A tunnel construction progress dynamic management method and system

Abstract

The application provides a tunnel construction progress dynamic management method and system, acquires a key construction path with the longest duration in multiple project construction paths in a tunnel construction project, inputs rate influencing factor data of each sub-construction project into a pre-trained tunnel construction rate prediction model and outputs a construction rate prediction value of each sub-construction project, divides the workload of each sub-construction project by the corresponding construction rate prediction value to obtain a predicted construction duration of each sub-construction project, adds up to obtain a tunnel predicted construction duration of the tunnel construction project and determines a construction plan date; dynamically sets multiple monitoring time points according to the supervision requirements of the tunnel construction project, calculates a current progress deviation rate and a dynamic target duration deviation rate of each monitoring time point to obtain a duration delay index; judges the construction progress of the tunnel construction project at each monitoring time point according to the duration delay index and gives a prompt and a warning to guide the adjustment of the subsequent construction progress of the tunnel construction project.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of progress management, and particularly relates to a tunnel construction progress dynamic management method and system. BACKGROUND

[0002] Railway construction projects have high cost, large investment demand, long line, many participating construction parties, strict quality standards, long construction period, complicated procedures, complex external coordination and much information processing, so that continuous and dynamic regulation and control are essential in the construction process. With the increasing complexity of the construction environment and the continuous expansion of the project scale, the traditional management strategy of construction plan has been unable to meet the needs of senior project management. Effective implementation of design goals, reduction of project risks, promotion of efficient circulation of information and ensuring of management accuracy are the main problems to be solved at present. Among the three goals of engineering project management, the optimization of progress management has a particularly important significance for improving the quality of management.

[0003] In the prior art, the research on construction progress prediction and optimization has achieved rich results, involving project management, data analysis and information technology. These researches mainly focus on two aspects of duration prediction and progress control. The duration prediction mainly relies on preliminary project planning and in-depth analysis of uncertain elements in the project to determine the overall expected duration of the project, while the progress control is more focused on using historical data and analyzing key construction paths to optimize progress plan and resource allocation in the project construction phase. The current progress control research often does not fully consider the dynamic changes in the actual construction process, which leads to a large deviation between the actual execution of resource allocation and progress plan. SUMMARY

[0004] Therefore, the embodiments of the present application provide a tunnel construction progress dynamic management method and system to eliminate or improve one or more defects in the prior art, and solve the problem that the tunnel construction progress cannot be dynamically managed and adjusted in the prior art.

[0005] One aspect of the present application provides a tunnel construction progress dynamic management method, which comprises the following steps:

[0006] Obtaining a key construction path in a tunnel construction project, the key construction path being the longest in duration among a plurality of project construction paths, the project construction path being obtained by arranging a plurality of sub-construction projects in construction order;

[0007] Based on the pre-established index system for personnel management, material reserves, process methods, environmental conditions and mechanical equipment, rate influencing factor data of each sub-construction project in the key construction path is obtained, the rate influencing factor data of each sub-construction project is input into a pre-trained tunnel construction rate prediction model, and a construction rate prediction value of each sub-construction project is output; the tunnel construction rate prediction model is trained based on a back propagation neural network model; the predicted construction duration of each sub-construction project is obtained by dividing the workload of each sub-construction project by the corresponding construction rate prediction value, and the tunnel predicted construction duration of the tunnel construction project is obtained by adding up, and the construction plan date is determined;

[0008] According to the supervision requirements of the tunnel construction project, a plurality of monitoring time points are dynamically set, the current progress deviation rate and the dynamic target duration deviation rate are calculated at each monitoring time point, and the duration delay index is obtained according to the current progress deviation rate and the dynamic target duration deviation rate;

[0009] According to the duration delay index, the construction progress of the tunnel construction project at each monitoring time point is judged, and prompt and warning are given to guide the adjustment of the subsequent construction progress of the tunnel construction project.

[0010] In some embodiments, the tunnel construction rate prediction model is trained by the following method:

[0011] A training sample set is obtained, the training sample set contains a plurality of samples, each sample contains rate influencing factor data collected for a single sub-construction project, and a corresponding construction rate prediction value is added as a label; the rate influencing factor data is collected based on the pre-established index system for personnel management, material reserves, process methods, environmental conditions and mechanical equipment;

[0012] An initial neural network model is obtained, the initial neural network model takes the rate influencing factor data in each sample as input and takes the construction rate prediction value as output; the initial neural network model adopts a back propagation neural network model; the back propagation neural network model includes an input layer, a hidden layer and an output layer arranged in sequence;

[0013] The construction rate prediction value of each sample is compared with the label and a loss function is constructed, and the initial neural network model is updated by parameter iteration to minimize the loss function, and the updated initial neural network model is constructed as a tunnel construction rate prediction model.

