CN114320316A - Shield tunneling machine construction early warning method and device - Google Patents
Shield tunneling machine construction early warning method and device Download PDFInfo
- Publication number
- CN114320316A CN114320316A CN202210047086.8A CN202210047086A CN114320316A CN 114320316 A CN114320316 A CN 114320316A CN 202210047086 A CN202210047086 A CN 202210047086A CN 114320316 A CN114320316 A CN 114320316A
- Authority
- CN
- China
- Prior art keywords
- network
- rock
- image
- images
- early warning
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000010276 construction Methods 0.000 title claims abstract description 22
- 230000005641 tunneling Effects 0.000 title claims abstract description 19
- 239000011435 rock Substances 0.000 claims abstract description 97
- 239000002893 slag Substances 0.000 claims abstract description 35
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 14
- 230000001133 acceleration Effects 0.000 claims abstract description 8
- 238000013461 design Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims abstract description 5
- 238000011176 pooling Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000013139 quantization Methods 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 2
- 238000007635 classification algorithm Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000013526 transfer learning Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims 4
- 230000000875 corresponding effect Effects 0.000 claims 3
- 230000002596 correlated effect Effects 0.000 claims 1
- 230000002093 peripheral effect Effects 0.000 claims 1
- 239000013589 supplement Substances 0.000 claims 1
- 230000001502 supplementing effect Effects 0.000 claims 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims 1
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000945 filler Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Abstract
The invention relates to a shield tunneling machine construction early warning method and a device, belonging to the technical field of tunnel tunneling, wherein a full face rock tunneling machine (TBM) has the advantages of high construction speed, high safety, good economical efficiency and the like, and is widely applied to heavy projects such as highways, railway transportation, urban subways and the like. Due to the severe working environment, a real-time construction early warning method and a real-time construction early warning device are needed. Aiming at two fields of cutter head detection and surrounding rock classification, the invention designs a method based on rock slag classification and surrounding rock integrity monitoring, and realizes tunnel construction monitoring and early warning. Both methods are based on a convolutional neural network, so the invention provides an OpenCL-based convolutional neural network acceleration architecture, and realizes a deployment acceleration device for an early warning method.
Description
Technical Field
The invention belongs to the technical field of tunnel excavation, and particularly relates to a shield machine construction early warning method and device.
Background
The full face rock Tunnel Boring Machine (TBM) has the advantages of high construction speed, high safety, good economy and the like, and is widely applied to heavy projects such as highways, railway transportation, urban subways and the like. Because the working environment is severe, the cutter disc hob is extremely easy to be abnormally worn and damaged, if the damage of the cutter cannot be found and processed in time in the construction process, the tunneling efficiency is reduced, the cutter disc is also abnormally worn, and the engineering progress and the construction quality are influenced. According to a rock breaking mechanism of a hob of a TBM cutterhead, when the cutterhead is worn or damaged, the size of rock debris generated by tunneling can be increased. Therefore, the state of the cutter head can be indirectly monitored by monitoring the rock slag fragment condition on the conveyor belt, and site constructors can be guided to check and replace the cutter in time. The camera collects images above the conveyor belt, avoids severe production environment, and has the advantages of simple equipment, low loss, low cost, long-time monitoring and the like.
Meanwhile, classification of tunnel surrounding rock grades plays a vital role in tunnel construction and is an important factor for judging stability after tunnel excavation and selecting corresponding support measures. Traditional surrounding rock is hierarchical according to the intensity of rock, the integrality of rock mass, crack filler, groundwater and ground stress etc. condition are synthesized and are decided, because work load is great and be difficult to obtain, lead to that the surrounding rock in the reconnaissance in earlier stage is hierarchical comparatively rough. Tunnel construction environment and process are complicated, and the TBM in the construction may influence the shooting sight, and simultaneously, can adopt certain supporting measures to ensure the stability of country rock after the country rock excavation, for example stock, reinforcing bar net, steel bow member etc. can interfere with the discernment of image. The surrounding rock integrity detection network based on the full convolution neural network can effectively avoid the influence of interferents, and meanwhile, the image segmentation network can segment cracks and backgrounds to display the integrity of the current surrounding rock more visually, so that construction personnel can be guided to select proper support design and construction according to the types of the surrounding rocks
Based on the background, the invention provides a shield tunneling machine construction early warning method and device based on a convolutional neural network. Rock slag classification and surrounding rock integrity monitoring are achieved through a convolutional neural network, and image acquisition and network calculation are achieved through the proposed equipment.
