Safety control method for tunnel excavation of three-arm drill jumbo

Abstract

The invention provides a safety control method for tunnel excavation of a three-arm drill jumbo, which is suitable for the field of tunnel excavation and comprises the steps of image acquisition equipment installation and calibration, image acquisition, image transmission, image processing and identification, state feedback and decision making and manual rechecking and emergency response. The safety control method for tunnel excavation of the three-arm drill jumbo has accurate danger identification and high safety and can be widely applied to the field of tunnel excavation.

Description

Technical Field

[0001] The invention relates to a safety control method for tunnel excavation using a three-arm rock drilling trolley, and is applicable to the field of tunnel excavation. Background Art

[0002] Tunnel excavation projects play an important role in modern infrastructure construction. With the continuous improvement of underground space utilization, tunnel construction technology is also developing. Especially in the excavation of large tunnel projects today, the control of safety, construction efficiency and construction quality has become crucial. In the process of tunnel excavation, the three-arm drilling rig is a common mechanical equipment, mainly used for drilling operations. Its multi-arm design can effectively improve the drilling efficiency, but it also brings higher operational complexity and safety risks.

[0003] Traditional tunnel excavation safety control methods usually rely on manual monitoring and empirical judgment, which has the following problems: First, manual monitoring is easily interfered by environmental factors, such as low light and high dust in the tunnel, which will affect the accuracy of monitoring; second, empirical judgment is highly subjective and can easily lead to misjudgment due to individual differences, thus affecting construction safety and project quality; finally, traditional methods lack real-time and automation, and cannot respond to potential risks in a timely manner, thereby increasing safety hazards.

[0004] With the rapid development of computer vision and deep learning technologies, the application of automated monitoring technology based on image recognition in tunnel construction has gradually become a research hotspot. By installing image acquisition equipment on the three-arm drilling rig, collecting image data of the tunnel excavation surface in real time, and using deep learning models to process and identify images, the tunnel excavation status can be monitored in real time and potential risks can be warned in a timely manner. This technology can not only improve the accuracy of monitoring, but also reduce dependence on manual monitoring, significantly improving the safety and efficiency of construction.

[0005] Although there are some tunnel monitoring systems based on image recognition, there are still some limitations. For example, the system has poor adaptability to environmental changes and is easily affected by the complex lighting conditions and dust environment in the tunnel, which leads to a decrease in image quality and thus affects the recognition accuracy. In addition, the existing systems mostly rely on a single image recognition model and cannot fully cope with the various complex situations that may arise during tunnel construction. Therefore, developing a more stable, reliable and intelligent tunnel excavation safety control method has important practical significance and application value. Summary of the invention

[0006] The present invention proposes a three-arm drilling rig tunnel excavation safety control method based on image acquisition and processing. Through the high dynamic range camera installed on the drilling rig and the image label prediction model, the image data of the tunnel excavation surface is collected and analyzed in real time, and automatic recognition and feedback of the construction status are realized. In addition, the dustproof packaging and cleaning system are combined to adapt to the complex environment of tunnel excavation, providing a more intelligent and efficient tunnel construction safety control method.

[0007] The purpose of the present invention can be achieved by adopting the following technical solutions:

[0008] A safety control method for tunnel excavation using a three-arm rock drilling trolley, characterized in that the safety control method for tunnel excavation using a three-arm rock drilling trolley comprises the following steps:

[0009] S101, image acquisition equipment installation and calibration;

[0010] The image acquisition device is installed and calibrated, including at a suitable position of the three-arm drilling rig to ensure that the device can cover the excavation face of the tunnel, and the image acquisition device is initially calibrated to ensure that the device can accurately capture a clear image of the excavation face;

[0011] S102, image acquisition;

[0012] The image acquisition includes setting the acquisition frequency of the image acquisition device, that is, automatically acquiring a frame of image at a certain time interval. During the excavation process using the three-arm rock drilling rig, the image acquisition device automatically acquires image data of the current excavation surface according to the set acquisition frequency;

[0013] S103, image transmission;

[0014] The image transmission includes the image acquisition device obtaining the image data of the excavation surface and transmitting the image data to the data processing center in the form of wired transmission;

[0015] S104, Image processing and recognition;

[0016] The image processing and recognition includes the data processing center receiving the image data of the excavation surface, the data processing center having an embedded image label prediction model, inputting the image data of the excavation surface into the image label prediction model to obtain a label prediction result, wherein the label prediction results are three types, namely a stable state, a vigilant state and a dangerous state;

[0017] S105, status feedback and decision making;

[0018] The state feedback and decision-making includes that according to the label prediction result, the data processing center will automatically generate a feedback signal and execute a corresponding action. When the label prediction result is a stable state, the three-arm rock drilling rig is allowed to continue normal excavation operations. If the label prediction result is an alert state, the system will issue a warning signal to prompt the operator to strengthen monitoring. If the label prediction result is a dangerous state, the system will immediately issue an alarm signal, automatically stop the excavation operation of the three-arm rock drilling rig, and wait for further processing by the operator;

[0019] S106, manual review and emergency response;

[0020] The manual review and emergency response, including for input images whose label prediction results are alert state and dangerous state, the system will automatically save and record them, prompting the operator to perform manual review, and the operator decides whether to stop or slow down the excavation operation of the three-arm rock drilling rig based on the review results.

[0021] Furthermore, in the above S101, the image acquisition device uses a high dynamic range camera, which can capture multiple pictures under different exposure conditions and synthesize them into a clearer image.

[0022] Furthermore, in the above S101, the image acquisition device adopts dust-proof packaging and a startup cleaning system to adapt to the tunnel excavation environment. The startup cleaning system can spray compressed air regularly or as needed to remove dust from the lens surface of the image acquisition device and keep the lens clean.

[0023] Furthermore, in the above S104, the step of obtaining the image label prediction model is:

[0024] a) Use image acquisition equipment to collect a certain number of tunnel excavation face images to form an image set C1, and use expert evaluation method to label each image. The labels are mainly divided into three categories: stable state, alert state and dangerous state. At the same time, it is required that the number of images in the three categories is greater than 10% of the number of images in the image set, and finally obtain the excavation face image set C2 containing labels,

[0025] b) preprocessing the excavation surface image set C2 containing the annotations, wherein the preprocessing includes deleting blurry and low-quality images, as well as image enhancement and data normalization, and finally obtaining the excavation surface image set C3 containing the labels after preprocessing,

[0026] c) Selecting the AlexNet architecture, which includes 5 convolutional layers and 3 fully connected layers, and the activation function used by the AlexNet architecture is the Mish function.

[0027] d) Performing model training, dividing the image set C3 into a training set and a validation set in a ratio of 8:2, using the training set, the training set images as input, and the training set image labels as output, performing model training based on the AlexNet architecture, and finally obtaining a preliminary label prediction model M1,

[0028] e) Model evaluation and optimization: the validation set is used to perform model evaluation on the preliminary label prediction model M1. The model evaluation indicator uses precision, and the preliminary model M1 is adjusted according to the precision result to finally obtain the label prediction model M2.

[0029] Furthermore, the mathematical form of the Mish function is shown in formula (1).

[0030] f(x)=x·tanh(softplus(x)) (1)

[0031] The beneficial effects of the present invention are:

[0032] The beneficial effects of the present invention are: (1) safety of high tunnel excavation; by installing image acquisition equipment on the three-arm drilling trolley, the condition of the tunnel excavation surface is monitored in real time, and combined with the analysis ability of the image label prediction model, potential risk conditions can be identified in time. When the system detects a dangerous or alert state, it automatically issues an alarm and stops the operation to prevent accidents, thereby greatly improving the safety of tunnel construction; (2) reducing manual intervention; improving work efficiency: the present invention adopts automated image acquisition and processing technology to replace the traditional manual monitoring method. Through the automated state feedback and decision-making system, the reliance on manual monitoring is reduced. The operator only needs to review when the system prompts, which greatly improves work efficiency and reduces the risk of human misjudgment. (3) Accurate risk identification and prediction: using the deep learning model of the AlexNet architecture for image processing and recognition, and using the Mish activation function, it can better capture image features and provide a higher recognition accuracy. The continuous optimization and evaluation of the model ensures that the system can provide accurate label prediction results in various complex situations, further improving the reliability of risk warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 : Flow chart of a safety control method for tunnel excavation using a three-arm drilling rig of the present invention. DETAILED DESCRIPTION

[0034] The specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings; it should be understood that the specific embodiments given here are only used to illustrate and explain the present invention and cannot be used to limit the present invention.

[0035] The following is a specific embodiment of a safety control method for tunnel excavation using a three-arm drilling rig.