[0014] In some embodiments, the method further comprises:

[0015] The hidden layer uses an activation function to process the weighted sum of the rate influencing element data in each sample to obtain the construction rate prediction value of each sample.

[0016] In some embodiments, dynamically setting multiple monitoring time points according to the regulatory requirements of the tunnel construction project comprises:

[0017] According to the time interval regulatory requirements of the tunnel construction project, the monitoring time points are set in time intervals of weeks, half months, and months.

[0018] In some embodiments, the expression for calculating the current progress deviation rate at each monitoring time point is:

[0019] ;

[0020] wherein, represents the actual construction date from the start of the tunnel construction project to the monitoring time point, represents the construction plan date from the start of the tunnel construction project to the monitoring time point.

[0021] In some embodiments, the expression for calculating the dynamic target duration deviation rate at each monitoring time point is:

[0022] ;

[0023] wherein, represents the predicted construction duration at the monitoring time point, represents the planned construction duration at the monitoring time point.

[0024] In some embodiments, the expression for obtaining the duration delay indicator according to the current progress deviation rate and the dynamic target duration deviation rate is:

[0025] ;

[0026] wherein, represents the weight of the current progress deviation rate, represents the weight of the dynamic target duration deviation rate.

[0027] In some embodiments, judging the construction progress of the tunnel construction project at each monitoring time point according to the duration delay indicator and providing prompts and warnings comprises:

[0028] According to the difficulty of the late-stage control of the tunnel construction project, a plurality of grade interval boundaries of the construction duration delay index are determined, and at least four grade intervals are divided by using the grade interval boundaries; each grade interval corresponds to an extremely difficult control early warning requiring severe warning, a difficult control early warning requiring moderate warning, a relatively difficult control early warning requiring light warning, and an easy control early warning requiring no warning.

[0029] Another aspect of the present application provides a tunnel construction progress dynamic management system, which is used to execute the tunnel construction progress dynamic management method described above, and the system comprises:

[0030] A critical construction path analysis module is configured to obtain a critical construction path in the tunnel construction project, the critical construction path being the longest in duration among a plurality of project construction paths, the project construction paths being obtained by arranging a plurality of sub-construction projects in a construction sequence;

[0031] A construction duration prediction module is configured to obtain rate influencing factor data of each sub-construction project in the critical construction path based on an index system pre-established for personnel management, material reserves, process methods, environmental conditions, and mechanical equipment, input the rate influencing factor data of each sub-construction project into a pre-trained tunnel construction rate prediction model, and output a construction rate prediction value of each sub-construction project; the tunnel construction rate prediction model is trained based on a back propagation neural network model; the predicted construction duration of each sub-construction project is obtained by dividing the workload of each sub-construction project by the corresponding construction rate prediction value, and the tunnel predicted construction duration of the tunnel construction project is obtained by adding the predicted construction durations of the sub-construction projects, and a construction plan date is determined;

[0032] A construction duration delay index calculation module is configured to dynamically set a plurality of monitoring time points according to the supervision requirements of the tunnel construction project, calculate a current progress deviation rate and a dynamic target duration deviation rate at each monitoring time point, and obtain a construction duration delay index according to the current progress deviation rate and the dynamic target duration deviation rate;

[0033] A construction progress early warning and adjustment module is configured to determine the construction progress of the tunnel construction project at each monitoring time point according to the construction duration delay index, and provide a prompt and an early warning to guide the adjustment of the subsequent construction progress of the tunnel construction project.

[0034] In some embodiments, the system further comprises:

[0035] A cloud storage module is configured to store the critical construction path, the construction rate prediction value of each sub-construction project, the predicted construction duration of each sub-construction project, the tunnel predicted construction duration, and the construction duration delay index.

[0036] The present application has at least the following beneficial effects:

[0037] The tunnel construction progress dynamic management method and system of this invention analyzes and obtains the critical construction path of the tunnel construction project, providing time and progress control for dynamic control of the construction period. The critical construction path is the longest construction path among multiple project construction paths, determining the shortest completion time of the tunnel construction project. Identifying the critical construction path facilitates refined management of the tunnel construction project. The rate influencing factor data of each sub-construction project are input into a pre-trained tunnel construction rate prediction model, and the predicted construction rate value of each sub-construction project is output. The predicted construction period of each sub-construction project is obtained by dividing the workload of each sub-construction project by the corresponding predicted construction rate value, which is conducive to adjusting resource allocation according to the actual construction situation to shorten the construction period and reduce costs. The construction period delay index is calculated based on the current progress deviation rate and the dynamic target construction period deviation rate, which can monitor the construction progress and actual completion status of the tunnel construction project. The tunnel construction project progress at the monitoring time point is obtained based on the construction period delay index, and prompts and warnings are given to adjust the subsequent construction progress of the tunnel construction project, thereby realizing dynamic management of the construction progress.

