Intelligent scheduling decision system for tunnel construction based on data fusion

Abstract

The present invention relates to the technical field of tunnel construction transportation scheduling, and specifically to a data fusion-based intelligent scheduling decision-making system for tunnel construction. The present invention uses a work surface demand prediction module to collect data in real time and, in combination with historical curves and schedules, predict concrete demand. This data is then combined with the concrete supply of the mixing station within a future time window to evaluate the supply and demand balance index of the mixing station. When the supply and demand balance index deviates from a threshold, a multi-factor combination is used to determine and generate a feed priority. A set of schedulable work surfaces is screened based on the feed priority and concrete demand of each work surface. Based on the last concrete transport time of all schedulable work surfaces and the concrete loading time of the mixing station, a transport scheduling target is dynamically generated for all concrete transport vehicles to be loaded at the mixing station. This provides precise decision-making support for intelligent scheduling of tunnel construction, improves transport efficiency and construction continuity, and enhances the flexibility and adaptability of transport scheduling.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction transportation scheduling, and in particular to a tunnel construction intelligent scheduling decision system based on data fusion. Background Art

[0002] As the scale of tunnel construction continues to expand, resource allocation and progress management during tunnel construction face unprecedented challenges. Tunnel construction involves multiple working surfaces, complex construction processes, and the coordinated operation of multiple resources. Efficient resource utilization and effective control of construction progress are pressing issues.

[0003] Existing technologies, such as Chinese Patent Publication No. CN119809216A, disclose a tunnel construction scheduling method and computer equipment. By obtaining information on the process and face operations of each construction tunnel, as well as the completion time of the current process, the method assesses the construction difficulty of the current process and allocates construction personnel, vehicles, and equipment accordingly. This method implements resource allocation based on process difficulty, ensures the timely completion of each process in each construction tunnel, and improves the work efficiency of each construction tunnel.

[0004] Chinese patent publication number CN119358988A discloses a material scheduling method and system based on tunnel construction progress. By dividing the target tunnel into multiple construction tunnel units, the detailed materials required for the next process stage are determined in combination with the construction design plan and the corresponding material scheduling is carried out to improve the accuracy of material scheduling during the tunnel construction process and enhance the efficiency of tunnel construction.

[0005] However, the existing technology has the following problems: 1. The existing technology has a single dimension for supply and demand balance assessment, which is only based on the scheduling of materials according to the construction progress. It does not comprehensively consider the constraints of raw material inventory and equipment operating status, and cannot accurately assess the supply and demand balance between the mixing station and the working surface, resulting in a deviation between resource supply and actual demand, and reducing the efficiency of resource allocation in the mixing station.

[0006] 2. Existing technologies determine resource allocation based solely on construction difficulty or a single factor, without considering the impact of geological conditions on construction urgency and the collaborative support capabilities of adjacent work surfaces. This results in incomplete scheduling decisions and makes it difficult to determine scientific and reasonable material supply priorities, resulting in incomplete scheduling decisions.

[0007] 3. The existing technology for generating transportation scheduling targets lacks dynamic timeliness analysis and does not combine the time difference analysis between the last transportation time and the loading time on the working surface. It is difficult to dynamically adjust the transportation sequence according to the real-time supply and demand status, which may lead to untimely concrete supply or waste of transportation resources. Summary of the Invention

[0008] The present invention aims to overcome the shortcomings of the existing technology and provide an intelligent scheduling decision-making system for tunnel construction based on data fusion. By collecting and analyzing data in real time, it can achieve accurate scheduling and efficient utilization of concrete resources during tunnel construction.

[0009] The technical solution adopted by the present invention to solve its technical problems is: an intelligent scheduling decision-making system for tunnel construction based on data fusion, including a working surface demand prediction module, a supply and demand balance assessment module, a scheduling demand judgment module, a schedulable working surface screening module and a transportation scheduling target generation module.

[0010] The connection relationship between each module is as follows: the work surface demand prediction module is connected to the supply and demand balance assessment module, the scheduling demand judgment module is connected to the supply and demand balance assessment module and the schedulable work surface screening module respectively, and the schedulable work surface screening module is connected to the transportation scheduling target generation module.

