Hob abrasion monitoring device and method, computer storage medium and equipment

Abstract

The invention discloses a hob abrasion monitoring device. The device comprises a cutter shaft capable of rotating, a cutter body fixedly mounted on the cutter shaft, a cutter head fixedly mounted on the cutter body, a pressure sensor which is arranged at the cutter shaft and can detect the pressure of a hob, and a torque sensor which is arranged at the cutter shaft and can detect the torque of the hob, the cutter box is arranged on one side edge of the cutter shaft and covers the cutter body and the cutter head located on the side edge, the counting device is arranged in the cutter box and can calculate the actual rotating distance of the hob, and the surrounding rock abrasion detection device is arranged on the surface of the cutter head and can quantitatively evaluate the abrasiveness of surrounding rock. According to the invention, real-time, accurate and comprehensive monitoring of the abrasion state of the hob is realized, the working safety and efficiency of the TBM are improved, the operation cost is reduced, technical innovation and development in the field of underground engineering construction are promoted, reference is provided for on-site constructors, the utilization efficiency of the hob is improved, the abnormal abrasion risk is reduced, and the construction cost is saved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel boring machines, and in particular to a device and method for monitoring the wear state of a TBM cutter, a computer storage medium and equipment. Background Art

[0002] When a full-face hard rock tunnel boring machine (TBM) is working, it uses the cutters on the rotating cutterhead to squeeze the rocks to break them; however, squeezing the rocks by the cutters will cause considerable wear on the cutter rings. When the cutter rings are worn to a certain extent, the excavation efficiency of the full-face hard rock tunnel boring machine will be significantly reduced. In order not to affect the tunnel excavation period, the cutter rings need to be replaced in time, so it is often necessary to monitor the wear of the cutter rings. Crushing rocks will cause serious obstacles to the cutter wear monitoring instrument. For example, crushing rocks will block light and sound wave signals, so optical and ultrasonic monitoring instruments are not applicable; in addition, when crushed rocks fall from the cutterhead, they will impact the monitoring instrument, posing a great threat to the safety of the monitoring instrument.

[0003] In underground engineering construction, TBM is an efficient fully mechanized construction equipment, and its cutter is a key working component responsible for breaking rocks and advancing the tunnel. The wear condition of the cutter directly affects the excavation efficiency, cost and engineering safety of TBM.

[0004] The current TBM cutter wear monitoring methods mainly include manual inspection during shutdown, analysis of cut rock samples, and monitoring of cutter head torque and thrust. These methods have the following limitations: manual inspection during shutdown will lead to interruption of excavation operations, seriously affecting the progress of the project; the analysis of cut rock samples is delayed and requires the support of professional laboratories, making it difficult to achieve real-time monitoring; although the monitoring of cutter head torque and thrust can reflect the cutter wear to a certain extent, it is often not accurate enough and is easily affected by various factors such as geological conditions.

[0005] In view of the limitations of the above-mentioned existing technologies, there is still a great demand for real-time and accurate monitoring of the wear status of TBM cutters. In order to ensure the continuous efficient and safe operation of TBM and reduce maintenance costs and downtime, it is urgent to develop a new TBM cutter wear monitoring method and device to achieve online, dynamic, and high-precision wear monitoring and early warning functions. Summary of the invention

[0006] The technical problem to be solved by the present invention is: in view of the defects of the roller cutter wear monitoring method in the prior art, a roller cutter wear monitoring method and device are proposed, which realizes real-time, accurate and comprehensive monitoring of the roller cutter wear state by monitoring the roller cutter force, torque, surrounding rock abrasiveness, and rolling distance, and combines theoretical calculation with neural network, big data model correction and other methods, thereby improving the safety and efficiency of TBM work, reducing operating costs, promoting technological innovation and development in the field of underground engineering construction, providing reference for on-site construction personnel, improving the utilization efficiency of roller cutters, reducing the risk of abnormal wear, and saving construction costs.

[0007] In order to solve the above technical problems, the present invention proposes the following technical solutions: a roller cutter wear monitoring device, which includes a rotatable cutter shaft, a cutter body mounted and fixed on the cutter shaft, a cutter disc mounted and fixed on the cutter body, a pressure sensor arranged at the cutter shaft and capable of detecting the roller cutter pressure, a torque sensor arranged at the cutter shaft and capable of detecting the roller cutter torque, a cutter box arranged on one side of the cutter shaft and covering the cutter body and the cutter disc located on the side, a counting device arranged inside the cutter box and capable of calculating the actual rotation distance of the roller cutter, and a surrounding rock wear detection device arranged on the surface of the cutter disc and capable of quantitatively evaluating the abrasiveness of the surrounding rock.