[0038] Additional advantages, objects, and features of the invention will be set forth in part in the description which follows, and will also become apparent in part to those skilled in the art upon studying the description, or may be learned by practice of the invention. The objects and other advantages of the invention can be realized and obtained by means of the structures specifically pointed out in the description and drawings.

[0039] Those skilled in the art will understand that the objectives and advantages achievable with the present invention are not limited to those specifically described above, and that the above and other objectives achievable with the present invention will become clearer from the following detailed description. Attached Figure Description

[0040] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, are not intended to limit the scope of the invention. In the drawings:

[0041] Figure 1 This is a flowchart illustrating the dynamic management method for tunnel construction progress according to an embodiment of the present invention.

[0042] Figure 2 This is a schematic diagram of the tunnel construction rate prediction model according to an embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the embodiments and accompanying drawings. Here, the illustrative embodiments and descriptions of this invention are used to explain the invention, but are not intended to limit the invention.

[0044] It should also be noted that, in order to avoid obscuring the invention with unnecessary details, only the structures and / or processing steps closely related to the solution according to the invention are shown in the accompanying drawings, while other details that are not closely related to the invention are omitted.

[0045] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, element, step, or component, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0046] It should also be noted that, unless otherwise specified, the term "connection" in this article can refer not only to a direct connection, but also to an indirect connection involving an intermediary.

[0047] In the following description, embodiments of the invention will be illustrated with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar parts, or the same or similar steps.

[0048] Existing technologies have yielded substantial results in construction schedule prediction and optimization, encompassing project management, data analysis, and information technology. These studies primarily focus on two aspects: schedule prediction and schedule control. Schedule prediction relies heavily on preliminary project planning and in-depth analysis of uncertainties within the project to determine the overall expected duration. Schedule control, on the other hand, emphasizes optimizing schedule plans and resource allocation during the construction phase by utilizing historical data and analyzing critical construction paths. Current schedule control research often fails to adequately consider the dynamic changes during actual construction, leading to significant deviations in resource allocation and schedule planning during actual execution. This invention proposes a dynamic management method and system for tunnel construction schedules, identifying the longest critical construction path among multiple project construction paths in a tunnel construction project. This is based on pre-established considerations for personnel management, material reserves, construction processes, environmental conditions, and machinery and equipment. The indicator system obtains the rate-influencing factor data of each sub-construction project in the key construction path. The rate-influencing factor data of each sub-construction project is input into a pre-trained tunnel construction rate prediction model, and the predicted construction rate value of each sub-construction project is output. The tunnel construction rate prediction model is trained based on a backpropagation neural network model. The workload of each sub-construction project is divided by the corresponding predicted construction rate value to obtain the predicted construction period of each sub-construction project. The predicted construction period of the tunnel construction project is obtained by summing them, and the construction plan date is determined. Multiple monitoring time points are dynamically set according to the supervision requirements of the tunnel construction project. The current progress deviation rate and dynamic target period deviation rate of each monitoring time point are calculated, and the period delay index used to judge the construction progress of the tunnel construction project at each monitoring time point is obtained. The subsequent construction progress of the tunnel construction project is adjusted according to the prompts and early warning guidance.

[0049] Figure 1 This is a flowchart illustrating a method for dynamic management of tunnel construction progress according to an embodiment of the present invention. Specifically, this application provides a method for dynamic management of tunnel construction progress, which includes the following steps S101~S104:

[0050] Step S101: Obtain the critical construction path in the tunnel construction project. The critical construction path is the one with the longest construction period among multiple project construction paths. The project construction path is obtained by arranging multiple sub-construction projects in the order of construction sequence.

[0051] Step S102: Based on the pre-established indicator system for personnel management, material reserves, process methods, environmental conditions, and machinery and equipment, obtain the rate influencing factor data of each sub-construction project in the critical construction path. Input the rate influencing factor data of each sub-construction project into the pre-trained tunnel construction rate prediction model and output the construction rate prediction value of each sub-construction project. The tunnel construction rate prediction model is trained based on the backpropagation neural network model. Divide the workload of each sub-construction project by the corresponding construction rate prediction value to obtain the predicted construction period of each sub-construction project. Add them together to obtain the predicted construction period of the tunnel construction project and determine the construction schedule date.

[0052] Step S103: Dynamically set multiple monitoring time points according to the supervision requirements of the tunnel construction project, calculate the current progress deviation rate and the dynamic target schedule deviation rate at each monitoring time point, and obtain the schedule delay index based on the current progress deviation rate and the dynamic target schedule deviation rate.

[0053] Step S104: Determine the construction progress of the tunnel construction project at each monitoring time point based on the construction delay index, and provide prompts and warnings to guide the adjustment of the subsequent construction progress of the tunnel construction project.

