CN116523144A - TRD construction process control method and system in hard soil layer - Google Patents
TRD construction process control method and system in hard soil layer Download PDFInfo
- Publication number
- CN116523144A CN116523144A CN202310760980.4A CN202310760980A CN116523144A CN 116523144 A CN116523144 A CN 116523144A CN 202310760980 A CN202310760980 A CN 202310760980A CN 116523144 A CN116523144 A CN 116523144A
- Authority
- CN
- China
- Prior art keywords
- construction
- result
- control
- optimization
- path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims abstract description 199
- 239000002689 soil Substances 0.000 title claims abstract description 68
- 238000004886 process control Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000005457 optimization Methods 0.000 claims abstract description 117
- 238000004140 cleaning Methods 0.000 claims abstract description 53
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 238000012795 verification Methods 0.000 claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000012937 correction Methods 0.000 claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 238000003756 stirring Methods 0.000 claims description 17
- 238000013507 mapping Methods 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 239000000428 dust Substances 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 10
- 238000012545 processing Methods 0.000 abstract description 6
- 230000002950 deficient Effects 0.000 abstract 1
- 239000006185 dispersion Substances 0.000 abstract 1
- 238000013433 optimization analysis Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 6
- 230000007547 defect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Multimedia (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a TRD construction process control method and a system in a hard soil layer, which relate to the technical field of intelligent control, plan a task path and set basic influence data, combine a related area to determine cleaning control data, perform cleaning and detection to compensate the basic influence data, perform modeling to perform optimization analysis and construction, perform construction monitoring and node control correction, solve the technical problems that in the prior art, the construction limitation on multiple influence factors and the processing of variables in actual construction are deficient, the construction control precision is insufficient, the construction flexibility is insufficient, the adjustment on intermediate errors is not timely enough, the final construction quality has a certain deviation compared with a construction target, perform optimization control analysis by taking the path influence and the temperature influence as constraint modeling through pre-cleaning and re-detection, improve the control accuracy, perform construction monitoring analysis verification and real-time adjustment synchronously, improve the construction flexibility, and timely adjust intermediate dispersion, and ensure the construction effect.
Description
Technical Field
The invention relates to the technical field of intelligent control, in particular to a TRD construction process control method and system in a hard soil layer.
Background
The TRD construction method has wide application in various building engineering fields, such as foundation reinforcement, seepage prevention treatment and the like of revetment engineering, can be used for continuous wall construction in various soil layers and gravel layers, and needs to ensure construction control effect. At present, engineering construction is executed through pre-construction planning and working condition monitoring, and the construction limitation on multiple influencing factors and the processing shortage of variables in actual construction lead to the defect of the accuracy of construction control, the defect of the flexibility of construction, the defect of the adjustment of intermediate errors in time and the defect of certain deviation of final construction quality compared with a construction target.
Disclosure of Invention
The application provides a TRD construction process control method and a TRD construction process control system in a hard soil layer, which are used for solving the technical problems that in the prior art, construction limitation on multiple influencing factors and processing shortage of variables in actual construction lead to insufficient accuracy of construction control, and insufficient construction flexibility, adjustment on intermediate errors is not timely enough, and a certain deviation exists in final construction quality compared with a construction target.
In view of the above, the present application provides a method and system for controlling TRD construction process in a hard soil layer.
In a first aspect, the present application provides a method for controlling TRD construction process in a hard soil layer, the method comprising:
task control information of a construction task is obtained, identification points are configured through the task control information, and a task path is planned;
region foundation information of an interactive construction region, and setting foundation influence data of construction process control based on the region foundation information, wherein the foundation influence data comprises soil influence data and ground influence data;
carrying out data acquisition of an associated area on the task path through an image acquisition device, constructing a path data set, and generating cleaning control data according to the path data set and the area basic information;
performing path cleaning on the task path through the cleaning control data, and performing cleaning detection to generate a path soil quality detection result;
compensating the basic influence data through the path soil texture detection result, generating optimization influence data, inputting the optimization influence data and the task control information into a process control optimization model, and outputting an optimization control result;
executing TRD optimization construction based on the optimization control result, matching image acquisition parameters based on the optimization influence data, controlling the image acquisition device to execute real-time soil and equipment image acquisition of TRD optimization construction through the image acquisition parameters, and generating compensation control information based on the acquisition result;
and carrying out node control correction of the optimization control result through the compensation control information so as to finish TRD optimization construction.