[0036] like Figure 1 Shown is a flow chart of a multi-source fusion water depth measurement method according to a safety control method for tunnel excavation of a three-arm drilling rig of the present invention.

[0037] A safety control method for tunnel excavation using a three-arm rock drilling trolley, characterized in that the safety control method for tunnel excavation using a three-arm rock drilling trolley comprises the following steps:

[0038] S101, image acquisition equipment installation and calibration;

[0039] The image acquisition device is installed and calibrated, including at a suitable position of the three-arm drilling rig to ensure that the device can cover the excavation face of the tunnel, and the image acquisition device is initially calibrated to ensure that the device can accurately capture a clear image of the excavation face;

[0040] S102, image acquisition;

[0041] The image acquisition includes setting the acquisition frequency of the image acquisition device, that is, automatically acquiring a frame of image at a certain time interval. During the excavation process using the three-arm rock drilling rig, the image acquisition device automatically acquires image data of the current excavation surface according to the set acquisition frequency;

[0042] S103, image transmission;

[0043] The image transmission includes the image acquisition device obtaining the image data of the excavation surface and transmitting the image data to the data processing center in the form of wired transmission;

[0044] S104, Image processing and recognition;

[0045] The image processing and recognition includes the data processing center receiving the image data of the excavation surface, the data processing center having an embedded image label prediction model, inputting the image data of the excavation surface into the image label prediction model to obtain a label prediction result, wherein the label prediction results are three types, namely a stable state, a vigilant state and a dangerous state;

[0046] S105, status feedback and decision making;

[0047] The state feedback and decision-making includes that according to the label prediction result, the data processing center will automatically generate a feedback signal and execute a corresponding action. When the label prediction result is a stable state, the three-arm rock drilling rig is allowed to continue normal excavation operations. If the label prediction result is an alert state, the system will issue a warning signal to prompt the operator to strengthen monitoring. If the label prediction result is a dangerous state, the system will immediately issue an alarm signal, automatically stop the excavation operation of the three-arm rock drilling rig, and wait for further processing by the operator;

[0048] S106, manual review and emergency response;

[0049] The manual review and emergency response, including for input images whose label prediction results are alert state and dangerous state, the system will automatically save and record them, prompting the operator to perform manual review, and the operator decides whether to stop or slow down the excavation operation of the three-arm rock drilling rig based on the review results.

[0050] Furthermore, in the above S101, the image acquisition device uses a high dynamic range camera, which can capture multiple pictures under different exposure conditions and synthesize them into a clearer image.

[0051] Furthermore, in the above S101, the image acquisition device adopts dust-proof packaging and a startup cleaning system to adapt to the tunnel excavation environment. The startup cleaning system can spray compressed air regularly or as needed to remove dust from the lens surface of the image acquisition device and keep the lens clean.

[0052] Furthermore, in the above S104, the step of obtaining the image label prediction model is:

[0053] a) Use image acquisition equipment to collect a certain number of tunnel excavation face images to form an image set C1, and use expert evaluation method to label each image. The labels are mainly divided into three categories: stable state, alert state and dangerous state. At the same time, it is required that the number of images in the three categories is greater than 10% of the number of images in the image set, and finally obtain the excavation face image set C2 containing labels,

[0054] b) preprocessing the excavation surface image set C2 containing the annotations, wherein the preprocessing includes deleting blurry and low-quality images, as well as image enhancement and data normalization, and finally obtaining the excavation surface image set C3 containing the labels after preprocessing,

[0055] c) Selecting the AlexNet architecture, which includes 5 convolutional layers and 3 fully connected layers, and the activation function used by the AlexNet architecture is the Mish function.

[0056] d) Performing model training, dividing the image set C3 into a training set and a validation set in a ratio of 8:2, using the training set, the training set images as input, and the training set image labels as output, performing model training based on the AlexNet architecture, and finally obtaining a preliminary label prediction model M1,

[0057] e) Model evaluation and optimization: the validation set is used to perform model evaluation on the preliminary label prediction model M1. The model evaluation indicator uses precision, and the preliminary model M1 is adjusted according to the precision result to finally obtain the label prediction model M2.

[0058] Furthermore, the mathematical form of the Mish function is shown in formula (1).

[0059] f(x)=x·tanh(softplus(x)) (1)

[0060] In the above embodiments, the present invention discloses a safety control method for tunnel excavation using a three-arm drilling rig; including image acquisition equipment installation and calibration, image acquisition, image transmission, image processing and recognition, state feedback and decision-making, and manual review and emergency response; the present invention proposes a safety control method for tunnel excavation using a three-arm drilling rig, which has accurate hazard identification and high safety, and can be widely used in the field of tunnel excavation.

