Road construction equipment scheduling method and system based on block chain
By generating optimized scheduling schemes through blockchain technology and adaptive multi-objective analysis algorithms, the problems of insufficient data authenticity and adaptability in traditional construction equipment scheduling are solved, realizing efficient and accurate scheduling and dynamic adjustment of construction equipment, and improving the controllability and safety of construction progress.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-20
- Publication Date
- 2026-03-27
AI Technical Summary
Traditional construction equipment scheduling relies on centralized databases, and the accuracy of the data depends on human reporting. It lacks adaptive capabilities, leading to inaccurate scheduling decisions, idle equipment, wasted resources, and project delays. It is unable to effectively cope with real-time changes at the construction site.
The system uses blockchain technology to collect equipment data and encrypts it on the chain. It then combines this data with an adaptive multi-objective analysis algorithm to generate an optimized scheduling scheme. The scheme is automatically executed and adjusted through smart contracts, and progress and position deviations are monitored in real time to dynamically optimize equipment scheduling.
It improves the accuracy and efficiency of construction equipment scheduling, ensures maximum equipment utilization, enables rapid response to complex construction site environments, reduces human intervention and errors, and ensures the efficient execution of construction tasks.
Smart Images
Figure CN121745540A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of road construction, in particular to a road construction equipment scheduling method and system based on a blockchain. BACKGROUND
[0002] Road construction equipment refers to various mechanical equipment used in road construction, maintenance and repair processes, such as bulldozers, road rollers, excavators, pavers, etc. Road construction equipment undertakes different construction tasks, such as earthwork, pavement paving, compaction, etc., and is the key to ensuring construction progress and quality.
[0003] In order to efficiently and reasonably allocate and use road construction equipment, ensure maximum equipment utilization, timely task completion and quality standards during construction, scheduling is necessary due to the variety of equipment and heavy tasks in the construction process. If not properly scheduled, it may lead to equipment idling, task delays, resource waste, etc., thereby affecting construction progress, cost and overall project quality.
[0004] Traditional construction equipment scheduling often relies on centralized databases, and the authenticity of the data depends on human reporting or a single source, which leads to inaccurate scheduling decisions, low safety, and ineffective traceability. In addition, equipment is scheduled based on static rules or pre-designed plans, lacking self-adaptability, and cannot be flexibly adjusted in the face of real-time changes in the construction site (such as traffic congestion, equipment failure, etc.), leading to equipment idling, resource waste or project delays, low scheduling efficiency and accuracy. SUMMARY
[0005] To solve this, the present application provides a road construction equipment scheduling method and system based on a blockchain.
[0006] In a first aspect, the present application provides a road construction equipment scheduling method based on a blockchain, which comprises the following steps: S1, collecting the running state, geographical position and component life data of each construction equipment, and encrypting the data for chaining to obtain a blockchain digital mirror; S2, based on the blockchain digital mirror, using an adaptive multi-objective analysis algorithm to analyze the correlation between equipment utilization and construction progress, and generating an optimized scheduling scheme by simulating the effects of different scheduling schemes; S3, converting the optimized scheduling scheme into a smart contract, and automatically triggering and executing equipment scheduling and transportation task assignment when the preset construction conditions are met; S4, automatically comparing the optimized scheduling scheme with the actual execution data recorded in the blockchain digital mirror in the smart contract to identify progress deviation or position deviation; S5. Based on the identified progress deviation or position deviation, re-execute step S2, generate a new optimized scheduling scheme, and then drive the smart contract to execute the new optimized scheduling scheme.
[0007] Optionally, data on the operating status, geographical location, and component lifespan of each construction piece of equipment are collected and encrypted and uploaded to the blockchain to obtain a blockchain digital image, including the following steps: S11. Pre-deploy positioning, status monitoring, and component life sensors on the construction equipment to collect the equipment's geographical location, operating parameters, and health status data, and send them to the edge gateway; S12. The edge gateway formats the geographic location, operating parameters and health status data, encapsulates them into a standard data packet with a timestamp and device ID, and digitally signs the standard data packet with a private key. S13. Transmit the signed standard data packet to the blockchain node server through an encrypted channel; S14. The node server calls the smart contract to construct the core information of the standard data packet into an on-chain transaction and submits it to the blockchain network. S15. The smart contract automatically verifies the digital signature and submitter's permissions on the chain. After verification, the data hash is written into a new block. S16. The transactions confirmed through the consensus mechanism are packaged into a new block, which is then added to the chain and together they form a digital image of the blockchain.
[0008] Optionally, the smart contract automatically verifies the digital signature and submitter's permissions on-chain. After successful verification, the data hash is written to a new block, including the following steps: S151. After receiving a transaction request, the smart contract verifies the submitter's identity and operating permissions, and confirms whether the data is qualified to be uploaded to the blockchain. S152. After the identity and operation permission verification is passed, the smart contract performs digital signature verification on the data packet to confirm that the data remains intact during the transmission process. S153. After completing the digital signature verification, the smart contract extracts key information from the data packet and generates the corresponding data hash fingerprint. S154. Store the generated data hash fingerprint and related transaction information in the blockchain state database, and record the transactions on the blockchain.
