Fabricated closed conduit field installation construction method based on artificial intelligence

Abstract

The invention relates to the field of closed conduit construction, and particularly discloses an assembly type closed conduit field installation construction method based on artificial intelligence, which comprises the following steps: S1, constructing an initial construction data set; s2, automatically identifying key performance indexes and potential efficiency bottlenecks in construction; s3, generating an optimal construction process and resource allocation scheme by using an improved genetic algorithm; s4, implementing an operation instruction through an artificial intelligence system, and scheduling related construction resources; s5, constructing a dynamic construction data set; s6, on the basis of the dynamic construction data set collected in the step S5 in real time, a construction plan and an operation instruction are adjusted in real time through an artificial intelligence system; s7, in the design stage of the prefabricated component, predicting and simulating the performance of the component by applying an artificial intelligence system; and S8, in the field assembly stage, according to the design scheme in the step S7, prefabricated assemblies are installed through artificial intelligence guidance, and correct butt joint and fixation of all the assemblies are ensured. The construction time and resource waste are effectively reduced, and the construction efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of culvert construction, and in particular to an artificial intelligence-based on-site installation construction method for assembled culverts. Background Art

[0002] In modern infrastructure construction, prefabricated culverts are a new type of drainage system structure that is widely used due to its advantages such as fast construction, environmental protection and high efficiency. However, in the actual construction process, the installation of prefabricated culverts faces many challenges, mainly including the complexity of the construction process, the efficiency of resource allocation, the necessity of real-time monitoring and dynamic adjustment, and the accuracy of prefabricated component design and on-site assembly. In response to these problems, the existing technology often has certain limitations in specific implementation, resulting in construction efficiency and quality that are difficult to meet the expected requirements.

[0003] First, in terms of construction process optimization, traditional construction methods usually rely on experience and manual operations. This method is inefficient in the face of complex construction environments and it is difficult to adjust and optimize the construction process in real time. For example, in the construction of prefabricated culverts, how to effectively arrange various construction tasks, how to reasonably allocate construction resources, and how to dynamically adjust the construction plan are all difficult to solve efficiently through traditional methods. The existing technology lacks a data-driven intelligent decision support system and cannot fully utilize the real-time data of the construction site to optimize the construction process.

[0004] Secondly, in terms of resource allocation and management, existing technologies often have difficulty in achieving optimal resource allocation. Traditional resource management mainly relies on manual statistics and scheduling, lacking systematic intelligent management methods. This method is not only labor-intensive and error-prone, but also unable to achieve real-time monitoring and dynamic adjustment of resource usage, resulting in resource waste and low construction efficiency. In the construction of prefabricated culverts, how to efficiently allocate human, mechanical equipment and material resources has become a bottleneck that is difficult to break through with existing technologies.

[0005] Furthermore, in terms of real-time monitoring and dynamic adjustment, existing technologies usually rely on manual monitoring and manual adjustment, and lack systematic and intelligent monitoring methods. The construction environment of prefabricated culverts is complex and changeable, and various emergencies are often encountered during the construction process, such as changes in environmental conditions and abnormal material conditions. If these problems cannot be discovered and handled in time, they will seriously affect the quality and progress of construction. Traditional monitoring methods often find it difficult to achieve comprehensive real-time monitoring of the construction site, and it is even more difficult to make timely and effective dynamic adjustments when problems are found.

[0006] Therefore, how to provide an artificial intelligence-based on-site installation and construction method for prefabricated culverts is an urgent problem that technicians in this field need to solve. Summary of the invention

[0007] In response to the above problems, an embodiment of the present invention provides an artificial intelligence-based on-site installation construction method for assembled culverts.

[0008] An artificial intelligence-based on-site installation construction method for assembled culverts provided in an embodiment of the present invention comprises the following steps:

[0009] S1. Collect initial construction data

[0010] Collect the linear data of position, elevation, water drop and culvert assembly, calculate the safe lifting radius and lifting position according to the lifting weight, and construct the initial construction data set;

[0011] S2. Analyze initial construction data

[0012] By applying the improved aggregate decision tree to analyze the initial construction data set, key performance indicators and potential efficiency bottlenecks in construction are automatically identified;

[0013] S3. Generate optimal construction process and resource allocation plan

[0014] Based on the analysis results of step S2, an improved genetic algorithm is used to generate an optimal construction process and resource allocation plan, where the resources include manpower, machinery and equipment, and materials;

[0015] S4. Convert and implement operation instructions

[0016] Convert the construction process and resource allocation plan generated in step S3 into specific operation instructions, and implement the operation instructions through the artificial intelligence system to dispatch relevant construction resources;

[0017] S5. Real-time monitoring of the construction site

[0018] During the construction process, a variety of sensors are used to monitor the environmental conditions, material status and worker behavior of the construction site in real time to build a dynamic construction data set. The sensors include position sensors, elevation sensors, water drop sensors, sensors for monitoring the linearity of the culvert after assembly, and lifting safety sensors.

[0019] S6. Dynamically adjust the construction plan

[0020] Based on the dynamic construction data set collected in real time in step S5, the construction plan and operation instructions are adjusted in real time by the artificial intelligence system to respond to any deviations or potential problems monitored in real time;

[0021] S7. Optimize prefabricated component design

[0022] In the design stage of prefabricated components, artificial intelligence systems are used to predict and simulate the performance of components and optimize the design of components to meet specific functional and durability requirements;

[0023] S8. Ensure components are installed correctly

[0024] During the on-site assembly phase, the prefabricated components are installed quickly and accurately according to the design plan in step S7 through artificial intelligence guidance to ensure the correct docking and fixation of each prefabricated component.