[0008] A further limitation of the above technical solution is that the counting device is composed of a magnet, a battery, a magnetic sensor, a counter, a wireless transmission module and a metal protective shell, wherein the magnet is arranged on the cutter disc, the battery, the magnetic sensor, the counter and the wireless transmission module are electrically connected, and the metal protective shell is installed and fixed on the outside of the battery, the magnetic sensor, the counter and the wireless transmission module. As the hob rotates one circle, the magnet is driven, and a signal is generated when it passes the magnetic sensor and the counter is turned on to record the number of rotations of the hob.

[0009] A further limitation of the above technical solution is that the surrounding rock wear detection device consists of a wear-resistant protective block, an insulating protective shell and a wear steel needle; the wear steel needle is wrapped with an insulating protective shell on the outside and then embedded in the wear-resistant protective block; when the cutter disc rotates, the length of the wear steel needle is obtained by measuring the resistance change of the wear steel needle and other means, and the abrasiveness of the surrounding rock is quantitatively evaluated based on the wear amount of the wear steel needle as the cutter disc rotates.

[0010] In order to solve the above technical problems, the present invention proposes the following technical solutions: a method for monitoring hob wear, comprising the following steps:

[0011] Step 1: Construct a database of reel pressure, reel torque and reel status;

[0012] Step 2: input the collected hob pressure data and hob torque data into the database described in step 1, establish a corresponding relationship between the hob force condition and the hob working state by using big data analysis, and then output the hob working state;

[0013] Step 3: When the cutter pressure and cutter torque are normal, the cutter working state is in the normal cutter wear state, and the theoretical cutter wear amount S is calculated, that is, the radial wear amount of the cutter ring per unit excavation distance;

[0014] Step 4: Use neural network to establish a cutter wear prediction model, use the pre-excavation section data as the training database, normalize the training samples and input them into the neural network model, find the optimal parameters of the model, and then establish the cutter wear prediction model. The more training data there is, the more accurate the cutter wear prediction model is. Then, the cutter wear can be predicted by the cutter wear prediction model in the formal excavation section.

[0015] Step 5: Compare the hob wear predicted in step 4 with the actual hob wear statistics of the staff, correct the hob wear prediction model through neural network learning, improve the prediction accuracy, and feed back to the database described in step 1 and the hob wear prediction model described in step 4.

[0016] The above technical solution is further limited in that, in step 2, the roller cutter pressure data is detected by a pressure sensor, and the roller cutter torque data is detected by a torque sensor.

[0017] The above technical solution is further limited in that, in step 3, the theoretical wear amount S of the hob is calculated by the following formula (1):

[0018] Formula (1):

[0019] Among them, K S is the abrasive wear coefficient, which is related to the geological conditions of the surrounding rock; R i is the installation radius of the hob on the cutterhead (hob installation radius); W is the vertical load of the hob, l is the rolling distance, T is the blade width, D0 is the hob diameter, h is the penetration, σ s is the blade yield strength.

[0020] The above technical solution is further limited in that the vertical load W of the hob and the abrasive wear coefficient K are selected. S , penetration h, hob installation radius R i , rolling distance l as the output layer, where the vertical load W of the hob is monitored by a pressure sensor, and the abrasive wear coefficient K S Through the surrounding rock wear detection device, the penetration h and the disc cutter installation radius R are quantitatively evaluated. i The rolling distance l is obtained through the TBM equipment parameters and calculated by the counting device.

[0021] In order to solve the above technical problems, the present invention proposes the following technical solutions: a computer storage medium having a computer program stored thereon, wherein the computer program implements the steps of the hob wear monitoring method when executed by a processor.

[0022] In order to solve the above technical problems, the present invention proposes the following technical solutions: a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the hob wear monitoring method when executing the computer program.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. The hob wear monitoring device of the present invention can detect the force, torque and rolling distance of the hob with high precision. As a result, the working state of the hob can be judged according to the obtained force and torque. Under normal working state, the wear amount of the hob can be predicted by combining the theoretical formula with the neural network learning model, and an early warning can be issued under abnormal state, and corresponding measures can be taken.