[0054] In step S101, based on the construction time parameters of each sub-construction project in the tunnel construction project, the sub-construction projects with zero total float and zero free float are identified as critical tasks. The critical tasks are arranged in the order of construction to obtain the critical construction path. The critical construction path is the path with the longest construction period among the multiple project construction paths. The shortest completion time of the tunnel construction project is determined based on the critical construction path. Identifying the critical construction path is beneficial for the refined management of the tunnel construction project, so as to ensure that the tunnel construction project can be executed according to plan.

[0055] In step S102, the predicted construction rate of each sub-construction project is obtained according to the tunnel construction rate prediction model, and the predicted tunnel construction time is calculated by combining it with the workload of tasks in the critical construction path. Figure 2This is a schematic diagram of the tunnel construction rate prediction model according to an embodiment of the present invention. In some embodiments, the training process of the tunnel construction rate prediction model includes steps S1021 to S1023:

[0056] Step S1021: Obtain the training sample set. The training sample set contains multiple samples. Each sample contains rate influencing factor data collected for a single sub-construction project, and adds the corresponding construction rate prediction value as a label. The rate influencing factor data is collected from a pre-established indicator system for personnel management, material reserves, process methods, environmental conditions, and machinery and equipment.

[0057] Step S1022: Obtain the initial neural network model. The initial neural network model takes the rate influence element data in each sample as input and the construction rate prediction value as output. The initial neural network model adopts the backpropagation neural network model. The backpropagation neural network model includes continuously set input layer, hidden layer and output layer.

[0058] Step S1023: Compare the predicted construction rate of each sample with the label and construct a loss function. With the goal of minimizing the loss function, iteratively update the parameters of the initial neural network model and construct the updated initial neural network model as a tunnel construction rate prediction model.

[0059] Specifically, based on the actual construction data from the railway engineering management platform, data related to progress management is obtained, and rate-influencing factor data with validity and accuracy are selected as the input layer sample according to the factors affecting tunnel construction progress. The sample includes rate-influencing factor data collected for individual sub-construction projects. Table 1 shows the rate-influencing factor data table. The personnel management indicator system collects data on the performance of key management personnel, the availability of management personnel, the availability of operational personnel, average monthly indicators, construction site environmental index, data on hidden danger investigation and management, safety risk control data, and geological risk control data; the material reserve indicator system collects data on the availability of main materials, data on unqualified materials, and monthly investment data; the process and method indicator system collects planned rate, planned construction period (speed), number of construction days, number of design changes, and construction efficiency under construction conditions; the environmental condition indicator system collects data on the impact of temperature, precipitation, high ground stress, adverse geology and weak surrounding rock, geological forecast risk rate, and environmental factors; the machinery and equipment indicator system collects the actual usage of machinery. After the samples are input into the initial neural network model, the data is processed by the hidden layer to output the predicted construction rate value of each sub-construction project; in some embodiments, the tunnel construction progress dynamic management method further includes: the hidden layer performs weighted summation of the rate influencing factor data in each sample and then uses an activation function to process the data to obtain the predicted construction rate value of each sample.

[0060] Table 1 Data table of factors affecting rate

[0061]

[0062] Table 1 Data table of factors affecting rate

[0063]

[0064] Furthermore, the initial neural network model employs a backpropagation (BP) neural network model. The backpropagation neural network model includes an input layer, hidden layers, and an output layer. After a sample enters the input layer, it is multiplied by its corresponding weight, summed, and then input into an activation function to calculate the output result. The predicted output is compared with the actual result. Based on the generated error, backpropagation is performed, and the weights are iteratively adjusted multiple times using gradient descent. A loss function is constructed by comparing the predicted construction rate with the label. The weights are adjusted multiple times by minimizing the loss function to reduce the error. The input layer contains input layer neurons, and the hidden layer contains hidden layer neurons. Data passing through the neurons is processed by activation functions, including the Sigmoid function, Tanh function, ReLU function, and Softmax function. Hidden layer neurons X... c1 X c2 , ..., X ck For the data X1, X2, X3, ..., X in the training sample set 23 The weighted W is calculated and then processed by an activation function to output the predicted construction rate.

[0065] In steps S103 and S104, multiple monitoring time points are dynamically set according to the supervision requirements of the tunnel construction project. The monitoring time points are set using various time units such as weeks and months. In some embodiments, dynamically setting multiple monitoring time points according to the supervision requirements of the tunnel construction project includes setting monitoring time points according to the time interval supervision requirements of the tunnel construction project, with time intervals of weeks, half months and months.

[0066] Specifically, the monitoring period between two monitoring time points is reserved for a period of one week, half a month, or one month. The monitoring time points are set on the critical construction path to predict the completion time of the entire tunnel construction project. The monitoring data at the monitoring time points are used to monitor the real-time changes in the construction progress and adjust the progress of the tunnel construction project according to the actual completion status at the monitoring time points.

