CN117052405A - Tunnel boring machine cutter loss detection device and detection method thereof - Google Patents

Abstract

The invention relates to the technical field of detection of cutters of tunneling machines, in particular to a cutter loss detection device of a tunneling machine and a detection method thereof, comprising a cutter monitoring unit, a data processing unit and a user interface, wherein the cutter monitoring unit is arranged at the cutter part of the tunneling machine and is used for acquiring state data of the cutter in the working process in real time; the data processing unit is connected with the cutter monitoring unit, receives and processes cutter state data, and calculates and generates the loss condition of the cutter; the user interface is connected with the data processing unit and used for displaying the cutter loss condition. The invention can automatically and accurately detect the loss condition of the cutter, greatly improves the efficiency and accuracy of cutter loss detection, reduces human errors and improves the working efficiency and safety of tunneling.

Description

A tunnel boring machine tool wear detection device and its detection method

Technical field

The invention relates to the technical field of boring machine tool detection, and in particular to a tunnel boring machine tool loss detection device and a detection method thereof.

Background technique

Tunneling is an important task in modern civil engineering, in which cutting tools play a vital role. However, the cutting tools will continue to wear out during use, and their wear status will directly affect the working efficiency and safety of the tunnel boring machine, and even affect the progress and quality of the entire project.

In early tunnel excavation work, the wear status of cutting tools was usually evaluated through manual observation and measurement. This method has many shortcomings. First, manual inspection is inefficient and requires regular shutdowns for inspection, which affects the work progress; secondly, the accuracy of manual inspection It is greatly affected by the operator's technical level and experience, and errors are prone to occur. Furthermore, manual inspection is difficult to achieve real-time monitoring and early warning, and it is impossible to detect excessive tool wear in a timely manner.

In order to improve this situation, some tool wear detection systems have begun to use electronic sensor technology. By collecting relevant data on the working status of the cutting tools, the wear status of the cutting tools is then evaluated through data analysis algorithms. Compared with manual detection, this method has greatly improved detection efficiency and accuracy. However, this method also has some problems, such as the weak anti-interference ability of the sensor, complex data processing algorithms, which require professional data analysts to operate, and cannot achieve automated and intelligent detection.

Contents of the invention

Based on the above objectives, the present invention provides a tunnel boring machine tool wear detection device and a detection method.

A tool loss detection device for a tunnel boring machine, including a tool monitoring unit, a data processing unit and a user interface. It is characterized in that the tool monitoring unit is provided at the tool part of the tunnel boring machine and is used to obtain real-time data of the tool during the working process. status data; the data processing unit is connected to the tool monitoring unit, receives and processes the tool status data, calculates and generates the tool wear status; the user interface is connected to the data processing unit, and is used to display the tool wear status.

Further, the tool monitoring unit is based on an image monitoring mechanism, which includes a tool image acquisition module, an image processing module, and an early warning module;

The tool image acquisition module is used to obtain real-time images of the tool during tunnel excavation;

The image processing module is used to analyze the real-time image of the tool surface and determine the wear of the tool;

The early warning module is used to generate and send a warning signal when tool wear reaches a preset value.

Further, the tool monitoring unit is based on a tool detection sensor. The tool detection sensor is used to obtain status data of the tool in real time during the working process. The data includes vibration frequency, vibration amplitude, sound frequency, and sound intensity.

Further, the data processing module also includes a wireless transmission module and a data storage module;

The wireless transmission module is used to transmit tool loss data to a remote monitoring center in real time;

The data storage module is used to store tool wear data for historical comparison, trend analysis and modeling prediction.

Further, the user interface includes a touch screen, through which the user can view and operate the tool wear situation;

The touch screen has a graphical user interface that displays the current wear status, wear trend, and early warning information of the tool;

The touch screen can set the loss warning threshold and adjust the loss calculation weight parameters;

The user interface also includes a data export function to export tool loss data into various formats to facilitate subsequent data analysis and report production. In remote monitoring mode, users can also remotely access the touch screen interface through the network to achieve remote monitoring and operation. .