In a second aspect, the present application provides a TRD construction process control system in a hard earth layer, the system comprising:
the path planning module is used for obtaining task control information of a construction task, configuring identification points through the task control information and planning a task path;
the data setting module is used for interacting area foundation information of a construction area and setting foundation influence data of construction process control based on the area foundation information, wherein the foundation influence data comprises soil property influence data and ground influence data;
the data acquisition and analysis module is used for carrying out data acquisition of the relevant area on the task path through the image acquisition device, constructing a path data set and generating cleaning control data according to the path data set and the area basic information;
the path cleaning detection module is used for performing path cleaning on the task path through the cleaning control data and performing cleaning detection to generate a path soil quality detection result;
the control optimization module is used for compensating the basic influence data through the path soil texture detection result, generating optimization influence data, inputting the optimization influence data and the task control information into a process control optimization model, and outputting an optimization control result;
the image acquisition and analysis module is used for executing TRD (total transformation description) optimization construction based on the optimization control result, matching image acquisition parameters based on the optimization influence data, controlling the image acquisition device to execute real-time soil and equipment image acquisition of the TRD optimization construction through the image acquisition parameters, and generating compensation control information based on the acquisition result;
and the control correction module is used for carrying out node control correction on the optimized control result through the compensation control information so as to finish TRD (blast furnace dust) optimized construction.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the TRD construction process control method in the hard soil layer, task control information of a construction task is obtained, and identification points are configured to plan a task path; the method comprises the steps of interacting area foundation information of a construction area, setting foundation influence data of construction process control, carrying out data acquisition of an associated area on a task path through an image acquisition device, constructing a path data set, generating cleaning control data by combining the area foundation information, carrying out path cleaning on the task path, and carrying out cleaning detection to generate a path soil property detection result; the method comprises the steps of compensating basic influence data through a path soil quality detection result, inputting generated optimization influence data and task control information into a process control optimization model, outputting an optimization control result, executing TRD (total internal reflection) optimization construction, controlling an image acquisition device to execute real-time soil and equipment image acquisition of TRD optimization construction based on the optimization influence data, generating compensation control information based on the acquisition result, carrying out node control correction on the optimization control result to complete TRD optimization construction, solving the technical problems that construction limitation of multiple influence factors and processing of variables in actual construction are insufficient, the accuracy of construction control is insufficient, the construction flexibility is insufficient, the adjustment of intermediate errors is not timely enough, and certain deviation exists in final construction quality compared with a construction target.
Drawings
Fig. 1 is a schematic flow chart of a TRD construction process control method in a hard soil layer;
fig. 2 is a schematic diagram of an optimization control result obtaining flow in the TRD construction process control method in a hard soil layer;
fig. 3 is a schematic diagram of an image acquisition parameter acquisition flow in the TRD construction process control method in a hard soil layer;
fig. 4 is a schematic structural diagram of a TRD construction process control system in a hard soil layer.
Reference numerals illustrate: the system comprises a path planning module 11, a data setting module 12, a data acquisition and analysis module 13, a path cleaning detection module 14, a control optimization module 15, an image acquisition and analysis module 16 and a control correction module 17.
Detailed Description
According to the TRD construction process control method and system in the hard soil layer, task control information is obtained to plan a task path, basic information of an area is interacted, basic influence data is set, relevant area data acquisition is carried out on the task path, cleaning control data is determined, path cleaning and cleaning detection are carried out, basic influence data compensation is carried out on a path soil texture detection result, an optimized control result is output based on a process control optimization model, optimized construction is carried out, construction collection is carried out by matching image acquisition parameters, and compensation control information node control correction is generated.
Example 1
As shown in fig. 1, the present application provides a TRD construction process control method in a hard soil layer, the method comprising:
step S100: task control information of a construction task is obtained, identification points are configured through the task control information, and a task path is planned;
specifically, the TRD construction method has wide application in various building engineering fields, such as foundation reinforcement, seepage prevention treatment and the like of revetment engineering, and can be used for continuous wall construction in various soil layers and gravel layers, so that the construction effect is a major concern. According to the TRD construction process control method in the hard soil layer, path pre-cleaning is carried out before construction, cleaning state rechecking is carried out, path influence and temperature influence are taken as constraints, modeling is carried out for optimal control analysis, control accuracy is ensured, construction monitoring analysis verification and real-time adjustment are synchronously carried out, and construction effect is ensured.
Specifically, the construction task is a project to be subjected to TRD construction, and the task control information of the construction task, such as a construction area, an excavation depth, equipment control, planning construction effects, and the like, is obtained. And further, determining a plurality of construction limiting positions, such as an initial position, a termination position, a middle fixed position and the like, based on the task control information, and performing sequential connection on the plurality of construction limiting positions to generate the task path, wherein the task path is a concrete construction path of the soil layer.
Step S200: region foundation information of an interactive construction region, and setting foundation influence data of construction process control based on the region foundation information, wherein the foundation influence data comprises soil influence data and ground influence data;
specifically, the regional foundation information of the construction region is collected, for example, an ecological monitoring station is connected, the construction region is used as an index, and the regional related foundation information is searched and integrated and called, wherein the regional foundation information comprises two dimensions of the earth surface and the earth bottom and is used as the regional foundation information. Carrying out construction influence analysis and judgment based on the regional foundation information, specifically, identifying regional ground foundation information, determining ground obstacles, ground vegetation and the like existing in a region, and carrying out position positioning and information identification on the regional foundation information as ground influence data; identifying regional underground basic information, such as geological mapping data, detection data and the like, determining poor geological phenomena, such as silt, rock and the like, or construction barriers of pipelines, cables, anchor ropes and the like, and carrying out position positioning and information identification on the regional basic information in the regional basic information, wherein the regional basic information is used as the soil property influence data, preferably, the identification of the soil property influence data and the ground influence data is carried out based on different identification modes, so that the follow-up distinguishing is facilitated. And taking the soil property influence data and the ground influence data as basic influence data of construction process control, and processing the basic influence data in advance.