[0009] Optionally, based on blockchain digital mirroring, an adaptive multi-objective analysis algorithm is used to analyze the correlation between equipment utilization and construction progress. The process of generating an optimized scheduling scheme by simulating the effects of different scheduling plans includes the following steps: S21. Obtain the geographical location, real-time status and construction progress plan of the equipment in the blockchain digital image, construct a topology network including equipment nodes, construction sites and transportation routes, and based on the topology network, initialize the multi-objective pheromone matrix required for multi-objective optimization and set adaptive parameters. S22. During the iterative optimization process, the search agent selects a path in the topology network based on dynamically adjusted heuristic rules, evaluates multiple objectives simultaneously through a multi-objective pheromone matrix, and integrates traffic status data from the blockchain in real time to update path weights and pheromone distribution. S23. Based on the reinforcement learning mechanism, the convergence state of the population and the quality of the Pareto solution set are monitored after each iteration, the adaptive parameters are dynamically adjusted, and the global optimization behavior is automatically executed when an emergency scheduling requirement is identified. S24. Evaluate the non-dominated solution set generated after multiple rounds of iterative optimization in multiple dimensions, output a Pareto optimal scheduling scheme set including trade-off analysis, and write the performance index and execution logic of the final scheme selected by decision into the blockchain smart contract. S25. Based on the historical implementation effects of the scheme recorded in the blockchain digital mirror, optimize the heuristic rules and multi-objective weight configuration through a feedback loop mechanism.
[0010] Optionally, during the iterative optimization process, the search agent selects paths in the topology network based on dynamically adjusted heuristic rules, simultaneously evaluates multiple objectives through a multi-objective pheromone matrix, and integrates traffic state data from the blockchain in real time to update path weights and pheromone distribution, including the following steps: S221. At the beginning of each iteration, load the currently dynamically adjusted heuristic rules for all search agents, and query and obtain the real-time traffic status data of all relevant path nodes in the current topology network from the blockchain digital mirror. S222. Each search agent selects and moves through the topology network step by step based on heuristic rules and real-time traffic status data to construct a complete candidate transportation path. S223. Based on the multi-objective pheromone matrix and real-time traffic data, calculate the multi-objective evaluation score of the candidate transportation path, and locally update the pheromone concentration on each path segment included in the candidate transportation path according to the multi-objective evaluation score. S224. After all search agents have completed the path construction for this iteration, the path weights of the topology network are updated globally based on all paths generated in this iteration and the evaluation results.
[0011] Optionally, based on the multi-objective pheromone matrix and real-time traffic data, the multi-objective evaluation score of the candidate transportation path is calculated. The pheromone concentration on each path segment of the candidate transportation path is then locally updated according to the multi-objective evaluation score, including the following steps: S2231. For a candidate transportation route, the historical experience values and real-time traffic data stored in the multi-objective pheromone matrix are comprehensively called to calculate the target values of the candidate transportation route in multiple optimization objectives, including time, cost and equipment loss, and the target values are normalized. S2232. The normalized target values are weighted and summed according to the preset weights to obtain the multi-target evaluation score of the candidate transportation path. S2233. Based on the multi-objective evaluation score of the path, calculate the pheromone increment proportionally, and add the pheromone increment to the current pheromone concentration of each path segment contained in the path to complete the local update.
[0012] Optionally, based on the reinforcement learning mechanism, the convergence state of the population and the quality of the Pareto solution set are monitored after each iteration, adaptive parameters are dynamically adjusted, and when an urgent scheduling need is identified, global optimization behavior is automatically executed, including the following steps: S231. After each iteration, calculate the convergence of the population, the distribution and breadth of the Pareto solution set, and generate a feature vector describing the current search state. S232. The reinforcement learning agent receives the generated feature vector, analyzes the current search state, outputs a decision action, and dynamically adjusts the adaptive parameters based on the decision result. S233. Continuously monitor external inputs. When a preset emergency dispatch demand signal is detected, immediately interrupt the current adaptive parameter adjustment process and issue a global optimization command. S234. Upon receiving the global optimization command, reset the current search state and switch to emergency search mode to automatically execute the global optimization behavior.
[0013] Optionally, automatically comparing and optimizing the scheduling scheme in the smart contract with the actual execution data recorded in the blockchain digital mirror to identify progress deviations or position deviations includes the following steps: S41. Simultaneously query the blockchain digital image and smart contract to obtain the verified actual execution data of the device and the currently effective optimization scheduling scheme, and integrate them into a benchmark dataset to be compared. S42. Based on the benchmark dataset, call the progress comparison logic to calculate the numerical difference between the actual progress and the planned progress, and directly determine whether there is a progress deviation based on the preset threshold. S43. Based on the benchmark dataset, call the location comparison logic to detect whether the actual location of the device exceeds the planned geofence, and directly determine whether there is a location deviation according to the preset tolerance range. S44. Judgment results of polymerization progress deviation and position deviation.
[0014] Secondly, this application also provides a blockchain-based road construction equipment scheduling system, which includes: The equipment data on-chain module collects the operating status, geographical location, and component lifespan data of each construction piece of equipment, and encrypts and uploads them to the blockchain to obtain a blockchain digital image; The intelligent optimization analysis module, based on blockchain digital mirroring, uses an adaptive multi-objective analysis algorithm to analyze the correlation between equipment utilization and construction progress, and generates an optimized scheduling scheme by simulating the effects of different scheduling schemes. The automatic contract execution module transforms the optimized scheduling scheme into a smart contract, which automatically triggers and executes equipment scheduling and transportation task assignment when the preset construction conditions are met. The execution deviation monitoring module automatically compares the optimized scheduling scheme in the smart contract with the actual execution data recorded in the blockchain digital mirror to identify progress deviations or position deviations. The closed-loop module is dynamically adjusted. Based on the identified progress or position deviations, the intelligent optimization analysis module is re-executed, and a new optimized scheduling scheme is generated. Then, the smart contract is driven to execute the new optimized scheduling scheme.