Furthermore, it also includes a power module to provide power for the tool detection sensor, image monitoring mechanism and user interface.

A method for detecting tool wear of a tunnel boring machine, including the following steps:

Step 1: Turn on the tool monitoring unit and collect tool status data;

Step 2: Use the data processing unit to receive and process the tool status data, calculate and generate the tool wear status;

Step 3: Display the tool wear status through the user interface to determine whether the tool needs to be replaced.

Further, when the tool status data in step one is based on the image monitoring mechanism, the details are as follows:

a) Through the tool image acquisition module, real-time images of the tool are obtained during tunnel excavation;

b) Preprocess the acquired real-time images, which includes denoising, enhancement, and cutting steps to improve image processing efficiency and accuracy;

c) Use an image recognition algorithm to analyze the pre-processed image to determine the loss of the tool;

d) Compare the analysis results to determine whether the tool needs to be replaced or repaired;

e) If replacement or repair is required, send instructions for replacement or repair.

Among them, the image recognition algorithm includes deep learning and machine learning methods, which effectively improves the efficiency and accuracy of loss detection of tunnel boring machine tools.

Furthermore, when comparing the analysis results, a preset threshold is used for comparison. If the loss of the tool exceeds the preset threshold, it is determined that the tool needs to be replaced or repaired, thereby improving the automation of tool loss detection, where the preset threshold can be Adjustments are made based on factors such as the material of the tool, the hardness of the tunnel excavation, and the history of tool use, making the detection of tool wear more accurate.

Further, when the tool status data of the tool in step one is based on the tool detection sensor, the details are as follows:

The tool detection sensor is used to obtain changes in physical signals of vibration and sound for analysis and calculation. The signal changes are analyzed through some specific algorithms, including spectrum analysis, time-frequency analysis, and waveform analysis. It is assumed that the loss state of the tool is determined by vibration and sound factors. Determined, the specific calculation formula is as follows:

Tool wear status=α1*VD+α2*AD+α3*VF+α4*AF

in,

VD represents the amplitude of vibration, obtained through a vibration sensor;

AD represents the intensity of sound, obtained through the sound sensor;

VF represents the frequency of vibration, obtained through a vibration sensor;

AF represents the frequency of sound, obtained through a sound sensor;

α1, α2, α3, and α4 are the weights of influencing factors, which can be trained and optimized through a large amount of historical data.

Beneficial effects of the present invention:

1. The present invention, using image acquisition and image recognition technology, can automatically, accurately and safely detect the loss of tools, improve the efficiency and safety of tunnel excavation, and reduce tunnel quality problems caused by excessive tool loss. In addition, , the detection process of this invention can be displayed in real time, so that users can intuitively understand the usage status of the tool, improve the user experience, and can also predict the life of the tool, providing users with comprehensive tool usage information.

2. The present invention, through the tool loss detection sensor, can automatically and accurately detect the loss status of the tool, greatly improving the efficiency and accuracy of tool loss detection, reducing human errors, and improving the efficiency and safety of tunnel excavation. In addition, through the early warning function, the user can be promptly reminded when tool wear is serious, avoiding equipment damage and safety accidents caused by excessive tool wear, reducing maintenance costs and downtime, and has broad application prospects.

3. In the present invention, the tool detection sensor and the image acquisition module perform dual monitoring to improve detection accuracy.

Description of the drawings

In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the purpose of explaining the present invention or the technical solutions in the prior art. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without any creative effort.

Figure 1 is a schematic diagram of a detection method according to an embodiment of the present invention;

Figure 2 is a schematic diagram of the detection process based on the image monitoring mechanism according to the embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to specific embodiments.

It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should have the usual meanings understood by those with ordinary skills in the field to which the present invention belongs. "First", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprising" mean that the elements or things appearing before the word include the elements or things listed after the word and their equivalents, without excluding other elements or things. Words such as "connected" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right", etc. are only used to express relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

As shown in Figure 1-2, a tunnel boring machine tool loss detection device includes a tool monitoring unit, a data processing unit and a user interface. It is characterized in that the tool monitoring unit is provided at the tool part of the tunnel boring machine for Real-time acquisition of the status data of the tool during the working process; the data processing unit is connected to the tool monitoring unit, receives and processes the tool status data, calculates and generates the loss status of the tool; the user interface is connected to the data processing unit to display the tool loss situation.