[0011] The working surface demand prediction module is used to collect the concrete consumption rate of each working surface in the tunnel construction project in real time, and combine the historical consumption curve with the construction schedule to predict the concrete demand in the future time window.

[0012] The supply and demand balance assessment module is used to collect raw material inventory and equipment operation data in the mixing station, analyze the concrete supply of the mixing station in the future time window, and evaluate the supply and demand balance index of the mixing station based on the concrete inventory and demand of each working surface.

[0013] The scheduling demand judgment module is used to generate the supply priority based on the current construction process key score, geological risk score and support capability value of the adjacent working surface when the supply and demand balance index deviates from the preset threshold.

[0014] The schedulable work surface screening module is used to obtain a set of schedulable work surfaces based on the fusion analysis of the feeding priority and concrete demand of each work surface.

[0015] The transport scheduling target generation module is used to obtain the last concrete transportation time of all schedulable work surfaces, combined with the concrete loading time of the mixing station, and dynamically generate the transport scheduling targets of all concrete transport vehicles to be loaded in the mixing station.

[0016] Compared with the existing technology, the present invention has the following beneficial effects: (1) The present invention adopts the working surface demand prediction module to collect the concrete consumption rate in real time, combines the historical consumption curve with the construction schedule to predict future demand, realizes the accurate prediction of concrete demand, and provides a reliable basis for scheduling decision-making.

[0017] (2) The present invention integrates the raw material inventory and equipment operation data of the mixing station, analyzes the effective supply under inventory constraints and equipment constraints, and combines the work surface demand with the inventory to evaluate the supply and demand balance index, effectively solving the problem of incomplete process evaluation, improving the matching degree between the mixing station's supply capacity and the work surface demand, optimizing the resource allocation efficiency, and ensuring the rational supply of concrete resources.

[0018] (3) The present invention generates material supply priorities based on a multi-dimensional comprehensive consideration of the key scores of the construction process of the working face, the geological risk scores and the support capability values ​​of the adjacent working faces, thereby solving the problem of a single factor in determining the scheduling priority, improving the scientificity and rationality of material supply decisions, and ensuring the smooth progress of tunnel construction.

[0019] (4) Based on the fusion analysis of material supply priority and concrete demand, the present invention forms a systematic scheduling operation surface set screening mechanism, realizes the optimal allocation of resources among different operation surfaces, and improves resource utilization efficiency.

[0020] (5) The present invention dynamically generates the transportation scheduling target of the transport vehicle by obtaining the last transportation time of the schedulable working surface and the loading time of the mixing station, ensuring the optimal configuration of the timing and sequence of concrete transportation, improving transportation efficiency and construction continuity, and enhancing the flexibility and adaptability of transportation scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a schematic diagram of system module connections of the present invention.

[0023] Figure 2 This is a schematic diagram of the specific steps of the concrete supply amount in the present invention.

[0024] Figure 3 This is a schematic diagram of the specific steps of the effective supply quantity of inventory constraints in the present invention.

[0025] Figure 4 Schematic diagram of the flow of the steps for determining the set of schedulable working surfaces in the present invention. DETAILED DESCRIPTION

[0026] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions, and numerical values ​​described in these embodiments do not limit the scope of the present invention. It should also be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn to scale.

[0027] The following description of at least one exemplary embodiment is merely illustrative in nature and is not intended to limit the invention, its application, or uses. Technologies, methods, and apparatus known to those skilled in the art may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the specification.

[0028] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0029] See also Figure 1 As shown, the present invention provides an intelligent scheduling decision-making system for tunnel construction based on data fusion, including a working surface demand prediction module, a supply and demand balance assessment module, a scheduling demand judgment module, a schedulable working surface screening module and a transportation scheduling target generation module.

[0030] The connection relationship between each module is as follows: the work surface demand prediction module is connected to the supply and demand balance assessment module, the scheduling demand judgment module is connected to the supply and demand balance assessment module and the schedulable work surface screening module respectively, and the schedulable work surface screening module is connected to the transportation scheduling target generation module.

[0031] The working surface demand prediction module is used to collect the concrete consumption rate of each working surface in the tunnel construction project in real time, and combine the historical consumption curve with the construction schedule to predict the concrete demand in the future time window.

[0032] It should be noted that the specific method of the working surface demand prediction module is: obtaining the concrete consumption of each working surface in the tunnel construction project in the current construction process, and obtaining the concrete consumption rate based on the comparative analysis of the concrete consumption and the construction time of the current construction process.

[0033] Based on the construction schedule of each working face, a tunnel construction project history record set that is identical to the construction schedule is selected, and a historical consumption curve of each working face is generated according to the concrete consumption of each historical record in the tunnel construction project history record set.

[0034] The concrete consumption rate of each working surface is matched with the historical consumption curve of the corresponding working surface in each historical record, and the concrete demand of each working surface in the future time window is extracted from the matched historical consumption curve.

[0035] Furthermore, the historical records of tunnel construction projects participated in in the past are collected from the internal file management and project management system of the tunnel construction project enterprise. The construction schedule includes the tunnel construction project type, construction schedule table, construction log and concrete consumption record.

[0036] The concrete demand for each working surface in the future time window is extracted as follows: if the concrete consumption rate of each working surface is the same as the concrete consumption rate corresponding to the historical consumption curve of the corresponding working surface in a certain historical record, the historical consumption curve of the corresponding working surface in the historical record is used as a matching historical consumption curve. The average concrete consumption in the future time window is extracted from all matching historical consumption curves and used as the concrete demand for each working surface in the future time window. The future time window can be set to the next 2 hours or 4 hours, for example.

[0037] The present invention adopts the working surface demand prediction module to collect the concrete consumption rate in real time, combines the historical consumption curve with the construction schedule to predict future demand, realizes the accurate prediction of concrete demand, and provides a reliable basis for scheduling decision-making.

[0038] The supply and demand balance assessment module is used to collect raw material inventory and equipment operation data in the mixing station, analyze the concrete supply of the mixing station in the future time window, and evaluate the supply and demand balance index of the mixing station based on the concrete inventory and demand of each working surface.

[0039] like Figure 2 As shown, the specific steps of analyzing the concrete supply of the mixing station in the future time window are as follows: S1. Based on the inventory of each raw material in the mixing station, a ratio analysis is performed between it and the unit concrete mix ratio usage of the corresponding raw material to infer the effective supply of the mixing station within the future time window under the inventory constraint.

[0040] S2. Analyze the operating data of each device in the mixing station in conjunction with the corresponding historical operating data of each device in the tunnel construction project to predict the probability of failure and average repair time of each device in the future time window. Combined with the length of the future time window, perform time difference analysis to determine the available time of the mixing station.

[0041] S3. The product of the available time of the mixing station and the rated capacity of the mixing station equipment is used as the effective supply of the equipment constraints of the mixing station in the future time window.

[0042] S4. Select the minimum value from the effective supply quantities of the inventory constraint and the equipment constraint of the mixing station in the future time window as the concrete supply quantity.

[0043] Furthermore, if Figure 3 As shown, the effective supply quantity of the mixing station constrained by inventory in the future time window is inferred in the following steps: S11, the ratio of the inventory quantity of each raw material to the unit concrete mix ratio of the corresponding raw material is used as the concrete production quantity corresponding to each raw material, and the minimum production quantity is selected as the concrete production quantity constrained by inventory.

[0044] S12. Based on the combined analysis of the future time window length and the rated capacity of the mixing station equipment, the theoretical maximum supply of the mixing station is obtained, and the minimum value between the concrete production volume and the theoretical maximum supply volume is used as the effective supply volume of the mixing station's inventory constraint within the future time window.

[0045] The theoretical maximum supply of the mixing station is the product of the length of the future time window and the rated production capacity of the mixing station equipment.

[0046] The raw materials of the concrete include but are not limited to cement, sand, gravel, and admixtures, etc. The amount of each raw material per unit concrete mix ratio is obtained from the standard concrete formula.

[0047] Furthermore, the steps for analyzing the available time of the mixing station are as follows: S21, normalizing the operating data of each device in the mixing station to generate an operating data vector for each device; similarly, extracting the historical operating data of each historical log in the current construction process from the corresponding historical operating data of each device in the tunnel construction project, and generating a historical operating data vector based on the historical operating data.

[0048] In a specific embodiment, the equipment in the mixing station includes a mixing main unit, a batching scale, a control system, an air compressor, a water pump, an admixture pump, etc. The operating data of each equipment includes current, voltage, temperature, pressure, vibration, etc.

[0049] S22. Calculate the similarity between the operating data vector of each device and the historical operating data vector of each historical log using a cosine similarity calculation formula. Filter out historical logs with similarities greater than a set similarity threshold. Filter out the number of historical logs with operating failures, and use the ratio of this number to the total number of filtered historical logs as the probability of failure. The cosine similarity calculation formula is based on prior art and will not be further described in detail in this invention.

[0050] S23. The average of the fault repair time in each historical log of the operational fault is used as the average repair time. A duration analysis is performed based on the product of the average repair time and the probability of the fault occurring and the duration of the future time window to obtain the available time of the mixing station.

[0051] The available time of the mixing plant is the future time duration minus the product of mean repair time and the probability of failure. The product of mean repair time and the probability of failure represents the expected downtime loss caused by sudden failure of the equipment in the future time window.

[0052] It should be noted that the evaluation of the supply and demand balance index of the mixing station specifically includes: comparing the concrete demand and inventory of each working surface to obtain the concrete difference, and taking the ratio of the sum of the concrete differences of each working surface to the concrete supply as the supply and demand balance index of the mixing station.

[0053] The present invention integrates the raw material inventory and equipment operation data of the mixing station, analyzes the effective supply under inventory constraints and equipment constraints, and combines the working surface demand with the inventory assessment supply and demand balance index to effectively solve the problem of incomplete process evaluation, improve the matching degree between the mixing station's supply capacity and the working surface demand, optimize the resource allocation efficiency, and ensure the rational supply of concrete resources.

[0054] The scheduling demand judgment module is used to generate the supply priority based on the current construction process key score, geological risk score and support capability value of the adjacent working surface when the supply and demand balance index deviates from the preset threshold.

[0055] It should be noted that the material supply priority of each working surface is generated by matching the current construction process of each working surface with the set key score of each construction process to obtain the current key score of the construction process of each working surface.

[0056] The distances, concrete stocks and key scores of the current construction process corresponding to each work surface are obtained, and the distances, concrete stocks and key scores of the current construction process of all adjacent work surfaces are collaboratively analyzed to obtain the support capability values ​​of the adjacent work surfaces.

[0057] The geological risk score of each working face is extracted from the tunnel project database and normalized with the key score of the current construction process and the support capability value of the adjacent working face. The normalized data is linearly weighted to obtain the urgency index. The feeding priority is obtained by sorting the working faces in descending order according to the urgency index.

[0058] The geological risk score of each working surface is assessed by professionals through on-site surveys before the construction of the tunnel project, and the scoring results are stored in the tunnel project database.

[0059] The present invention generates material supply priorities based on a multi-dimensional comprehensive consideration of the key scores of the working face construction process, the geological risk scores, and the support capability values ​​of the adjacent working faces. This solves the problem of a single factor in determining scheduling priorities, improves the scientificity and rationality of material supply decisions, and ensures the smooth progress of tunnel construction.

[0060] Furthermore, the urgency index calculation formula is: , where is the urgency index, They are geological risk score, current construction process key score and adjacent working surface support capability value, They are the influencing factors corresponding to the geological risk score, the key score of the construction process and the support capability value of the adjacent working surface. The setting of the influencing factors of the geological risk score, the key score of the construction process and the support capability value of the adjacent working surface can be set according to industry experience, or can be obtained through a limited number of test data. For example, the historical priority assessment correlation data corresponding to multiple working surfaces in the tunnel construction project are first collected, and the correlation coefficients of the influence of the geological risk score, the key score of the construction process and the support capability value of the adjacent working surface on the historical priority assessment correlation data corresponding to different working surfaces and the urgency are calculated. The least squares method is used to perform linear regression equation analysis to determine the contribution of the geological risk score, the key score of the construction process and the support capability value of the adjacent working surface. Finally, after normalization, the contribution is converted into the influencing factors of the geological risk score, the key score of the construction process and the support capability value of the adjacent working surface, and the sum of them is 1.

[0061] In one specific embodiment, the critical scores for each construction process include: The secondary lining pouring process and the invert arch closure process directly impact the tunnel's structural safety, waterproofing, and overall stability. Interruptions can lead to serious risks such as landslides and water leaks, and resuming work can be difficult and time-consuming. For example, the critical score is the highest score within a criticality score range, such as 10.

[0062] Initial support shotcrete and anchor grouting ensure surrounding rock stability and prevent local instability. Interruptions may result in local collapse, requiring additional reinforcement and delaying subsequent processes. For example, a critical score of 7 may be achieved.

[0063] Invert filling and trench construction: These processes have a relatively indirect impact on overall structural safety, but interruptions may cause delays in subsequent processes. For example, a critical score of 4 may be awarded.

[0064] Local leveling and repair processes: These processes have minimal disruption and can usually be scheduled flexibly. For example, a critical score of 1 may be given.

[0065] Furthermore, the adjacent working surface support capability value analysis method is: performing distance attenuation analysis on the distances between all adjacent working surfaces to obtain a distance attenuation coefficient.

[0066] Extract the concrete demand of all adjacent working surfaces in the future time window, compare it with the corresponding concrete stock, and set the representative value of the stock availability of all adjacent working surfaces based on the comparison results.

[0067] The critical inhibition factor is obtained by ratio analysis of the current construction process key score and the total score of all adjacent work surfaces, and the average of the critical inhibition factor, the distance attenuation coefficient and the representative value of stock availability is used as the support capability value of the adjacent work surface.

[0068] In a specific embodiment, the distance attenuation coefficient analysis formula is: , where is the distance attenuation coefficient, is the distance between the working surface and the adjacent working surface, is the minimum distance between all adjacent working surfaces, The distance attenuation factor is set to quantify the attenuation effect of distance on mutual influence, which can more accurately consider the actual interaction relationship between working surfaces. The distance attenuation factor is set as follows: the actual distances and corresponding actual attenuation values ​​between different working surfaces and other working surfaces are extracted from historical engineering scenarios, the minimum value is screened from the actual distances between different working surfaces and other working surfaces, and the optimal distance attenuation factor is obtained by nonlinear regression fitting through the least squares method.

[0069] The stock availability representative value is set as follows: when the concrete stock is greater than the concrete demand in the future time window, 1 is used as the stock availability representative value; otherwise, the ratio of the concrete stock to the concrete demand in the future time window is used as the stock availability representative value.

[0070] The critical inhibition factor is analyzed by obtaining the ratio of the critical score of the current construction process to the total score, and taking the difference between 1 and the ratio of the critical score of the current construction process to the total score as the critical inhibition factor.

[0071] The schedulable work surface screening module is used to obtain a set of schedulable work surfaces based on the fusion analysis of the feeding priority and concrete demand of each work surface.

[0072] It should be noted that if Figure 4 As shown, the method for obtaining the schedulable work surface set is: starting from the work surface with the first feeding priority, its concrete demand is accumulated step by step, and it is compared with the concrete supply in real time. If the accumulated concrete demand is less than or equal to the supply, the accumulation continues step by step. Otherwise, the accumulation stop judgment is triggered, and all the currently accumulated work surfaces are schedulable work surfaces, generating a schedulable work surface set.

[0073] For example, the concrete demand of the working surface with the first feeding priority is compared with the concrete supply in real time. If the concrete demand of the working surface with the first feeding priority is less than or equal to the supply, the concrete demand of the working surface with the first feeding priority and the second feeding priority is accumulated and compared with the concrete supply to make a judgment. Otherwise, the accumulation judgment is stopped and the working surface with the first feeding priority is designated as a schedulable working surface.

[0074] The present invention forms a systematic schedulable work surface set screening mechanism based on the fusion analysis of feed priority and concrete demand, realizes the optimal allocation of resources among different work surfaces, and improves resource utilization efficiency.

[0075] The transport scheduling target generation module is used to obtain the last concrete transportation time of all schedulable work surfaces, combined with the concrete loading time of the mixing station, and dynamically generate the transport scheduling targets of all concrete transport vehicles to be loaded in the mixing station.

[0076] It should be noted that the analysis method of the transportation scheduling target generation module is: obtain the last concrete transportation time of the work surface corresponding to the first feeding priority in the schedulable work surface set, and compare it with the concrete transportation interval duration set for the corresponding work surface to obtain the next concrete transportation interval duration.

[0077] Obtain the concrete loading time of the mixing station, compare the next concrete transportation interval with the concrete loading time. If the next concrete transportation interval is less than the concrete loading time, use the working surface corresponding to the first feeding priority as the transportation scheduling target for the concrete transport truck that has currently completed loading in the mixing station. Otherwise, compare them step by step until the next concrete transportation interval corresponding to a certain feeding priority is less than the concrete loading time. Then use the working surface corresponding to this feeding priority as the transportation scheduling target for the concrete transport truck that has currently completed loading. Repeat the analysis according to the above steps to generate the transportation scheduling targets corresponding to all concrete transport trucks to be loaded in the mixing station.

[0078] The concrete loading time of the mixing station is the loading time required to fill a single concrete transport truck at the mixing station.

[0079] The present invention obtains the last transportation time of the schedulable working surface and the loading time of the mixing station, dynamically generates the transportation scheduling target of the transport vehicle, ensures the optimal configuration of the timing and sequence of concrete transportation, improves transportation efficiency and construction continuity, and enhances the flexibility and adaptability of transportation scheduling.

[0080] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0081] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0082] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel 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 application.

[0083] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0084] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0085] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The intelligent scheduling decision-making system for tunnel construction based on data fusion is characterized by: include: The working surface demand prediction module is used to collect the concrete consumption rate of each working surface in the tunnel construction project in real time, and combine the historical consumption curve with the construction schedule to predict the concrete demand in the future time window; The supply and demand balance assessment module is used to collect raw material inventory and equipment operation data within the mixing plant, analyze the concrete supply volume of the mixing plant in the future time window, and evaluate the supply and demand balance index of the mixing plant based on the concrete inventory and demand of each working surface; The scheduling demand judgment module is used to generate the material supply priority based on the current construction process key score of each working face, the geological risk score, and the support capability value of the adjacent working face when the supply and demand balance index deviates from the preset threshold; The schedulable working surface screening module is used to obtain the set of schedulable working surfaces based on the integrated analysis of the material supply priority and concrete demand of each working surface; The transport scheduling target generation module is used to obtain the last concrete transportation time of all schedulable work surfaces, and combine it with the concrete transportation time of the mixing station to dynamically generate the transport scheduling targets of all concrete transport vehicles to be transported in the mixing station; The analysis method of the transportation scheduling target generation module is: Obtain the last concrete transportation time of the work surface corresponding to the first feeding priority in the set of schedulable work surfaces, and compare it with the concrete transportation interval time set for the corresponding work surface to obtain the next concrete transportation interval time; Obtain the concrete loading time of the mixing station, compare the next concrete transportation interval with the concrete loading time, and if the next concrete transportation interval is less than the concrete loading time, use the working surface corresponding to the first feeding priority as the transportation scheduling target for the concrete transport truck that has currently completed loading in the mixing station. Otherwise, compare them level by level until the next concrete transportation interval corresponding to a certain feeding priority is less than the concrete loading time. Then use the working surface corresponding to this feeding priority as the transportation scheduling target for the concrete transport truck that has currently completed loading. Repeat the above steps to generate the transportation scheduling targets for all concrete transport trucks to be loaded in the mixing station. The method for obtaining the schedulable working surface set is as follows: Starting from the work surface with the first feeding priority, its concrete demand is accumulated step by step and compared with the concrete supply in real time. If the accumulated concrete demand is less than or equal to the supply, the accumulation continues step by step. Otherwise, the accumulation stop judgment is triggered. All currently accumulated work surfaces are schedulable work surfaces, and a schedulable work surface set is generated.

2. The intelligent scheduling and decision-making system for tunnel construction based on data fusion according to claim 1 is characterized by: The specific method of the working surface demand prediction module is: Obtain the concrete consumption of each working face in the current construction process in the tunnel construction project, and compare and analyze the concrete consumption with the construction time of the current construction process to obtain the concrete consumption rate; Based on the construction schedule of each working face, a tunnel construction project history record set that is identical to the construction schedule is selected, and a historical consumption curve of each working face is generated based on the concrete consumption of each historical record in the tunnel construction project history record set; The concrete consumption rate of each working surface is matched with the historical consumption curve of the corresponding working surface in each historical record, and the concrete demand of each working surface in the future time window is extracted from the matched historical consumption curve.

3. The intelligent scheduling and decision-making system for tunnel construction based on data fusion according to claim 1 is characterized by: The specific content of analyzing the concrete supply quantity of the mixing station in the future time window is as follows: Based on the inventory of each raw material in the mixing station, the ratio analysis is performed between it and the unit concrete mix ratio of the corresponding raw material to infer the effective supply of the mixing station within the future time window under the inventory constraint; The operating data of each device in the mixing station is combined with the corresponding historical operating data of each device in the tunnel construction project to predict the probability of failure and average repair time of each device in the future time window. The time difference analysis is combined with the length of the future time window to obtain the mixing station's available time. The product of the mixing station's available time and the rated capacity of the mixing station's equipment is taken as the effective supply of the mixing station's equipment constraints in the future time window; The minimum value is selected from the effective supply quantities of inventory constraints and equipment constraints of the mixing station in the future time window as the concrete supply quantity.

4. The intelligent scheduling and decision-making system for tunnel construction based on data fusion according to claim 3 is characterized by: The method for inferring the effective supply of the mixing station's inventory constraints in the future time window is as follows: The ratio of each raw material inventory to the corresponding raw material unit concrete mix ratio is used as the concrete production volume corresponding to each raw material, and the minimum production volume is selected as the concrete production volume with inventory constraints; Based on the combined analysis of the future time window length and the rated capacity of the mixing station equipment, the theoretical maximum supply of the mixing station is obtained, and the minimum value between the concrete production volume and the theoretical maximum supply volume is taken as the effective supply volume of the mixing station under inventory constraints within the future time window.

5. The intelligent scheduling and decision-making system for tunnel construction based on data fusion according to claim 3 is characterized by: The available time analysis method of the mixing station is: Normalize the operating data of each device in the mixing plant to generate an operating data vector for each device. Similarly, extract the historical operating data of each historical log in the current construction process from the corresponding historical operating data of each device in the tunnel construction project, and generate a historical operating data vector based on the historical operating data. The cosine similarity calculation formula is used to calculate the similarity between the operating data vector of each device and the historical operating data vector of each historical log. The historical logs with similarity greater than the set similarity threshold are selected. The number of historical logs with operating faults is selected from them, and the ratio of this number to the total number of selected historical logs is used as the probability of fault occurrence. The average of the fault repair time in each historical log of the operational fault is taken as the average repair time. The duration analysis is performed based on the product of the average repair time and the probability of fault occurrence and the length of the future time window to obtain the available time of the mixing station.

6. The intelligent scheduling and decision-making system for tunnel construction based on data fusion according to claim 1 is characterized by: The supply and demand balance index of the mixing station is evaluated, specifically including: The concrete demand and inventory of each working surface are compared to obtain the concrete difference, and the ratio of the sum of the concrete differences of each working surface to the concrete supply is used as the supply and demand balance index of the mixing station.

7. The intelligent scheduling and decision-making system for tunnel construction based on data fusion according to claim 1 is characterized by: The method for generating the feeding priority of each working surface is as follows: Match the current construction process of each work surface with the set key scores of each construction process to obtain the current key scores of each work surface; Obtain the distance, concrete stock, and current construction process key scores of all adjacent working surfaces corresponding to each working surface, and conduct a collaborative analysis of the distance, concrete stock, and current construction process key scores of all adjacent working surfaces to obtain the adjacent working surface support capability value; The geological risk score of each working face is extracted from the tunnel project database and normalized with the key score of the current construction process and the support capability value of the adjacent working face. The normalized data is linearly weighted to obtain the urgency index. The feeding priority is obtained by sorting the working faces in descending order according to the urgency index.

8. The intelligent scheduling and decision-making system for tunnel construction based on data fusion according to claim 7 is characterized by: The analysis method of the adjacent working surface support capability value is as follows: Perform distance attenuation analysis on the distances between all adjacent working surfaces to obtain the distance attenuation coefficient; Extract the concrete demand of all adjacent working faces in the future time window, compare it with the corresponding concrete stock, and set the representative value of the stock availability of all adjacent working faces based on the comparison results; The critical inhibition factor is obtained by ratio analysis of the current construction process key score and the total score of all adjacent work surfaces, and the average of the critical inhibition factor, the distance attenuation coefficient and the representative value of stock availability is used as the support capability value of the adjacent work surface.

Images