[0025] Optionally, the S1 includes:

[0026] S11. Collect the location information of the construction site and obtain the coordinate data of the construction site through the GPS positioning system. The coordinate data includes X, Y, and Z coordinates:

[0027] X=Rcos(φ)cos(λ)

[0028] Y=Rcos(φ)sin(λ)

[0029] Z=Rsin(φ)

[0030] Among them, R is the radius of the earth, φ is the latitude, and λ is the longitude;

[0031] S12. Use a laser rangefinder and a level to measure the elevation of the construction site, and organize the measured absolute elevation and relative elevation into elevation data:

[0032]

[0033] Where H is the elevation, D1 and D2 are the distances between two points measured by the rangefinder, and Δh i is the height difference of each measuring point, n (1 is the number of measuring points;

[0034] S13, using a flow velocity sensor and a water level sensor to measure the water drop at the construction site, and generate water drop data:

[0035]

[0036] Among them, Δh is the water drop, Q is the flow rate, A is the cross-sectional area, v is the flow velocity, g is the gravitational acceleration, and h f is the friction loss head;

[0037] S14. Use a laser scanner or other measuring equipment to obtain the linear data of the length, width and curvature of the culvert after it is assembled:

[0038]

[0039] Where C is the curvature, L is the length of the culvert, is the derivative of the curve;

[0040] S15. Calculate the safe lifting radius R'' according to the lifting weight W of the culvert:

[0041]

[0042] Among them, σ is the safety factor of the lifting equipment, W is the lifting weight, E is the elastic modulus of the material, and ν is the Poisson's ratio of the material;

[0043] S16. Based on the data collected in steps S11-S14, determine the specific coordinates of each hoisting position, and calculate and analyze the bearing capacity and stability of each position to avoid tilting or offset during the hoisting process. The bearing capacity and stability calculation formula is:

[0044]

[0045] Among them, P is the bearing capacity, F is the force, A is the cross-sectional area, M y and M z is the bending moment, I y and I z is the moment of inertia, y and z are the coordinate positions;

[0046] S17, combining the safe lifting position determined in steps S11-S16 with the construction progress and resource allocation plan to construct an initial construction data set, wherein the initial construction data set includes position data, elevation data, water drop data, linear data, and safe lifting radius data:

[0047]

[0048] Where D is the initial construction data set, X i ,Y i ,Z i is the position data, H i is the elevation data, Δh i is the water drop data, C i For linear data, R' i ' is the safe lifting radius data, n (2) is the number of initial construction data points.

[0049] Optionally, S2 includes:

[0050] S21, performing data cleaning, missing value filling and data standardization on the initial construction data set D to obtain a preprocessed construction data set;

[0051] S22. By using feature selection technology, key features that affect construction performance are selected from the preprocessed construction data set D to form a key feature data set:

[0052] Use a hybrid feature selection algorithm based on information gain and mutual information to calculate each feature F i The comprehensive score is as follows:

[0053] Score(F i )=α·IG(F i )+β·MI(F i )

[0054] Among them, IG(F i ) is the feature F i The information gain, MI(F i ) is the feature F i The mutual information of , α and β are adjustment parameters used to balance the contribution of information gain and mutual information;

[0055] According to the comprehensive score, the first k features are selected as key features to form a key feature data set:

[0056] F key ={F1,F2,…,F k}

[0057] S23, based on key feature dataset F key , apply the improved aggregate decision tree algorithm for analysis:

[0058] Use multi-model ensemble techniques to combine decision trees, random forests, and gradient boosted trees:

[0059]

[0060] in, is the final prediction result, h m (x) is the prediction result of the decision tree model, f n (x) is the prediction result of the random forest model, g p (x) is the prediction result of the gradient boosting tree model, α m , β n and γ p is the weight of the corresponding model, M, N and P are the number of decision tree, random forest and gradient boosting tree models respectively;

[0061] In the process of multi-model integration, an adaptive weight adjustment mechanism is introduced to dynamically adjust the weight of each model by minimizing the prediction error. The formula is as follows:

[0062]

[0063] Among them, α m is the weight of the mth decision tree model, y i is the actual value, xi is the input feature vector, λ is the adjustment coefficient, and Z is the normalization constant;

[0064] Through feature selection technology, the most important features are selected from the results of multi-model integration to construct an optimized feature set. The formula for constructing the optimized feature set is:

[0065]

[0066] Among them, F opt is the optimized feature set, F i is the candidate feature set, K is the number of cross-validation folds, G k (F i ) is the feature gain of the kth fold, H k (F i ) is the feature loss of the k-th fold, ∈ is the smoothing term;

[0067] S24: Based on the analysis results of step S23, automatically identify the key performance indicators (KPIs) and potential efficiency bottlenecks in the construction process. i The key performance indicators include construction progress, material utilization rate and equipment utilization rate. The efficiency bottleneck includes uneven allocation of construction resources and bottleneck links in the construction process. The calculation formula of the key performance indicators is:

[0068]

[0069] Among them, KPI is the key performance indicator, ω i is the weight of the i-th sample, y i is the actual value, is the predicted value, n (3 is the sample size;

[0070]

[0071] Among them, Bottleneck i is the efficiency bottleneck index of the i-th construction resource, Resource i is the usage of the i-th resource, Capacity i is the total capacity of the i-th resource, Delay ij PlannedTime is the delay time of the jth task on the ith resource. ij is the planned time for the jth task, n (4) is the number of tasks.