The tool monitoring unit is based on an image monitoring mechanism, which includes a tool image acquisition module, an image processing module, and an early warning module;

The tool image acquisition module is used to obtain real-time images of the tool during tunnel excavation;

The image processing module is used to analyze the real-time image of the tool surface and determine the wear of the tool;

The early warning module is used to generate and send a warning signal when tool wear reaches a preset value.

The tool monitoring unit is based on a tool detection sensor. The tool detection sensor is used to obtain status data of the tool in real time during the working process. The data includes vibration frequency, vibration amplitude, sound frequency, and sound intensity.

The data processing module also includes a wireless transmission module and a data storage module;

The wireless transmission module is used to transmit tool loss data to a remote monitoring center in real time;

The data storage module is used to store tool wear data for historical comparison, trend analysis and modeling prediction.

The user interface includes a touch screen, through which the user can view and operate tool wear conditions;

The touch screen has a graphical user interface that displays the current wear status, wear trend, and early warning information of the tool;

The touch screen can set the loss warning threshold and adjust the loss calculation weight parameters;

The user interface also includes a data export function to export tool loss data into various formats to facilitate subsequent data analysis and report production. In remote monitoring mode, users can also remotely access the touch screen interface through the network to achieve remote monitoring and operation. .

It also includes a power module to provide power for the tool detection sensor, image monitoring mechanism and user interface.

A method for detecting tool wear of a tunnel boring machine, including the following steps:

Step 1: Turn on the tool monitoring unit and collect tool status data;

Step 2: Use the data processing unit to receive and process the tool status data, calculate and generate the tool wear status;

Step 3: Display the tool wear status through the user interface to determine whether the tool needs to be replaced.

When the tool status data in step one is based on the image monitoring mechanism, the details are as follows:

a) Through the tool image acquisition module, real-time images of the tool are obtained during tunnel excavation;

b) Preprocess the acquired real-time images through the data processing unit. The preprocessing includes denoising, enhancement, and cutting steps to improve image processing efficiency and accuracy;

c) Use an image recognition algorithm to analyze the pre-processed image to determine the loss of the tool;

d) Compare the analysis results to determine whether the tool needs to be replaced or repaired;

e) If replacement or repair is required, send instructions for replacement or repair.

Among them, the image recognition algorithm includes deep learning and machine learning methods, which effectively improves the efficiency and accuracy of loss detection of tunnel boring machine tools.

When comparing the analysis results, a preset threshold is used for comparison. If the loss of the tool exceeds the preset threshold, it is determined that the tool needs to be replaced or repaired, thereby improving the automation of tool loss detection. The preset threshold can be based on the tool's Factors such as material, tunneling hardness, and tool usage history are adjusted to make tool wear detection more accurate.

When the tool status data of the tool in step one is based on the tool detection sensor, the details are as follows:

The tool detection sensor is used to obtain changes in physical signals of vibration and sound for analysis and calculation. The signal changes are analyzed through some specific algorithms, including spectrum analysis, time-frequency analysis, and waveform analysis. It is assumed that the loss state of the tool is determined by vibration and sound factors. Determined, the specific calculation formula is as follows:

Tool wear status=α1*VD+α2*AD+α3*VF+α4*AF

in,

VD represents the amplitude of vibration, obtained through a vibration sensor;

AD represents the intensity of sound, obtained through the sound sensor;

VF represents the frequency of vibration, obtained through a vibration sensor;

AF represents the frequency of sound, obtained through a sound sensor;

α1, α2, α3, and α4 are the weights of influencing factors, which can be trained and optimized through a large amount of historical data.