Step S300: carrying out data acquisition of an associated area on the task path through an image acquisition device, constructing a path data set, and generating cleaning control data according to the path data set and the area basic information;
step S400: performing path cleaning on the task path through the cleaning control data, and performing cleaning detection to generate a path soil quality detection result;
specifically, the task path is a specific construction range of a soil layer, and in the engineering construction process, for example, an area such as equipment operation, field management scheduling and the like is used as the associated area, and the associated area is a working area and needs to ensure the state of the earth surface. Based on the image acquisition device, acquiring an associated area of the task path, performing construction influence feature recognition on an acquired image, and performing positioning identification on a recognition result and the associated area to serve as the path data set. Further, based on the path data set and the area basic information, identification information identification is carried out to determine cleaning targets, cleaning modes and cleaning control parameters which are adapted to the cleaning targets are determined, mapping association of the cleaning targets, the cleaning modes and the cleaning control parameters is carried out, and a plurality of cleaning sequences are generated and used as the cleaning control data. Further, based on the cleaning control parameters, path cleaning is performed on the task path, after cleaning is completed, inspection is performed again, detection can be performed through modes such as signal detection, feedback information is received, and the result is used as the path soil property detection result. And the path soil property detection result is posterior information for executing path cleaning.
Step S500: compensating the basic influence data through the path soil texture detection result, generating optimization influence data, inputting the optimization influence data and the task control information into a process control optimization model, and outputting an optimization control result;
further, as shown in fig. 2, step S500 of the present application further includes:
step S510: executing temperature information acquisition and prediction of a construction environment, and constructing a temperature set, wherein the temperature set comprises a measured temperature set and a predicted temperature set;
step S520: before the process control optimization model outputs an optimization control result, executing model parameter updating on the process control optimization model through the temperature set;
step S530: and outputting the optimized control result according to the process control optimized model with updated parameters.
Specifically, based on the path soil property detection result, the basic influence data is compensated, the compensated basic influence data is used as the optimized influence data, namely, construction influence exists after path cleaning, the optimized influence data is used as follow-up construction constraint, and process optimization control analysis is performed. The environment temperature has a certain influence on construction, for example, in a cold winter environment, a certain protection measure is needed for cement stirring technology, for example, at the temperature of-2 ℃, along with the reduction of the temperature, the construction difficulty exists in a hard geological condition, and the construction environment temperature is used as a construction constraint condition.
Specifically, the process control optimization model is built, and is a self-built analysis model for construction control optimization, sample construction influence data, sample task control information and sample optimization control results are collected, the sample data is constructed collection information and can be directly obtained, the sample construction influence data, the task control information and the sample optimization control results are mapped and associated, and as construction data, neural network training is performed based on the construction data, so that the construction optimization control model is generated. Furthermore, the construction environment temperature information is determined by combining the construction task, and the construction optimization control model is calibrated, so that the fit degree of the construction optimization control model and the construction task is guaranteed, and the accuracy of the model output result is improved.
Further, temperature information is acquired for the current construction environment, for example, the measured temperature set is acquired based on a temperature sensor. And performing environmental temperature prediction within a time limit of a construction period based on the construction task, for example, as the predicted temperature set, and performing time-series integration of the measured temperature set and the predicted temperature set as the temperature set. Embedding the temperature set into the process control optimization model, inputting the optimization influence data and the task control information into the process control optimization model, determining a preliminary optimization control result by identification matching and decision making, and further, carrying out temperature matching and temperature influence control adjustment on the preliminary optimization control result by combining the temperature set so as to update model parameters, namely the preliminary optimization control result, and outputting the updated model parameters as the optimization control result, wherein the optimization control result has higher accuracy and is more suitable for a construction target.
Step S600: executing TRD optimization construction based on the optimization control result, matching image acquisition parameters based on the optimization influence data, controlling the image acquisition device to execute real-time soil and equipment image acquisition of TRD optimization construction through the image acquisition parameters, and generating compensation control information based on the acquisition result;
further, as shown in fig. 3, step S600 of the present application further includes:
step S610: configuring a conversion node of a mobile control step length based on the optimized control result;
step S620: matching an ending delay interval of a node according to the optimized control result, and setting an image acquisition starting node of the conversion node according to the conversion node and the ending delay interval;
step S630: matching the image acquisition constraint frequency through the optimization influence data;
step S640: and generating the image acquisition parameters according to the image acquisition starting node and the image acquisition constraint frequency.