[0061] The above description is a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A safety control method for tunnel excavation using a three-arm drilling rig, characterized in that: The safety control method for tunnel excavation of a three-arm drilling rig comprises the following steps: 1) Installation and calibration of image acquisition equipment; The image acquisition device is installed and calibrated, including at a suitable position of the three-arm drilling rig to ensure that the device can cover the excavation face of the tunnel, and the image acquisition device is initially calibrated to ensure that the device can accurately capture a clear image of the excavation face; 2) Image acquisition; The image acquisition includes setting the acquisition frequency of the image acquisition device, that is, automatically acquiring a frame of image at a certain time interval. During the excavation process using the three-arm rock drilling rig, the image acquisition device automatically acquires image data of the current excavation surface according to the set acquisition frequency; 3) Image transmission; The image transmission includes the image acquisition device obtaining the image data of the excavation surface and transmitting the image data to the data processing center in the form of wired transmission; 4) Image processing and recognition; The image processing and recognition includes the data processing center receiving the image data of the excavation surface, the data processing center having an embedded image label prediction model, inputting the image data of the excavation surface into the image label prediction model to obtain a label prediction result, wherein the label prediction results are three types, namely a stable state, a vigilant state and a dangerous state; 5) Status feedback and decision making; The state feedback and decision-making includes that according to the label prediction result, the data processing center will automatically generate a feedback signal and execute a corresponding action. When the label prediction result is a stable state, the three-arm rock drilling rig is allowed to continue normal excavation operations. If the label prediction result is an alert state, the system will issue a warning signal to prompt the operator to strengthen monitoring. If the label prediction result is a dangerous state, the system will immediately issue an alarm signal, automatically stop the excavation operation of the three-arm rock drilling rig, and wait for further processing by the operator; 6) Manual review and emergency response; The manual review and emergency response, including for input images whose label prediction results are alert state and dangerous state, the system will automatically save and record them, prompting the operator to perform manual review, and the operator decides whether to stop or slow down the excavation operation of the three-arm rock drilling rig based on the review results.

2. The safety control method for tunnel excavation of a three-arm drilling rig according to claim 1 is characterized in that: In 1), the image acquisition device uses a high dynamic range camera, which can capture multiple pictures under different exposure conditions and synthesize them into a clearer image.

3. The safety control method for tunnel excavation of a three-arm drilling rig according to claim 1 is characterized in that: In 1), the image acquisition device adopts dust-proof packaging and a startup cleaning system to adapt to the tunnel excavation environment. The startup cleaning system can spray compressed air regularly or as needed to remove dust from the lens surface of the image acquisition device and keep the lens clean.

4. The safety control method for tunnel excavation of a three-arm drilling rig according to claim 1 is characterized in that: In 4), the steps of obtaining the image label prediction model are: a) Use image acquisition equipment to collect a certain number of tunnel excavation face images to form an image set C1, and use expert evaluation method to label each image. The labels are mainly divided into three categories: stable state, alert state and dangerous state. At the same time, it is required that the number of images in the three categories is greater than 10% of the number of images in the image set, and finally obtain the excavation face image set C2 containing labels, b) preprocessing the excavation surface image set C2 containing the annotations, wherein the preprocessing includes deleting blurry and low-quality images, as well as image enhancement and data normalization, and finally obtaining the excavation surface image set C3 containing the labels after preprocessing, c) Selecting the AlexNet architecture, which includes 5 convolutional layers and 3 fully connected layers, and the activation function used by the AlexNet architecture is the Mish function. d) Performing model training, dividing the image set C3 into a training set and a validation set in a ratio of 8:2, using the training set, the training set images as input, and the training set image labels as output, performing model training based on the AlexNet architecture, and finally obtaining a preliminary label prediction model M1, e) Model evaluation and optimization: the validation set is used to perform model evaluation on the preliminary label prediction model M1. The model evaluation indicator uses precision, and the preliminary model M1 is adjusted according to the precision result to finally obtain the label prediction model M2.

5. The safety control method for tunnel excavation of a three-arm drilling rig according to claim 4 is characterized in that: The mathematical form of the Mish function is shown in formula (1). f(x)=x·tanh(softplus(x)) (1).

Images