[0067] In some embodiments, the expression for calculating the current progress deviation rate at each monitoring time point is:

[0068] ;

[0069] in, This indicates the actual construction period from the start of the tunnel construction project to the monitoring time point. This indicates the planned construction dates from the start of the tunnel construction project to the monitoring time point.

[0070] In some embodiments, the expression for calculating the dynamic target schedule deviation rate at each monitoring time point is:

[0071] ;

[0072] in, This indicates the predicted construction period at the monitoring time point. This indicates the planned construction period at the monitoring time point.

[0073] Specifically, the current progress deviation rate is used to determine the current construction progress delays of the tunnel construction project and to ascertain the difficulty of subsequent construction work; when hour, This indicates that construction progress is delayed and risks are escalating. This indicates that the construction progress delay remains unchanged. This indicates that construction delays have been effectively controlled and risks have been reduced. This indicates that the construction progress is ahead of schedule, increasing the probability of the tunnel construction project being completed; the current progress deviation rate describes the time delay status before the current monitoring time point and the time delay trend around the current monitoring time point, which is helpful in showing the delay status of the entire project. express The current progress deviation rate at the next monitoring time point.

[0074] In some embodiments, the expression for calculating the schedule delay index based on the current schedule deviation rate and the dynamic target schedule deviation rate is as follows:

[0075] ;

[0076] in, The weight representing the current schedule deviation rate, The weight representing the deviation rate of the dynamic target schedule.

[0077] Specifically, and The sum of these factors is 1. Based on preset tunnel progress management standards, the construction progress at each monitoring point is judged by the schedule delay index calculated according to the current progress deviation rate and the dynamic target schedule deviation rate at each monitoring time point. The tunnel construction project schedule is affected by various factors and will change during the construction process. By establishing an effective monitoring system to monitor the real-time changes in construction progress, the progress of the construction project can be dynamically adjusted and controlled in a timely manner. The tunnel construction project progress status at the current monitoring time point is obtained based on the schedule delay index, and progress warnings are issued according to the level of the tunnel construction project progress status.

[0078] In some embodiments, tunnel construction project progress warnings based on schedule delay indicators at monitoring time points include extremely difficult control warnings requiring severe alerts, difficult control warnings requiring moderate alerts, relatively difficult control warnings requiring mild alerts, and easily controllable warnings requiring no alerts. Table 2 is a tunnel progress management standard table. Level interval boundaries are set according to the actual tunnel construction project conditions. and The different construction progress situations are classified into levels based on the level range boundaries. The levels are divided into controllable work areas, requiring only minor warnings, relatively difficult controllable work areas, and uncontrollable work areas, according to the difficulty of controlling the construction progress from easy to difficult. When it is an uncontrollable working surface, This is a relatively difficult-to-control work surface, when At that time, the work surface was basically controllable. The time is within the controllable working area.

[0079] Table 2. Tunnel Construction Progress Management Standards

[0080]

[0081] On the other hand, the present invention also provides a dynamic management system for tunnel construction progress, the system being used to execute the above-described dynamic management method for tunnel construction progress, the system comprising:

[0082] The critical construction path analysis module is used to obtain the critical construction path in a tunnel construction project. The critical construction path is the one with the longest construction period among multiple project construction paths. The project construction path is obtained by arranging multiple sub-construction projects in the order of construction.

[0083] The construction period prediction module is used to acquire rate-influencing factor data for each sub-construction item in the critical construction path based on a pre-established indicator system for personnel management, material reserves, construction processes, environmental conditions, and machinery and equipment. This data is then input into a pre-trained tunnel construction rate prediction model, which outputs the predicted construction rate value for each sub-construction item. The tunnel construction rate prediction model is trained based on a backpropagation neural network model. The predicted construction period for each sub-construction item is obtained by dividing its workload by its corresponding predicted construction rate value. These predicted values ​​are then summed to obtain the predicted tunnel construction period for the entire tunnel project, and the planned construction date is determined.

[0084] The project delay index calculation module is used to dynamically set multiple monitoring time points according to the supervision requirements of tunnel construction projects. At each monitoring time point, the current progress deviation rate and the dynamic target project duration deviation rate are calculated, and the project delay index is obtained based on the current progress deviation rate and the dynamic target project duration deviation rate.

[0085] The construction progress early warning and adjustment module is used to determine the construction progress of the tunnel construction project at each monitoring time point based on the construction period delay index, and to provide prompts and early warnings to guide the adjustment of the subsequent construction progress of the tunnel construction project.

[0086] In some embodiments, the system further includes:

[0087] The cloud storage module is used to store critical construction paths, predicted construction rates for each sub-construction project, predicted construction periods for each sub-construction project, predicted tunnel construction periods, and project delay indicators.