Further, step S650 of the present application further includes:
step S651: constructing a stirring state image feature library of soil through big data;
step S652: configuring a fuzzy association value, and carrying out feature matching on the stirring state image feature library based on the optimization influence data and the fuzzy association value to obtain a feature matching result;
step S653: constructing an image recognition convolution kernel based on the feature matching result, and performing image traversal according to the acquisition result by the image recognition convolution kernel;
step S654: and generating the compensation control information according to the image traversal comparison result.
Further, step S654 of the present application further includes:
step S6541: configuring a preset comparison similarity threshold;
step S6542: judging whether the image traversal comparison result meets the preset comparison similarity threshold value or not;
step S6543: when the image traversing comparison result cannot meet the preset comparison similarity threshold, node delay control is carried out according to the acquisition nodes of the corresponding images and the acquisition constraint frequency;
step S6544: when any image traversal comparison result meets the preset comparison similarity threshold, generating a node ending instruction;
step S6545: and generating the compensation control information according to the node delay control and the node ending instruction.
Specifically, the optimized control result is control information of TRD construction, TRD optimized construction is executed, and image acquisition is synchronously carried out to monitor real-time working conditions. And (3) matching image acquisition parameters based on the optimization influence data, specifically, determining the movement control compensation based on the optimization control result, namely, in the construction process, a plurality of procedures such as digging, grouting, stirring to form a wall and the like are required to be completed, taking the length of a single construction path as the movement control step length, and taking the termination point of the step length as a conversion node, namely, monitoring the range of the later step after the process construction in the step length is completed. Meanwhile, due to the influence of temperature influence and the influence of optimization influence data, the construction time of each step length is different, the construction time of each step length node is determined based on the optimization control result, the normal construction time in the step length is used as a standard time interval, and the difference value between the construction time and the standard time interval is used as the ending delay interval. And determining an image acquisition starting time based on the image acquisition position and the image acquisition starting time, and determining the image acquisition starting node based on the image acquisition position and the image acquisition starting time.
Further, based on the optimized influence data, the image acquisition constraint frequency is matched, and for different optimized acquisition influence data, for different influence grades, the image acquisition frequency is respectively configured by combining expert experience, mapping and associating the two to generate a plurality of influence item-acquisition frequency reference sequences, matching is performed in the reference sequences, and the image acquisition constraint frequency is determined. And taking the image acquisition starting node and the image acquisition constraint frequency as the image acquisition parameters, and carrying out synchronous monitoring control on construction based on the image acquisition parameters.
Further, based on the image acquisition parameters, controlling the image acquisition device to acquire real-time soil and equipment images of TRD (total transformation and total transformation) optimized construction, acquiring an acquisition result, and performing characteristic recognition on the acquisition result to perform control compensation so as to maximally ensure that the construction effect is consistent with a construction target.
Specifically, the soil stirring state is taken as a searching target, big data searching is carried out, stirring state images are called, image recognition is carried out, convolution kernel features of the images are extracted, image identification is carried out, and the identified stirring state images are integrated to be used as the stirring state image feature library. Further, a fuzzy association value is configured, namely, based on the critical association degree set by an expert group and used for carrying out matching limitation on the stirring state image characteristics and the optimization influence data, the fuzzy association value is used as a matching basis, the optimization influence data and the stirring state image characteristics library are matched, if the fuzzy association value is met, the matching is successful, and mapping association and integration are carried out on the matched optimization influence data and the stirring state image characteristics to be used as the characteristic matching result. Further, based on the feature matching result, performing convolution kernel feature recognition of image identification, which is used as an image recognition convolution kernel corresponding to each item of optimization influence data, and is used for performing similarity comparison of corresponding monitoring images to determine a construction state.
Further, based on the image recognition convolution kernel, image traversal and similarity comparison are carried out on the acquisition result, the image traversal comparison result is obtained, and the image traversal comparison result identification has a similarity value which refers to the similarity of the acquired image and the image recognition convolution kernel. And setting the preset comparison similarity threshold, namely, customizing the preset critical similarity for carrying out the coincidence judgment of the image and the convolution kernel based on expert experience. Checking the image traversal comparison result and the preset comparison similarity threshold, if the image traversal comparison result does not meet the preset comparison threshold, indicating that the moment point of an image acquisition node does not meet the construction requirement, continuing to perform construction control of the node, and performing delay control of the node based on the acquisition constraint frequency until the convolution kernel comparison similarity of the monitored image meets the preset comparison similarity threshold; and if the image traversing comparison result meets the preset dissimilarity threshold, indicating that the image acquisition node has reached the construction requirement, generating the node ending instruction, stopping the construction of the current node and starting the construction and monitoring of the next node. And generating the compensation control information based on the node delay control and the node constraint instruction, and performing construction adjustment based on a real-time monitoring working condition so as to improve the fit degree of the construction effect and an expected construction target.
Step S700: and carrying out node control correction of the optimization control result through the compensation control information so as to finish TRD optimization construction.