[0015] In summary, this application includes at least one of the following beneficial technical effects: 1. This application collects equipment data in real time and encrypts and uploads it to the blockchain to ensure data security. It optimizes the automatic generation and execution of scheduling schemes and dynamically adjusts the schemes to cope with progress and location deviations, thereby improving scheduling efficiency and controllability of construction progress, reducing the possibility of human intervention and errors, and ensuring efficient execution and real-time feedback of construction tasks.
[0016] 2. This application encrypts and stores the operating status, geographical location, and component lifespan data of construction equipment on the blockchain, and uses smart contracts to automatically verify the authenticity and integrity of the data, ensuring the security, immutability, and transparency of the data, effectively improving the accuracy and trustworthiness of construction equipment scheduling, and enhancing security.
[0017] 3. This application dynamically adjusts the scheduling scheme in each iteration to ensure maximum equipment utilization and construction progress. At the same time, the reinforcement learning mechanism can quickly adjust the optimization strategy and automatically perform global optimization when emergency scheduling needs arise, effectively coping with complex and dynamic construction site environments and improving scheduling efficiency and accuracy. Attached Figure Description
[0018] Figure 1 This is a flowchart of the method in this application. Detailed Implementation
[0019] The embodiments of this application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.
[0020] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0021] The first embodiment of this application discloses a blockchain-based road construction equipment scheduling method, referencing... Figure 1 The road construction equipment scheduling method includes the following steps: S1. Collect the operating status, geographical location, and component lifespan data of each construction equipment, and encrypt and upload them to the blockchain to obtain a blockchain digital image.
[0022] Preferably, the process of collecting data on the operating status, geographical location, and component lifespan of each construction device, and encrypting and uploading this data to the blockchain to obtain a blockchain digital image includes the following steps: S11. Pre-deploy positioning, status monitoring, and component life sensors on the construction equipment to collect the equipment's geographical location, operating parameters, and health status data, and send them to the edge gateway.
[0023] S12. The edge gateway formats the geographic location, operating parameters and health status data, encapsulates them into standard data packets with timestamps and device IDs, and digitally signs the standard data packets using a private key.
[0024] S13. Transmit the signed standard data packet to the blockchain node server through an encrypted channel.
[0025] S14. The node server calls the smart contract to construct the core information of the standard data packet into an on-chain transaction and submits it to the blockchain network.
[0026] It should be explained that the sensors pre-deployed on the construction equipment include positioning sensors, condition monitoring sensors, and component life sensors; Among them, the positioning sensor is used to obtain the real-time geographical location of the equipment, ensuring that the location of the equipment in the construction area can be tracked. Condition monitoring sensors: used to monitor the operating parameters of equipment, such as speed, power consumption, temperature, pressure, etc., which helps to assess the working status of the equipment.
[0027] Component life sensors: used to track the health status of various components of equipment, such as the wear and tear of engines, hydraulic systems, transmission systems, etc., thereby assessing the remaining service life of the equipment; After receiving the raw data sent by the device, the edge gateway needs to format the data to conform to the standard data format. The edge gateway then encapsulates the formatted data into a standard data packet. Timestamp: Records the time of data collection to ensure the timeliness and order of the data; Device ID: Used to uniquely identify a device, ensuring that transmitted data corresponds to a specific device; The signed data packet will be transmitted to the blockchain node server through an encrypted channel. The encrypted channel ensures that the data will not be stolen or tampered with during transmission, thus protecting the privacy and security of the data.
[0028] Blockchain node servers extract core information (such as device ID, timestamp, geographical location, health status, etc.) from standard data packets by calling smart contracts and transform it into an on-chain transaction. On-chain transaction does not refer to a traditional financial transaction, but rather to recording device data into the blockchain as a transaction. This is an immutable record that ensures the authenticity and trustworthiness of the data. The constructed transaction will be submitted to the blockchain network, and after the data enters the blockchain, it will be verified and stored by multiple nodes.
[0029] S15. The smart contract automatically verifies the digital signature and submitter's permissions on the chain. After successful verification, the data hash is written into a new block.
[0030] Preferably, the smart contract automatically verifies the digital signature and submitter's permissions on-chain. After successful verification, the data hash is written to a new block, including the following steps: S151. After receiving a transaction request, the smart contract verifies the submitter's identity and operating permissions, and confirms whether the data is qualified to be uploaded to the blockchain. S152. After the identity and operation permission verification is passed, the smart contract performs digital signature verification on the data packet to confirm that the data remains intact during the transmission process. S153. After completing the digital signature verification, the smart contract extracts key information from the data packet and generates the corresponding data hash fingerprint. S154. Store the generated data hash fingerprint and related transaction information in the blockchain state database, and record the transactions on the blockchain.