Disclosure of Invention
The invention provides a shield machine early warning method and device based on computer vision. In order to achieve the purpose, the invention adopts the following technical scheme:
step 1: and collecting rock slag images and surrounding rock images in the tunneling process through image collecting devices distributed at different positions of the shield tunneling machine.
Step 2: and transmitting the image to a heterogeneous computing terminal, preprocessing the image, inputting the preprocessed image to different convolutional neural networks, and performing network computing on the input rock slag image and the input surrounding rock image respectively.
And step 3: and (3) feature extraction, namely performing feature extraction branch by adopting a convolutional layer, classifying the rock slag classification network by connecting a full connection layer after the convolutional layer, and classifying and abnormally segmenting the surrounding rock integrity detection network by connecting a decoding layer.
And 4, step 4: and (4) feature classification, namely classifying the rock slag image into a normal type and an abnormal type through a Softmax function, and classifying the surrounding rock image into a complete region and an incomplete region through a decoder.
And 5: and outputting the classification result to a display device for displaying, thereby helping constructors to determine the current construction condition.
Drawings
FIG. 1 is an overall flow chart of a rock slag classification method based on a convolutional neural network according to the present invention
FIG. 2 is a schematic of a rock slag data set
FIG. 3 is a method for monitoring the integrity of surrounding rocks based on a full convolution network
FIG. 4 is a schematic diagram of a calculation result of a surrounding rock integrity detection network
FIG. 5 is a convolutional neural network heterogeneous computing architecture based on CPU + FPGA
FIG. 6 System Overall architecture
Detailed Description
The invention provides a shield machine early warning method and a shield machine early warning device based on computer vision, and in order to make the technical scheme and the effect of the invention clearer and clearer, the following describes the specific implementation mode of the invention in detail with reference to the attached drawings.
As shown in FIG. 1, the invention relates to a rock debris classification algorithm flow chart based on a convolutional neural network. The rock slag classification network is composed of three network layers, namely a convolution layer, a pooling layer and a full-connection layer. The convolutional layer is used for extracting features and is the most main calculation layer of the convolutional neural network. High-level features in the image may be extracted. For each convolution calculation, each output characteristic value is obtained by multiplying the corresponding convolution kernel and the input characteristic value by accumulation operation and then adding offset. The operation between different characteristic values has no data dependency, thus the convolution calculation can be calculated in parallel.
The pooling layer is usually located behind the convolutional layer, plays a role in reducing the amount of calculation and controlling overfitting, and usually performs pooling downsampling respectively behind each feature map to reduce the dimensionality of the feature map, and there are generally two pooling methods: average pooling and maximum pooling, maximum pooling is used in the algorithm herein because maximum pooling allows more retention of information such as edges, textures, etc. of the image, and the extracted features allow better classification functionality.
The full connection layer plays a role of a classifier in the whole network, and because the result obtained by network convolution operation is the characteristic information of the image, and manual screening processing cannot be performed, the full connection layer is required to integrate the characteristic information, and the features extracted by the convolution layer are classified by the SoftMax classifier to establish a relation with a sample marking space.
The rock slag images collected in the production process are used in the network training process, and are divided into three types as shown in fig. 2, wherein the two types are normal types, one type is abnormal, the normal type represents that the hob normally works, and the abnormal type represents that the working state of the hob is abnormal.
In the actual production process, the rock slag may have random distribution in the direction, and the camera may be influenced by the environment to acquire images containing noise, so that aiming at the characteristics, the data set is amplified by adopting a random rotation and Gaussian noise adding mode, the transfer learning is used, and the rock slag classification network is retrained. And learning the weight of the pre-training network into the rock slag classification network, thereby realizing the rock slag classification network with high accuracy.