[0088] The present invention will now be described with reference to a specific embodiment:

[0089] This invention provides a dynamic management method and system for tunnel construction. It aims to combine data from a railway engineering management platform with existing standards to analyze factors affecting tunnel construction progress, including personnel management, material reserves, construction techniques, environmental conditions, and machinery. The system comprehensively identifies and dynamically tracks construction progress, constructs a BP neural network to establish the coupling relationship between multiple factors (personnel, machinery, materials, methods, environment, and schedule) and the construction period, and establishes a tunnel construction rate prediction model. A dynamic control method for construction progress based on critical construction path constraints is proposed and verified using a railway tunnel as an example in a project. This continuously improves the optimal allocation of on-site resources under the given time constraints, enhancing construction efficiency in different sections and work areas while ensuring quality, quantity, and safety. It also promotes more advanced construction concepts and management models among different construction companies, achieving dynamic management of tunnel construction progress.

[0090] A tunnel construction rate prediction model is established based on a pre-established indicator system for personnel management, material reserves, construction techniques, environmental conditions, and machinery and equipment. This model acquires data on the rate-influencing factors of each sub-construction item in the critical construction path and their impact on the project duration. First, text mining analysis is used to analyze the rate-influencing factor data. Then, a backpropagation (BP) neural network is used to analyze and learn from the existing data, calculating the impact of different rate-influencing factor data on the project duration and predicting the construction time required to complete the construction plan for a specific period under different influencing conditions. This model allows for monitoring the progress of a specific working face and the overall tunnel construction project, understanding the impact of resource allocation on construction progress, and providing a basis for timely updating of the schedule and adjusting the tunnel breakthrough time.

[0091] Schedule management of tunnel construction projects is achieved through critical construction paths. First, existing project data is obtained, including multiple sub-projects within the tunnel construction project and the time impact parameters of each sub-project. Then, the critical construction path is identified to provide time and schedule constraints for dynamic control of the project duration. The critical construction path is the path that has the greatest impact on the overall project duration and determines the shortest completion time of the tunnel construction project. Identifying the critical construction path helps to achieve refined management of the construction schedule.

[0092] By combining the time and schedule constraints provided by the critical construction path with the calculation results of the tunnel construction rate prediction model, the project duration prediction and optimal resource allocation can be achieved. The expression is as follows:

[0093] ;

[0094] The tunnel construction period is calculated by combining the workload of critical activities along the critical construction path with the construction rate predicted by the tunnel construction rate prediction model. This allows for the estimation of the tunnel's completion time, facilitating the rational scheduling of construction activities. This method helps adjust resource allocation based on actual construction conditions, thereby shortening the construction period and reducing costs.

[0095] 1. By filtering data related to progress management through the railway engineering management platform, and based on the pre-established indicator system for personnel management, material reserves, process methods, environmental conditions and mechanical equipment, data on the rate-influencing factors of each sub-construction project in the critical construction path are obtained.

[0096] 2. Construct a tunnel construction rate prediction model based on BP neural network.

[0097] (1) The railway engineering management platform collects and sets the types and numerical limits of the input layer data.

[0098] (2) The data of the input layer were preprocessed to form a training sample set for duration rate prediction.

[0099] (3) The code for the initial neural network model was written using Matlab software.

[0100] (4) The training sample set for duration prediction was imported and iterative calculations were performed.

[0101] (5) Analyze the calculation results and select the weight with the smallest error to construct a tunnel construction rate prediction model; obtain the prediction results of tunnel construction rate by inputting the data sample to be predicted.

[0102] (6) Compare and analyze whether the accuracy of the predicted data has improved over time; compare and analyze the accuracy of prediction based on weekly, semi-monthly and monthly data collection, and select a reasonable data collection time.

[0103] The tunnel construction rate prediction model requires a training sample encompassing 23 variables X that may affect construction progress, and one output variable: the predicted construction rate value. The selected training sample varies depending on the construction location and workflow. The chosen training sample is based on actual construction data recorded on the management platform, and is rationally selected and eliminated based on the degree of influence of the variables affecting progress on specific processes to ensure data validity and accuracy. Furthermore, due to the uncertainties of tunnel construction, progress is not recorded daily, and the daily progress in meters is not entirely accurate due to the uncertainties of drill-and-blast blasting. Therefore, this study prioritizes weekly data for statistical analysis. Progress is the distance the tunnel excavation face advances during tunnel excavation.

[0104] 3. Progress control methods for tunnel construction projects.

[0105] Based on the principles for establishing a construction delay early warning index system and referring to existing literature, monitoring time points were selected. Current schedule deviation rate ( ) and dynamic target schedule deviation rate ( () as a dynamic control indicator.

[0106] 3.1 Setting monitoring time points.