[0031] It should be explained that smart contracts wait to receive transaction requests from external parties on the blockchain network. Typically, transaction requests may involve the submission, modification, or deletion of device data. Upon receiving a transaction request, the smart contract first needs to verify the identity of the submitter and their operating permissions to ensure that only authorized users (such as device owners, administrators, certified service providers, etc.) can submit transaction requests. Authentication: Verify the submitter's identity through digital certificates, private key signing, or other authentication mechanisms; Permission verification: In addition to identity verification, smart contracts also need to check whether the submitter has sufficient operating permissions, such as whether they have the authority to submit device data to the blockchain. After verifying identity and permissions, the smart contract also needs to confirm whether the submitter is qualified to put the data on the blockchain; for example, the data must meet certain standards or its source must be verified before it can be submitted to the blockchain. Once identity and authorization verification is successful, the smart contract will digitally sign the data packet. The digital signature is usually generated using a private key when the data packet is signed by a device or other entity to ensure that the data has not been tampered with. A hash fingerprint is a fixed-length byte string generated by a hash algorithm (such as SHA-256). It is a unique identifier for data and can ensure that data is uniquely identified on the blockchain. Through hash fingerprints, smart contracts can ensure the uniqueness of data content and prevent data tampering. Any small change will cause a change in the hash value, thus allowing the detection of whether the data has changed. S16. The transactions confirmed through the consensus mechanism are packaged into a new block, which is then added to the chain and together they form a digital image of the blockchain.
[0032] It needs to be explained that smart contracts submit transaction information and data hash fingerprints to the blockchain network. After submission, nodes in the blockchain network will verify and confirm the transaction and record it in a block. Once the transaction is successfully packaged into a block and confirmed by the blockchain network, the transaction becomes an immutable part of the blockchain, and anyone can view and verify the transaction.
[0033] S2. Based on blockchain digital mirroring, an adaptive multi-objective analysis algorithm is used to analyze the correlation between equipment utilization and construction progress. By simulating the effects of different scheduling schemes, an optimized scheduling scheme is generated.
[0034] Preferably, based on blockchain digital mirroring, an adaptive multi-objective analysis algorithm is used to analyze the correlation between equipment utilization and construction progress. The process of generating an optimized scheduling scheme by simulating the effects of different scheduling schemes includes the following steps: S21. Obtain the geographical location, real-time status and construction progress plan of the equipment in the blockchain digital image, construct a topology network including equipment nodes, construction sites and transportation routes, and based on the topology network, initialize the multi-objective pheromone matrix required for multi-objective optimization and set adaptive parameters.
[0035] It should be noted that the constructed topology network includes the following nodes and paths: 1. Equipment Nodes: Each piece of construction equipment, sensor, or other critical equipment acts as a node in the network. These nodes will store real-time data about the equipment (such as geographical location, status, etc.). 2. Construction site nodes: Construction sites or key work sites, which are the locations where tasks are performed during the construction process, and may include material storage, equipment maintenance, etc. 3. Transportation routes: Transportation routes from equipment or construction sites to other locations (such as material supply points, construction sites, etc.) to ensure that equipment routes can be planned and scheduled reasonably.
[0036] Pheromones refer to a certain marker on each node or path, which affects subsequent decisions. For example, the pheromone on a transportation path can indicate the quality of the path. The stronger the pheromone, the higher the efficiency of the path, and the more likely the equipment or transportation task is to choose this path.
[0037] The process of initializing a multi-objective pheromone matrix is to map the optimization requirements of different objectives (such as equipment scheduling, transportation routes, time schedules, etc.) into a matrix. Each element of the matrix represents the pheromone concentration of a certain objective under different constraints, that is, the direction or value of optimization. During the optimization process, some parameters (such as the evaporation rate of pheromones and the weight of path selection) need to be adjusted to cope with the constantly changing current state. For example, based on the actual situation during construction (such as weather, equipment failure, delays, etc.), the weight parameters in the objective function of the optimization algorithm need to be dynamically adjusted according to real-time data to ensure that multi-objective optimization can always adapt to the current construction environment and needs.
[0038] S22. During the iterative optimization process, the search agent selects a path in the topology network based on dynamically adjusted heuristic rules, simultaneously evaluates multiple objectives through a multi-objective pheromone matrix, and integrates traffic status data from the blockchain in real time to update path weights and pheromone distribution.
[0039] Preferably, during the iterative optimization process, the search agent selects paths in the topology network based on dynamically adjusted heuristic rules, simultaneously evaluates multiple objectives through a multi-objective pheromone matrix, and integrates traffic state data from the blockchain in real time to update path weights and pheromone distribution, including the following steps: S221. At the start of each iteration, load the currently dynamically adjusted heuristic rules for all search agents, and query and obtain the real-time traffic status data of all relevant path nodes in the current topology network from the blockchain digital mirror.
[0040] S222. Each search agent selects and moves through the topology network step by step based on heuristic rules and real-time traffic status data to construct a complete candidate transportation path.
[0041] S223. Based on the multi-objective pheromone matrix and real-time traffic data, calculate the multi-objective evaluation score of the candidate transportation path, and locally update the pheromone concentration on each path segment included in the candidate transportation path according to the multi-objective evaluation score.
[0042] Preferably, the multi-objective evaluation score of the candidate transportation path is calculated based on the multi-objective pheromone matrix and real-time traffic data. The pheromone concentration on each path segment of the candidate transportation path is then locally updated according to the multi-objective evaluation score, comprising the following steps: S2231. For a candidate transportation route, the historical experience values and real-time traffic data stored in the multi-objective pheromone matrix are comprehensively called to calculate the target values of the candidate transportation route in multiple optimization objectives, including time, cost and equipment loss, and the target values are normalized. S2232. The normalized target values are weighted and summed according to the preset weights to obtain the multi-target evaluation score of the candidate transportation path. S2233. Based on the multi-objective evaluation score of the path, calculate the pheromone increment proportionally, and add the pheromone increment to the current pheromone concentration of each path segment contained in the path to complete the local update.
