A load self-sensing tunneling cutter and a cutter monitoring method

Abstract

The embodiment of the present application discloses a load self-sensing tunneling cutter and a cutter monitoring method, belonging to the technical field of cutter monitoring, and solving the problem that non-integrated packaged sensing devices cannot install various types of sensing elements due to space size limitations and can only monitor a single parameter, making it difficult to accurately analyze the actual working conditions of tunneling cutters. The cutter includes: a cutter body, a multi-source sensor integration module, and a host computer; an axial center blind hole is provided at the axis center of the cutter shaft of the cutter body; the protective shell of the multi-source sensor integration module fits with the inner wall of the axial center blind hole, and the multi-source sensor integration module includes a multi-source sensor module, a self-power generation module, and a signal transmission module; the multi-source sensor integration module is wirelessly connected to the host computer, and the multi-source sensor integration module is used to transmit the collected multi-source state data of the cutter to the host computer, so that the host computer analyzes the multi-source state data of the cutter to realize the monitoring of the load self-sensing tunneling cutter.

Description

Technical Field

[0001] This application relates to the technical field of tool monitoring, and in particular to a load self-sensing tunneling tool and a tool monitoring method. Background Art

[0002] With the rapid development of urban underground facilities, the demand for tunneling equipment is also increasing continuously. Tunneling equipment mainly relies on the tunneling tools on the cutter head to break rocks. At present, the existing equipment for monitoring the working conditions of tools is externally mounted on the tool box seat, and the complex and harsh tunneling environment results in poor stability.

[0003] In the prior art, non-integrated packaged sensing devices are usually used to monitor tools. The non-integrated packaged sensing devices have high requirements for the working environment and are easily affected by external factors such as dust, high temperature, and strong vibration during operation, resulting in difficult data acquisition or even equipment damage. Secondly, more wires are required between non-integrated packaged sensors, occupying more space. In applications where the internal space of the tool is limited, it increases the difficulty of assembly and layout, restricting the flexibility of equipment design. At the same time, due to space size limitations, non-integrated packaged sensing devices cannot install various types of sensing elements and can only monitor a single parameter, making it difficult to accurately analyze the actual working conditions of tunneling tools. Summary of the Invention

[0004] The embodiments of this application provide a load self-sensing tunneling tool and a tool monitoring method, which are used to solve the following technical problems: Due to space size limitations, non-integrated packaged sensing devices cannot install various types of sensing elements and can only monitor a single parameter, making it difficult to accurately analyze the actual working conditions of tunneling tools.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] The embodiments of this application provide a load self-sensing tunneling tool, which is characterized in that the tool includes: a tool body, a multi-source sensor integration module, and a host computer; an axial center blind hole is provided at the axis of the tool shaft of the tool body; the protective shell of the multi-source sensor integration module fits with the inner wall of the axial center blind hole, and the multi-source sensor integration module includes a multi-source sensor module, a self-power generation module, and a signal transmission module; the multi-source sensor integration module is wirelessly connected to the host computer, and the multi-source sensor integration module is used to transmit the collected multi-source state data of the tool to the host computer, so that the host computer analyzes the multi-source state data of the tool to realize the monitoring of the load self-sensing tunneling tool.

[0007] On the basis of ensuring the overall stiffness and strength of the tool, the embodiment of the present application solves the problem of difficult wiring in the tunneling cutter head tool by installing highly integrated sensors and self-power generation modules. At the same time, the front-end integrated module of the embodiment of the present application is of an integrated design. By machining corresponding blind holes at the hoisting hole on the axis side of the tool shaft, various types and sizes of tunneling tools are modified into intelligent tools with sensing functions, which does not affect the normal operation of the tools and improves the applicability of the tools. In addition, the embodiment of the present application monitors various state parameters of the tunneling tool in real time through multi-source sensors, and the user can obtain the operating condition of a single tool in real time. At the same time, the overall working condition and potential faults of the cutter head can be evaluated by comprehensively comparing and analyzing the operating conditions of the tool array.