[0072] Optionally, the S3 includes:

[0073] S31. Based on the analysis result of step S2, an initial population is constructed. Each individual in the initial population represents a construction process and a resource allocation scheme. The representation form of the individual is:

[0074]

[0075] Among them, P i is the construction parameter of the ith task, n (5) is the number of tasks;

[0076] S32. Define a fitness function f, which is used to evaluate the quality of each individual. The fitness function is calculated based on key performance indicators and efficiency bottlenecks. The formula of the fitness function is:

[0077]

[0078] Among them, KPI i is the key performance indicator of the i-th task, Bottleneck i is the efficiency bottleneck of the i-th task, and is the corresponding weight;

[0079] S33, according to the fitness function f, select individuals with fitness higher than the set value as the parent generation, perform a crossover operation to generate offspring individuals, and the crossover operation adopts a single-point crossover:

[0080]

[0081] in, represents the i-th task parameter from the j-th parent;

[0082] S34, introducing a mutation operation in the offspring individuals, adjusting some parameters of the individuals through random mutation and adaptive mutation rate, the formula of the mutation operation is:

[0083] P' i =P i +δ·randn(0,1)

[0084] Among them, P' i is the parameter after mutation, δ is the amplitude of mutation, and randn(0,1) is a normally distributed random number with mean 0 and variance 1;

[0085] S35, evaluating the quality of offspring individuals through the dynamic fitness function f, retaining individuals with fitness higher than the set value to enter the next generation, and repeating steps S33 to S35 until the maximum number of iterations is reached or the fitness converges;

[0086] S36. The individual with the highest fitness is used as the final construction process and resource allocation plan, and the final plan includes the optimal configuration of manpower, mechanical equipment and materials.

[0087] Optionally, the S4 includes:

[0088] S41, converting the construction process and resource allocation plan generated in S3 into specific operation instructions, including the specific execution steps of each construction task and the required resource configuration, wherein the resources include manpower, machinery and equipment, and materials, and the operation instructions are expressed in the form of:

[0089] O={T1,T2,…,T m}

[0090] Among them, T i is the operation instruction of the i-th construction task, and m is the number of tasks;

[0091] S42, assigning operation instructions to each construction task through the construction scheduling module, resource management module and task assignment module in the artificial intelligence system, the specific steps include:

[0092] The construction scheduling module dynamically adjusts the execution order of operation instructions according to the real-time status and resource conditions of the construction site to ensure the continuity and efficiency of the construction process;

[0093] The resource management module monitors the resource usage at the construction site, including manpower, machinery and materials, updates the resource allocation plan in real time, and confirms the optimal configuration of resources;

[0094] The task allocation module allocates operation instructions to specific construction personnel and equipment, and tracks the execution of tasks through the monitoring system to confirm the accurate implementation of the operation instructions.

[0095] Optionally, during the construction process, the artificial intelligence system monitors the environmental conditions, material status and construction progress of the construction site in real time through a sensor network. The sensors include position sensors, elevation sensors, water drop sensors and sensors for monitoring the linearity of the culvert after assembly. The data collected by the sensors form a real-time monitoring data set, which is expressed as:

[0096]

[0097] Among them, d i is the i-th real-time monitoring data, n (6) The number of monitoring data points.

[0098] Optionally, based on real-time monitoring dataset D real-time , the artificial intelligence system evaluates the status of the construction site in real time and dynamically adjusts operating instructions and resource allocation plans based on the evaluation results:

[0099] When it is detected that the construction progress is lagging behind, adjust the task allocation strategy and increase manpower and equipment input;

[0100] When uneven resource usage is detected, resources are reallocated to ensure that the resource requirements of each task are met;

[0101] When changes in environmental conditions are detected, the construction process is adjusted to ensure construction safety and efficiency;

[0102] All adjusted operation instructions and resource allocation plans are recorded in a construction log, which includes task execution records, resource usage records, and adjustment records.

[0103] Optionally, the S7 includes:

[0104] S71. During the design phase of the prefabricated component, various parameters related to the prefabricated component, including material properties, geometric dimensions, and usage environment, are collected to construct a prefabricated component design data set, which is expressed as:

[0105]

[0106] Among them, M i is the material property of the i-th prefabricated component, G i is the geometric size, E i is the usage environment parameter, n (7 is the number of parameter data points;

[0107] S72. Application of artificial intelligence system to prefabricated component design dataset D design Perform analysis and use machine learning models to predict performance. The machine learning models include regression models and neural network models. The performance prediction formula is:

[0108]

[0109] Among them, σ is the activation function, is the weight parameter of the neural network, is the weight of the input parameter, is the bias term, n1, n2, n3 are the number of layers of the neural network;

[0110] S73, based on the performance prediction result of step S72, the prefabricated component design is optimized using an optimization algorithm, the optimization goal includes meeting specific functional requirements and durability requirements, and the objective function of the optimization algorithm is:

[0111]

[0112] Among them, P target is the target performance value, θ is the adjustment coefficient, β jis the weight of different features, γ is the bias term, a j , b j 、c j is the weight of the input parameter;

[0113] S74. Verify the optimized prefabricated component design by simulation technology, wherein the simulation technology includes finite element analysis and computer simulation to verify the performance of the prefabricated component in an actual use environment;

[0114] S75. Further adjust and optimize the design of prefabricated components based on the results of simulation verification to ensure that the prefabricated components meet the functional and durability requirements in actual use;

[0115] S76, converting the final optimized prefabricated component design into manufacturing instructions to guide the production and manufacturing of the prefabricated components, wherein the manufacturing instructions are expressed in the form of:

[0116] O manufacturing ={C1,C2,…,C m‘’}

[0117] Among them, C i is the instruction for the i-th manufacturing step, and m'' is the number of manufacturing steps.