[0025] 2. The roller cutter wear monitoring method of the present invention provides a reference for on-site construction personnel, improves the roller cutter utilization efficiency, reduces the risk of abnormal wear, and saves construction costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a structural schematic diagram of the hob wear monitoring device of the present invention.

[0027] Figure 2 It is a structural schematic diagram of the surrounding rock wear detection device of the present invention.

[0028] Figure 3 It is a flow chart of the hob wear monitoring method of the present invention. DETAILED DESCRIPTION

[0029] Embodiment 1:

[0030] like Figure 1 and Figure 2 As shown, the present invention proposes a roller cutter wear monitoring device, which includes a rotatable cutter shaft 1, a cutter body 2 mounted and fixed on the cutter shaft 1, a cutter disc 3 mounted and fixed on the cutter body 2, a pressure sensor 4 arranged at the cutter shaft 1, a torque sensor 5 arranged at the cutter shaft 1, a cutter box 8 arranged on one side of the cutter shaft 1 and covering the cutter body 2 and the cutter disc 3 located on the side, a counting device 6 arranged inside the cutter box 8 and capable of calculating the actual rotation distance of the roller cutter, and a surrounding rock wear detection device 7 arranged on the surface of the cutter disc 3 and capable of quantitatively evaluating the abrasiveness of the surrounding rock.

[0031] When the cutter shaft 1 rotates, the cutter body 2 and the cutter disc 3 are driven to rotate together.

[0032] The pressure sensor 4 is used to directly and accurately detect the actual pressure on the roller cutter in the vertical direction (referred to as roller cutter pressure).

[0033] The torque sensor 5 is used to directly and accurately detect the actual torque of the reel in the rotation direction (referred to as reel torque).

[0034] The counting device 6 is composed of a magnet 61 , a battery 62 , a magnetic sensor 63 , a counter 64 , a wireless transmitting module 65 and a metal protective shell 66 .

[0035] The magnet 61 is arranged on the blade disc 3 , and the battery 62 , the magnetic sensor 63 , the counter 64 and the wireless transmitting module 65 are electrically connected.

[0036] The metal protective shell 66 is installed and fixed outside the battery 62 , the magnetic sensor 63 , the counter 64 and the wireless transmission module 65 .

[0037] As the roller rotates one circle, it drives the magnet 61, which generates a signal when passing through the magnetic sensor 63 and starts the counter 64 to record the number of rotations of the roller. The monitored data is sent to the control room of the TBM equipment (not shown) via a wireless transmission mode.

[0038] The surrounding rock wear detection device 7 is composed of a wear-resistant protective block 71, an insulating protective shell 72 and a wear steel needle 73. The wear steel needle 73 is wrapped with the insulating protective shell 72 and then embedded in the wear-resistant protective block 71. When the cutterhead 3 rotates, the length of the wear steel needle 73 is obtained by measuring the resistance change of the wear steel needle 73, and the abrasiveness of the surrounding rock is quantitatively evaluated according to the wear amount of the wear steel needle 73 as the cutterhead 3 rotates.

[0039] Embodiment 2:

[0040] The above embodiment 1 proposes a hob wear monitoring device, correspondingly, as Figure 3 As shown, the present invention provides a method for monitoring hob wear, which comprises the following steps:

[0041] Step 1: Build a database of hob pressure, hob torque and hob status based on engineering cases.

[0042] Step 2: Input the hob pressure data collected by the pressure sensor 4 and the hob torque data collected by the torque sensor 5 into the database described in step 1, and use big data analysis to establish a corresponding relationship between the hob force condition and the hob working state (as shown in Table 1 below), and then output the hob working state.

[0043] Table 1: Correspondence between the hob force condition and the hob working state and the treatment method

[0044]

[0045]

[0046] Step 3: When the cutter pressure and cutter torque are normal, the cutter working state is in the normal cutter wear state, and the theoretical cutter wear amount S (radial wear amount of the cutter ring per unit excavation distance) is calculated by the following formula (1).

[0047] Formula (1):

[0048] Among them, K S is the abrasive wear coefficient, which is related to the geological conditions of the surrounding rock; R i is the installation radius of the hob on the cutter disc 3 (hob installation radius); W is the vertical load of the hob, l is the rolling distance, T is the blade width, D0 is the hob diameter, h is the penetration, σ s is the blade yield strength.

[0049] Step 4: Use neural network to establish a hob wear prediction model.