[0008] In an implementation manner of the present application, the multi-source sensor module includes a force sensor, a vibration sensor, and a temperature sensor; the force sensor is attached to the inner wall flexible structure of the multi-source sensor integration module, and the force sensor is used to obtain the force data of the load self-sensing tool; the vibration sensor is arranged on the central axis of the multi-source sensor integration module, and the vibration sensor is a MEMS accelerometer; the vibration sensor is used to obtain the vibration data of the load self-sensing tool; the temperature sensor is arranged inside the multi-source sensor integration module and is adjacent to the inner ring of the installation bearing of the tunneling tool. After assembly, the temperature sensor is located at the bottom of the axial center blind hole and is used to obtain the temperature data of the load self-sensing tool.

[0009] In an implementation manner of the present application, the vibration sensor further includes a three-axis vibration sensing element, a thin film resistance layer, and a signal conditioning circuit; the three-axis vibration sensing element is used to measure the vibration amplitude and frequency of the load self-sensing tunneling tool in three orthogonal directions; the thin film resistance layer is used to measure the vibration intensity by detecting the strain change caused by vibration; the signal conditioning circuit is used to perform amplification processing, filtering processing, and conversion processing on the obtained vibration signal to generate a digital signal corresponding to the vibration signal.

[0010] In an implementation manner of the present application, the temperature sensor is provided with a temperature sensing element; the temperature sensing element is arranged at the side opening of the protective shell of the multi-source sensor integration module; the temperature sensing element is provided with a temperature sensing probe; the temperature sensing probe is placed exposed, and the exposed height of the temperature sensing probe is lower than the surface of the protective shell of the multi-source sensor integration module.

[0011] In an implementation manner of the present application, the self-power generation module is connected to the signal transmission module; the self-power generation module is a ring-shaped thin film piezoelectric self-power generation module, and the self-power generation module is arranged on the outer wall surface of the multi-source sensor integration module; the self-power generation module supplies power to the multi-source sensor module through the data line of the signal transmission module.

[0012] In an implementation manner of the present application, the signal transmission module is connected to the multi-source sensor module; the signal transmission module is arranged at the bottom of the multi-source sensor integration module and is located at the top of the axial center blind hole after assembly.

[0013] In an implementation manner of the present application, the size of the axial center blind hole matches the size of the protective shell of the multi-source sensor integration module; a sealing support mechanism is arranged at the open end of the axial center blind hole; a shock-absorbing sealant is filled between the multi-source sensor integration module and the inner wall of the axial center blind hole.

[0014] The embodiment of the present application provides a tool monitoring method, and the method includes: the upper computer receives the tool multi-source signal uploaded by the multi-source sensor integration module; the upper computer preprocesses and extracts features from the tool multi-source signal, and generates a feature matrix based on the extracted feature data; the upper computer compares each feature data with the corresponding preset threshold respectively to determine the abnormal points, and determines the abnormal state of the tool based on the abnormal points; the upper computer determines the cross-correlation coefficient between the tool multi-source signals based on the preset function, and determines the correlation between the tool multi-source signals in the time domain and the frequency domain based on the cross-correlation coefficient; the upper computer determines the working condition type of the tool based on the correlation, generates a working condition warning signal based on the working condition type, and feeds back the working condition type and the tool multi-source data to the tool management system to realize the monitoring of the tool.

[0015] In an implementation manner of the present application, the upper computer determines the cross-correlation coefficient between the tool multi-source signals based on the preset function, and determines the correlation between the tool multi-source signals in the time domain and the frequency domain based on the cross-correlation coefficient, which specifically includes: the upper computer determines the cross-correlation coefficient between the tool multi-source signals based on the time domain characteristics corresponding to the tool multi-source signals and the preset function to quantify the time domain correlation of the tool multi-source signals; wherein the tool multi-source signals include pressure signals, vibration signals and temperature signals; the upper computer converts the tool multi-source signals from the time domain to the frequency domain through fast Fourier transform to obtain the spectrum corresponding to the tool multi-source signals to extract the frequency domain characteristics of the tool multi-source signals; the upper computer determines the time domain signal correlation corresponding to the tool multi-source signals based on the synchronism of the tool multi-source signals in the same time period; the upper computer determines the frequency domain signal correlation corresponding to the tool multi-source signals based on the consistency of the tool multi-source signals in different frequency ranges.