[0118] Compared with the prior art, the present invention has the following beneficial effects:

[0119] (1) The present invention uses an improved aggregate decision tree algorithm and genetic algorithm to intelligently analyze and optimize the construction process, automatically identify key performance indicators and potential efficiency bottlenecks in construction, and generate the optimal construction process and resource allocation plan, effectively reducing construction time and resource waste, and improving overall construction efficiency. The use of dynamic fitness functions and adaptive mutation rates makes the genetic algorithm more flexible and efficient in optimizing construction processes and resource allocation, and can adapt to real-time changes at the construction site, ensuring the optimality and practicality of the construction plan.

[0120] (2) The present invention uses the construction scheduling module, resource management module and task allocation module in the artificial intelligence system to monitor the resource usage of the construction site in real time, dynamically adjust the resource allocation plan, ensure the optimal allocation of resources, effectively reduce resource waste, and improve the management efficiency of the construction site. The artificial intelligence system is used to generate specific operation instructions to ensure that the specific execution steps and required resource allocation of each construction task are clear and unambiguous, thereby improving the continuity and execution efficiency of the construction.

[0121] (3) During the construction process, the present invention uses a sensor network to monitor the environmental conditions, material status and construction progress of the construction site in real time, build a dynamic construction data set, and ensure that various parameters of the construction site are under control. When an abnormal situation is monitored, the artificial intelligence system can respond quickly and dynamically adjust the construction plan and operating instructions to ensure construction quality and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0122] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of the present application, and do not constitute a limitation of the present invention. In the drawings:

[0123] Figure 1 The present invention is a schematic flow chart of an artificial intelligence-based on-site installation construction method for assembled culverts. DETAILED DESCRIPTION

[0124] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0125] Reference Figure 1 , an embodiment of the present invention provides an artificial intelligence-based assembled culvert on-site installation construction method, comprising the following steps;

[0126] S1. Collect initial construction data

[0127] Collect the linear data of position, elevation, water drop and culvert assembly, calculate the safe lifting radius and lifting position according to the lifting weight, and construct the initial construction data set;

[0128] S2. Analyze initial construction data

[0129] By applying the improved aggregate decision tree to analyze the initial construction data set, key performance indicators and potential efficiency bottlenecks in construction are automatically identified;

[0130] S3. Generate optimal construction process and resource allocation plan

[0131] Based on the analysis results of step S2, an improved genetic algorithm is used to generate an optimal construction process and resource allocation plan, where the resources include manpower, machinery and equipment, and materials;

[0132] S4. Convert and implement operation instructions

[0133] Convert the construction process and resource allocation plan generated in step S3 into specific operation instructions, and implement the operation instructions through the artificial intelligence system to dispatch relevant construction resources;

[0134] S5. Real-time monitoring of the construction site

[0135] During the construction process, a variety of sensors are used to monitor the environmental conditions, material status and worker behavior of the construction site in real time to build a dynamic construction data set. The sensors include position sensors, elevation sensors, water drop sensors, sensors for monitoring the linearity of the culvert after assembly, and lifting safety sensors.

[0136] S6. Dynamically adjust the construction plan

[0137] Based on the dynamic construction data set collected in real time in step S5, the construction plan and operation instructions are adjusted in real time by the artificial intelligence system to respond to any deviations or potential problems monitored in real time;

[0138] S7. Optimize prefabricated component design

[0139] In the design stage of prefabricated components, artificial intelligence systems are used to predict and simulate the performance of components and optimize the design of components to meet specific functional and durability requirements;

[0140] S8. Ensure components are installed correctly

[0141] During the on-site assembly phase, the prefabricated components are installed quickly and accurately according to the design plan in step S7 through artificial intelligence guidance to ensure the correct docking and fixation of each prefabricated component.

[0142] In this implementation, S1 includes:

[0143] S11. Collect the location information of the construction site and obtain the coordinate data of the construction site through the GPS positioning system. The coordinate data includes X, Y, and Z coordinates:

[0144] X=Rcos(φ)cos(λ)

[0145] Y=Rcos(φ)sin(λ)

[0146] Z=Rsin(φ)

[0147] Among them, R is the radius of the earth, φ is the latitude, and λ is the longitude;

[0148] S12. Use a laser rangefinder and a level to measure the elevation of the construction site, and organize the measured absolute elevation and relative elevation into elevation data:

[0149]

[0150] Where H is the elevation, D1 and D2 are the distances between two points measured by the rangefinder, and Δh i is the height difference of each measuring point, n (1) is the number of measuring points;

[0151] S13, using a flow velocity sensor and a water level sensor to measure the water drop at the construction site, and generate water drop data:

[0152]

[0153] Among them, Δh is the water drop, Q is the flow rate, A is the cross-sectional area, v is the flow velocity, g is the gravitational acceleration, and h f is the friction loss head;

[0154] S14. Use a laser scanner or other measuring equipment to obtain the linear data of the length, width and curvature of the culvert after it is assembled:

[0155]

[0156] Where C is the curvature, L is the length of the culvert, is the derivative of the curve;

[0157] S15. Calculate the safe lifting radius R'' based on the lifting weight W of the culvert:

[0158]

[0159] Among them, σ is the safety factor of the lifting equipment, W is the lifting weight, E is the elastic modulus of the material, and ν is the Poisson's ratio of the material;

[0160] S16. Based on the data collected in steps S11-S14, determine the specific coordinates of each hoisting position, and calculate and analyze the bearing capacity and stability of each position to avoid tilting or offset during the hoisting process. The bearing capacity and stability calculation formula is:

[0161]

[0162] Among them, P is the bearing capacity, F is the force, A is the cross-sectional area, M y and M z is the bending moment, I y and I z is the moment of inertia, y and z are the coordinate positions;

[0163] S17, combining the safe lifting position determined in steps S11-S16 with the construction progress and resource allocation plan to construct an initial construction data set, which includes position data, elevation data, water drop data, linear data, and safe lifting radius data:

[0164]

[0165] Where D is the initial construction data set, X i ,Y i ,Zi is the position data, H i is the elevation data, Δh i is the water drop data, C i For linear data, R'' i is the safe lifting radius data, n (2) is the number of initial construction data points.