On the tunnel boring machine, the tool image acquisition device or tool detection sensor can be installed in front of or next to the cutter head. The specific position can be adjusted according to the layout of the cutter and the working environment. The main goal is to be able to clearly capture the image of the cutter. . Of course, if conditions permit, multiple image acquisition devices can be set up to obtain images of the tool from different angles in order to more comprehensively and accurately assess the wear of the tool.

In order to enable the image acquisition device to adapt to complex working conditions such as vibration, dust, and water spray during tunnel excavation, the following measures can be adopted:

Vibration protection: The image acquisition device can be equipped with anti-shock devices, such as springs or rubber pads, to reduce the impact of vibration on image acquisition during tunnel excavation.

Dust-proof: The image acquisition device can adopt a dust-proof design. For example, the equipment shell adopts a sealed design to prevent dust from entering the inside of the equipment. At the same time, dust-proof materials or coatings can be used on the surface of the equipment to reduce dust adhesion.

Waterproof: Since water spray may be involved during tunneling, the image acquisition device needs to be waterproof. This can be achieved by adopting a waterproof design for the device case, using waterproof interfaces and cables, etc.

Cleaning: Since a large amount of dust and mud will be generated during tunneling, this may contaminate the lens of the image acquisition device and affect the clarity of the image. Therefore, the image acquisition device can be configured with a cleaning system, such as an automatic cleaning device, to clean the lens regularly or as needed.

Lighting: Since lighting conditions may change during tunneling, the image acquisition device may need to be equipped with lighting equipment to ensure clear images under any lighting conditions.

Through the above design, it can be ensured that the image acquisition device works stably and reliably in a complex working environment, and obtains high-quality tool images, thereby effectively detecting tool wear.

The criteria at which a tool needs to be replaced or repaired will vary depending on the specific application and tool type, but are generally based on several factors:

Wear degree of the tool: When the blade of the tool is worn to a certain extent, the excavation efficiency of the tool will be reduced, and it may also lead to a decrease in the quality of the excavation. Therefore, a wear threshold is usually set. When the wear level of the tool reaches or exceeds this threshold, the tool needs to be replaced or repaired.

The wear shape of the cutting tool: In addition to the degree of wear, the wear shape of the cutting tool will also affect its excavation efficiency and excavation quality. For example, if a tool's blade cracks or breaks, the tool may need to be replaced or repaired even if the wear level has not reached a threshold.

Usage history of the tool: The usage history of the tool includes information such as its usage time, usage conditions, etc. This information can be used to predict the remaining life of the tool. If the predicted remaining life is lower than a certain set threshold, even if the current wear level of the tool does not reach the threshold for replacement or repair, the tool may need to be replaced or repaired in advance to prevent tool failure at critical moments.

Performance test results of the tool: For some special applications, performance tests of the tool may be performed regularly, such as cutting force, thermal stability, etc. If the test results show that the tool's performance has fallen below a certain set threshold, the tool needs to be replaced or repaired.

Based on the above factors, the wear degree and wear shape of the tool can be evaluated by analyzing the collected tool images, and combined with the tool's usage history and performance test results, to determine whether the tool needs to be replaced or repaired. Specific replacement or repair criteria will need to be set based on the specific application and tool type.

The invention is intended to cover all such alternatives, modifications and variations falling within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims (10)

1. The device for detecting the cutter loss of the tunnel boring machine comprises a cutter monitoring unit, a data processing unit and a user interface, and is characterized in that the cutter monitoring unit is arranged at the cutter part of the tunnel boring machine and is used for acquiring state data of a cutter in the working process in real time; the data processing unit is connected with the cutter monitoring unit, receives and processes cutter state data, and calculates and generates the loss condition of the cutter; the user interface is connected with the data processing unit and used for displaying the cutter loss condition.

2. The tunneling machine cutter loss detection device according to claim 1, wherein the cutter monitoring unit is based on an image monitoring mechanism, and the image monitoring mechanism comprises a cutter image acquisition module, an image processing module and an early warning module;

the cutter image acquisition module is used for acquiring real-time images of the cutters in the tunneling process;

the image processing module is used for analyzing the real-time image of the surface of the cutter and judging the abrasion condition of the cutter;

and the early warning module is used for generating and sending a warning signal when the cutter loss reaches a preset value.