[0016] In an implementation manner of the present application, the host computer determines the working condition type of the tool based on the correlation, specifically including: when the correlation between the mean value and the root mean square value of the vibration signal and the pressure signal in the time domain is greater than a preset first correlation threshold, and the energy ratio corresponding to the low-frequency band in the frequency domain characteristics is greater than a preset energy ratio value, it is determined that the tool is in a normal working condition; when the correlation between the vibration signal and the temperature signal in the time domain characteristics is greater than a preset second correlation threshold, and there is a new high-frequency component in the temperature signal in the frequency domain characteristics, it is determined that the tool is in a wear working condition; when the fluctuation value of the pressure signal in the time domain characteristics is greater than a preset fluctuation threshold, and the main frequency distribution of the vibration signal is inconsistent with the main frequency of the pressure signal in the frequency domain characteristics, it is determined that the tool is in an abnormal vibration working condition.

[0017] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects: On the basis of ensuring the overall stiffness and strength of the tool, the embodiments of the present application solve the problem of difficult wiring in the tunneling cutterhead tools by installing highly integrated sensors and self-power generation modules. At the same time, the front-end integrated module in the embodiments of the present application is an integrated design. By processing corresponding blind holes at the hoisting hole on the axis side of the tool shaft, various types and sizes of tunneling tools are modified into intelligent tools with sensing functions, which does not affect the normal operation of the tools and improves the applicability of the tools. In addition, the embodiments of the present application monitor various state parameters of the tunneling tool in real time through multi-source sensors, and users can obtain the operating conditions of single tools in real time. At the same time, the overall working condition and potential faults of the cutterhead can be evaluated by comprehensively comparing and analyzing the operating conditions of the tool array. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the attached

[0019] In the figure:

[0020] Figure 1 is a schematic structural diagram of a load self-sensing tunneling tool provided by an embodiment of the present application;

[0021] Figure 2 is a structural sectional view of a load self-sensing tunneling tool provided by an embodiment of the present application;

[0022] Figure 3 is a flowchart of a tool monitoring method provided by an embodiment of the present application.

[0023] Reference numerals: 1, tool body; 2, axial center blind hole; 3, temperature sensor; 4, pressure sensor; 5, vibration sensor; 6, self-power generation module; 7, signal transmission module; 8, tool bearing; 9, tool shaft. Detailed implementation manners

[0024] An embodiment of the present application provides a load self-sensing tunneling tool and a tool monitoring method.

[0025] In order to enable those skilled in the art to better understand the technical solutions in the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0026] The following will detail the technical solutions proposed in the embodiments of the present invention with reference to the accompanying drawings.

[0027] Figure 1 It is a structural schematic diagram of a load self-sensing tunneling tool provided by an embodiment of the present application. Figure 2 It is a structural cross-sectional view of a load self-sensing tunneling tool provided by an embodiment of the present application. As Figure 1 and Figure 2 shown, the load self-sensing tunneling tool includes a tool body 1, a multi-source sensor integration module, and a host computer. An axial center blind hole 2 is provided at the axis center of the tool shaft 9 of the tool body 1. The protective shell of the multi-source sensor integration module is attached to the inner wall of the axial center blind hole 2. The multi-source sensor integration module includes a multi-source sensor module, a self-power generation module 6, and a signal transmission module 7. The multi-source sensor integration module is wirelessly connected to the host computer. The multi-source sensor integration module is used to transmit the collected multi-source state data of the tool to the host computer so that the host computer analyzes the multi-source state data of the tool to realize the monitoring of the load self-sensing tunneling tool.

[0028] Specifically, the load self-sensing tunneling tool includes a tool body 1, a multi-source sensor integration module, and a host computer. The multi-source sensor integration module includes a multi-source sensor module, a self-power generation module 6, a signal transmission module 7, and a tool bearing 8. Each module is encapsulated in a protective shell and installed in the blind hole on one side of the tool shaft 9 of the tunneling tool. The multi-source sensor module is connected to the signal transmission module 7 and wirelessly transmits the collected data to the host computer in the operation room.

[0029] Furthermore, the self-power generation module 6 supplies power to the main control board and the monitoring component, thus eliminating the need for external wiring outside the hob, reducing the modification to the hob and the tool holder, lowering the processing difficulty, and having good applicability to different types of tools.

