it is detected by infrared that the current asphalt softening point has met the standard (for example, the softening point is 54°C, higher than the standard requirement of 53°C), the frequency of the modifier metering pump is set to the current frequency (usually about 30 Hz) for normal mixing, and the data is recorded and uploaded to the chain code layer 13.

[0065] The intelligent optimization module 32 optimizes the modifier addition scheme using a method based on deep reinforcement learning. This method uses the Deep Q-Network (DQN) as the core algorithm for reinforcement learning. The state space includes the current asphalt softening point, the current temperature, the type of modifier, and the metering pump frequency, etc.; the action space includes different strategies for adjusting the metering pump frequency of the modifier; the reward function is designed as:

[0066] ,

[0067] where, is the reward value for taking action under state , with the unit being a dimensionless value; is the softening point quality score, with a value range of 0 - 100 points, indicating the degree of compliance of the softening point; is the construction efficiency score, with a value range of 0 - 100 points, indicating the construction speed and resource utilization efficiency; is the modifier cost, with the unit being yuan / ton; , β, and γ are weight coefficients, dimensionless, used to balance the three aspects of quality, efficiency, and cost, and usually take values of to ensure that while quality is the main consideration, efficiency and cost are also taken into account.

[0068] During the construction process of asphalt pavement, the softening point is a key index for evaluating the performance of asphalt, directly affecting the high-temperature stability and rutting resistance of the pavement. Through the reinforcement learning algorithm, the present invention establishes an intelligent optimization model for softening point control. This model can automatically adjust the modifier addition amount according to real-time detection data to ensure that the asphalt softening point reaches the best state. Compared with the traditional empirical adjustment method, this method has higher accuracy and stability, significantly improving the construction quality of asphalt pavement.

[0069] The reinforcement learning model continuously optimizes the decision-making strategy by interacting with the environment, and finally finds the best modifier addition scheme to achieve precise control of the asphalt softening point and improvement of construction quality. In practical applications, through the training of a large amount of construction data, this model gradually improves the decision-making accuracy, adapts to different construction environments and material characteristics, and provides intelligent support for asphalt pavement construction.

[0070] The reinforcement learning algorithm of the intelligent optimization module 32 can be further optimized into a system with continuous learning ability, continuously improving the decision-making strategy by accumulating construction experience data. The specific implementation method is:

[0071] Establish an experience replay buffer (Experience Replay Buffer) to store historical decision data;

[0072] Adopt a Double Deep Q - Network (Double DQN) structure to reduce the over - estimation problem of Q - value estimation;

[0073] Introduce a Prioritized Experience Replay mechanism to preferentially learn important samples;

[0074] Design an algorithm for adaptively adjusting the learning frequency to dynamically adjust the learning step size according to environmental changes;

[0075] This continuously optimized reinforcement learning mechanism enables the system to continuously adapt to new construction environments and material properties, improving the robustness and adaptability of decision - making.

[0076] Refer to Figure 5 , the detection module 33 of the present invention for the softening point of asphalt mainly includes the following steps:

[0077] First, use infrared thermal imaging technology for temperature measurement and calibrate it with a temperature sensor. Infrared thermal imaging can directly obtain the temperature field distribution, with an accuracy of up to ±0.5°C, which is suitable for monitoring the temperature change process of asphalt. At the same time, FTIR spectroscopy can be used to analyze the chemical composition changes of asphalt as an auxiliary basis for softening point judgment. This combined use can form a unique technical advantage: infrared thermal imaging provides temperature data, and FTIR provides data on chemical structure changes. The combination of the two can more accurately judge the softening point of asphalt.

[0078] Second, store the detection data in the chain code layer 13. Use the AES - 256 encryption algorithm to encrypt the detection data to ensure data security. The storage process uses blockchain technology to ensure that the data cannot be tampered with.

[0079] Third, encrypt and compress the data through the smart contract of blockchain technology. The compression rate can reach more than 60%, effectively reducing the storage space requirement. The compressed data is recorded on the blockchain to form a complete data chain.