As shown in fig. 3, the invention relates to a method for monitoring the integrity of surrounding rock based on a full convolution network. The full convolutional network is a convolutional neural network in deep learning and is specially used for semantic segmentation of images. For a full convolution network, the network input is one image and the output is also one image, and the function of the network is to learn pixel-to-pixel mappings to achieve pixel-level identification. The method comprises the steps of using a classical full convolution network SegNet to construct a network structure for surrounding rock integrity recognition on the basis of an original network, inputting original images and label images with concentrated surrounding rock image sample data into the network, carrying out convolution operation and pooling operation on the input images for many times through an encoder part of the network, extracting high-level features of the input images, then carrying out convolution and anti-pooling operation through a decoder part, recovering the high-level features to the same size as the input images, meanwhile, calculating the probability of incomplete areas of each pixel point, comparing the probability with corresponding convenient future to realize one-time forward reasoning operation, then updating and learning network weights by adopting a back propagation algorithm, and realizing design and training of a surrounding rock network through continuous iteration so as to obtain an available surrounding rock integrity monitoring network. As shown in fig. 4, after the surrounding rock image is subjected to network computation, the surrounding rock fractures and the background are represented by pixels with different colors.
For the discrimination of the integrity of the rock mass, table 1 gives detailed descriptions of different surrounding rock types.
Table 1: surrounding rock integrity differentiation
According to the development degree of the cracks and the combination degree of the main cracks, the types of the surrounding rocks can be divided into 5 types, namely complete, relatively broken, broken and extremely broken. And segmenting the cracks and the background of the input surrounding rock image through calculation of the surrounding rock integrity monitoring network, thereby guiding constructors to classify the surrounding rock so as to perform subsequent support design and construction.
During production, surrounding rock images are collected through an image sensor, the images are input into a heterogeneous terminal through the sensor, and network operation is carried out through the terminal. In the aspect of algorithm deployment acceleration, most of the conventional convolutional neural networks are operated on a CPU/GPU platform, but the number of internal computing units of the CPU is small, and the computing power cannot meet the computing requirement; the GPU has great advantages in parallel computing, and is mostly used in a training phase of a neural network, but in an inference phase, the GPU cannot exert the characteristics of high bandwidth and multiple computing cores, and challenges in multiple aspects such as hardware power consumption and size are faced in actual edge-end application deployment. The FPGA integrates abundant storage hardware resources, flexible programmable logic resources and high-performance computing resources, can meet the requirements of parallel computing and low power consumption at the same time, has high flexibility and reconfigurability, and provides an effective solution for the edge terminal deployment of the convolutional neural network.
Therefore, the terminal designed by the method is based on the CPU + FPGA heterogeneous design, and an FPGA convolutional neural network acceleration architecture based on the OpenCL development process is provided for accelerating the rock slag classification network, as shown in FIG. 5. According to the independence among the calculation layers of the convolutional neural network, a configurable OpenCL kernel is designed to respectively complete the operation of the convolution, pooling and full connection layers of the network. The whole framework is mainly divided into an on-chip part and an off-chip part, an off-chip global memory is mainly used for storing characteristic values, model parameters and quantization parameter information, and an on-chip memory is used for storing and transmitting characteristic value data, weight parameters, quantization parameters of a current calculation layer, calculation results of the current layer and the like.
In the architecture, the cores are mutually connected through a configurable pipeline, and the pipeline is an efficient non-blocking FIFO queue data transmission module constructed by using on-chip resources, so that data between the cores is directly transmitted on the chip, the access times of an off-chip memory can be reduced, and the data transmission efficiency is improved. Complex network operation acceleration can be realized through hardware resources by flexibly combining control words with kernel connection.
When the control word is 0, the convolution or full connection operation is completed, and the connection mode of the pipeline and the kernel is as follows: off-chip memory-on-chip cache-data pipeline-convolution kernel-data pipeline-on-chip cache-off-chip memory.