[0050] For a specific project, the hob diameter D0, blade width T and blade yield strength σ s is a fixed value and can be treated as a constant. Select the vertical load W of the hob and the abrasive wear coefficient K S , penetration h, hob installation radius R i , rolling distance l as the output layer, where the vertical load W of the hob can be monitored by the pressure sensor 4, and the abrasive wear coefficient K S The penetration h and the cutter installation radius R can be quantitatively evaluated by the surrounding rock wear detection device 7. i It can be obtained through TBM equipment parameters, the rolling distance l can be calculated by the counting device 6, and then the pre-excavation section data is used as a training database, the training samples are normalized and input into the neural network model, and the optimal parameters of the model are found, and then the cutter wear prediction model is established. The more training data, the more accurate the cutter wear prediction model is, and the cutter wear can be predicted by the cutter wear prediction model in the formal excavation section.

[0051] Step 5: Compare the hob wear predicted in step 4 with the actual hob wear statistics of the staff, correct the hob wear prediction model through neural network learning, improve the prediction accuracy, and feed back to the database described in step 1 and the hob wear prediction model described in step 4.

[0052] Embodiment 3:

[0053] This embodiment provides a processing device for implementing the roller cutter wear monitoring method provided in this embodiment 2. The processing device can be a processing device for a client, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the method of embodiment 2.

[0054] The processing device includes a processor, a memory, a communication interface and a bus, and the processor, the memory and the communication interface are connected through the bus to complete mutual communication. The memory stores a computer program that can be run on the processor, and the processor executes the hob wear monitoring method provided in this embodiment 2 when running the computer program.

[0055] Preferably, the memory may be a high-speed random access memory RAM:

[0056] Random Access Memory), and may also include non-volatile memory), such as at least one disk memory.

[0057] Preferably, the processor may be a central processing unit (CPU), a digital signal processor (DSP) or other general-purpose processors of various types, which are not limited here.

[0058] Embodiment 4:

[0059] The roller cutter wear monitoring method of the second embodiment can be specifically implemented as a computer program product. The computer program product may include a computer-readable storage medium on which computer-readable program instructions for executing the method described in the second embodiment are loaded.

[0060] Computer readable storage media can be tangible devices that hold and store instructions used by instruction execution devices. Computer readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any combination thereof.

[0061] The TBM cutter wear monitoring device and method proposed in the present invention have the following beneficial effects:

[0062] 1. When the hob is working normally, a large number of engineering cases show that the hob wear is highly correlated with the stress state and geological conditions. Since there are many parameters related to the hob wear and the data contains noise, the direct use of all parameters using the neural network learning convergence speed is slow, and it is difficult to accurately obtain all parameters. Therefore, it is necessary to pre-process the factors related to the hob wear, screen out the main components with large contribution rates, and finally predict the hob wear through the ability of the neural network to approximate nonlinear continuous functions. Later, the actual wear of the hob is statistically analyzed to correct the prediction model, thereby achieving accurate prediction of the hob wear.

[0063] 2. Improved real-time performance and accuracy: The use of precise detection of main parameters and data analysis algorithms realizes real-time online monitoring of the working status of the hob, which can timely and accurately predict the wear of the hob, effectively avoiding delays and misjudgments caused by lags in traditional methods.

[0064] 3. Improve work efficiency and safety: Through real-time prediction of cutter wear, the cutter life can be predicted in advance, replacement plans can be arranged reasonably, unnecessary downtime and maintenance costs can be reduced, and the continuity and efficiency of TBM excavation operations can be further improved. At the same time, the risk of accidents caused by excessive cutter wear can be avoided to ensure the safety of the construction site.

[0065] 4. Optimize tunneling strategy: The accurate wear information provided by the monitoring method and device helps to adjust tunneling parameters (such as propulsion speed, torque, cutterhead speed, etc.), optimize tunneling strategy in real time according to geological conditions and cutter wear conditions, and further improve the overall performance and economic benefits of TBM.

[0066] There are many theoretical calculation formulas for cutter wear, but the main influencing factors are related to the working state of the cutter and the abrasiveness of the surrounding rock. The cases are only examples and can be selected according to actual conditions.

[0067] In addition to neural network learning, the hob wear prediction model also has many other methods such as big data mining and artificial intelligence. In addition, the working status of the hob and the measures to be taken need to be classified according to the actual situation.

Claims

1. A hob wear monitoring device, characterized in that: The invention comprises a rotatable cutter shaft (1), a cutter body (2) mounted and fixed on the cutter shaft (1), a cutter disc (3) mounted and fixed on the cutter body (2), a pressure sensor (4) arranged at the cutter shaft (1) and capable of detecting the pressure of the roller cutter, a torque sensor (5) arranged at the cutter shaft (1) and capable of detecting the torque of the roller cutter, a cutter box (8) arranged at one side of the cutter shaft (1) and covering the cutter body (2) and the cutter disc (3) located at the side, a counting device (6) arranged inside the cutter box (8) and capable of calculating the actual rotation distance of the roller cutter, and a surrounding rock wear detection device (7) arranged on the surface of the cutter disc (3) and capable of quantitatively evaluating the abrasiveness of the surrounding rock.

2. The hob wear monitoring device according to claim 1, characterized in that: The counting device (6) is composed of a magnet (61), a battery (62), a magnetic sensor (63), a counter (64), a wireless transmitting module (65) and a metal protective shell (66), wherein the magnet (61) is arranged on the cutter disc (3), the battery (62), the magnetic sensor (63), the counter (64) and the wireless transmitting module (65) are electrically connected, and the metal protective shell (66) is fixedly installed outside the battery (62), the magnetic sensor (63), the counter (64) and the wireless transmitting module (65). When the hob rotates one circle, the magnet (61) is driven, and when it passes the magnetic sensor (63), a signal is generated and the counter (64) is turned on to record the number of rotations of the hob.

3. The hob wear monitoring device according to claim 1, characterized in that: The surrounding rock wear detection device (7) is composed of a wear-resistant protective block (71), an insulating protective shell (72) and a wear steel needle (73); the wear steel needle (73) is wrapped with the insulating protective shell (72) and then embedded in the wear-resistant protective block (71); when the cutter head (3) rotates, the length of the wear steel needle (73) is obtained by measuring the resistance change of the wear steel needle (73), and the surrounding rock abrasiveness is quantitatively evaluated according to the wear amount of the wear steel needle (73) as the cutter head (3) rotates.

4. A method for monitoring roller cutter wear using the roller cutter wear monitoring device according to claim 1, characterized in that: It includes the following steps: Step 1: Construct a database of reel pressure, reel torque and reel status; Step 2: input the collected hob pressure data and hob torque data into the database described in step 1, establish a corresponding relationship between the hob force condition and the hob working state by using big data analysis, and then output the hob working state; Step 3: When the cutter pressure and cutter torque are normal, the cutter working state is in the normal cutter wear state, and the theoretical cutter wear amount S is calculated, that is, the radial wear amount of the cutter ring per unit excavation distance; Step 4: Use neural network to establish a cutter wear prediction model, use the pre-excavation section data as the training database, normalize the training samples and input them into the neural network model, find the optimal parameters of the model, and then establish the cutter wear prediction model. The more training data there is, the more accurate the cutter wear prediction model is. Then, the cutter wear can be predicted by the cutter wear prediction model in the formal excavation section. Step 5: Compare the hob wear predicted in step 4 with the actual hob wear statistics of the staff, correct the hob wear prediction model through neural network learning, improve the prediction accuracy, and feed back to the database described in step 1 and the hob wear prediction model described in step 4.

5. The method for monitoring hob wear according to claim 4, characterized in that: In step 2, the roller cutter pressure data is detected by the pressure sensor (4), and the roller cutter torque data is detected by the torque sensor (5).

6. The method for monitoring hob wear according to claim 4, characterized in that: In step 3, the theoretical wear amount S of the hob is calculated by the following formula (1): Formula (1): Among them, K S is the abrasive wear coefficient, which is related to the geological conditions of the surrounding rock; R i is the installation radius of the hob on the cutterhead (3) (hob installation radius); W is the vertical load of the hob, l is the rolling distance, T is the blade width, D0 is the hob diameter, h is the penetration, σ s is the blade yield strength.

7. The method for monitoring hob wear according to claim 6, characterized in that: Select the vertical load W and abrasive wear coefficient K of the hob S , penetration h, hob installation radius R i , rolling distance l as the output layer, where the vertical load W of the hob is monitored by the pressure sensor (4), and the abrasive wear coefficient K S The penetration h and the cutter installation radius R are quantitatively evaluated by the surrounding rock wear detection device (7). i The rolling distance l is obtained through the TBM equipment parameters and calculated by the counting device (6).

8. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the hob wear monitoring method according to any one of claims 4 to 7 are implemented.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the hob wear monitoring method described in any one of claims 4 to 7 are implemented.

Images