[0043] It should be explained that heuristic rules are dynamically adjusted based on current construction needs and environment (such as traffic conditions, construction progress, etc.) to help search agents (such as simulated intelligent agents or ants in ant colony algorithms) select the optimal path or scheduling strategy; for example, the rules may prioritize paths with smooth traffic or schedule equipment based on the current health status of the equipment. Real-time data, such as traffic flow, congestion in construction areas, and equipment status, is extracted from the blockchain digital mirror. Real-time data is crucial for route selection because road construction is often affected by factors such as traffic flow, accidents, and equipment failures. The search agent selects suitable route segments based on heuristic rules and real-time traffic data (such as road conditions, construction progress, equipment availability, etc.). For example, if a route is deemed unsuitable due to traffic congestion, the agent will prioritize uncongested route segments. The agent gradually selects route segments until a complete candidate transportation route is formed. This route not only needs to consider time and cost but also optimize equipment usage and the scheduling of construction resources.
[0044] Specific examples are as follows: Assuming the candidate transport route is 50 kilometers long, traffic flow is part of real-time data, and road conditions can be smooth, congested, or moderate. For example, if traffic conditions are smooth and the equipment travels at a speed of 60 km / h, the formula for calculating transportation time is:
[0045] Assume that the transportation cost of the route includes fuel costs and labor costs; assume that the fuel cost is 2 yuan per kilometer and the labor cost is 50 yuan per hour. If the equipment's operating time is 0.833 hours, the formula for calculating the cost target is: Yuan Equipment loss may be related to the length of the route, the workload of the equipment, and the transportation time. Assuming that the equipment loses 1 hour of working time for every 100 kilometers traveled, the expression for the equipment loss target is:
[0046] Assuming that among all candidate routes, the minimum time is 0.5 hours and the maximum is 1 hour, the minimum cost is 100 yuan and the maximum is 200 yuan, and the minimum equipment loss is 0 hours and the maximum is 1 hour, then normalization is performed to obtain the transportation time. =0.667, cost target =0.4165, Equipment Loss Target =0.5; Each objective has a different impact on the final evaluation, so we calculate the total evaluation score by weighted summation, assuming that the weights of time, cost and equipment depreciation are w1=0.4, w2=0.4 and w3=0.2, respectively. Multi-objective assessment score The calculation formula is:
[0047] Substitute multi-objective assessment scores Calculations yielded =0.5334; In the formula, Weights indicating the transit time; Indicates the transit time; Indicates the weight of cost targets; Indicate cost target; The weight representing the equipment loss target; Indicates equipment wear and tear targets; Indicates multi-objective assessment score .
[0048] Based on the multi-objective evaluation score of the candidate path Calculate the pheromone increment and add the increment to the pheromone concentration of the path segment, assuming the pheromone increment proportional coefficient α is 0.1; Pheromones increment =0.05334; Assuming the original pheromone concentration of candidate path i is 0.2, the updated pheromone concentration is:
[0049] In the formula, This indicates the updated pheromone concentration; Indicates the original pheromone concentration; This indicates the pheromone increment.
[0050] Therefore, the updated pheromone concentration of candidate path i is 0.25334.
[0051] S224. After all search agents have completed the path construction for this iteration, the path weights of the topology network are updated globally based on all paths generated in this iteration and the evaluation results.
[0052] S23. Based on the reinforcement learning mechanism, the convergence state of the population and the quality of the Pareto solution set are monitored after each iteration, the adaptive parameters are dynamically adjusted, and the global optimization behavior is automatically executed when an emergency scheduling requirement is identified.
[0053] Preferably, based on the reinforcement learning mechanism, the convergence state of the population and the quality of the Pareto solution set are monitored after each iteration, adaptive parameters are dynamically adjusted, and global optimization behavior is automatically executed when an urgent scheduling need is identified, including the following steps: S231. After each iteration, calculate the convergence of the population, the distribution and breadth of the Pareto solution set, and generate a feature vector describing the current search state. S232. The reinforcement learning agent receives the generated feature vector, analyzes the current search state, outputs a decision action, and dynamically adjusts the adaptive parameters based on the decision result. S233. Continuously monitor external inputs. When a preset emergency dispatch demand signal is detected, immediately interrupt the current adaptive parameter adjustment process and issue a global optimization command. S234. Upon receiving the global optimization command, reset the current search state and switch to emergency search mode to automatically execute the global optimization behavior.
[0054] It needs to be explained that convergence refers to whether the current population has converged to a global optimum or a local optimum. Generally speaking, a high convergence rate means that the algorithm has found a relatively good solution. A population with a high convergence rate means that the fitness differences between individuals are small, tending towards a relatively stable solution. The expression for the convergence rate formula is:
[0055] In the formula, Indicates the degree of convergence; Indicates the total number of candidate paths; Indicates candidate paths; This indicates the fitness of the i-th candidate path; This represents the fitness of the globally optimal path.
[0056] The distributionality of the Pareto solution set measures whether the solutions at the Pareto front are uniformly distributed in the current population. A more uniform distribution means that the algorithm handles the trade-offs between different objectives well in the multi-objective space. The expression for the distributionality index is:
[0057] In the formula, It represents the distribution index. The higher the distribution, the more uniformly the solutions in the solution set are distributed in the target space. This indicates the number of solutions in the Pareto solution set, i.e., the total number of solutions in the solution set; Denotes the solutions in the Pareto solution set; Indicates the first The fitness value of a Pareto solution; Indicates the first The fitness value of a Pareto solution; This represents the maximum fitness of the current Pareto solution set; This represents the minimum fitness of the current Pareto solution set.