Further, step S700 of the present application further includes:
step S710-1: performing image region division based on the image acquisition parameters to obtain an image region division result, wherein the image region division result comprises an equipment image region, a movable soil layer region and an environment region;
step S720-1: carrying out path feature recognition of the task path on the environment area at the conversion node to generate a path direction recognition result and a path area recognition result;
step S730-1: performing equipment state identification on the equipment image area at the conversion node to generate an equipment state identification result;
step S740-1: performing equipment operation verification on the equipment state recognition result, the path direction recognition result and the path area recognition result to generate a verification abnormal recognition result;
step S750-1: and performing TRD optimization construction based on the verification abnormal recognition result.
Further, step S700 of the present application further includes:
step S710-2: after TRD construction is completed, performing quality verification and monitoring on the TRD construction to obtain a quality verification and detection result;
step S720-2: extracting an abnormal result of the quality verification detection result, and constructing mapping association of the abnormal result and the compensation control information;
step S730-2: and performing construction optimization of subsequent TRD construction based on the mapping association.
Specifically, in the construction process, the running state of the equipment is one of decisive factors of the construction effect, the equipment is subjected to real-time running verification, and the conditions of abnormal equipment construction, deviation of working condition areas and the like are avoided, so that the promotion of working conditions is influenced. Specifically, the device image area, the movable soil layer area and the environment area are used as division standards, and the image acquisition parameters are combined to divide the image area of the acquired image, so that the image area division result is obtained. And performing targeted analysis processing of different dimensions based on the image region division result.
Specifically, extracting the environment area from the image area dividing result at the conversion node, taking the path direction and the path area as identification targets, and carrying out path feature identification on the environment area to obtain the path direction identification result and the path area identification result; and similarly, extracting the equipment image area from the image area division result at the conversion node, and carrying out equipment state recognition, such as drilling tool detachment, hard soil layer cutter abrasion and the like, as the equipment state recognition result. And carrying out construction state verification based on the equipment state recognition result, the path direction recognition result and the path area recognition result, carrying out matching and deviation verification with the optimized control result, and if the deviation is large, namely, the device belongs to uncontrollable deviation control, influences the working condition effect, carrying out verification information extraction identification, and generating the verification abnormal recognition result. And performing TRD optimized construction based on the verification abnormal recognition result, and timely performing construction deviation correction to ensure the working condition.
Further, after the TRD construction is completed, performing quality verification and monitoring on the TRD construction, for example, completing a construction task of one period, performing periodic overall quality verification on the optimized control result corresponding to the period, and extracting and identifying aspects of quality failure as the quality verification detection result, for example, 1 for quality qualified identification and 0 for quality unqualified identification. And identifying the identification information of the quality verification detection result, and extracting information with the identification of 0 as the abnormal result. And configuring a compensation scheme for the abnormal result as the compensation control information, such as mining depth shortage-depth control parameter adjustment; insufficient stirring uniformity, stirring rate, time adjustment and the like, and mapping and correlating the abnormal result with the compensation control information. And carrying out construction optimization of subsequent TRD construction based on the mapping association, and avoiding repeated occurrence of similar problems so as to ensure construction quality.
Example two
Based on the same inventive concept as the TRD construction process control method in the hard soil layer in the foregoing embodiment, as shown in fig. 4, the present application provides a TRD construction process control system in the hard soil layer, the system comprising:
the path planning module 11 is used for obtaining task control information of a construction task, configuring identification points through the task control information and planning a task path;
a data setting module 12, wherein the data setting module 12 is used for interacting area foundation information of a construction area, and setting foundation influence data of construction process control based on the area foundation information, wherein the foundation influence data comprises soil property influence data and ground influence data;
the data acquisition and analysis module 13 is used for carrying out data acquisition of an associated area on the task path through an image acquisition device, constructing a path data set and generating cleaning control data according to the path data set and the area basic information;
the path cleaning detection module 14 is configured to perform path cleaning on the task path according to the cleaning control data, and perform cleaning detection to generate a path soil detection result;
the control optimization module 15 is used for compensating the basic influence data through the path soil property detection result, generating optimization influence data, inputting the optimization influence data and the task control information into a process control optimization model, and outputting an optimization control result;
the image acquisition and analysis module 16 is used for executing TRD (TRD optimization construction based on the optimization control result, matching image acquisition parameters based on the optimization influence data, controlling the image acquisition device to execute real-time soil and equipment image acquisition of TRD optimization construction through the image acquisition parameters, and generating compensation control information based on the acquisition result;
and the control correction module 17 is used for carrying out node control correction of the optimized control result through the compensation control information so as to complete TRD optimized construction.
Further, the image acquisition and analysis module further comprises:
the characteristic library construction module is used for constructing a stirring state image characteristic library of the soil through big data;
the feature matching module is used for configuring a fuzzy association value, and carrying out feature matching on the stirring state image feature library based on the optimization influence data and the fuzzy association value to obtain a feature matching result;
the image recognition module is used for constructing an image recognition convolution kernel based on the feature matching result and carrying out image traversal on the acquisition result according to the image recognition convolution kernel;
and the information generation module is used for generating the compensation control information according to the image traversal comparison result.