[0166] In this implementation, S2 includes:

[0167] S21, performing data cleaning, missing value filling and data standardization on the initial construction data set D to obtain a preprocessed construction data set;

[0168] S22. By using feature selection technology, key features that affect construction performance are selected from the preprocessed construction data set D to form a key feature data set:

[0169] Use a hybrid feature selection algorithm based on information gain and mutual information to calculate each feature F i The comprehensive score is as follows:

[0170] Score(F i )=α·IG(F i )+β·MI(F i )

[0171] Among them, IG(F i ) is the feature F i The information gain, MI(F i ) is the feature F i The mutual information of , α and β are adjustment parameters used to balance the contribution of information gain and mutual information;

[0172] According to the comprehensive score, the first k features are selected as key features to form a key feature data set:

[0173] F key ={F1,F2,…,F k}

[0174] S23, based on key feature dataset F key , apply the improved aggregate decision tree algorithm for analysis:

[0175] Use multi-model ensemble techniques to combine decision trees, random forests, and gradient boosted trees:

[0176]

[0177] in, is the final prediction result, h m (x) is the prediction result of the decision tree model, f n(x) is the prediction result of the random forest model, g p (x) is the prediction result of the gradient boosting tree model, α m , β n and γ p is the weight of the corresponding model, M, N and P are the number of decision tree, random forest and gradient boosting tree models respectively;

[0178] In the process of multi-model integration, an adaptive weight adjustment mechanism is introduced to dynamically adjust the weight of each model by minimizing the prediction error. The formula is as follows:

[0179]

[0180] Among them, α m is the weight of the mth decision tree model, y i is the actual value, x i is the input feature vector, λ is the adjustment coefficient, Z is the normalization constant; β n and γ p The adjustment principle is the same;

[0181] Through feature selection technology, the most important features are selected from the results of multi-model integration to build an optimized feature set. The formula for building the optimized feature set is:

[0182]

[0183] Among them, F opt is the optimized feature set, F i is the candidate feature set, K is the number of cross-validation folds, G k (F i ) is the feature gain of the kth fold, H k (F i ) is the feature loss of the k-th fold, ∈ is the smoothing term;

[0184] S24: Based on the analysis results of step S23, automatically identify the key performance indicators (KPIs) and potential efficiency bottlenecks in the construction process. i , the key performance indicators include construction progress, material utilization rate and equipment utilization rate. The efficiency bottlenecks include uneven allocation of construction resources and bottleneck links in the construction process. The calculation formula of the key performance indicators is:

[0185]

[0186] Among them, KPI is the key performance indicator, ω i is the weight of the i-th sample, y i is the actual value, is the predicted value, n (3) is the sample size;

[0187]

[0188] Among them, Bottleneck i is the efficiency bottleneck index of the i-th construction resource, Resource i is the usage of the i-th resource, Capacity i is the total capacity of the i-th resource, Delay ij PlannedTime is the delay time of the jth task on the ith resource. ij is the planned time for the jth task, n (4) is the number of tasks.

[0189] In this implementation, S3 includes:

[0190] S31. Based on the analysis result of step S2, an initial population is constructed. Each individual in the initial population represents a construction process and resource allocation scheme. The representation form of the individual is:

[0191]

[0192] Among them, P i is the construction parameter of the ith task, n (5) is the number of tasks;

[0193] S32. Define a fitness function f, which is used to evaluate the quality of each individual. The fitness function is calculated based on key performance indicators and efficiency bottlenecks. The formula of the fitness function is:

[0194]

[0195] Among them, KPI i is the key performance indicator of the i-th task, Bottleneck i is the efficiency bottleneck of the i-th task, and is the corresponding weight;

[0196] S33, according to the fitness function f, select individuals with fitness higher than the set value as the parent generation, perform crossover operation to generate offspring individuals, and the crossover operation adopts single-point crossover:

[0197]

[0198] in, represents the i-th task parameter from the j-th parent;

[0199] S34, introduce mutation operation in the offspring individuals, adjust some parameters of the individuals through random mutation and adaptive mutation rate, the formula of mutation operation is:

[0200] P' i =P i +δ·randn(0,1)

[0201] Among them, P' i is the parameter after mutation, δ is the amplitude of mutation, and randn(0,1) is a normally distributed random number with mean 0 and variance 1;

[0202] S35, evaluating the quality of offspring individuals through the dynamic fitness function f, retaining individuals with fitness higher than the set value to enter the next generation, and repeating steps S33 to S35 until the maximum number of iterations is reached or the fitness converges;

[0203] S36. The individual with the highest fitness is selected as the final construction process and resource allocation plan. The final plan includes the optimal configuration of manpower, mechanical equipment and materials.

[0204] In this implementation, S4 includes:

[0205] S41, convert the construction process and resource allocation plan generated in S3 into specific operation instructions, including the specific execution steps of each construction task and the required resource allocation, the resources include manpower, machinery and equipment and materials, and the operation instructions are expressed in the form of:

[0206] O={T1,T2,…,Tm}

[0207] Among them, T i is the operation instruction of the i-th construction task, and m is the number of tasks;

[0208] S42, assigning operation instructions to each construction task through the construction scheduling module, resource management module and task assignment module in the artificial intelligence system, the specific steps include:

[0209] The construction scheduling module dynamically adjusts the execution order of operation instructions according to the real-time status and resource conditions of the construction site to ensure the continuity and efficiency of the construction process;

[0210] The resource management module monitors the resource usage at the construction site, including manpower, machinery and materials, updates the resource allocation plan in real time, and confirms the optimal configuration of resources;

[0211] The task allocation module assigns operation instructions to specific construction personnel and equipment, and tracks the execution of tasks through the monitoring system to confirm the accurate implementation of the operation instructions.