[0058] Breadth measures the coverage of the Pareto front, that is, how much of the target space the solution set covers. A solution set with greater breadth can better meet the requirements of different objectives. The expression for breadth is:
[0059] In the formula, Indicates breadth; This represents the maximum value of the objective function; This represents the minimum value of the objective function; This represents the maximum fitness of the current Pareto solution set; This represents the minimum fitness of the current Pareto solution set.
[0060] The reinforcement learning agent analyzes the current search state through the received feature vectors and outputs a decision action. The current search state is described by the feature vectors generated in the previous stage, which includes convergence, distribution, and breadth. The agent determines its action based on the current state through the policy function. The action can include adjusting the search strategy, selecting the search path, etc. Assuming that the action space is continuous, the agent will output a control signal to adjust the parameters of the search process.
[0061] Specific examples are as follows: Suppose that in one iteration of equipment scheduling, there are 5 candidate paths in the population, and their fitness (i.e., the transportation cost of the path) are as follows: Path 1: 200 yuan; Route 2: 210 yuan; Route 3: 205 yuan; Route 4: 215 yuan; Route 5: 220 yuan; Assuming the fitness (minimum cost) of the globally optimal path is 200 yuan, substituting it into the convergence calculation formula, we get... =10; Suppose the fitness of the five solutions in the Pareto solution set are as follows: Solution 1: 200 yuan; Solution 2: 210 yuan; Solution 3: 215 yuan; Solution 4: 220 yuan; Solution 5: 230 yuan; Calculate the distance between the solutions and normalize them to the range of the maximum and minimum values of the objective function. Assume the minimum value is 200 yuan and the maximum value is 230 yuan. Substitute these values into the distribution calculation to obtain... =0.25 Based on the maximum fitness (230 yuan) and minimum fitness (200 yuan) of the solution set, substituting them into the breadth-first search algorithm, we obtain... =1.
[0062] The goal of an agent is to optimize device scheduling by adjusting adaptive parameters. For example, an agent updates its policy using the Q-learning algorithm. Suppose that a reinforcement learning agent generates an action decision based on the current feature vector. Based on the feature vector, the agent updates the Q value to decide whether to adjust parameters (such as step size, exploration rate, etc.). Based on the decision result, the agent may choose to reduce the exploration rate and increase the probability of selecting the current optimal path.
[0063] In actual road construction, emergencies may occur, such as equipment failure, weather changes, or construction progress being ahead of schedule, requiring a rapid response in these emergencies: 1. External input monitoring: Continuously monitor data inputs at the construction site (such as equipment status monitoring, traffic conditions, etc.); when an emergency event is detected—equipment A needs to be replaced immediately due to failure—an emergency dispatch request signal is triggered. 2. Interrupt adaptive parameter adjustment: Once an emergency signal is detected, the current adaptive parameter adjustment is immediately stopped, and the strategy originally used to optimize equipment scheduling will be paused in order to adjust the scheduling target; 3. Issue a global optimization command: Issue a global optimization command to immediately begin a global optimization search for emergency dispatch needs, ensuring that faulty equipment is replaced in a timely manner and construction can continue.
[0064] S24. Perform multi-dimensional evaluation on the non-dominated solution set generated after multiple rounds of iterative optimization, output a Pareto optimal scheduling scheme set including trade-off analysis, and write the performance index and execution logic of the final scheme selected by decision into the blockchain smart contract.
[0065] S25. Based on the historical implementation effects of the scheme recorded in the blockchain digital mirror, optimize the heuristic rules and multi-objective weight configuration through a feedback loop mechanism.
[0066] S3. Transform the optimized scheduling scheme into a smart contract, which will automatically trigger and execute equipment scheduling and transportation task assignment when the preset construction conditions are met.
[0067] S4. Automatically compare and optimize the scheduling scheme in the smart contract with the actual execution data recorded in the blockchain digital mirror to identify progress deviations or position deviations.
[0068] Preferably, automatically comparing and optimizing the scheduling scheme in the smart contract with the actual execution data recorded in the blockchain digital mirror to identify progress deviations or position deviations includes the following steps: S41. Simultaneously query the blockchain digital image and smart contract to obtain the verified actual execution data of the device and the currently effective optimization scheduling scheme, and integrate them into a benchmark dataset to be compared. S42. Based on the benchmark dataset, call the progress comparison logic to calculate the numerical difference between the actual progress and the planned progress, and directly determine whether there is a progress deviation based on the preset threshold. S43. Based on the benchmark dataset, call the location comparison logic to detect whether the actual location of the device exceeds the planned geofence, and directly determine whether there is a location deviation according to the preset tolerance range. S44. Judgment results of polymerization progress deviation and position deviation.
[0069] S5. Based on the identified progress deviation or position deviation, re-execute step S2, generate a new optimized scheduling scheme, and then drive the smart contract to execute the new optimized scheduling scheme.