When the control word is 1, the convolution and pooling operation is completed, and the connection mode of the pipeline and the kernel is as follows: off-chip memory-on-chip cache-data pipeline-volume and kernel-data pipeline-pool kernel-data pipeline-on-chip cache-off-chip memory.
When the control word is 2, the convolution and anti-pooling operation is completed, and the connection mode of the pipeline and the kernel is as follows: off-chip memory-on-chip cache-data pipeline-convolution kernel-inverse pooling kernel-data pipeline-on-chip cache-off-chip memory.
When related connection mode data pipelining is carried out, each kernel is executed only once, and the contention of kernel resources can not occur, so that the smoothness of the whole assembly line is ensured. And through the combination of the control words, a computational rock slag classification network or a surrounding rock integrity monitoring network can be controlled and constructed.
Therefore, in combination with the method and apparatus, the complete system is shown in fig. 6, and the system works as follows:
1. and respectively acquiring a rock slag image and a surrounding rock image through an image sensor above the rock slag conveying belt and an image sensor outside the shield tunneling machine.
2. The image sensor transmits the collected rock slag image and the collected surrounding rock image to the heterogeneous computing equipment, and the equipment CPU cuts the image to meet the input requirement of the network.
3. The rock slag image and the surrounding rock image are respectively input into the network acceleration framework provided by the invention, and the flow direction of the characteristic diagram data is controlled according to the set control word through the scheduling of the CPU end and the intensive calculation of the FPGA end, so that the operation of the rock slag classification network and the surrounding rock integrity monitoring network is realized.
4. And after the calculation is finished, the original image and the output result are output to a CPU (central processing unit) end from the FPGA end, and are displayed after being processed. Wherein, the rock slag classification network outputs and displays the current rock slag image and the type thereof; and outputting and displaying the current surrounding rock image and the binary image obtained after image segmentation by the surrounding rock integrity network.
Claims (6)
1. A shield machine construction early warning method and a device are characterized in that the device comprises: a vision sensor, a heterogeneous computing device, an operating room display; the method mainly achieves the functions of rock slag state recognition and surrounding rock integrity recognition. Wherein:
the visual sensors are multiple, comprise components such as an industrial camera, a zoom lens and a light supplementing lamp, are arranged above the rock slag conveyor belt and in front of the shield tunneling machine, and are respectively used for collecting rock slag images on the rock slag conveyor belt and peripheral surrounding rock images of the shield tunneling machine.
The heterogeneous computing equipment is connected with the visual sensor, is used for receiving and processing images acquired by the visual sensor, is connected with the operating room display, displays information through the display, comprises a CPU (central processing unit) part and an FPGA (field programmable gate array) part, and performs computation of the early warning algorithm based on the convolutional neural network through the cooperative heterogeneous computation of the CPU and the FPGA.
The operation room display is used for displaying the acquired image information and the corresponding calculation result.
2. The shield tunneling machine early warning device according to claim 1, characterized in that: the vision sensor usually selects an industrial lens with high temperature resistance and high humidity resistance, and is matched with a zoom lens and a light supplement lamp to realize image acquisition. In the device, two image sensors at different positions are used as image acquisition devices, wherein a visual sensor is erected above a rock slag conveyor belt and is used for acquiring rock slag images in the tunneling process; the method is characterized in that a vision sensor is erected at the front part of the shield tunneling machine and used for collecting the images of the surrounding rocks of the shield tunneling machine in construction, and the image sensor also has the function of collecting images with different resolutions in order to be matched with subsequent network calculation.
3. The shield tunneling machine early warning method according to claim 1, characterized in that: for the rock slag image, a rock slag classification algorithm based on a convolutional neural network is designed and deployed; for the surrounding rock image, a surrounding rock image integrity detection network based on image segmentation is designed and deployed, and network computing is achieved through a heterogeneous computing architecture. The rock residue classification network is obtained by modifying and training a VGG16 network, the pre-training network is subjected to transfer learning through rock residue images collected in an engineering scene to obtain the rock residue classification network, a rock residue classification result is positively correlated with the state of a current shield machine cutter head hob, and the aim of indirectly monitoring the state of the hob can be fulfilled by monitoring the state of the rock residue; the surrounding rock integrity monitoring network realizes semantic segmentation of input images through an image segmentation network SegNet, classifies pixel points of input surrounding rock images into incomplete surrounding rock areas and background areas, and obtains specific positions and accurate geometric information of the incomplete areas.