[0212] In this embodiment, during the construction process, the artificial intelligence system monitors the environmental conditions, material status and construction progress of the construction site in real time through a sensor network. The sensors include position sensors, elevation sensors, water drop sensors and sensors for monitoring the linearity of the culvert after assembly. The data collected by the sensors form a real-time monitoring data set, which is expressed as:

[0213]

[0214] Among them, d i is the i-th real-time monitoring data, n (6) The number of monitoring data points.

[0215] In this embodiment, based on the real-time monitoring data set D real-time , the artificial intelligence system evaluates the status of the construction site in real time and dynamically adjusts operating instructions and resource allocation plans based on the evaluation results:

[0216] When it is detected that the construction progress is lagging behind, adjust the task allocation strategy and increase manpower and equipment input;

[0217] When uneven resource usage is detected, resources are reallocated to ensure that the resource requirements of each task are met;

[0218] When changes in environmental conditions are detected, the construction process is adjusted to ensure construction safety and efficiency;

[0219] All adjusted operation instructions and resource allocation plans shall be recorded in the construction log, which shall include task execution records, resource usage records and adjustment records.

[0220] In this implementation, S7 includes:

[0221] S71. During the design phase of the prefabricated component, various parameters related to the prefabricated component, including material properties, geometric dimensions, and usage environment, are collected to construct a prefabricated component design data set, which is expressed as:

[0222]

[0223] Among them, M i is the material property of the i-th prefabricated component, G i is the geometric size, E i is the usage environment parameter, n (7) is the number of parameter data points;

[0224] S72. Application of artificial intelligence system to prefabricated component design dataset D design Perform analysis and use machine learning models to predict performance. Machine learning models include regression models and neural network models. The performance prediction formula is:

[0225]

[0226] Among them, σ is the activation function, is the weight parameter of the neural network, is the weight of the input parameter, is the bias term, n1, n2, n3 are the number of layers of the neural network;

[0227] S73, based on the performance prediction result of step S72, the prefabricated component design is optimized using an optimization algorithm, the optimization goal includes meeting specific functional requirements and durability requirements, and the objective function of the optimization algorithm is:

[0228]

[0229] Among them, P target is the target performance value, θ is the adjustment coefficient, β j is the weight of different features, γ is the bias term, a j , b j 、c j is the weight of the input parameter;

[0230] S74. Verify the optimized prefabricated component design through simulation technology, including finite element analysis and computer simulation, to verify the performance of the prefabricated component in the actual use environment;

[0231] S75. Further adjust and optimize the design of prefabricated components based on the results of simulation verification to ensure that the prefabricated components meet the functional and durability requirements in actual use;

[0232] S76. Convert the final optimized prefabricated component design into manufacturing instructions to guide the production and manufacturing of the prefabricated components. The manufacturing instructions are expressed in the form of:

[0233] O manufacturing ={C1,C2,…,C m‘’}

[0234] Among them, C i is the instruction for the i-th manufacturing step, and m'' is the number of manufacturing steps

[0235] The present invention uses an improved aggregate decision tree algorithm and a genetic algorithm to intelligently analyze and optimize the construction process, automatically identify key performance indicators and potential efficiency bottlenecks in construction, generate the optimal construction process and resource allocation plan, effectively reduce construction time and resource waste, and improve overall construction efficiency. The use of dynamic fitness functions and adaptive mutation rates makes the genetic algorithm more flexible and efficient in optimizing construction processes and resource allocation, and can adapt to real-time changes at the construction site, ensuring the optimality and practicality of the construction plan.

[0236] The present invention uses the construction scheduling module, resource management module and task allocation module in the artificial intelligence system to monitor the resource usage of the construction site in real time, dynamically adjust the resource allocation plan, ensure the optimal configuration of resources, effectively reduce resource waste, and improve the management efficiency of the construction site. The artificial intelligence system is used to generate specific operation instructions to ensure that the specific execution steps and required resource allocation of each construction task are clear and unambiguous, thereby improving the continuity and execution efficiency of the construction.

[0237] During the construction process, the present invention monitors the environmental conditions, material status and construction progress of the construction site in real time through a sensor network, builds a dynamic construction data set, and ensures that various parameters of the construction site are under control. When an abnormal situation is monitored, the artificial intelligence system can respond quickly and dynamically adjust the construction plan and operating instructions to ensure construction quality and safety.

[0238] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. An artificial intelligence-based assembled culvert on-site installation construction method, characterized in that: The method comprises the following steps: S1. Collect initial construction data Collect the linear data of position, elevation, water drop and culvert assembly, calculate the safe lifting radius and lifting position according to the lifting weight, and construct the initial construction data set; S2. Analyze initial construction data By applying the improved aggregate decision tree to analyze the initial construction data set, key performance indicators and potential efficiency bottlenecks in construction are automatically identified; S3. Generate optimal construction process and resource allocation plan Based on the analysis results of step S2, an improved genetic algorithm is used to generate an optimal construction process and resource allocation plan, where the resources include manpower, machinery and equipment, and materials; S4. Convert and implement operation instructions Convert the construction process and resource allocation plan generated in step S3 into specific operation instructions, and implement the operation instructions through the artificial intelligence system to dispatch relevant construction resources; S5. Real-time monitoring of the construction site During the construction process, a variety of sensors are used to monitor the environmental conditions, material status and worker behavior of the construction site in real time to build a dynamic construction data set. The sensors include position sensors, elevation sensors, water drop sensors, sensors for monitoring the linearity of the culvert after assembly, and lifting safety sensors. S6. Dynamically adjust the construction plan Based on the dynamic construction data set collected in real time in step S5, the construction plan and operation instructions are adjusted in real time by the artificial intelligence system to respond to any deviations or potential problems monitored in real time; S7. Optimize prefabricated component design In the design stage of prefabricated components, artificial intelligence systems are used to predict and simulate the performance of components and optimize the design of components to meet specific functional and durability requirements; S8. Ensure components are installed correctly During the on-site assembly phase, the prefabricated components are installed quickly and accurately according to the design plan in step S7 through artificial intelligence guidance to ensure the correct docking and fixation of each prefabricated component.

2. According to the artificial intelligence-based assembled culvert on-site installation construction method of claim 1, it is characterized in that: The S1 includes: S11. Collect the location information of the construction site and obtain the coordinate data of the construction site through the GPS positioning system. The coordinate data includes X, Y, and Z coordinates: X=Rcos(φ)cos(λ) Y=Rcos(φ)sin(λ) Z=Rsin(φ) Among them, R is the radius of the earth, φ is the latitude, and λ is the longitude; S12. Use a laser rangefinder and a level to measure the elevation of the construction site, and organize the measured absolute elevation and relative elevation into elevation data: Where H is the elevation, D1 and D2 are the distances between two points measured by the rangefinder, and Δh i is the height difference of each measuring point, n (1) is the number of measuring points; S13, using a flow velocity sensor and a water level sensor to measure the water drop at the construction site, and generate water drop data: Among them, Δh is the water drop, Q is the flow rate, A is the cross-sectional area, v is the flow velocity, g is the gravitational acceleration, and h f is the friction loss head; S14. Use a laser scanner or other measuring equipment to obtain the linear data of the length, width and curvature of the culvert after it is assembled: Where C is the curvature, L is the length of the culvert, is the derivative of the curve; S15. Calculate the safe lifting radius R according to the lifting weight W of the culvert. ‘’ : Among them, σ is the safety factor of the lifting equipment, W is the lifting weight, E is the elastic modulus of the material, and v is the Poisson's ratio of the material; S16. Based on the data collected in steps S11-S14, determine the specific coordinates of each hoisting position, and calculate and analyze the bearing capacity and stability of each position to avoid tilting or offset during the hoisting process. The bearing capacity and stability calculation formula is: Among them, P is the bearing capacity, F is the force, A is the cross-sectional area, M y and M z is the bending moment, I y and I z is the moment of inertia, y and z are the coordinate positions; S17, combining the safe lifting position determined in steps S11-S16 with the construction progress and resource allocation plan to construct an initial construction data set, wherein the initial construction data set includes position data, elevation data, water drop data, linear data, and safe lifting radius data: Where D is the initial construction data set, X i ,Y i ,Z i is the position data, H i is the elevation data, Δh i is the water drop data, C i For linear data, is the safe lifting radius data, n (2) is the number of initial construction data points.

3. The artificial intelligence-based assembled culvert on-site installation construction method according to claim 2 is characterized in that: The S2 includes: S21, performing data cleaning, missing value filling and data standardization on the initial construction data set D to obtain a preprocessed construction data set; S22. By using feature selection technology, key features that affect construction performance are selected from the preprocessed construction data set D to form a key feature data set: Use a hybrid feature selection algorithm based on information gain and mutual information to calculate each feature F i The comprehensive score is as follows: Score(F i )=α·IG(F i )+β·MI(F i ) Among them, IG(F i ) is the feature F i The information gain, MI(F i ) is the feature F i The mutual information of , α and β are adjustment parameters used to balance the contribution of information gain and mutual information; According to the comprehensive score, the first k features are selected as key features to form a key feature data set: F key ={F1,F2,…,F k } S23, based on key feature dataset F key , apply the improved aggregate decision tree algorithm for analysis: Use multi-model ensemble techniques to combine decision trees, random forests, and gradient boosted trees: in, is the final prediction result, h m (x) is the prediction result of the decision tree model, f n (x) is the prediction result of the random forest model, g p (x) is the prediction result of the gradient boosting tree model, α m , β n and γ p is the weight of the corresponding model, M, N and P are the number of decision tree, random forest and gradient boosting tree models respectively; In the process of multi-model integration, an adaptive weight adjustment mechanism is introduced to dynamically adjust the weight of each model by minimizing the prediction error. The formula is as follows: Among them, α m is the weight of the mth decision tree model, y i is the actual value, x i is the input feature vector, λ is the adjustment coefficient, and Z is the normalization constant; Through feature selection technology, the most important features are selected from the results of multi-model integration to construct an optimized feature set. The formula for constructing the optimized feature set is: Among them, F opt is the optimized feature set, F i is the candidate feature set, K is the number of cross-validation folds, G k (F i ) is the feature gain of the k-th fold, H k (F i ) is the feature loss of the k-th fold, ∈ is the smoothing term; S24: Based on the analysis results of step S23, automatically identify the key performance indicators (KPIs) and potential efficiency bottlenecks in the construction process. i The key performance indicators include construction progress, material utilization rate and equipment utilization rate. The efficiency bottleneck includes uneven allocation of construction resources and bottleneck links in the construction process. The calculation formula of the key performance indicators is: Among them, KPI is the key performance indicator, ω i is the weight of the i-th sample, y i is the actual value, is the predicted value, n (3) is the sample size; Among them, Bottleneck i is the efficiency bottleneck index of the i-th construction resource, Resource i is the usage of the i-th resource, Capacity i is the total capacity of the i-th resource, Delay ij PlannedTime is the delay time of the jth task on the ith resource. ij is the planned time for the jth task, n (4) is the number of tasks.