3. A tunnel boring machine cutter loss detection apparatus according to claim 1, wherein the cutter monitoring unit is based on a cutter detection sensor for acquiring in real time state data of the cutter during operation, the data including vibration frequency, vibration amplitude, sound frequency, sound intensity.

4. The tunneling machine cutter loss detection device according to claim 2, wherein the data processing module further comprises a wireless transmission module and a data storage module;

the wireless transmission module is used for transmitting the cutter loss data to a remote monitoring center in real time;

the data storage module is used for storing cutter loss data so as to carry out history comparison, trend analysis and modeling prediction.

5. A tunnel boring machine cutter loss detection apparatus according to claim 1, wherein the user interface comprises a touch screen through which a user views and manipulates cutter loss conditions;

the touch screen is provided with a graphical user interface for displaying the current loss condition, loss trend and early warning information of the cutter;

the touch screen can set a loss early warning threshold value and adjust loss calculation weight parameters;

the user interface also comprises a data export function for exporting the cutter loss data into various formats, so that the subsequent data analysis and report production are convenient, and in a remote monitoring mode, a user can remotely access the touch screen interface through a network to realize remote monitoring and operation.

6. A tunnel boring machine tool loss detection apparatus according to any one of claims 1 to 5 further comprising a power module to provide power to the tool detection sensor, the image monitoring mechanism and the user interface.

7. The method for detecting the cutter loss of the tunnel boring machine is characterized by comprising the following steps of:

step one: starting a cutter monitoring unit and collecting cutter state data;

step two: the method comprises the steps of receiving and processing cutter state data by a data processing unit, and calculating and generating a cutter loss condition;

step three: and displaying the loss condition of the cutter through a user interface, and judging whether the cutter needs to be replaced or not.

8. The method for detecting cutter loss of tunnel boring machine according to claim 7, wherein the cutter status data in the first step is based on the image monitoring mechanism, specifically comprising the following steps:

a) Acquiring a real-time image of a cutter in the tunneling process through a cutter image acquisition module;

b) Preprocessing the acquired real-time image, wherein the preprocessing comprises denoising, enhancing and cutting steps, so that the processing efficiency and accuracy of the image are improved;

c) Analyzing the preprocessed image by using an image recognition algorithm to determine the loss condition of the cutter;

d) Comparing the analysis results to judge whether the cutter needs to be replaced or repaired;

e) If the replacement or repair is needed, sending an instruction to replace or repair.

The image recognition algorithm comprises a deep learning method and a machine learning method, and the loss detection efficiency and accuracy of the tunnel boring machine cutter are effectively improved.

9. The method for detecting the loss of the cutter of the tunnel boring machine according to claim 8, wherein when the analysis results are compared, a preset threshold is adopted for comparison, if the loss condition of the cutter exceeds the preset threshold, the cutter is judged to need to be replaced or repaired, the automation degree of the cutter loss detection is improved, and the preset threshold can be adjusted according to factors such as the material of the cutter, the tunneling hardness, the history record of the cutter use and the like, so that the cutter loss detection is more accurate.

10. The method for detecting cutter loss of tunnel boring machine according to claim 7, wherein when the cutter state data of the cutter in the first step is based on the cutter detection sensor, the method comprises the following steps:

the vibration and sound physical signal change is obtained by using a cutter detection sensor to analyze and calculate, the signal change is analyzed by a plurality of specific algorithms, including frequency spectrum analysis, time-frequency analysis and waveform analysis, and the loss state of the cutter is assumed to be determined by the vibration and sound factors together, and the specific calculation formula is as follows:

tool loss state = α1 vd+α2 ad+α3 vf+α4 af

Wherein,

VD represents the amplitude of the vibration, obtained by a vibration sensor;

AD represents the intensity of sound obtained by the sound sensor;

VF represents the frequency of vibration, obtained by a vibration sensor;

AF represents the frequency of sound, obtained by a sound sensor;

α1, α2, α3, α4 are weights of influence factors, and can be trained and optimized by a large amount of history data.