4. The convolutional neural network-based rock slag classification method as claimed in claim 3, wherein: the rock slag classification network method comprises a convolutional layer, a pooling layer and a full-connection layer, rock slag image features are extracted through the convolutional layer, network calculated amount is reduced through the pooling layer, overfitting of a network is controlled, the effect of a classifier is achieved through the full-connection layer, and the relation between feature information and a marking space is established.
5. The method for identifying the integrity of the surrounding rock based on the full convolution network as claimed in claim 3, wherein the method comprises the following steps: the convolutional neural network model comprises an encoder and a decoder, wherein the encoder comprises a convolutional layer and a pooling layer, in the encoder, after a plurality of times of convolutional operation and pooling operation are carried out on an input surrounding rock image, a high-level feature map is generated, then the decoder is used for recovering the abstract high-level feature to the same size as the input image through convolutional operation and anti-pooling operation, and meanwhile, through network operation, each pixel in an output image is provided with a predicted value for indicating whether the surrounding rock at the position corresponding to the pixel has a crack or water leakage condition. And (4) selecting strategies according to stability judgment and corresponding support measures in the segmented image guidance construction process.
6. The shield tunneling machine early warning device according to claim 3, characterized in that: the device comprises a CPU and an FPGA, is connected with an image sensor and a display, and has the main function of receiving images and performing convolutional neural network operation. In the OpenCL process, a CPU is responsible for preprocessing and scheduling data, and an FPGA is responsible for intensive calculation of data. The heterogeneous computing device can receive images acquired by the image sensor, preprocesses the images and designs a convolutional neural network acceleration architecture of a CPU + FPGA through an OpenCL flow. And designing a configurable OpenCL kernel to respectively complete the convolution, pooling, anti-pooling and full-connection layer operations of the network according to the independence among the computing layers of the CNN. The whole framework is mainly divided into an on-chip part and an off-chip part, an off-chip global memory is mainly used for storing characteristic values, model parameters and quantization parameter information, and an on-chip memory is used for storing and transmitting characteristic value data, weight parameters, quantization parameters of a current calculation layer, calculation results of the current layer and the like. In the architecture, the cores are connected with each other through a configurable pipeline, and the pipeline is an efficient non-blocking First-in First-out (FIFO) data transmission module constructed by using on-chip resources, so that data between the cores are directly transmitted on the chip, the access times of an off-chip memory can be reduced, and the data transmission efficiency is improved. Complex network operation acceleration can be realized through hardware resources by flexibly combining control words with kernel connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210047086.8A CN114320316A (en) | 2022-01-14 | 2022-01-14 | Shield tunneling machine construction early warning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210047086.8A CN114320316A (en) | 2022-01-14 | 2022-01-14 | Shield tunneling machine construction early warning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114320316A true CN114320316A (en) | 2022-04-12 |
Family
ID=81027616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210047086.8A Pending CN114320316A (en) | 2022-01-14 | 2022-01-14 | Shield tunneling machine construction early warning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114320316A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2620807A (en) * | 2022-07-18 | 2024-01-24 | Xinjiang Irtysh Invest And Development Co Ltd | TBM adaptive surrounding rock classification method |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101105126A (en) * | 2007-08-03 | 2008-01-16 | 重庆邮电大学 | Logging-while-drilling orientation measurement error compensation method based on micro-quartz angular rate sensor |
| JP2015004194A (en) * | 2013-06-20 | 2015-01-08 | 株式会社マシノ | Geological survey method of mountain tunnel working face front natural ground |
| WO2019063024A1 (en) * | 2017-09-30 | 2019-04-04 | 中铁工程装备集团有限公司 | Smart decision making method and system for boring control parameters of hard rock tbm |
| CN109886329A (en) * | 2019-02-18 | 2019-06-14 | 中国铁建重工集团有限公司 | Rock crusher level detection method, detection system and heading equipment |
| CN110245695A (en) * | 2019-05-30 | 2019-09-17 | 华中科技大学 | A kind of TBM rock slag order of magnitude recognition methods based on convolutional neural networks |
| CN110331983A (en) * | 2019-07-11 | 2019-10-15 | 中国电建集团成都勘测设计研究院有限公司 | Double-shielded TBM tunneling construction method |
| CN110516730A (en) * | 2019-08-20 | 2019-11-29 | 中铁工程装备集团有限公司 | The online stage division of quality of surrounding rock based on PSO-SVM algorithm and image recognition |
| CN110593929A (en) * | 2019-10-28 | 2019-12-20 | 中冶沈勘秦皇岛工程设计研究总院有限公司 | Secondary multi-section anchoring anchor cable and use method thereof |
| CN110686616A (en) * | 2019-10-23 | 2020-01-14 | 中南大学 | TBM tunnel surrounding rock morphology acquisition method and device |
| CN110751676A (en) * | 2019-10-21 | 2020-02-04 | 中国科学院空间应用工程与技术中心 | Heterogeneous computing system and method based on target detection and readable storage medium |
| CN110991632A (en) * | 2019-11-29 | 2020-04-10 | 电子科技大学 | Method for designing heterogeneous neural network computing accelerator based on FPGA |
| WO2020199290A1 (en) * | 2019-04-04 | 2020-10-08 | 山东大学 | Tbm-mounted advance geological forecast system and method based on recognition of lithology and unfavorable geological precursor characteristics |
| CN111879610A (en) * | 2020-07-10 | 2020-11-03 | 武汉大学 | Rock slag mechanical parameter real-time measurement system and measurement method in tunneling process |
| CN112127896A (en) * | 2020-09-18 | 2020-12-25 | 武汉大学 | Automatic acquisition and analysis system and method for TBM excavation rock slag information |
| CN112647965A (en) * | 2020-12-09 | 2021-04-13 | 山东大学 | Method and system suitable for real-time card-blocking prediction of TBM tunneling tunnel |
| CN112990227A (en) * | 2021-02-08 | 2021-06-18 | 中国铁建重工集团股份有限公司 | Face geology detection method |
-
2022
- 2022-01-14 CN CN202210047086.8A patent/CN114320316A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101105126A (en) * | 2007-08-03 | 2008-01-16 | 重庆邮电大学 | Logging-while-drilling orientation measurement error compensation method based on micro-quartz angular rate sensor |
| JP2015004194A (en) * | 2013-06-20 | 2015-01-08 | 株式会社マシノ | Geological survey method of mountain tunnel working face front natural ground |
| WO2019063024A1 (en) * | 2017-09-30 | 2019-04-04 | 中铁工程装备集团有限公司 | Smart decision making method and system for boring control parameters of hard rock tbm |
| CN109886329A (en) * | 2019-02-18 | 2019-06-14 | 中国铁建重工集团有限公司 | Rock crusher level detection method, detection system and heading equipment |
| WO2020199290A1 (en) * | 2019-04-04 | 2020-10-08 | 山东大学 | Tbm-mounted advance geological forecast system and method based on recognition of lithology and unfavorable geological precursor characteristics |
| CN110245695A (en) * | 2019-05-30 | 2019-09-17 | 华中科技大学 | A kind of TBM rock slag order of magnitude recognition methods based on convolutional neural networks |
| CN110331983A (en) * | 2019-07-11 | 2019-10-15 | 中国电建集团成都勘测设计研究院有限公司 | Double-shielded TBM tunneling construction method |
| CN110516730A (en) * | 2019-08-20 | 2019-11-29 | 中铁工程装备集团有限公司 | The online stage division of quality of surrounding rock based on PSO-SVM algorithm and image recognition |
| CN110751676A (en) * | 2019-10-21 | 2020-02-04 | 中国科学院空间应用工程与技术中心 | Heterogeneous computing system and method based on target detection and readable storage medium |
| CN110686616A (en) * | 2019-10-23 | 2020-01-14 | 中南大学 | TBM tunnel surrounding rock morphology acquisition method and device |
| CN110593929A (en) * | 2019-10-28 | 2019-12-20 | 中冶沈勘秦皇岛工程设计研究总院有限公司 | Secondary multi-section anchoring anchor cable and use method thereof |
| CN110991632A (en) * | 2019-11-29 | 2020-04-10 | 电子科技大学 | Method for designing heterogeneous neural network computing accelerator based on FPGA |
| CN111879610A (en) * | 2020-07-10 | 2020-11-03 | 武汉大学 | Rock slag mechanical parameter real-time measurement system and measurement method in tunneling process |
| US20220011204A1 (en) * | 2020-07-10 | 2022-01-13 | Wuhan University | Real-time measurement system and measurement method for mechanical parameters of rock slag during excavation |
| CN112127896A (en) * | 2020-09-18 | 2020-12-25 | 武汉大学 | Automatic acquisition and analysis system and method for TBM excavation rock slag information |
| CN112647965A (en) * | 2020-12-09 | 2021-04-13 | 山东大学 | Method and system suitable for real-time card-blocking prediction of TBM tunneling tunnel |
| CN112990227A (en) * | 2021-02-08 | 2021-06-18 | 中国铁建重工集团股份有限公司 | Face geology detection method |
Non-Patent Citations (2)
| Title |
|---|
| 孙金山;卢文波;苏利军;周创兵;: "基于TBM掘进参数和渣料特征的岩体质量指标辨识", 岩土工程学报, vol. 30, no. 12, pages 1847 - 1854 * |
| 程秋菊;陈国平;王璐;管春;: "基于卷积神经网络的毫米波图像目标检测", 科学技术与工程, vol. 20, no. 13, pages 5224 - 5229 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2620807A (en) * | 2022-07-18 | 2024-01-24 | Xinjiang Irtysh Invest And Development Co Ltd | TBM adaptive surrounding rock classification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126325B (en) | Intelligent personnel security identification statistical method based on video | |
| CN113469177B (en) | Deep learning-based drainage pipeline defect detection method and system | |
| CN111899288B (en) | Tunnel leakage water area detection and identification method based on infrared and visible light image fusion | |
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| CN111696075A (en) | Intelligent fan blade defect detection method based on double-spectrum image | |
| CN106934796B (en) | The high-speed belt conveyor rock slag video analytic system and method that rock tunnel(ling) machine carries | |
| Kanaeva et al. | Road pavement crack detection using deep learning with synthetic data | |
| Ren et al. | YOLOv5s-M: A deep learning network model for road pavement damage detection from urban street-view imagery | |
| CN112633052A (en) | Belt tearing detection method | |
| CN114320316A (en) | Shield tunneling machine construction early warning method and device | |
| CN111680610A (en) | Construction scene abnormity monitoring method and device | |
| CN113128476A (en) | Low-power consumption real-time helmet detection method based on computer vision target detection | |
| Huang et al. | GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection | |
| Carranza-García et al. | Object detection using depth completion and camera-LiDAR fusion for autonomous driving | |
| CN111582084B (en) | Weak supervision learning-based rail foreign matter detection method and system under empty base view angle | |
| CN117423157A (en) | Mine abnormal video action understanding method combining migration learning and regional invasion | |
| CN110751150A (en) | FPGA-based binary neural network license plate recognition method and system | |
| CN116883650A (en) | Image-level weak supervision semantic segmentation method based on attention and local stitching | |
| CN115984672A (en) | Method and device for detecting small target in high-definition image based on deep learning | |
| CN113362330B (en) | Pantograph cavel real-time detection method, device, computer equipment and storage medium | |
| CN112990169B (en) | Coal-rock interface identification method and coal cutting track determination method and device | |
| CN115909245A (en) | Visual multi-task processing method based on deep learning | |
| CN113569943A (en) | Deep neural network-based slag piece bulk early warning method, system and device | |
| CN213241250U (en) | Miner safety helmet detection system | |
| CN116342571B (en) | State detection method and device for ventilation system control box and storage medium |
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 |