Further, the image acquisition and analysis module further comprises:
the conversion node configuration module is used for configuring conversion nodes of the mobile control step length based on the optimized control result;
the image acquisition starting node setting module is used for matching an ending delay interval of the node according to the optimization control result and setting an image acquisition starting node of the conversion node according to the conversion node and the ending delay interval;
the acquisition constraint frequency matching module is used for matching the image acquisition constraint frequency through the optimization influence data;
and the image acquisition parameter generation module is used for generating the image acquisition parameters according to the image acquisition starting node and the image acquisition constraint frequency.
Further, the information generating module further includes:
the threshold configuration module is used for configuring a preset comparison similarity threshold;
the result judging module is used for judging whether the image traversal comparison result meets the preset comparison similarity threshold value or not;
the node delay control module is used for carrying out node delay control according to the acquisition nodes of the corresponding images and the acquisition constraint frequency when the image traversal comparison result cannot meet the preset comparison similarity threshold value;
the node constraint instruction generation module is used for generating a node ending instruction when any image traversal comparison result meets the preset comparison similarity threshold value;
and the compensation control information generation module is used for generating the compensation control information according to the node delay control and the node ending instruction.
Further, the control correction module further includes:
the region division module is used for executing image region division based on the image acquisition parameters to obtain an image region division result, wherein the image region division result comprises an equipment image region, a movable soil layer region and an environment region;
the path characteristic recognition module is used for carrying out path characteristic recognition of the task path on the environment area at the conversion node and generating a path direction recognition result and a path area recognition result;
the equipment state identification module is used for carrying out equipment state identification on the equipment image area at the conversion node to generate an equipment state identification result;
the equipment operation verification module is used for carrying out equipment operation verification on the equipment state recognition result, the path direction recognition result and the path area recognition result to generate a verification abnormal recognition result;
and the optimized construction module is used for performing TRD optimized construction based on the verification abnormal identification result.
Further, the control optimization module further includes:
the temperature collection prediction module is used for performing temperature information collection prediction of a construction environment and constructing a temperature set, wherein the temperature set comprises a measured temperature set and a predicted temperature set;
the model parameter updating module is used for executing model parameter updating on the process control optimization model through the temperature set before the process control optimization model outputs an optimization control result;
and the optimal control result output module is used for outputting the optimal control result according to the process control optimal model after parameter updating.
Further, the control correction module further includes:
the quality verification monitoring module is used for carrying out quality verification monitoring on TRD construction after the TRD construction is completed, so as to obtain a quality verification detection result;
the association construction module is used for extracting an abnormal result of the quality verification detection result and constructing mapping association between the abnormal result and the compensation control information;
and the construction optimization module is used for carrying out construction optimization of subsequent TRD construction based on the mapping association.
The foregoing detailed description of the TRD construction process control method in the hard soil layer will be clear to those skilled in the art, and the device disclosed in this embodiment is relatively simple in description, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The TRD construction process control method in the hard soil layer is characterized by comprising the following steps of:
task control information of a construction task is obtained, identification points are configured through the task control information, and a task path is planned;
region foundation information of an interactive construction region, and setting foundation influence data of construction process control based on the region foundation information, wherein the foundation influence data comprises soil influence data and ground influence data;
carrying out data acquisition of an associated area on the task path through an image acquisition device, constructing a path data set, and generating cleaning control data according to the path data set and the area basic information;
performing path cleaning on the task path through the cleaning control data, and performing cleaning detection to generate a path soil quality detection result;
compensating the basic influence data through the path soil texture detection result, generating optimization influence data, inputting the optimization influence data and the task control information into a process control optimization model, and outputting an optimization control result;
executing TRD optimization construction based on the optimization control result, matching image acquisition parameters based on the optimization influence data, controlling the image acquisition device to execute real-time soil and equipment image acquisition of TRD optimization construction through the image acquisition parameters, and generating compensation control information based on the acquisition result;
and carrying out node control correction of the optimization control result through the compensation control information so as to finish TRD optimization construction.
2. The method of claim 1, wherein the method further comprises:
constructing a stirring state image feature library of soil through big data;
configuring a fuzzy association value, and carrying out feature matching on the stirring state image feature library based on the optimization influence data and the fuzzy association value to obtain a feature matching result;
constructing an image recognition convolution kernel based on the feature matching result, and performing image traversal according to the acquisition result by the image recognition convolution kernel;
and generating the compensation control information according to the image traversal comparison result.
3. The method of claim 2, wherein the method further comprises:
configuring a conversion node of a mobile control step length based on the optimized control result;
matching an ending delay interval of a node according to the optimized control result, and setting an image acquisition starting node of the conversion node according to the conversion node and the ending delay interval;
matching the image acquisition constraint frequency through the optimization influence data;
and generating the image acquisition parameters according to the image acquisition starting node and the image acquisition constraint frequency.