[0080] Finally, call the on - chain detection data through the chain code layer 13 and complete the data uploading based on the blockchain traceability technology. After the data is uploaded, all authorized nodes can access and verify the data, realizing the openness, transparency, and traceability of the data.

[0081] In the preferred embodiment of the present invention, the detection module 33 adopts an adaptive threshold technology to improve the detection accuracy. When the environmental temperature is lower than 10°C, a lower detection threshold is used (such as the softening point standard is 50°C); when the environmental temperature is between 10 - 30°C, the standard detection threshold is used (such as the softening point standard is 53°C); when the environmental temperature is higher than 30°C, a higher detection threshold is used (such as the softening point standard is 55°C). This adaptive threshold technology can effectively reduce the influence of environmental factors on the detection results and improve the detection accuracy.

[0082] Refer to Figure 5 , the infrared detection and analysis process of the detection module 33 of the present invention mainly includes the following steps:

[0083] First, in the mixing plant laboratory, infrared spectrum tests are carried out on asphalt raw materials to obtain temperature parameters. The test environment temperature is controlled at 20±2°C, and the humidity is controlled at 50±5%RH. The test sample quantity is 5±0.1g, and homogenization treatment is carried out before the test. The test process adopts a programmed temperature rise method, with a temperature rise rate of 5°C / min, rising from room temperature to 200°C, and spectral data is collected every 5°C.

[0084] Secondly, based on neural network technology, an asphalt softening point fitting function is established. The fitting function adopts the following form:

[0085] ,

[0086] Where: is the temperature value at any point on the temperature curve, with the unit of °C, representing the actual temperature of the asphalt at a specific time point; is the asphalt softening point, with the unit of °C, representing the critical temperature at which the asphalt begins to soften, and is an important index for evaluating the high-temperature performance of asphalt; is the temperature fluctuation amplitude parameter, with the unit of °C, usually taking a value of 3-5°C, reflecting the severity of temperature change; is the angular frequency of temperature change, with the unit of rad / s, representing the periodicity of temperature change, and is related to the heating rate and material properties; is the time, with the unit of s, representing the duration from the start of the test to the current moment; is the initial phase, with the unit of rad, related to the test starting conditions.

[0087] In asphalt pavement construction, accurately measuring the softening point is crucial for controlling the performance of asphalt mixtures. Traditional softening point test methods require a large amount of manual operation and have a long test cycle, making it difficult to meet the real-time requirements of the construction site. The present invention realizes the rapid and accurate determination of the asphalt softening point through infrared spectrum technology and neural network algorithms. The test time is shortened from several hours of the traditional method to a few minutes, and the measurement accuracy reaches ±1°C, meeting the real-time quality control requirements of the construction site.

[0088] The fitting function is obtained through neural network training, and the training data is sourced from a large number of experimental test results. The neural network has a three-layer structure. The input layer has 10 neurons that receive the feature vectors of the infrared spectrum. The hidden layer has 20 neurons that process the feature information using the ReLU activation function. The output layer has 1 neuron that outputs the predicted softening point temperature. The training algorithm uses the Adam optimizer with a learning rate set to 0.001 and 1000 training epochs, and the training error is less than 0.5 °C.

[0089] Next, calculate the characteristic values of the temperature curve, including the maximum value of the temperature curve, the area enclosed by the temperature curve and the X-axis, and the number of periods of the temperature curve. The maximum value of the temperature curve is usually between 170 - 190 °C, which represents the highest temperature reached by the asphalt during the test and is of great significance for evaluating the thermal stability of the asphalt. The area enclosed by the temperature curve and the X-axis is related to the heat capacity of the sample and reflects the heat absorption and dissipation characteristics of the asphalt. The number of periods of the temperature curve reflects the phase change process of the sample and is usually related to the asphalt component structure.