[0030] Further, the signal transmission module 7 is wirelessly connected to the receiving device behind the cutter head through an antenna, and transmits the collected multi-source status data of the cutting tools to the upper computer through wireless transmission, thereby realizing the real-time monitoring of the status of the tunneling cutting tools. At the same time, the upper computer analyzes these parameters to obtain the working status of the cutting tool array, judges the condition of the working face of the cutter head in front, and guides the operator to replace the cutting tools, maintain the equipment, and optimize the tunneling parameters.

[0031] As Figure 1 and Figure 2 shown, the multi-source sensor module includes a force sensor, a vibration sensor 5, and a temperature sensor 3. The force sensor is attached to the flexible structure on the inner wall of the multi-source sensor integration module, and the force sensor is used to obtain the force data of the load self-sensing cutting tool. The vibration sensor 5 is arranged on the central axis of the multi-source sensor integration module, and the vibration sensor 5 is a MEMS accelerometer; the vibration sensor 5 is used to obtain the vibration data of the load self-sensing cutting tool. The temperature sensor 3 is arranged inside the multi-source sensor integration module and is adjacent to the inner ring of the installation bearing of the tunneling cutting tool. After assembly, the temperature sensor 3 is located at the bottom of the axial center blind hole 2 and is used to obtain the temperature data of the load self-sensing cutting tool.

[0032] Specifically, the force sensor of the multi-source sensor integration module is attached to the flexible structure on the inner wall of the module, and detects the external force action by sensing the tiny deformation of the flexible structure. The arrangement method of this force sensor can enhance the sensitivity to the internal and external force distribution of the module, and realize the accurate monitoring and evaluation of the force state of the cutting tool during tunneling. The vibration sensor 5 of the multi-source sensor integration module is designed with a MEMS accelerometer and is arranged in the middle position of the integration module, and is used to detect the vibration signal generated by the tunneling cutting tool during operation. The vibration sensor 5 is installed on the central axis inside the module, and can effectively sense the vibration characteristics of the cutting tool in all directions during rock breaking, and realize the accurate monitoring of the cutting tool state. The temperature sensor 3 of the multi-source sensor integration module is designed with a micro thermocouple and is arranged inside the integration module near the inner ring of the installation bearing of the tunneling cutting tool; after the module is assembled in the hob, the temperature sensor 3 contacts the bottom of the central blind hole of the tool shaft 9 and is used to monitor the internal temperature change of the cutting tool.

[0033] As Figure 1 and Figure 2 shown, the vibration sensor 5 further includes a three-axis vibration sensing element, a thin film resistance layer, and a signal conditioning circuit. The three-axis vibration sensing element is used to measure the vibration amplitude and frequency of the load self-sensing tunneling cutting tool in three orthogonal directions. The thin film resistance layer is used to measure the vibration intensity by detecting the strain change caused by vibration. The signal conditioning circuit is used to perform amplification processing, filtering processing, and conversion processing on the obtained vibration signal to generate a digital signal corresponding to the vibration signal.

[0034] Specifically, the vibration sensor 5 includes a three-axis vibration sensing element, a thin-film resistance layer, and a signal conditioning circuit. These sensors can accurately capture the vibration data of the cutting tool in the X, Y, and Z directions, thereby providing detailed information about the working state of the cutting tool. Specifically, the three-axis vibration sensing element is used to measure the vibration amplitude and frequency of the cutting tool in three orthogonal directions, the thin-film resistance layer measures the vibration intensity by detecting the strain change caused by vibration, and the signal conditioning circuit amplifies, filters, and converts these original signals to generate digital signals for further processing.

[0035] As Figure 1 and Figure 2 shown, the temperature sensor 3 is provided with a temperature sensing element, and the temperature sensing element is arranged at the side opening of the protective shell of the multi-source sensor integration module. The temperature sensing element is provided with a temperature sensing probe. The temperature sensing probe is placed externally, and the external height of the temperature sensing probe is lower than the surface of the protective shell of the multi-source sensor integration module.

[0036] Specifically, the temperature sensing element of the temperature sensor 3 is installed at the side opening of the integrated module protective shell, and the probe part is externally exposed, and its exposed height is slightly lower than the outer surface of the protective shell to ensure the sensitivity and response speed of temperature detection, and at the same time avoid external damage to the probe during tunneling.

[0037] As Figure 1 and Figure 2 shown, the self-power generation module 6 is connected to the signal transmission module 7. The self-power generation module 6 is a ring-shaped thin-film piezoelectric self-power generation module 6, and the self-power generation module 6 is arranged on the outer wall of the surface of the multi-source sensor integration module. The self-power generation module 6 supplies power to the multi-source sensor module through the data line of the signal transmission module 7.

[0038] Specifically, the self-power generation module 6 of the multi-source sensor integration module is a ring-shaped thin-film piezoelectric self-power generation module 6, which is placed on the outer wall of the module surface. It is connected to the signal transmission module 7 and supplies power to the sensor through the data line of the signal transmission module 7. The self-power generation module 6 supplies power to the main control board and the monitoring component, thus eliminating the need for external wiring outside the hob, reducing the modification of the hob and the tool holder, reducing the processing difficulty, and having good applicability for different types of cutting tools.

[0039] As Figure 1 and Figure 2 shown, the signal transmission module 7 is connected to the multi-source sensor module. The signal transmission module 7 is arranged at the bottom of the multi-source sensor integration module and is located at the top of the axial center blind hole 2 after assembly.

[0040] Specifically, the multi-source sensor is connected to the signal transmission module 7, and the collected data is transmitted to the upper computer in the operation room of the tunneling equipment through the signal transmission module 7. The signal transmission module 7 is wirelessly connected to the receiving device behind the cutter head through an antenna, and the multi-source status data of the cutter is transmitted to the upper computer by wireless transmission.

[0041] As Figure 1 and Figure 2 shown, the size of the axial center blind hole 2 matches the size of the protective shell of the multi-source sensor integration module. A sealing and supporting mechanism is provided at the open end of the axial center blind hole 2. A damping sealant is filled between the multi-source sensor integration module and the inner wall of the axial center blind hole 2.

[0042] Specifically, the size of the axial center blind hole 2 opened at the axis of the tool shaft 9 of the tool body 1 matches the protective shell of the multi-source sensor integration module. The protective shell fits with the inner wall of the blind hole, a sealing and supporting mechanism is provided at the open end, and a damping sealant is filled between the integration module and the inner wall of the blind hole. The integrated sensor module has a compact structure after encapsulation and does not interfere with other original parts.

[0043] Figure 3 This is a flow chart of a tool monitoring method provided by an embodiment of the present application. As Figure 3 shown, the tool monitoring method includes the following steps:

[0044] S101. The upper computer receives the multi-source tool signals uploaded by the multi-source sensor integration module.

[0045] In an embodiment of the present application, the upper computer receives the multi-source tool signals uploaded by the multi-source sensor integration module, including the pressure signal sent by the pressure sensor 4, the vibration signal sent by the vibration sensor 5, and the temperature signal sent by the temperature sensor 3.

[0046] S102. The upper computer preprocesses and extracts features from the multi-source tool signals, and generates a feature matrix based on the extracted feature data.

[0047] In an embodiment of the present application, the pressure, vibration, and temperature signals are subjected to low-pass filtering, wavelet denoising, and normalization processing, and features such as the average value, standard deviation, peak value, root mean square value, and spectral energy of the signals are extracted to form a feature matrix X = {x1, x2,..., x n}.

[0048] Specifically, the upper computer preprocesses the received vibration data, including noise filtering and data smoothing. Noise filtering uses a low-pass filter to remove high-frequency interference signals, and data smoothing uses a moving average or exponentially weighted moving average method to reduce short-term fluctuations in the data.

[0049] Specifically, the host computer first preprocesses the temperature data, including noise filtering and data smoothing, to ensure the stability and accuracy of the data. Noise filtering uses a low-pass filter to remove high-frequency noise, while data smoothing uses a moving average or exponentially weighted moving average method.

[0050] The temperature sensor 3 can promptly identify overheating problems caused by tool wear, jamming, and uneven wear. By continuously monitoring the tool temperature, the host computer can capture early signs of temperature anomalies. Temperature trend analysis and statistical-based anomaly detection algorithms are used to identify abnormal temperature changes and promptly warn of potential tool failures. These algorithms compare real-time temperature data with historical temperature data to determine if there are significant deviations and issue an alarm when an anomaly is detected.

[0051] Through continuous monitoring of this temperature data, operators can promptly discover potential problems and thus take preventive measures, such as adjusting tunneling parameters or pausing work for inspection and maintenance. In addition, the embodiments of the present application can also identify the temperature change patterns under different operating conditions through long-term temperature data analysis, which helps optimize tool design and selection. Combining the temperature data with the data of the vibration sensor 5 can provide more comprehensive tool status information and further improve the accuracy of fault prediction.

[0052] S103. The host computer compares each characteristic data with the corresponding preset threshold to determine the abnormal points and determines the abnormal state of the tool based on the abnormal points.

[0053] In an embodiment of the present application, each characteristic is compared with its set threshold (such as the pressure threshold ΔP th , the vibration threshold ΔV th , the temperature slope threshold ΔT / dt th ) to identify the abnormal points and mark them as the abnormal state {0, 1}.

[0054] S104. The host computer determines the cross-correlation coefficient between the multi-source signals of the tool based on a preset function and determines the correlation of the multi-source signals of the tool in the time domain and frequency domain based on the cross-correlation coefficient.

[0055] In one embodiment of the present application, the host computer determines the cross-correlation coefficient between the multi-source signals of the tool based on the time-domain characteristics corresponding to the multi-source signals of the tool and the preset function, so as to quantify the time-domain correlation of the multi-source signals of the tool; wherein the multi-source signals of the tool include pressure signals, vibration signals, and temperature signals. The host computer converts the multi-source signals of the tool from the time domain to the frequency domain through fast Fourier transform to obtain the spectrum corresponding to the multi-source signals of the tool, so as to extract the frequency-domain characteristics of the multi-source signals of the tool. The host computer determines the time-domain signal correlation corresponding to the multi-source signals of the tool based on the synchronism of the multi-source signals of the tool within the same time period. The host computer determines the frequency-domain signal correlation corresponding to the multi-source signals of the tool based on the consistency of the multi-source signals of the tool within different frequency ranges.

[0056] Specifically, calculate the cross-correlation coefficient between each signal Identify the correlation of multi-source signals in the time domain and frequency domain, and analyze the correlation characteristics of pressure, vibration, and temperature signals;

[0057] where p ij represents the cross-correlation coefficient between signal i and signal j, and the value range is from -1 to 1. The closer the value is to 1, the stronger the positive correlation between the two signals; the closer it is to -1, the stronger the negative correlation; and the closer it is to 0, the weaker the linear correlation. x i represents the sample data value of signal i. It represents the specific value of signal i at a certain moment or a certain measurement point. The average value (mean) of signal i represents the average data value of signal i over the entire time period or sampling interval.

[0058] Specifically, when identifying the correlation of pressure, vibration, and temperature signals in the time domain and frequency domain, first, preprocess the three collected signals to eliminate noise interference and dimensional differences. Then, segment each signal according to a set time window (such as 1 second) and extract the time-domain characteristics within each time window, such as mean, standard deviation, peak value, root mean square value, etc., to reflect the instantaneous characteristics of the signal. Then calculate the correlation coefficient p ij between each signal feature to quantify the time-domain correlation between signals. Then, transform the signal from the time domain to the frequency domain through fast Fourier transform to obtain the spectrum of the signal. Frequency-domain feature extraction includes main frequency, frequency band energy ratio, frequency center, etc., to describe the frequency distribution of the signal.

[0059] S105. The host computer determines the working condition type of the tool based on the correlation, generates a working condition warning signal based on the working condition type, and feeds back the working condition type and the multi-source data of the tool to the tool management system to realize the monitoring of the tool.

[0060] In one embodiment of the present application, when the correlation of the mean value and root mean square value of the vibration signal and the pressure signal in the time domain is greater than a preset first correlation threshold, and the energy ratio corresponding to the low-frequency band in the frequency domain characteristics is greater than a preset energy ratio value, it is determined that the tool is in a normal working condition. When the correlation between the vibration signal and the temperature signal in the time domain characteristics is greater than a preset second correlation threshold, and new high-frequency components appear in the frequency domain characteristics of the temperature signal, it is determined that the tool is in a worn working condition. When the fluctuation value of the pressure signal in the time domain characteristics is greater than a preset fluctuation threshold, and the main frequencies of the vibration signal and the pressure signal in the frequency domain characteristics are inconsistently distributed, it is determined that the tool is in an abnormal vibration working condition.

[0061] Based on the matching results, the support vector machine algorithm is used to classify and identify the feature data, and the working condition type (such as excessive wear, eccentric wear, jamming) is output to achieve accurate working condition judgment;

[0062] According to the judgment results, a working condition warning signal is generated, and the results and feature data are fed back to the tool management system in real time.

[0063] Operators can view the working status of the tool in real time through the user interface of the tool management system, including rotation speed, pressure, temperature, and vibration information. The data displayed on the user interface is sourced from the data collected in real time by the multi-source sensor integration module and transmitted to the upper computer, which processes and analyzes this data, enabling operators to adjust the operation parameters in a timely manner. When the vibration frequency and amplitude increase abnormally, the operator can reduce the tunneling speed or adjust the tool pressure; when the temperature continues to rise, the operator can suspend tunneling for inspection or replace the tool. Through these real-time adjustments, operators can improve the safety and efficiency of operations.

[0064] In addition, the wear warning function provided by the system can notify the operator in advance that the tool is about to reach the service limit, preventing failures and accidents caused by excessive tool wear. In this way, not only the service life of the tool is extended, but also the unplanned downtime caused by emergency maintenance and tool replacement is reduced, thereby reducing the construction cost. Generally speaking, through real-time monitoring and intelligent analysis, the system helps operators optimize the tunneling process, improve work efficiency and safety, while reducing maintenance costs and construction risks.

[0065] Furthermore, through the correlation analysis of time-domain features, the synchronism of signals within the same time period can be identified. For example, the correlation between the mean values of pressure and vibration signals can be used to determine whether the force state is consistent with the vibration response. The coherence analysis of frequency-domain features can reveal the consistency of signals within a specific frequency range. For example, the vibration and temperature changes caused by rock breaking may increase simultaneously in the high-frequency band. By analyzing the correlation between time-domain and frequency-domain features, the internal relationship between vibration, pressure, and temperature signals can be revealed, and the specific analysis is as follows: Normal operating condition: The mean values and RMS values of vibration and pressure signals are highly correlated in the time domain, and the energy ratio of the low-frequency band in the frequency-domain features is high, with strong coherence. Tool wear condition: The correlation between vibration and temperature signals is significantly improved in the time domain, and new high-frequency components appear in the frequency spectrum of the temperature signal. Abnormal vibration condition: The main frequency of the vibration signal is inconsistent with the frequency distribution of the pressure signal, the coherence decreases, and the fluctuation of the pressure signal increases in the time domain.

[0066] The embodiments in the present application are all described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, equipment, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the description of the method embodiments.

[0067] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various modifications and changes can be made to the embodiments of the present application. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A load self-sensing tunneling cutter, characterized in that, The tool includes: a tool body, a multi-source sensor integration module, and a host computer; An axial center blind hole is provided at the axis of the tool shaft of the tool body; The protective shell of the multi-source sensor integration module fits against the inner wall of the axial center blind hole. The multi-source sensor integration module includes a multi-source sensor module, a self-power generation module, and a signal transmission module; The multi-source sensor integration module is wirelessly connected to the host computer. The multi-source sensor integration module is used to transmit the collected multi-source state data of the tool to the host computer, so that the host computer analyzes the multi-source state data of the tool to realize the monitoring of the load self-sensing tunneling tool; The multi-source sensor module includes a force sensor, a vibration sensor, and a temperature sensor; The force sensor is attached to the inner wall flexible structure of the multi-source sensor integration module. The force sensor is used to obtain the force data of the load self-sensing tool; The vibration sensor is arranged on the central axis of the multi-source sensor integration module. The vibration sensor is a MEMS accelerometer; the vibration sensor is used to obtain the vibration data of the load self-sensing tool; The temperature sensor is arranged inside the multi-source sensor integration module and is adjacent to the inner ring of the installation bearing of the tunneling tool. After assembly, the temperature sensor is located at the bottom of the axial center blind hole and is used to obtain the temperature data of the load self-sensing tool; The vibration sensor further includes a three-axis vibration sensing element, a thin film resistor layer, and a signal conditioning circuit; The three-axis vibration sensing element is used to measure the vibration amplitude and frequency of the load self-sensing tunneling tool in three orthogonal directions; The thin film resistor layer is used to measure the vibration intensity by detecting the strain change caused by vibration; The signal conditioning circuit is used to amplify, filter, and convert the acquired vibration signal to generate a digital signal corresponding to the vibration signal; The temperature sensor is provided with a temperature sensing element; The temperature sensing element is arranged at the side opening of the protective shell of the multi-source sensor integration module; The temperature sensing element is provided with a temperature sensing probe; The temperature sensing probe is placed externally, and the external height of the temperature sensing probe is lower than the surface of the protective shell of the multi-source sensor integration module.

2. The load self-sensing tunneling cutter according to claim 1, characterized in that The self-power generation module is connected to the signal transmission module; The self-power generation module is a ring-shaped thin film piezoelectric self-power generation module, and the self-power generation module is arranged on the outer wall surface of the multi-source sensor integration module; The self-power generation module supplies power to the multi-source sensor module through the data line of the signal transmission module.

3. The self-sensing tunneling cutter according to claim 1, characterized in that, The signal transmission module is connected to the multi-source sensor module; The signal transmission module is arranged at the bottom of the multi-source sensor integration module and is located at the top of the axial center blind hole after assembly.

4. The self-sensing tunneling cutter according to claim 1, characterized in that, The size of the axial center blind hole matches the size of the protective shell of the multi-source sensor integration module; A sealing support mechanism is arranged at the open end of the axial center blind hole; A damping sealant is filled between the multi-source sensor integration module and the inner wall of the axial center blind hole.

5. A tool monitoring method, characterized in that, Applied to a load self-sensing tunneling tool as described in claim 1, the method includes: The host computer receives the multi-source tool signals uploaded by the multi-source sensor integration module; The host computer preprocesses and extracts features from the multi-source tool signals, and generates a feature matrix based on the extracted feature data; The host computer compares each of the feature data with corresponding preset thresholds to determine abnormal points, and determines the abnormal state of the tool based on the abnormal points; The host computer determines the cross-correlation coefficient between the multi-source tool signals based on a preset function, and determines the correlation between the multi-source tool signals in the time domain and the frequency domain based on the cross-correlation coefficient; The host computer determines the working condition type of the tool based on the correlation, generates a working condition warning signal based on the working condition type, and feeds back the working condition type and the multi-source tool data to the tool management system to realize the monitoring of the tool.

6. A tool monitoring method according to claim 5, characterized in that, The host computer determines the cross-correlation coefficient between the multi-source tool signals based on a preset function, and determines the correlation between the multi-source tool signals in the time domain and the frequency domain based on the cross-correlation coefficient, specifically including: The host computer determines the cross-correlation coefficient between the multi-source tool signals based on the time-domain characteristics corresponding to the multi-source tool signals and the preset function to quantify the time-domain correlation of the multi-source tool signals; wherein the multi-source tool signals include pressure signals, vibration signals, and temperature signals; The host computer converts the multi-source tool signals from the time domain to the frequency domain through fast Fourier transform to obtain the spectrum corresponding to the multi-source tool signals, so as to extract the frequency-domain characteristics of the multi-source tool signals; The host computer determines the time-domain signal correlation corresponding to the multi-source tool signals based on the synchronism of the multi-source tool signals within the same time period; The host computer determines the frequency-domain signal correlation corresponding to the multi-source tool signals based on the consistency of the multi-source tool signals within different frequency ranges.

7. A tool monitoring method according to claim 6, characterized in that, The host computer determines the working condition type of the tool based on the correlation, specifically including: When the correlation between the mean and root mean square value of the vibration signal and the pressure signal in the time domain is greater than a preset first correlation threshold, and the energy ratio corresponding to the low-frequency band in the frequency-domain characteristics is greater than a preset energy ratio value, it is determined that the tool is in a normal working condition; When the correlation between the vibration signal and the temperature signal in the time-domain characteristics is greater than a preset second correlation threshold, and a new high-frequency component appears in the temperature signal in the frequency-domain characteristics, it is determined that the tool is in a wear working condition; When the fluctuation value of the pressure signal in the time-domain characteristics is greater than a preset fluctuation threshold, and the main frequencies of the vibration signal and the pressure signal in the frequency-domain characteristics are inconsistently distributed, it is determined that the tool is in an abnormal vibration working condition.

Images