[0107] Because the construction period is affected by numerous factors and may fluctuate during tunnel construction, establishing an effective monitoring system is crucial for capturing real-time changes in construction progress. To ensure the achievement of predetermined tunnel construction project goals, monitoring equipment is typically deployed on-site to effectively track and control the project's timeline and actual progress. Utilizing monitoring data to adjust and improve the construction schedule is an efficient method. In this process, rationally determining monitoring time points is key. Based on the specific monitoring requirements of the tunnel construction project, various time units such as weeks, bi-weekly periods, and months can be selected as benchmarks for progress monitoring. These monitoring time points are set on the critical construction paths of the construction network plan, and the setting of monitoring time points also needs to have a certain time span, estimating the completion time of the working face to control the overall tunnel breakthrough time.

[0108] 3.2 The expression for the current schedule deviation rate is:

[0109] ;

[0110] in, This indicates the actual construction period from the start of the tunnel construction project to the monitoring time point. This indicates the planned construction dates from the start of the tunnel construction project to the monitoring point. hour, This indicates that the risk of schedule delays is accelerating and the situation continues to worsen. This indicates that the progress will remain at the original pace despite the delay. This indicates that schedule delays have been effectively controlled, and risks have been relatively reduced; when This indicates an increased probability of tunnel construction progress being completed ahead of schedule.

[0111] 3.3 The expression for the dynamic target schedule deviation rate is:

[0112] ;

[0113] ;

[0114] in, This indicates the predicted construction period at the monitoring time point. The planned construction period at the monitoring time point is indicated by the current surrounding rock grade calendar day, which represents the actual number of days the tunnel construction project has taken, and the construction day of the current surrounding rock grade represents the number of days with tunnel progress.

[0115] Current schedule deviation rate ( This describes the time delay status before the monitoring time point and the time delay trend closer to the monitoring time point, which helps to show the delay status of the entire tunnel construction project.

[0116] 3.4 The expression for the project delay index is:

[0117] ;

[0118] in, The weight representing the current schedule deviation rate, The weights representing the dynamic target schedule deviation rate, and The sum of is 1.

[0119] 3.5 Tunnel construction progress management standards.

[0120] Progress control sets grade interval boundaries based on the actual tunnel construction project. and Different construction progress situations are divided into controllable work areas, basically controllable work areas, relatively difficult controllable work areas, and uncontrollable work areas. The work area is currently uncontrollable and extremely difficult to control later. A severe warning is warranted, and measures should be taken to avoid it or reduce the level of risk. The work area is relatively difficult to control at the time, and subsequent control will be difficult. It is a moderate warning and requires enhanced monitoring and handling. The work area is basically under control at the time, but later control is difficult. A slight warning is warranted, and monitoring is required. The work area is under control and requires no warning; it can be ignored.

[0121] In summary, this invention provides a method and system for dynamic management of tunnel construction progress. It obtains the critical construction path in a tunnel construction project, which is the longest construction path among multiple project construction paths. The project construction path is obtained by arranging multiple sub-construction projects in the order of construction. The rate-influencing factor data of each sub-construction project are input into a pre-trained tunnel construction rate prediction model, and the predicted construction rate value of each sub-construction project is output. The workload of each sub-construction project is divided by the corresponding predicted construction rate value to obtain the predicted construction period of each sub-construction project. These are summed to obtain the predicted tunnel construction period of the entire tunnel construction project, and the planned construction date is determined. Multiple monitoring time points are dynamically set according to the supervision requirements of the tunnel construction project, and the current progress deviation rate and dynamic target construction period deviation rate are calculated at each monitoring time point. A construction period delay index is obtained based on the current progress deviation rate and the dynamic target construction period deviation rate. The construction progress of the tunnel construction project at each monitoring time point is judged based on the construction period delay index, and prompts and warnings are issued to guide adjustments to the subsequent construction progress of the tunnel construction project.

[0122] Those skilled in the art will understand that the exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention. When implemented in hardware, it can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the desired tasks. The programs or code segments can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave.

[0123] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0124] In this invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or in place of features of other embodiments.

Claims

1. A method for dynamic management of tunnel construction progress, characterized in that, The method includes the following steps: The critical construction path in a tunnel construction project is obtained. The critical construction path is the one with the longest construction period among multiple project construction paths. The project construction path is obtained by arranging multiple sub-construction projects in the order of construction. Based on a pre-established indicator system for personnel management, material reserves, construction processes, environmental conditions, and machinery and equipment, data on the rate-influencing factors of each sub-construction project in the critical construction path are obtained. This data is then input into a pre-trained tunnel construction rate prediction model, which outputs a predicted construction rate value for each sub-construction project. The tunnel construction rate prediction model is trained based on a backpropagation neural network model. The predicted construction period for each sub-construction project is obtained by dividing its workload by the corresponding predicted construction rate value. These predicted construction periods are then summed to obtain the predicted tunnel construction period for the entire tunnel project, and the planned construction date is determined. Multiple monitoring time points are dynamically set according to the supervision requirements of the tunnel construction project. At each monitoring time point, the current progress deviation rate and the dynamic target schedule deviation rate are calculated. The schedule delay index is obtained based on the current progress deviation rate and the dynamic target schedule deviation rate. The construction progress of the tunnel construction project at each monitoring time point is determined based on the aforementioned construction period delay index, and prompts and warnings are issued to guide adjustments to the subsequent construction progress of the tunnel construction project. The tunnel construction rate prediction model is trained using the following method: A training sample set is obtained, which contains multiple samples. Each sample contains rate-influencing factor data collected for a single sub-construction project, and the corresponding construction rate prediction value is added as a label. The rate-influencing factor data is collected from a pre-established indicator system for personnel management, material reserves, process methods, environmental conditions, and machinery and equipment. An initial neural network model is obtained, which takes the rate-influencing factor data in each sample as input and the construction rate prediction value as output; the initial neural network model adopts a backpropagation neural network model; the backpropagation neural network model includes a continuously set input layer, hidden layer and output layer. The predicted construction rate value of each sample is compared with the label and a loss function is constructed. The parameters of the initial neural network model are iteratively updated with the goal of minimizing the loss function. The updated initial neural network model is then used to construct a tunnel construction rate prediction model. Furthermore, the hidden layer performs a weighted summation of the rate-influencing factor data in each sample and then uses an activation function to process the data to obtain the construction rate prediction value for each sample. Among them, multiple monitoring time points are dynamically set according to the supervision requirements of the tunnel construction project, including: Based on the time interval monitoring requirements of the tunnel construction project, monitoring time points are set at weekly, semi-monthly, and monthly intervals. The expression for calculating the current progress deviation rate at each monitoring time point is as follows: ； in, This indicates the actual construction period from the start of the tunnel construction project to the monitoring time point. This indicates the planned construction dates from the start of the tunnel construction project to the monitoring time point; The expression for calculating the dynamic target schedule deviation rate at each monitoring time point is as follows: ； in, This indicates the predicted construction period at the monitoring time point. This indicates the planned construction period at the monitored time point; The expression for obtaining the schedule delay index based on the current schedule deviation rate and the dynamic target schedule deviation rate is as follows: ； in, The weight representing the current schedule deviation rate, The weight representing the dynamic target schedule deviation rate; The process of determining the construction progress of the tunnel construction project at each monitoring time point based on the aforementioned construction delay index, and providing prompts and warnings, includes: Based on the difficulty of controlling the later stages of the tunnel construction project, multiple level interval boundary values ​​for the construction period delay index are determined, and at least four level intervals are divided using the level interval boundary values; each level interval corresponds to an extremely difficult control warning requiring severe warning, a difficult control warning requiring moderate warning, a relatively difficult control warning requiring mild warning, and an easy control warning requiring no warning.

2. A dynamic management system for tunnel construction progress, characterized in that, The system is used to execute the dynamic management method for tunnel construction progress as described in claim 1, and the system includes: The critical construction path analysis module is used to obtain the critical construction path in a tunnel construction project. The critical construction path is the one with the longest construction period among multiple project construction paths. The project construction path is obtained by arranging multiple sub-construction projects in the order of construction. The construction period prediction module is used to acquire rate-influencing factor data for each sub-construction project in the critical construction path based on a pre-established indicator system for personnel management, material reserves, construction processes, environmental conditions, and machinery and equipment. The module inputs the rate-influencing factor data for each sub-construction project into a pre-trained tunnel construction rate prediction model and outputs the predicted construction rate value for each sub-construction project. The tunnel construction rate prediction model is trained based on a backpropagation neural network model. The predicted construction period for each sub-construction project is obtained by dividing the workload of each sub-construction project by the corresponding predicted construction rate value. These predicted construction periods are then summed to obtain the predicted tunnel construction period for the entire tunnel construction project, and the planned construction date is determined. The project delay index calculation module is used to dynamically set multiple monitoring time points according to the supervision requirements of the tunnel construction project, calculate the current progress deviation rate and the dynamic target project duration deviation rate at each monitoring time point, and obtain the project delay index based on the current progress deviation rate and the dynamic target project duration deviation rate. The construction progress early warning and adjustment module is used to determine the construction progress of the tunnel construction project at each monitoring time point based on the construction period delay index, and to provide prompts and early warnings to guide the adjustment of the subsequent construction progress of the tunnel construction project.

3. The tunnel construction progress dynamic management system according to claim 2, characterized in that, The system also includes: The cloud storage module is used to store the key construction path, the predicted construction rate of each sub-construction project, the predicted construction period of each sub-construction project, the predicted construction period of the tunnel, and the construction period delay index.

Images