4. The artificial intelligence-based assembled culvert on-site installation construction method according to claim 3 is characterized in that: The S3 includes: S31. Based on the analysis result of step S2, an initial population is constructed. Each individual in the initial population represents a construction process and a resource allocation scheme. The representation form of the individual is: Among them, P i is the construction parameter of the ith task, n (5) is the number of tasks; S32. Define a fitness function f, which is used to evaluate the quality of each individual. The fitness function is calculated based on key performance indicators and efficiency bottlenecks. The formula of the fitness function is: Among them, KPI i is the key performance indicator of the i-th task, Bottleneck i is the efficiency bottleneck of the i-th task, and is the corresponding weight; S33, according to the fitness function f, select individuals with fitness higher than the set value as the parent generation, perform a crossover operation to generate offspring individuals, and the crossover operation adopts a single-point crossover: in, represents the i-th task parameter from the j-th parent; S34, introducing a mutation operation in the offspring individuals, adjusting some parameters of the individuals through random mutation and adaptive mutation rate, the formula of the mutation operation is: P i =P i +δ·randn(0,1) Among them, P' i is the parameter after mutation, δ is the amplitude of mutation, and randn(0,1) is a normally distributed random number with mean 0 and variance 1; S35, evaluating the quality of offspring individuals through the dynamic fitness function f, retaining individuals with fitness higher than the set value to enter the next generation, and repeating steps S33 to S35 until the maximum number of iterations is reached or the fitness converges; S36. The individual with the highest fitness is used as the final construction process and resource allocation plan, and the final plan includes the optimal configuration of manpower, mechanical equipment and materials.

5. The artificial intelligence-based assembled culvert on-site installation construction method according to claim 4 is characterized in that: The S4 includes: S41, converting the construction process and resource allocation plan generated in S3 into specific operation instructions, including the specific execution steps of each construction task and the required resource configuration, wherein the resources include manpower, machinery and equipment, and materials, and the operation instructions are expressed in the form of: O={T1,T2,…,T m } Among them, T i is the operation instruction of the i-th construction task, and m is the number of tasks; S42, assigning operation instructions to each construction task through the construction scheduling module, resource management module and task assignment module in the artificial intelligence system, the specific steps include: The construction scheduling module dynamically adjusts the execution order of operation instructions according to the real-time status and resource conditions of the construction site to ensure the continuity and efficiency of the construction process; The resource management module monitors the resource usage at the construction site, including manpower, machinery and materials, updates the resource allocation plan in real time, and confirms the optimal configuration of resources; The task allocation module allocates operation instructions to specific construction personnel and equipment, and tracks the execution of tasks through the monitoring system to confirm the accurate implementation of the operation instructions.

6. The artificial intelligence-based on-site installation construction method of a prefabricated culvert according to claim 5 is characterized in that: During the construction process, the artificial intelligence system monitors the environmental conditions, material status and construction progress of the construction site in real time through a sensor network. The sensors include position sensors, elevation sensors, water drop sensors and sensors for monitoring the linearity of the culvert after assembly. The data collected by the sensors form a real-time monitoring data set, which is expressed as: Among them, d i is the i-th real-time monitoring data, n (6) The number of monitoring data points.

7. The artificial intelligence-based on-site installation construction method of a prefabricated culvert according to claim 6 is characterized in that: Based on real-time monitoring data set D real-time , the artificial intelligence system evaluates the status of the construction site in real time and dynamically adjusts operating instructions and resource allocation plans based on the evaluation results: When it is detected that the construction progress is lagging behind, adjust the task allocation strategy and increase manpower and equipment input; When uneven resource usage is detected, resources are reallocated to ensure that the resource requirements of each task are met; When changes in environmental conditions are detected, the construction process is adjusted to ensure construction safety and efficiency; All adjusted operation instructions and resource allocation plans are recorded in a construction log, which includes task execution records, resource usage records, and adjustment records.

8. The artificial intelligence-based on-site installation construction method of a prefabricated culvert according to claim 7 is characterized in that: The S7 includes: S71. During the design phase of the prefabricated component, various parameters related to the prefabricated component, including material properties, geometric dimensions, and usage environment, are collected to construct a prefabricated component design data set, which is expressed as: Among them, M i is the material property of the i-th prefabricated component, G i is the geometric size, E i is the usage environment parameter, n (7) is the number of parameter data points; S72. Application of artificial intelligence system to prefabricated component design dataset D design Perform analysis and use machine learning models to predict performance. The machine learning models include regression models and neural network models. The performance prediction formula is: Among them, σ is the activation function, is the weight parameter of the neural network, is the weight of the input parameter, is the bias term, n1, n2, n3 are the number of layers of the neural network; S73, based on the performance prediction result of step S72, the prefabricated component design is optimized using an optimization algorithm, the optimization goal includes meeting specific functional requirements and durability requirements, and the objective function of the optimization algorithm is: Among them, P target is the target performance value, θ is the adjustment coefficient, β j is the weight of different features, γ is the bias term, a j , b j 、c j is the weight of the input parameter; S74. Verify the optimized prefabricated component design by simulation technology, wherein the simulation technology includes finite element analysis and computer simulation to verify the performance of the prefabricated component in an actual use environment; S75. Further adjust and optimize the design of prefabricated components based on the results of simulation verification to ensure that the prefabricated components meet the functional and durability requirements in actual use; S76, converting the final optimized prefabricated component design into manufacturing instructions to guide the production and manufacturing of the prefabricated components, wherein the manufacturing instructions are expressed in the form of: Among them, C i is the instruction for the i-th manufacturing step, and m'' is the number of manufacturing steps.

Images