[0070] It should be explained that after the scheduling optimization is completed, the generated scheduling scheme will be encoded into a smart contract. The smart contract not only contains information such as the time, location, and equipment resource allocation of the scheduling task, but also embeds trigger conditions (such as time arrival, equipment idle time, etc.). When these conditions are met, the contract will be executed automatically to complete the issuance of equipment scheduling commands and the dispatch of transportation tasks. Smart contracts are not only responsible for the automatic execution of tasks, but also for verifying the execution status of the schedule. By automatically comparing the optimization plan with the actual execution records on the blockchain, they can determine whether there are scheduling deviations, mainly including progress deviations and position deviations. Once a progress or position deviation is identified, the scheduling optimization process will be automatically re-executed (i.e., returning to the path of S2), and a new scheduling plan will be generated based on the current deviation. The smart contract will then be driven to execute new tasks again, which can dynamically respond to unpredictable on-site problems such as equipment delays and abnormal positions.
[0071] A second embodiment of this application discloses a blockchain-based road construction equipment scheduling system, which includes: The equipment data on-chain module collects the operating status, geographical location, and component lifespan data of each construction piece of equipment, and encrypts and uploads them to the blockchain to obtain a blockchain digital image; The intelligent optimization analysis module, based on blockchain digital mirroring, uses an adaptive multi-objective analysis algorithm to analyze the correlation between equipment utilization and construction progress, and generates an optimized scheduling scheme by simulating the effects of different scheduling schemes. The automatic contract execution module transforms the optimized scheduling scheme into a smart contract, which automatically triggers and executes equipment scheduling and transportation task dispatch when the preset construction conditions are met. The execution deviation monitoring module automatically compares the optimized scheduling plan in the smart contract with the actual execution data recorded in the blockchain digital mirror to identify progress deviations or position deviations. The closed-loop module is dynamically adjusted. Based on the identified progress or position deviations, the intelligent optimization analysis module is re-executed, and a new optimized scheduling scheme is generated. Then, the smart contract is driven to execute the new optimized scheduling scheme.
[0072] It should be noted that the calculation formulas and all parameters involved in the calculations in this application have been dimensionless beforehand. The process of dimensionless processing is well known in the industry and will not be described here.
[0073] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.
Claims
1. A blockchain-based method for scheduling road construction equipment, characterized in that, The method for scheduling road construction equipment includes the following steps: S1. Collect the operating status, geographical location, and component lifespan data of each construction equipment, and encrypt and upload them to the blockchain to obtain a blockchain digital image; S2. Based on blockchain digital mirroring, an adaptive multi-objective analysis algorithm is used to analyze the correlation between equipment utilization and construction progress. By simulating the effects of different scheduling schemes, an optimized scheduling scheme is generated. S3. Transform the optimized scheduling scheme into a smart contract, which will automatically trigger and execute equipment scheduling and transportation task dispatch when the preset construction conditions are met. S4. Automatically compare and optimize the scheduling scheme in the smart contract with the actual execution data recorded in the blockchain digital mirror to identify progress deviations or position deviations. S5. Based on the identified progress deviation or position deviation, re-execute step S2, generate a new optimized scheduling scheme, and then drive the smart contract to execute the new optimized scheduling scheme.
2. The blockchain-based road construction equipment scheduling method according to claim 1, characterized in that, The process of collecting operational status, geographical location, and component lifespan data for each construction piece of equipment, and encrypting and uploading it to the blockchain to obtain a blockchain digital image includes the following steps: S11. Pre-deploy positioning, status monitoring, and component life sensors on the construction equipment to collect the equipment's geographical location, operating parameters, and health status data, and send them to the edge gateway; S12. The edge gateway formats the geographic location, operating parameters and health status data, encapsulates them into a standard data packet with a timestamp and device ID, and digitally signs the standard data packet with a private key. S13. Transmit the signed standard data packet to the blockchain node server through an encrypted channel; S14. The node server calls the smart contract to construct the core information of the standard data packet into an on-chain transaction and submits it to the blockchain network. S15. The smart contract automatically verifies the digital signature and submitter's permissions on the chain. After verification, the data hash is written into a new block. S16. The transactions confirmed through the consensus mechanism are packaged into a new block, which is then added to the chain and together they form a digital image of the blockchain.
3. The blockchain-based road construction equipment scheduling method according to claim 2, characterized in that, The smart contract automatically verifies the digital signature and submitter's permissions on the blockchain. After successful verification, the data hash is written to a new block, including the following steps: S151. After receiving a transaction request, the smart contract verifies the submitter's identity and operating permissions, and confirms whether the data is qualified to be uploaded to the blockchain. S152. After the identity and operation permission verification is passed, the smart contract performs digital signature verification on the data packet to confirm that the data remains intact during the transmission process. S153. After completing the digital signature verification, the smart contract extracts key information from the data packet and generates the corresponding data hash fingerprint. S154. Store the generated data hash fingerprint and related transaction information in the blockchain state database, and record the transactions on the blockchain.
4. The blockchain-based road construction equipment scheduling method according to claim 1, characterized in that, The method based on blockchain digital mirroring, employing an adaptive multi-objective analysis algorithm to analyze the correlation between equipment utilization and construction progress, and generating an optimized scheduling scheme by simulating the effects of different scheduling schemes, includes the following steps: S21. Obtain the geographical location, real-time status and construction progress plan of the equipment in the blockchain digital image, construct a topology network including equipment nodes, construction sites and transportation routes, and based on the topology network, initialize the multi-objective pheromone matrix required for multi-objective optimization and set adaptive parameters. S22. During the iterative optimization process, the search agent selects a path in the topology network based on dynamically adjusted heuristic rules, evaluates multiple objectives simultaneously through a multi-objective pheromone matrix, and integrates traffic status data from the blockchain in real time to update path weights and pheromone distribution. S23. Based on the reinforcement learning mechanism, the convergence state of the population and the quality of the Pareto solution set are monitored after each iteration, the adaptive parameters are dynamically adjusted, and the global optimization behavior is automatically executed when an emergency scheduling requirement is identified. S24. Evaluate the non-dominated solution set generated after multiple rounds of iterative optimization in multiple dimensions, output a Pareto optimal scheduling scheme set including trade-off analysis, and write the performance index and execution logic of the final scheme selected by decision into the blockchain smart contract. S25. Based on the historical implementation effects of the scheme recorded in the blockchain digital mirror, optimize the heuristic rules and multi-objective weight configuration through a feedback loop mechanism.