4. A method as claimed in claim 3, wherein the method further comprises:
configuring a preset comparison similarity threshold;
judging whether the image traversal comparison result meets the preset comparison similarity threshold value or not;
when the image traversing comparison result cannot meet the preset comparison similarity threshold, node delay control is carried out according to the acquisition nodes of the corresponding images and the acquisition constraint frequency;
when any image traversal comparison result meets the preset comparison similarity threshold, generating a node ending instruction;
and generating the compensation control information according to the node delay control and the node ending instruction.
5. A method as claimed in claim 3, wherein the method further comprises:
performing image region division based on the image acquisition parameters to obtain an image region division result, wherein the image region division result comprises an equipment image region, a movable soil layer region and an environment region;
carrying out path feature recognition of the task path on the environment area at the conversion node to generate a path direction recognition result and a path area recognition result;
performing equipment state identification on the equipment image area at the conversion node to generate an equipment state identification result;
performing equipment operation verification on the equipment state recognition result, the path direction recognition result and the path area recognition result to generate a verification abnormal recognition result;
and performing TRD optimization construction based on the verification abnormal recognition result.
6. The method of claim 1, wherein the method further comprises:
executing temperature information acquisition and prediction of a construction environment, and constructing a temperature set, wherein the temperature set comprises a measured temperature set and a predicted temperature set;
before the process control optimization model outputs an optimization control result, executing model parameter updating on the process control optimization model through the temperature set;
and outputting the optimized control result according to the process control optimized model with updated parameters.
7. The method of claim 1, wherein the method further comprises:
after TRD construction is completed, performing quality verification and monitoring on the TRD construction to obtain a quality verification and detection result;
extracting an abnormal result of the quality verification detection result, and constructing mapping association of the abnormal result and the compensation control information;
and performing construction optimization of subsequent TRD construction based on the mapping association.
8. TRD construction process control system in stereoplasm soil layer, its characterized in that, the system includes:
the path planning module is used for obtaining task control information of a construction task, configuring identification points through the task control information and planning a task path;
the data setting module is used for interacting area foundation information of a construction area and setting foundation influence data of construction process control based on the area foundation information, wherein the foundation influence data comprises soil property influence data and ground influence data;
the data acquisition and analysis module is used for carrying out data acquisition of the relevant area on the task path through the image acquisition device, constructing a path data set and generating cleaning control data according to the path data set and the area basic information;
the path cleaning detection module is used for performing path cleaning on the task path through the cleaning control data and performing cleaning detection to generate a path soil quality detection result;
the control optimization module is used for compensating the basic influence data through the path soil texture detection result, generating optimization influence data, inputting the optimization influence data and the task control information into a process control optimization model, and outputting an optimization control result;
the image acquisition and analysis module is used for executing TRD (total transformation description) optimization construction based on the optimization control result, matching image acquisition parameters based on the optimization influence data, controlling the image acquisition device to execute real-time soil and equipment image acquisition of the TRD optimization construction through the image acquisition parameters, and generating compensation control information based on the acquisition result;
and the control correction module is used for carrying out node control correction on the optimized control result through the compensation control information so as to finish TRD (blast furnace dust) optimized construction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310760980.4A CN116523144B (en) | 2023-06-27 | 2023-06-27 | TRD construction process control method and system in hard soil layer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310760980.4A CN116523144B (en) | 2023-06-27 | 2023-06-27 | TRD construction process control method and system in hard soil layer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116523144A true CN116523144A (en) | 2023-08-01 |
| CN116523144B CN116523144B (en) | 2023-09-15 |
Family
ID=87396166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310760980.4A Active CN116523144B (en) | 2023-06-27 | 2023-06-27 | TRD construction process control method and system in hard soil layer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116523144B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019114191A1 (en) * | 2017-12-14 | 2019-06-20 | 特斯联（北京）科技有限公司 | Internet of things-based building operation device status monitoring and visual analysis system |
| US20210209939A1 (en) * | 2020-12-08 | 2021-07-08 | Harbin Engineering University | Large-scale real-time traffic flow prediction method based on fuzzy logic and deep LSTM |