[0090] Finally, based on the characteristic values of the temperature curve, calculate the difference between the test data and the asphalt softening point through a convolutional neural network, and upload the difference calculation result to the chain code layer 13. The convolutional neural network adopts the ResNet-18 structure. The input is the temperature curve feature matrix with a size of 28×28×3, representing the spectral features at different temperature points. The network contains 4 residual blocks, and each residual block contains 2 convolutional layers and a skip connection. The output is the softening point difference, representing the deviation between the predicted value and the standard value. The network has been trained on a large number of standard samples, and the accuracy rate can reach over 95%.

[0091] The temperature curve data can be converted into a two-dimensional image representation of time - temperature, such as the spectrogram obtained after performing time-frequency analysis on the temperature curve;

[0092] The three channels can respectively represent:

[0093] Channel 1: Two-dimensional representation of the original temperature curve;

[0094] Channel 2: Two-dimensional representation of the first derivative (rate of change) of temperature;

[0095] Channel 3: Two-dimensional representation of the second derivative (acceleration rate) of temperature;

[0096] This multi-channel design can capture various features during the temperature change process and improve the recognition ability of the model. A more reasonable mathematical expression should be adopted for the processing of the temperature curve:

[0097] ,

[0098] Where: is the temperature value at time in °C is the reference temperature, in °C, is the amplitude of the th harmonic component, in °C, is the th harmonic component's angular frequency, in rad / s, is the th harmonic component's phase, in rad, is the number of harmonic components. Generally, taking 5 - 10 components can well fit the actual temperature curve.

[0099] This infrared detection and analysis method based on neural network has higher accuracy and self - adaptability compared with traditional methods. It can adapt to the detection needs of different types of asphalt, providing a reliable basis for optimizing the modifier addition scheme. By recording and sharing detection data through blockchain technology, the transparency of the detection process and the traceability of results are realized, effectively improving the quality management level of asphalt pavement construction.

[0100] The data storage process of the paver construction process in the present invention mainly includes the following steps:

[0101] First, encrypt and store the GPS trajectory information during the paver construction process. GPS data includes information such as longitude, latitude, altitude, speed, direction, and time, with a collection frequency of 1 time per second. The encryption uses the RSA - 2048 algorithm to ensure the security of data during transmission and storage. The storage process adopts distributed storage technology to improve the fault tolerance and reliability of the system.

[0102] Second, encrypt and store the paving temperature field thermal image, paving temperature trajectory coordinates x and y, paving temperature trajectory data z, and paving temperature and humidity together to the blockchain through the chain code layer 13. The paving temperature field thermal image is obtained by infrared imaging technology, with a resolution of 640×480 pixels, a temperature accuracy of ±0.5°C, and a collection frequency of 1 time per 10 seconds. The paving temperature trajectory coordinates x, y, and data z constitute a three - dimensional temperature distribution map, which can visually display the construction quality.

[0103] Finally, broadcast and confirm all nodes through the consensus layer 12 to ensure the immutability of data. The broadcast uses the improved Practical Byzantine Fault Tolerance (PBFT) algorithm. When more than two - thirds of the nodes confirm, the data is considered valid and recorded on the blockchain.

[0104] In the preferred embodiment of the present invention, the data storage process further includes a data compression and backup mechanism. For large - capacity data (such as temperature field thermal images), a lossless compression algorithm is used for compression, and the compression rate can reach more than 60%. At the same time, a multi - level backup mechanism is established, including local backup, remote backup, and blockchain backup, to ensure the security and recoverability of data.

[0105] In addition, the present invention also adopts a data hierarchical storage strategy. For data with high access frequency (such as construction data in the recent 7 days), it is stored in the cache; for data with medium access frequency (such as construction data in the recent 30 days), it is stored in the main storage system; for historical data with low access frequency, it is stored in the archival system. This hierarchical storage strategy effectively improves the response speed and storage efficiency of the system.

[0106] Refer to Figure 6 , the process of tracing the construction quality of the asphalt pavement of the present invention mainly includes the following steps:

[0107] First, the paving temperature field thermal image is uploaded to the intelligent contract layer 11 through the interface unit 21 of the access layer 2. The thermal image acquisition device uses a high-precision infrared thermal imager with a resolution of 640×480 pixels and a collection frequency of 1 time per 10 seconds. The upload process uses a secure transmission protocol (such as HTTPS) to ensure the security of data transmission.

[0108] Secondly, the data information is synchronized to the data traceability module through the link layer. The synchronization process uses blockchain technology to ensure the consistency and reliability of the data. The data traceability module can access all historical data on the blockchain and supports multi-dimensional queries and analyses.

[0109] The three-dimensional modeling technology of the traceability module can adopt a multi-scale progressive modeling method, and automatically adjust the model accuracy and expression according to the quality assessment requirements of different levels:

[0110] Macro level (kilometer level): A simplified model is adopted to mainly show the overall quality distribution trend;

[0111] Medium level (hundred-meter level): A medium-precision model is adopted to show the quality characteristics of the section;

[0112] Micro level (meter level): A high-precision model is adopted to show the local quality details;

[0113] The models of each level can show various quality attributes such as temperature, density, and flatness, and users can switch and combine the displays according to needs. This multi-scale modeling technology makes quality traceability more intuitive and efficient.

[0114] Thirdly, coordinate transformation is performed on the GPS device of the paver. The original GPS coordinates usually adopt the WGS84 coordinate system and need to be converted to the local engineering coordinate system. The coordinate transformation adopts the seven-parameter transformation method, and the transformation accuracy is better than 5 cm. The trajectory data after coordinate transformation is corrected, and the correction contents include abnormal point filtering, data smoothing, and interpolation supplementation, etc.

[0115] Finally, using 3D modeling technology, the final trajectory points and coordinate heights are modeled in 3D to obtain a 3D traceability map of the construction quality of the asphalt pavement. The 3D modeling uses a triangular mesh model with a mesh accuracy of up to 10 cm × 10 cm. The model supports multi-view viewing, zooming, and slicing analysis, facilitating users to intuitively understand the construction quality situation.

[0116] In specific implementation, the coordinate transformation uses the following formula:

[0117] ,

[0118] where, is the transformed coordinate with the unit of m, is the original coordinate with the unit of m, is the translation parameter with the unit of m, is the scale factor, dimensionless, representing the scale difference between the two coordinate systems, is the rotation matrix, determined by three rotation angles 、 and .

[0119] The rotation matrix has the complete expression as:

[0120] ,

[0121] ,

[0122] where, is the rotation angle around the X-axis with the unit of rad, is the rotation angle around the Y-axis with the unit of rad, is the rotation angle around the Z-axis with the unit of rad. The coordinate transformation model completely includes seven parameters: three translation parameters 、 、 , three rotation parameters 、 、 , and a scale parameter . Only in this way can the transformation relationship between the two 3D coordinate systems be accurately described.

[0123] In the construction of asphalt pavement, accurate trajectory point coordinates are crucial for quality control. Direct application of traditional GPS data in construction management has problems such as inconsistent coordinate systems and insufficient accuracy. Through coordinate transformation and data correction, the present invention converts GPS trajectory data into standard engineering coordinates and combines them with elevation data to form a 3D construction trajectory model. This model is fused with temperature field data to generate an intuitive 3D quality traceability map, making the spatial distribution of construction quality clear at a glance and facilitating quality assessment and problem location.

[0124] For different projects, the coordinate transformation parameters need to be calibrated according to the actual situation. The calibration process usually adopts the control point method, that is, several control points with known coordinates are set within the project area, usually 4 - 6, and the distribution should evenly cover the entire project area. The WGS84 coordinates of the control points are obtained through GPS measurement, and then compared with the known project coordinates to calculate the conversion parameters. The conversion accuracy is usually required to be better than 5 cm to meet the needs of construction quality control.

[0125] The three-dimensional modeling process adopts the multi-level detail (LOD) technology, which dynamically adjusts the model accuracy according to the user's viewing distance. When viewing closely, a high-precision model is displayed (such as a grid size of 10 cm × 10 cm), and when viewing from a distance, the model accuracy is reduced (such as a grid size of 1 m × 1 m) to improve the system response speed and user experience. At the same time, the model supports the visual expression of various attributes such as temperature, density, and flatness, and users can select different attributes for display according to their needs to comprehensively understand the construction quality situation.

[0126] Refer to Figure 7 , the blockchain traceability method for asphalt pavement construction quality based on the above system mainly includes the following steps:

[0127] First, the consortium chain layer 1 realizes data encryption and consensus through the smart contract layer 11, the consensus layer 12, and the chain code layer 13. Data encryption uses algorithms such as AES-256 and RSA-2048 to ensure data security. The consensus mechanism adopts the improved Practical Byzantine Fault Tolerance (PBFT) algorithm to improve the system throughput and fault tolerance.

[0128] In addition to the improved PBFT algorithm mentioned above, the system can also introduce a reputation evaluation system in the consensus mechanism to evaluate the historical behavior of participating nodes and dynamically adjust the node weights according to the reputation values. This reputation-based consensus mechanism can further improve the security and efficiency of the system.

[0129] The reputation value calculation formula can be expressed as:

[0130] ,

[0131] Among them, is the current reputation value of node i, dimensionless, with a value range of [0, 1], is the historical reputation value of node i, dimensionless, with a value range of [0, 1], is the number of successful consensus times of node i, is the total number of times node i participates in consensus, is the proportion of valid data provided by node i, with a value range of [0, 1], is the number of abnormal behavior times of node i, , , , are weight coefficients, satisfying ,

[0132] Secondly, through the access layer 2, the data effectively interacts with external data and internal data through the interface unit 21. The interface unit 21 supports multiple data formats and communication protocols, including HTTP / HTTPS, WebSocket, MQTT, etc., to adapt to the access requirements of different devices and systems.

[0133] Thirdly, through the application layer 3, the data is processed through the traceability module 31, the intelligent optimization module 32, and the detection module 33. The traceability module 31 processes the paving temperature GPS trajectory data and the thermal image of the paving temperature field to realize the visual expression of the construction quality; the intelligent optimization module 32 extracts the features of the thermal image of the paving temperature field and recommends the best modifier addition scheme based on the reinforcement learning technology; the detection module 33 extracts the data information related to the asphalt softening point to provide a basis for quality control.

[0134] Finally, the processed data is stored in the blockchain traceability database 34 through the chain code layer 13, and system services are provided through the server 35 to realize the visualization and traceability of the construction quality of the asphalt pavement. The server 35 supports access from multiple terminals, including the PC terminal, the mobile terminal, and the Web terminal, to meet the usage needs of different users.

[0135] In a preferred embodiment of the present invention, the method further includes a data analysis and early warning function. The system analyzes the historical data, establishes a quality assessment model, and realizes the real-time assessment and early warning of the construction quality. When quality anomalies are detected, the system automatically sends early warning information and provides treatment suggestions to help users take timely measures to avoid the expansion of quality problems.

[0136] In addition, the present invention also supports multi-level permission management and a data sharing mechanism. According to the user roles and permissions, the system provides different levels of data access and operation permissions. At the same time, through blockchain technology, the secure sharing of multi-party data is realized, breaking the information silos and improving the construction collaboration efficiency and quality management level.

[0137] The blockchain traceability system for the construction quality of the asphalt pavement of the present invention has a remarkable application effect in actual projects. Taking an asphalt pavement construction project of a certain expressway as an example, after adopting this system, the authenticity and integrity of the construction quality data records have been significantly improved, and the problems of data tampering and loss have been effectively solved.

[0138] In terms of optimizing the modifier addition plan, the intelligent optimization module based on reinforcement learning in the system has successfully controlled the softening point of asphalt within the target range (53 ± 2 °C), with an optimization rate of over 95%. This represents a significant improvement compared to the traditional empirical method (controlled within 53 ± 5 °C, with an optimization rate of approximately 70%). This precise control effectively enhances the durability and rutting resistance of asphalt pavements.

[0139] In terms of tracing the construction quality, the system has achieved full-process and multi-dimensional quality tracing, with a tracing accuracy of up to the meter level and a time accuracy of up to the second level. When quality problems are detected, the location, time, and cause of the problems can be quickly located, providing a reliable basis for quality improvement and liability determination.

[0140] In terms of multi-party collaboration, the system has achieved data sharing and collaboration among multiple parties such as the construction unit, supervision unit, and owner unit through blockchain technology, reducing communication costs and information asymmetry problems, and improving construction efficiency and management transparency.

[0141] In summary, the blockchain traceability system and method for asphalt pavement construction quality provided by the present invention have achieved trustworthy recording and full-process traceability of construction quality data through blockchain technology, and improved the construction quality control level through intelligent analysis and optimization technology, providing an innovative solution for asphalt pavement construction quality management.

[0142] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various changes and modifications can be made to the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. Asphalt pavement construction quality blockchain traceability system, characterized in that, Including: The consortium blockchain layer, including the smart contract layer, the consensus layer, and the chain code layer; among which, The smart contract layer is used to process the whole-process data of asphalt pavement construction by using encryption technology, and process the data information by using the underlying blockchain technology to obtain block data, and automatically execute the smart contract and transaction processing functions; The consensus layer adopts the improved Practical Byzantine Fault Tolerance (PBFT) algorithm to broadcast the block header of the block data, request other nodes to confirm the record result of the block, realize the consensus of the data, and selectively synchronize the data based on the Byzantine fault tolerance mechanism; The chain code layer is used to store the stored block data in the smart contract layer, realize the system business logic function, and upload the information after processing the data to the access layer; The access layer includes an interface unit; among which, the interface unit is used to provide a data call interface for the interaction between external data and internal system data; The application layer includes a traceability module, an intelligent optimization module, a detection module, a blockchain traceability database, and a server; among which, The traceability module is used to store the working parameters of the paver equipment during operation, including the processing of paving temperature GPS trajectory data, the processing of paving temperature field thermal images, the extraction of paving data, and the three-dimensional construction quality traceability; The intelligent optimization module is used to extract the image features of the paving temperature field thermal image, the working parameters of the compaction equipment, and the paving GPS trajectory information, recommend the best modifier addition scheme based on reinforcement learning, and upload the data information to the chain code layer, and synchronize the data to other nodes through the consortium blockchain for recording to achieve multi-party sharing; The detection module is used to extract the data information related to the asphalt softening point, record it in the chain code layer, and synchronize the data through the consortium blockchain to provide a reference for the quality control of the paving equipment; The blockchain traceability database is used to store blockchain data; The server is used to provide system services; The process of the intelligent optimization module includes: extracting the image features of the paving temperature field thermal image, the working parameters of the compaction equipment, and the paving GPS trajectory information; dividing the asphalt pavement construction process into two cases. Case 1: When it is detected by infrared that the current asphalt softening point has reached but not reached the standard, increase the modifier metering pump frequency to the maximum value, continue to stir for 15s, and then upload the collected data to the chain code layer, and upload it to the smart contract layer through the interface unit of the access layer, and complete the on-chain synchronization after consensus by the consensus layer. Case 2: When it is detected by infrared that the current asphalt softening point has reached the standard, set the modifier metering pump frequency to the current frequency for normal mixing, and upload the data record to the chain code layer.

2. The blockchain traceability system for asphalt pavement construction quality according to claim 1, wherein The system also includes a front-end APP and a background management subsystem.

3. The asphalt pavement construction quality blockchain traceability system according to claim 1, characterized in that, The described block data includes a block data header and a block data body. The block data header includes the block height, version, hash value of the previous block, Merkle root, timestamp, difficulty, nonce, and hash value. The block data body includes a paving temperature field thermal image, block ID, timestamp, paver GPS trajectory, paving temperature trajectory coordinates x and y, paving temperature trajectory data z, paving temperature and humidity, infrared spectrum, asphalt gradation, as well as the type of modifier and metering pump frequency.

4. The blockchain traceability system for the construction quality of asphalt pavement according to claim 1, characterized in that, The working process of the smart contract layer includes: encrypting and compressing raw materials, construction process data, inspection data, and paver construction trajectory data through the smart contract of blockchain technology, and automatically executing the smart contract and transaction processing functions. The smart contract layer stores the stored block data in the chain code layer, realizes the system business logic function, and uploads the information after processing the data to the access layer; extracts the features of the paving temperature field thermal image through the smart contract layer, stores it in the blockchain, and calls the data on the chain, and combines the actual construction conditions for three-dimensional construction quality traceability to realize the visualization and traceability of the construction quality of asphalt pavement.

5. The asphalt pavement construction quality blockchain traceability system according to claim 1, wherein The detection module detects the softening point of asphalt, including: using infrared spectrum technology to detect the asphalt temperature curve to obtain detection data, storing the detection data in the chain code layer, encrypting and compressing the data through the smart contract of blockchain technology, calling the detection data on the chain through the chain code layer, and completing the data uploading to the chain based on the blockchain traceability technology.

6. The asphalt pavement construction quality blockchain traceability system according to claim 5, wherein The infrared detection and analysis process of the detection data in the detection module includes: in the mixing plant laboratory, performing infrared spectrum tests on asphalt raw materials to obtain temperature parameters, and establishing an asphalt softening point fitting function based on neural network technology; calculating the characteristic values of the temperature curve, including the maximum value of the temperature curve, the area enclosed by the temperature curve and the X-axis, and the number of periods of the temperature curve. Based on the characteristic values of the temperature curve, calculate the difference between the detection data and the asphalt softening point through a convolutional neural network, and upload the difference calculation result to the chain code layer.

7. The asphalt pavement construction quality blockchain traceability system according to claim 1, characterized in that, The data storage process during the paver construction process includes: encrypting and storing the GPS trajectory information during the paver construction process; encrypting and storing the paving temperature field thermal image, paving temperature trajectory coordinates x and y, paving temperature trajectory data z, and paving temperature and humidity together through the chain code layer in the blockchain, and broadcasting and confirming to all nodes through the consensus layer to ensure the immutability of the data.

8. The asphalt pavement construction quality blockchain traceability system according to claim 1, characterized in that, The process of tracing the construction quality of asphalt pavement includes: uploading the paving temperature field thermal image through the interface unit of the access layer to the smart contract layer, and synchronizing the data information to the data traceability module through the link layer; performing coordinate transformation on the paver GPS device, correcting the trajectory data after coordinate transformation to obtain the final trajectory points, and using three-dimensional modeling technology to perform three-dimensional modeling on the final trajectory points and the coordinate height together to obtain a three-dimensional traceability map of the construction quality of asphalt pavement.

9. The blockchain traceability method for the construction quality of asphalt pavement, which adopts the blockchain traceability system for the construction quality of asphalt pavement described in any one of claims 1-8, is characterized in that The method includes: Implementing data encryption and consensus for the consortium chain through the smart contract layer, the consensus layer, and the chain code layer; Through the access layer, data effectively interacts with external data and internal data through the interface unit; Through the application layer, data is processed through the traceability module, the intelligent optimization module, and the detection module. Among them, the traceability module processes paving temperature GPS trajectory data and paving temperature field thermal images, the intelligent optimization module extracts features from the paving temperature field thermal images and recommends the best modifier addition scheme, and the detection module extracts relevant data information on asphalt softening point; The processed data is stored in the blockchain traceability database through the chain code layer, and system services are provided through the server to achieve visualization and traceability of the construction quality of asphalt pavements.

Images