5. The blockchain-based road construction equipment scheduling method according to claim 4, characterized in that, The iterative optimization process involves using dynamically adjusted heuristic rules to drive the search agent to select paths in the topological network, simultaneously evaluating multiple objectives through a multi-objective pheromone matrix, and integrating traffic state data from the blockchain in real time to update path weights and pheromone distribution. This includes the following steps: S221. At the beginning of each iteration, load the currently dynamically adjusted heuristic rules for all search agents, and query and obtain the real-time traffic status data of all relevant path nodes in the current topology network from the blockchain digital mirror. S222. Each search agent selects and moves through the topology network step by step based on heuristic rules and real-time traffic status data to construct a complete candidate transportation path. S223. Based on the multi-objective pheromone matrix and real-time traffic data, calculate the multi-objective evaluation score of the candidate transportation path, and locally update the pheromone concentration on each path segment included in the candidate transportation path according to the multi-objective evaluation score. S224. After all search agents have completed the path construction for this iteration, the path weights of the topology network are updated globally based on all paths generated in this iteration and the evaluation results.
6. The blockchain-based road construction equipment scheduling method according to claim 5, characterized in that, The process of calculating the multi-objective evaluation score of candidate transportation routes based on a multi-objective pheromone matrix and real-time traffic data, and then locally updating the pheromone concentration on each route segment of the candidate transportation routes based on the multi-objective evaluation score, includes the following steps: S2231. For a candidate transportation route, the historical experience values and real-time traffic data stored in the multi-objective pheromone matrix are comprehensively called to calculate the target values of the candidate transportation route in multiple optimization objectives, including time, cost and equipment loss, and the target values are normalized. S2232. The normalized target values are weighted and summed according to the preset weights to obtain the multi-target evaluation score of the candidate transportation path. S2233. Based on the multi-objective evaluation score of the path, calculate the pheromone increment proportionally, and add the pheromone increment to the current pheromone concentration of each path segment contained in the path to complete the local update.
7. The blockchain-based road construction equipment scheduling method according to claim 4, characterized in that, The reinforcement learning mechanism monitors the convergence state of the population and the quality of the Pareto solution set after each iteration, dynamically adjusts adaptive parameters, and automatically executes global optimization behavior when an urgent scheduling need is identified. This includes the following steps: S231. After each iteration, calculate the convergence of the population, the distribution and breadth of the Pareto solution set, and generate a feature vector describing the current search state. S232. The reinforcement learning agent receives the generated feature vector, analyzes the current search state, outputs a decision action, and dynamically adjusts the adaptive parameters based on the decision result. S233. Continuously monitor external inputs. When a preset emergency dispatch demand signal is detected, immediately interrupt the current adaptive parameter adjustment process and issue a global optimization command. S234. Upon receiving the global optimization command, reset the current search state and switch to emergency search mode to automatically execute the global optimization behavior.
8. The blockchain-based road construction equipment scheduling method according to claim 1, characterized in that, The process of automatically comparing and optimizing the scheduling scheme in the smart contract with the actual execution data recorded in the blockchain digital mirror to identify progress deviations or position deviations includes the following steps: S41. Simultaneously query the blockchain digital image and smart contract to obtain the verified actual execution data of the device and the currently effective optimization scheduling scheme, and integrate them into a benchmark dataset to be compared. S42. Based on the benchmark dataset, call the progress comparison logic to calculate the numerical difference between the actual progress and the planned progress, and directly determine whether there is a progress deviation based on the preset threshold. S43. Based on the benchmark dataset, call the location comparison logic to detect whether the actual location of the device exceeds the planned geofence, and directly determine whether there is a location deviation according to the preset tolerance range. S44. Judgment results of polymerization progress deviation and position deviation.
9. A blockchain-based road construction equipment scheduling system, used to implement the blockchain-based road construction equipment scheduling method according to any one of claims 1-8, characterized in that, The road construction equipment dispatching system includes: The equipment data on-chain module collects the operating status, geographical location, and component lifespan data of each construction piece of equipment, and encrypts and uploads them to the blockchain to obtain a blockchain digital image; The intelligent optimization analysis module, based on blockchain digital mirroring, uses an adaptive multi-objective analysis algorithm to analyze the correlation between equipment utilization and construction progress, and generates an optimized scheduling scheme by simulating the effects of different scheduling schemes. The automatic contract execution module transforms the optimized scheduling scheme into a smart contract, which automatically triggers and executes equipment scheduling and transportation task dispatch when the preset construction conditions are met. The execution deviation monitoring module automatically compares the optimized scheduling plan in the smart contract with the actual execution data recorded in the blockchain digital mirror to identify progress deviations or position deviations. The closed-loop module is dynamically adjusted. Based on the identified progress or position deviations, the intelligent optimization analysis module is re-executed, and a new optimized scheduling scheme is generated. Then, the smart contract is driven to execute the new optimized scheduling scheme.