| CN115421465A (en) * | 2022-10-31 | 2022-12-02 | 北京聚新工程技术有限公司 | Optimized self-adaptive control method and system for textile equipment |
| CN115470566A (en) * | 2022-11-07 | 2022-12-13 | 南京惠派智慧后勤服务有限公司 | Intelligent building energy consumption control method and system based on BIM |
| KR102478499B1 (en) * | 2022-04-07 | 2022-12-20 | 세이지리서치 주식회사 | A method for controlling a prosess and a device for controlling a process |
| CN115993807A (en) * | 2023-03-23 | 2023-04-21 | 日照鲁光电子科技有限公司 | Production monitoring optimization control method and system for silicon carbide |
| CN116029529A (en) * | 2023-02-20 | 2023-04-28 | 山东迈源建设集团有限公司 | BIM-based bridge construction progress management method and system |
| CN116092214A (en) * | 2023-04-11 | 2023-05-09 | 海斯坦普汽车组件(北京)有限公司 | Synchronous monitoring method and system for production of lightweight body-in-white assembly |
| CN116151042A (en) * | 2023-04-20 | 2023-05-23 | 天津市特种设备监督检验技术研究院(天津市特种设备事故应急调查处理中心) | Crane monitoring and maintaining method and system based on multidimensional data analysis |
| WO2023087181A1 (en) * | 2021-11-17 | 2023-05-25 | 浙江吉利控股集团有限公司 | Vehicle-road collaborative multi-vehicle path planning and right-of-way decision method and system, and roadbed unit |
-
2023
- 2023-06-27 CN CN202310760980.4A patent/CN116523144B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019114191A1 (en) * | 2017-12-14 | 2019-06-20 | 特斯联（北京）科技有限公司 | Internet of things-based building operation device status monitoring and visual analysis system |
| US20210209939A1 (en) * | 2020-12-08 | 2021-07-08 | Harbin Engineering University | Large-scale real-time traffic flow prediction method based on fuzzy logic and deep LSTM |
| WO2023087181A1 (en) * | 2021-11-17 | 2023-05-25 | 浙江吉利控股集团有限公司 | Vehicle-road collaborative multi-vehicle path planning and right-of-way decision method and system, and roadbed unit |
| KR102478499B1 (en) * | 2022-04-07 | 2022-12-20 | 세이지리서치 주식회사 | A method for controlling a prosess and a device for controlling a process |
| CN115421465A (en) * | 2022-10-31 | 2022-12-02 | 北京聚新工程技术有限公司 | Optimized self-adaptive control method and system for textile equipment |
| CN115470566A (en) * | 2022-11-07 | 2022-12-13 | 南京惠派智慧后勤服务有限公司 | Intelligent building energy consumption control method and system based on BIM |
| CN116029529A (en) * | 2023-02-20 | 2023-04-28 | 山东迈源建设集团有限公司 | BIM-based bridge construction progress management method and system |
| CN115993807A (en) * | 2023-03-23 | 2023-04-21 | 日照鲁光电子科技有限公司 | Production monitoring optimization control method and system for silicon carbide |
| CN116092214A (en) * | 2023-04-11 | 2023-05-09 | 海斯坦普汽车组件(北京)有限公司 | Synchronous monitoring method and system for production of lightweight body-in-white assembly |
| CN116151042A (en) * | 2023-04-20 | 2023-05-23 | 天津市特种设备监督检验技术研究院(天津市特种设备事故应急调查处理中心) | Crane monitoring and maintaining method and system based on multidimensional data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116523144B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110411370B (en) | Tunnel construction risk management and control system based on space time parameters | |
| Huang et al. | BIM, machine learning and computer vision techniques in underground construction: Current status and future perspectives | |
| Shen et al. | Real-time prediction of shield moving trajectory during tunnelling | |
| CN109359412A (en) | The calculation method and system that prediction tunneling shield digging process deforms entirely | |
| CN111832223A (en) | Neural network-based shield construction surface subsidence prediction method | |
| Zhang et al. | Collapse risk analysis of deep foundation pits in metro stations using a fuzzy Bayesian network and a fuzzy AHP | |
| CN106248672A (en) | Rock crack mode of extension recognition methods and system in a kind of on-the-spot hole based on DIC technology | |
| Zhao et al. | Spatiotemporal deep learning approach on estimation of diaphragm wall deformation induced by excavation | |
| CN102880918B (en) | Based on the deep excavation risk evaluation method that data fusion is analyzed | |
| CN113255990A (en) | Real-time prediction system and method for soil quality of excavation surface in tunnel construction by shield method | |
| CN116523144B (en) | TRD construction process control method and system in hard soil layer | |
| Shen et al. | Evaluation and prediction of earth pressure balance shield performance in complex rock strata: a case study in Dalian, China | |
| Li et al. | Digital-twin-enabled JIT design of rock tunnel: Methodology and application | |
| Ren et al. | Deformation monitoring of ultra-deep foundation excavation using distributed fiber optic sensors | |
| CN112257154B (en) | Transparent construction monitoring method and system for urban tunnel | |
| Stöckel et al. | Mining-induced ground deformations in Kiruna and Malmberget | |
| CN114923519A (en) | Engineering geology monitoring system and three-dimensional geology modeling method for multi-phase aerial photography mapping | |
| CN114066271A (en) | Tunnel water inrush disaster monitoring and management system | |
| Jiaxu et al. | A water leakage risk assessment model for shield tunnel based on Kalman filter data fusion method | |
| Hosseinian et al. | Finding best model to forecast construction duration of road tunnels with new Austrian tunneling method using Bayesian inference: case study of Niayesh highway tunnel in Iran | |
| Zheng | Applying Probabilistic Approaches for Reliable Sequential Excavation Method Tunnel Design and Construction | |
| Li et al. | Subway structure health monitoring system based on internet of things | |
| Wu et al. | An MLS-based high-accuracy measurement and automatic analysis method for roadway deformation | |
| CN114117776B (en) | Cutter head damage sensing method for underground large-scale equipment tunneller of coal mine | |
| Huang | BIM for Underground Stations: Supporting Decision Making on Lifecycle Stages |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |