A method, system, medium and product for monitoring damage to a cutter of a tunnel boring machine

Abstract

A TBM cutter damage monitoring method, system, medium and product, relating to the technical field of shield construction monitoring. The cutter damage monitoring system first acquires the vibration signal and acoustic emission signal of the cutter, and divides the signals into time-synchronous segments to ensure data correspondence. Then the vibration feature vector is extracted and the Euclidean distance is calculated to reflect the vibration trend; and the acoustic emission feature parameters and the change rate are determined to reflect the acoustic emission signal characteristics. After removing the interference data segments, the abnormal signals are marked to determine whether the cutter is damaged according to the abnormal signal duration and the number density. Each step cooperates to form a complete process, which can effectively distinguish the vibration signal and acoustic emission signal mutation caused by instantaneous impact from the signal characteristics generated by the real damage of the cutter, accurately identify the cutter damage, and timely issue an early warning to improve the accuracy of monitoring and reduce the false alarm rate, and ensure the safety and continuity of construction.

Description

Technical Field

[0001] This application relates to the field of tunnel boring machine (TBM) construction monitoring technology, and in particular to a method, system, medium, and product for monitoring cutterhead damage in TBMs. Background Technology

[0002] Tunnel boring machines (TBMs) are crucial equipment in tunnel excavation projects. The cutterhead cutters, as the components that directly break rock, frequently face harsh operating environments. During excavation, the TBM cutterheads endure immense impact and wear, making them prone to chipping, breakage, and other damage—critical and vulnerable components of the entire machine. Failure to detect cutterhead damage in a timely manner not only reduces excavation efficiency but can also cause secondary damage to the cutterhead, leading to significant economic losses and project delays. Therefore, real-time monitoring of the TBM cutterhead's operating status and timely damage warnings are essential for ensuring the safety and efficiency of tunnel engineering.

[0003] To achieve real-time monitoring of the tunnel boring machine (TBM) cutterhead, a vibration analysis-based method is commonly used. This method involves installing vibration sensors near the TBM cutterhead to collect vibration signals generated during cutterhead operation. The monitoring system performs spectral analysis on the collected vibration signals and calculates the total vibration energy within a preset characteristic frequency band. When the total vibration energy within this band exceeds a preset threshold, the system determines that the TBM cutterhead may be damaged and issues an alarm.

[0004] During actual tunneling operations, the cutterhead of a tunnel boring machine (TBM) often encounters sudden geological changes, such as moving from soft soil to hard rock or boulders. These changes in operating conditions can cause instantaneous and severe impact vibrations in the cutterhead, resulting in a sudden increase in the total vibration energy within a certain preset characteristic frequency band, exceeding a preset threshold. This can lead to false alarms from the monitoring system, reducing the accuracy of cutterhead damage monitoring. Summary of the Invention

[0005] This application provides a method, system, medium, and product for monitoring cutterhead damage in tunnel boring machines, which can improve the accuracy of monitoring and reduce the false alarm rate under complex tunneling conditions.

[0006] In a first aspect, this application provides a method for monitoring cutterhead damage in a tunnel boring machine (TBM) and applying it to a cutterhead damage monitoring system. The method includes: acquiring vibration signals and acoustic emission signals of the TBM cutterhead, wherein the acoustic emission signal refers to the transient elastic wave generated when the TBM cutterhead contacts and rolls over the tunnel; dividing the vibration signal into multiple vibration signal segments and the acoustic emission signal into multiple acoustic emission signal segments, wherein the vibration signal segments and their corresponding acoustic emission signal segments are time-synchronized in the rotation cycle of the TBM cutterhead; extracting vibration feature vectors corresponding to each vibration signal segment based on a preset standard operating frequency, and calculating the Euclidean distance between the vibration feature vectors of adjacent vibration signal segments, wherein the preset standard operating frequency refers to the frequency at which a single TBM cutterhead makes a complete contact with and rolls over the tunnel under the current TBM operating conditions; and determining the frequency of each acoustic emission signal segment based on its corresponding spectral data. The acoustic emission characteristic parameters corresponding to each signal segment are calculated, and the rate of change between the acoustic emission characteristic parameters corresponding to adjacent acoustic emission signal segments is calculated. The acoustic emission characteristic parameter refers to the amplitude ratio of the dominant frequency component to the secondary frequency component determined based on the spectrum data. When the Euclidean distance exceeds a preset Euclidean distance threshold or / and the rate of change exceeds a preset rate of change threshold, the corresponding vibration signal segment and acoustic emission signal are marked as interference data segments and removed. When the vibration characteristic vector corresponding to the vibration signal segment exceeds a preset vibration characteristic vector range, the vibration signal segment is recorded as a first anomaly marker. When the acoustic emission characteristic parameter corresponding to the acoustic emission signal segment exceeds a preset acoustic emission characteristic parameter threshold, the acoustic emission signal segment is recorded as a second anomaly marker. If the duration of the first anomaly marker exceeds a preset duration and the number density of the second anomaly marker exceeds a preset density threshold, it is determined that the cutter head of the tunnel boring machine is damaged and an early warning signal is issued.

[0007] By adopting the above technical solution, the cutterhead damage monitoring system first acquires the vibration and acoustic emission signals of the tunnel boring machine's cutterhead, accurately collecting information containing the cutterhead's working status. The system divides the signals into time-synchronized segments to ensure data correspondence. Based on a preset standard operating frequency, it extracts vibration feature vectors and calculates Euclidean distance to reflect vibration change trends; it determines acoustic emission characteristic parameters and their rate of change based on spectral data, reflecting the characteristics of the acoustic emission signal. After removing interfering data segments, the system identifies cutterhead damage by marking abnormal signals and using the duration and density of these abnormal markings. This effectively distinguishes between vibration signals and abrupt changes in acoustic emission signals caused by instantaneous impacts and the signal characteristics generated by actual cutterhead damage, accurately identifying cutterhead damage and issuing timely warnings to improve monitoring accuracy and reduce false alarm rates.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, when the Euclidean distance exceeds a preset Euclidean distance threshold and / or the rate of change exceeds a preset rate of change threshold, the corresponding vibration signal segment and acoustic emission signal are marked as interference data segments and discarded. Specifically, this includes: inputting two adjacent vibration signal segments and two adjacent acoustic emission signal segments into a data processing queue according to their time sequence; comparing the Euclidean distance with the preset Euclidean distance threshold and comparing the rate of change with the preset rate of change threshold; when the Euclidean distance exceeds the preset Euclidean distance threshold and / or the rate of change exceeds the preset rate of change threshold, determining the vibration signal segment and acoustic emission signal segment with the later time sequence as interference data segments and discarding them.

[0009] By adopting the above technical solution, adjacent vibration and acoustic emission signal segments are sequentially input into a queue for unified processing. Euclidean distance and rate of change are compared with preset thresholds to establish judgment criteria. When the Euclidean distance or rate of change exceeds the threshold, the later-sequenced signal segment is identified as interference data and discarded, thus removing invalid data caused by external interference or abnormal operating conditions. This process, through quantitative comparison and threshold judgment, effectively eliminates the influence of interference signals caused by sudden changes in instantaneous impact vibration signals and acoustic emission signals on the analysis results, ensuring the validity and accuracy of the vibration and acoustic emission signal data used to determine the cutter's condition, avoiding misjudgments of cutter damage due to interference signals, and improving the reliability of the cutter damage monitoring system.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, before determining and removing the vibration signal segment and acoustic emission signal segment that are later in time as interference data segments, the method further includes: obtaining the vibration feature vector corresponding to the vibration signal segment that is later in time, and the acoustic emission feature parameter corresponding to the acoustic emission signal segment; determining whether the vibration feature vector exceeds a preset vibration feature vector range, or whether the acoustic emission feature parameter exceeds a preset acoustic emission feature parameter threshold; if any or all of the determination results are yes, retaining the vibration signal segment and acoustic emission signal segment that are later in time.

[0011] By employing the above technical solution, before discarding signal segments, the vibration feature vector and acoustic emission feature parameters of later-time signal segments are obtained to further mine signal information. It is determined whether the vibration feature vector exceeds the range and whether the acoustic emission feature parameters exceed the threshold, providing a basis for retaining signal segments. If either condition is met, the signal segment is retained, avoiding the erroneous deletion of signals that actually reflect the abnormal state of the hob due to Euclidean distance or rate of change exceeding the threshold. A verification step is added during the process of discarding interference signals to balance the removal of interference with the retention of valid abnormal signals, avoiding the rejection of abnormal signals as interference signals and reducing the accuracy of hob damage assessment.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, if the duration of the first abnormal marker exceeds a preset duration and the number density of the second abnormal marker exceeds a preset density threshold, determining that the tunnel boring machine cutter head is damaged and issuing a warning signal specifically includes: acquiring all first abnormal markers and second abnormal markers within a signal segment to be processed, the signal segment to be processed including the unprocessed vibration signal segment and acoustic emission signal segment after removing the interference data segment; calculating the duration of the first abnormal marker in the signal segment to be processed; counting the number of occurrences of the second abnormal marker in the signal segment to be processed, and calculating the number density of the second abnormal marker per unit time; if the duration of the first abnormal marker exceeds a preset duration and the number density of the second abnormal marker exceeds a preset density threshold, determining that the tunnel boring machine cutter head is damaged and issuing a warning signal.

[0013] By employing the above technical solution, abnormal markers are obtained from the signal segment to be processed after removing interference data, focusing on abnormal information in the effective signal. The duration of the first abnormal marker is calculated to reflect the continuity of vibration anomalies; the number and density of the second abnormal marker are counted to reflect the frequency of acoustic emission anomalies. Cutter damage is determined based on both duration and density, comprehensively considering both vibration and acoustic emission signal anomalies. Cutter damage is only confirmed when both the duration and density of the abnormal markers simultaneously meet threshold conditions, avoiding misjudgments due to a single anomaly or brief fluctuations, thus improving the accuracy and reliability of cutter damage assessment.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, dividing the vibration signal into multiple vibration signal segments and dividing the acoustic emission signal into multiple acoustic emission signal segments specifically includes: acquiring the real-time rotational speed and angular position information of the tunnel boring machine cutterhead; calculating the rotational cycle required for the cutterhead to complete one full rotation based on the real-time rotational speed; dividing the vibration signal into multiple vibration signal segments of equal length based on the rotational cycle and angular position information, each vibration signal segment containing a corresponding timestamp; and dividing the acoustic emission signal into multiple acoustic emission signal segments of equal length based on the rotational cycle and angular position information, each acoustic emission signal segment containing a corresponding timestamp, and corresponding one-to-one with the timestamp of the vibration signal segment.

[0015] By employing the above technical solution, real-time rotational speed and angular position information of the tunnel boring machine cutterhead are obtained. Combined with the rotational speed, the rotational period is calculated, providing a time reference for signal segmentation. Based on the rotational period and angular position, the vibration and acoustic emission signals are divided into equal-length segments and assigned corresponding timestamps, aligning the signals in the time dimension. This segmentation method ensures that the vibration signal segments and acoustic emission signal segments are time-synchronized, guaranteeing that subsequent characteristic analysis of the two types of signals is based on corresponding working conditions, thus improving the accuracy and correlation of vibration and acoustic emission signal analysis.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, the extraction of vibration feature vectors corresponding to each vibration signal segment based on a preset standard operating frequency, and the calculation of the Euclidean distance between the vibration feature vectors corresponding to adjacent vibration signal segments, specifically includes: extracting effective vibration signals from each vibration signal segment based on a preset standard operating frequency; performing wavelet transform on the effective vibration signals to obtain effective vibration sub-signals in multiple frequency bands; arranging the energy values ​​of the effective vibration sub-signals in each frequency band according to the frequency band to obtain vibration feature vectors; and calculating the Euclidean distance between the vibration feature vectors corresponding to adjacent vibration signal segments.

[0017] By employing the above technical solution, effective vibration signals are extracted from vibration signal segments based on a preset standard operating frequency, eliminating interference from irrelevant frequencies. Wavelet transform is performed on the effective vibration signals, decomposing them into multiple effective vibration sub-signals in multiple frequency bands, enabling refined signal analysis. The energy values ​​of each frequency band sub-signal are arranged to obtain vibration feature vectors, representing vibration characteristics in a quantified form. The Euclidean distance between adjacent vibration feature vectors is calculated to quantify the degree of change in vibration characteristics. This provides a precise basis for determining whether the vibration signal is abnormal, thereby assisting in judging whether the hobbing cutter's working state is stable.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, determining the acoustic emission characteristic parameters corresponding to each acoustic emission signal segment based on the spectral data corresponding to each of the acoustic emission signal segments, and calculating the rate of change between the acoustic emission characteristic parameters corresponding to adjacent acoustic emission signal segments, specifically includes: extracting the spectral data corresponding to each of the acoustic emission signal segments; determining, based on the spectral data, the frequency component with the highest amplitude in the acoustic emission signal as the dominant frequency component, and the frequency component with the second highest amplitude as the secondary frequency component; calculating the amplitude ratio of the dominant frequency component to the secondary frequency component to obtain the acoustic emission characteristic parameters; and calculating the rate of change between the acoustic emission characteristic parameters corresponding to adjacent acoustic emission signal segments based on the acoustic emission characteristic parameters arranged in time sequence.

[0019] By employing the above technical solution, spectral data of acoustic emission signal segments are extracted, and the signal is analyzed from a frequency perspective. The dominant and secondary frequency components are determined, capturing the main frequency characteristics of the signal. The amplitude ratio of these two components is calculated to obtain acoustic emission characteristic parameters, which characterize the frequency characteristics of the acoustic emission signal as a single parameter. The rate of change of adjacent acoustic emission characteristic parameters is calculated based on time series analysis, reflecting the trend of parameter variation over time. This analytical process, from spectral data to characteristic parameters and then to the rate of change, transforms complex acoustic emission signals into quantifiable and comparable parameters and trends. It effectively identifies abnormal changes in acoustic emission signals, providing a reliable basis for judging the working state of the hobbing cutter based on acoustic emission signals, complementing vibration signal analysis.

[0020] In a second aspect, embodiments of this application provide a hob damage monitoring system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, which includes computer instructions, and the one or more processors call the computer instructions to cause the hob damage monitoring system to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a hob damage monitoring system, cause the hob damage monitoring system to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a hob damage monitoring system, cause the hob damage monitoring system to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the hob damage monitoring system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0025] 1. By adopting a technical solution that acquires the vibration and acoustic emission signals of the tunnel boring machine cutter head, and performs signal segmentation, feature extraction, interference removal, and anomaly marking, the working status of the cutter head can be analyzed comprehensively and accurately. This effectively solves the problems of inaccurate and untimely judgment of cutter head damage in related technologies, thereby enabling accurate monitoring of cutter head damage under complex tunneling conditions of the tunnel boring machine and reducing the risk of construction interruption or secondary equipment damage caused by cutter head failure.

[0026] 2. By adopting a technical solution that sequentially inputs adjacent vibration and acoustic emission signal segments into a queue, compares the Euclidean distance and rate of change with a preset threshold, and removes subsequent signal segments that exceed the threshold as interference data, it can effectively remove invalid signal data generated by external interference or abnormal working conditions. This effectively solves the problem of interference signals affecting the accuracy of cutter damage judgment in related technologies, ensuring that the signal data used to analyze the cutter status is true and reliable, and improving the accuracy and reliability of the monitoring system.

[0027] 3. By adopting a technical solution that calculates the duration of the first abnormal marker and statistically analyzes the density of the second abnormal marker to determine the cutter damage under dual conditions, the abnormality of vibration and acoustic emission signals can be comprehensively considered. This avoids misjudgment caused by a single abnormality or short-term fluctuation, effectively solving the problem of high false alarm rate in cutter damage monitoring in related technologies. As a result, accurate judgment of cutter damage status is achieved, and timely and accurate early warning signals are issued to ensure the normal construction effect of the tunnel boring machine. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the cutterhead of a tunnel boring machine in one of the embodiments of this application;

[0029] Figure 2 This is a flowchart illustrating a method for monitoring cutterhead damage in tunnel boring machines according to an embodiment of this application.

[0030] Figure 3 This is another flowchart illustrating the method for monitoring cutterhead damage in tunnel boring machines in this application embodiment;

[0031] Figure 4 This is a schematic diagram of the physical device structure of a hobbing cutter damage monitoring system in the embodiments of this application. Detailed Implementation

[0032] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0033] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0034] To facilitate understanding, the following will be combined with Figure 1 This section introduces an application scenario for the cutterhead of a tunnel boring machine. Please refer to [link / reference]. Figure 1 , Figure 1 This is a schematic diagram of the cutterhead of a tunnel boring machine in an embodiment of this application.

[0035] The tunnel boring machine cutterhead includes: cutterhead body 101, cutter head 102, vibration sensor 103 and acoustic emission sensor 104.

[0036] The cutterhead body 101 is a key component of the tunnel boring machine (TBM) cutterhead. It rotates continuously during the TBM's excavation process, driving the cutterhead rollers mounted on it to crush and break up the tunnel face. The cutterhead rollers 102, mounted on the cutterhead body 101, are the key components that directly interact with the soil and rock during the TBM's excavation. A vibration sensor 103 is installed on the cutterhead body 101 to collect vibration signals, and an acoustic emission sensor 104 is installed on the cutterhead rollers 102 to collect acoustic emission signals, thus acquiring the signals generated by the cutterhead rollers 102 in real time. The signals collected by the vibration sensor 103 and the acoustic emission sensor 104 are sent to the cutterhead roller damage monitoring system for processing.

[0037] In related technologies, cutterhead damage can be monitored by employing a single vibration signal monitoring method and setting a fixed vibration energy threshold. The following describes a scenario where a cutterhead damage monitoring method from this related technology is used.

[0038] During tunneling, when the cutterhead 101 suddenly encounters a hard boulder, the cutter head 102, which is in good working order, will experience severe impact vibration upon contact with the boulder. The monitoring methods used in related technologies only analyze the vibration signal, and the vibration energy detected can spike instantaneously, exceeding its preset threshold. Therefore, this method will issue an alarm, mistakenly identifying the instantaneous impact experienced by the healthy cutter head 102 as cutter damage. This false alarm caused by non-damaging factors reduces the reliability of the monitoring system.

[0039] The shield tunneling machine cutterhead damage monitoring method provided in this application comprehensively processes and judges both vibration and acoustic emission signals to achieve high-precision, low-false-alarm early warning of cutterhead damage. It can not only identify continuous and progressive damage but also effectively eliminate interference from events such as instantaneous impacts. The following describes a scenario where the shield tunneling machine cutterhead damage monitoring method of this application is used.

[0040] Similarly, in a scenario where the cutterhead 101 encounters a hard boulder, the vibration signal of the healthy hob 102 will produce a brief, intense spike. This may cause its corresponding vibration feature vector to exceed the range within one or two data segments, thus being recorded as the first anomaly marker. However, since the impact is instantaneous, this anomaly will not last, and its duration will not exceed the preset duration. Simultaneously, although its acoustic emission signal will also contain transient waves generated by the impact, since the material itself does not suffer sustained damage, the frequency of the second anomaly marker is low, and its number density will not exceed the preset density threshold. Ultimately, since neither of the two warning conditions (duration and number density) is met, the method of this application will not issue an alarm, successfully avoiding false alarms.

[0041] For the damaged cutter head 102: its internal microcracks will continue to propagate during normal tunneling and impacts. Its vibration characteristic vector will continuously exceed the range due to abnormal rolling, causing the first anomaly marker to appear consecutively, and its duration can easily exceed a preset duration. More importantly, each micro-expansion of the crack releases an acoustic emission signal, causing the second anomaly marker to appear densely within that time period, with its number density significantly exceeding a preset density threshold. Ultimately, since both warning conditions are met simultaneously, the method of this application accurately determines that the cutter head 102 is damaged and issues a warning signal.

[0042] It is evident that the tunnel boring machine cutter damage monitoring method provided in this application can not only reliably monitor the actual damage to the cutter, but also effectively solve the problem of false alarms in monitoring and early warning caused by non-damaging factors such as instantaneous impact, thereby significantly improving the accuracy and reliability of cutter damage monitoring.

[0043] To facilitate understanding, the following description, based on the above scenario, outlines the process of a tunnel boring machine cutterhead damage monitoring method provided in this implementation, which can be applied to a cutterhead damage monitoring system (hereinafter referred to as the monitoring system). Please refer to [link / reference]. Figure 2 This is a flowchart illustrating a method for monitoring cutterhead damage in tunnel boring machines according to an embodiment of this application.

[0044] S201. Obtain the vibration signal and acoustic emission signal of the tunnel boring machine cutter head. The acoustic emission signal refers to the transient elastic wave generated when the tunnel boring machine cutter head contacts and rolls the tunnel.

[0045] Vibration signal refers to the signal generated by the mechanical vibration of the tunnel boring machine cutter head due to various forces during operation. This signal contains relevant information about the cutter head's operating status, such as the impact vibration signal when the cutter head contacts the soil and rock. Acoustic emission signal refers to the signal generated by transient elastic waves inside the material due to local stress concentration, crack propagation, etc. when the tunnel boring machine cutter head contacts and rolls the tunnel. It can reflect the wear and damage of the cutter head. For example, when cracks appear in the cutter head, a specific acoustic emission signal will be generated.

[0046] Throughout the tunnel excavation process, as long as the tunnel boring machine (TBM) is operational, it needs to continuously acquire signals. Specifically, during TBM operation, vibration sensors installed near the cutterhead collect vibration signals generated by the cutterhead during operation. These sensors convert the mechanical vibrations into electrical signals, which are then sent to the monitoring system. Simultaneously, acoustic emission sensors collect acoustic emission signals generated during the cutterhead's contact with and compaction of the tunnel. These sensors capture transient elastic waves generated within the material due to stress changes and convert them into electrical signals, which are then sent to the monitoring system. The monitoring system receives both the vibration and acoustic emission signals collected by the sensors.

[0047] S202. Divide the vibration signal into multiple vibration signal segments and the acoustic emission signal into multiple acoustic emission signal segments. The vibration signal segments and the corresponding acoustic emission signal segments are in a time-synchronous relationship in the rotation cycle of the tunnel boring machine cutterhead.

[0048] Among them, the vibration signal segment refers to the continuous vibration signal divided into several small signal segments, each of which contains the vibration information of the cutterhead within a certain time period; the acoustic emission signal segment refers to the small signal segment obtained by dividing the continuous acoustic emission signal, each of which records the acoustic emission of the cutterhead within the corresponding time period; the rotation period of the tunnel boring machine cutterhead is used to represent the time required for the cutterhead to rotate once in actual working conditions. During the rotation of the cutterhead, the cutterhead will continuously contact and crush the tunnel excavation face, generating vibration signals and acoustic emission signals.

[0049] After receiving the vibration and acoustic emission signals, the monitoring system segments the continuous signals. Specifically, based on the rotation cycle of the tunnel boring machine (TBM) cutterhead, the collected continuous vibration signals are divided into multiple vibration signal segments in chronological order. Each vibration signal segment corresponds to the time period during which a single TBM cutter head makes a complete contact with and compacts the tunnel within the TBM cutterhead rotation cycle. Similarly, the continuous acoustic emission signals are also divided into multiple acoustic emission signal segments according to the same chronological order and correspondence. This ensures that each vibration signal segment and its corresponding acoustic emission signal segment are synchronized in time within the TBM cutterhead rotation cycle, reflecting the working state of the cutter head during the same stage of cutterhead rotation. This allows for a comprehensive analysis of the cutter head status from both vibration and acoustic emission perspectives.

[0050] S203. Based on the preset standard working frequency, extract the vibration feature vectors corresponding to each vibration signal segment, and calculate the Euclidean distance between the vibration feature vectors corresponding to adjacent vibration signal segments. The preset standard working frequency refers to the frequency at which a single cutter of the tunnel boring machine makes a complete contact with and compacts the tunnel under the current working conditions.

[0051] The preset standard operating frequency refers to the frequency at which a single tunnel boring machine cutter makes a complete contact with and compacts the tunnel under the current tunnel boring machine operating conditions. This frequency is preset based on factors such as the design parameters of the tunnel boring machine and the geological conditions of the excavation. The vibration feature vector represents a set of data vectors obtained by extracting features from vibration signal segments. It contains key feature information of the vibration signal segments, such as frequency and amplitude, and is used to describe the characteristics of the vibration signal segments. Euclidean distance is a metric for measuring the distance between two vectors. In this step, it is used to calculate the degree of difference between the vibration feature vectors corresponding to adjacent vibration signal segments. The greater the degree of difference, the greater the Euclidean distance.

[0052] After dividing the vibration signal into segments, the monitoring system analyzes the characteristics of each segment and the differences between adjacent segments. Specifically, based on a preset standard operating frequency, feature extraction is performed on each vibration signal segment. Algorithms (such as wavelet transform) are used to extract parameters that reflect the essential characteristics of the segment, forming a corresponding vibration feature vector. Then, the Euclidean distance between the vibration feature vectors of two adjacent segments is calculated. For example, for the vibration feature vector V corresponding to the nth vibration signal segment... n The vibration feature vector V corresponding to the (n+1)th vibration signal segment n+1 The distance between them is calculated using the Euclidean distance formula, which is used to determine the characteristic changes between adjacent vibration signal segments.

[0053] S204. Based on the spectral data corresponding to each acoustic emission signal segment, determine the acoustic emission characteristic parameters corresponding to each acoustic emission signal segment, and calculate the rate of change between the acoustic emission characteristic parameters corresponding to adjacent acoustic emission signal segments. The acoustic emission characteristic parameter refers to the amplitude ratio of the main frequency component to the secondary frequency component determined based on the spectral data.

[0054] Among them, the spectrum data represents the data obtained after converting the acoustic emission signal segment to the frequency domain through signal processing methods such as Fourier transform, which shows the distribution of the signal at different frequency components; the acoustic emission characteristic parameters refer to the amplitude ratio of the dominant frequency component to the secondary frequency component determined according to the spectrum data, which is used to quantify the characteristics of the acoustic emission signal and reflect the working state of the hobbing cutter; the dominant frequency component represents the frequency component with the highest energy in the spectrum data, corresponding to the main frequency characteristics of the acoustic emission signal; the secondary frequency component refers to the frequency component with the second highest energy in the spectrum data, which is an important component of the acoustic emission signal; the rate of change is used to represent the degree of difference between the acoustic emission characteristic parameters corresponding to adjacent acoustic emission signal segments, which is obtained by calculating the ratio of the difference between the two parameters to the previous parameter.

[0055] After segmenting the acoustic emission signal, the monitoring system analyzes the characteristic changes of the acoustic emission signal. Specifically, firstly, spectral analysis is performed on each acoustic emission signal segment to obtain spectral data. The dominant frequency component and the secondary frequency component are identified from the spectral data, and their amplitude ratio is calculated to obtain the acoustic emission characteristic parameters. Then, the rate of change between the acoustic emission characteristic parameters corresponding to two adjacent acoustic emission signal segments is calculated. For example, for the acoustic emission characteristic parameter P corresponding to the nth acoustic emission signal segment... n The acoustic emission characteristic parameter P corresponding to the (n+1)th acoustic emission signal segment n+1 Calculate the rate of change = (P) n+1 -P n ) / P n The monitoring system can capture dynamic changes in the characteristics of acoustic emission signals.

[0056] S205. When the Euclidean distance exceeds a preset Euclidean distance threshold or / and the rate of change exceeds a preset rate of change threshold, the corresponding vibration signal segment and acoustic emission signal are marked as interference data segments and removed.

[0057] Among them, the preset Euclidean distance threshold refers to a distance limit set in advance by the monitoring system to determine whether the vibration signal segment is abnormal; the preset rate of change threshold refers to a change limit set in advance by the monitoring system to determine whether the acoustic emission signal segment is abnormal; and the interference data segment refers to the vibration signal segment and acoustic emission signal segment that do not conform to the characteristics of normal working conditions, which may be caused by external interference or equipment malfunction.

[0058] After calculating the Euclidean distance of the vibration feature vector and the rate of change of the acoustic emission feature parameters, the monitoring system filters valid data. Specifically, the system compares the Euclidean distance corresponding to each vibration signal segment with a preset Euclidean distance threshold, and simultaneously compares the rate of change corresponding to each acoustic emission signal segment with a preset rate of change threshold. When the Euclidean distance exceeds the preset threshold, it indicates that the characteristics of the vibration signal segment differ too much from those of adjacent segments, potentially indicating an anomaly; when the rate of change exceeds the preset threshold, it indicates that the characteristics of the acoustic emission signal segment change too drastically, also potentially indicating an anomaly. If either of these conditions is met, the monitoring system marks the corresponding vibration signal segment and acoustic emission signal segment as interference data segments, and removes both the interference data segments and their corresponding vibration signal segments or acoustic emission signal segments from the dataset for subsequent analysis, ensuring that only normal signal segments participate in subsequent anomaly detection.

[0059] S206. When the vibration feature vector corresponding to the vibration signal segment exceeds the preset vibration feature vector range, the vibration signal segment is recorded as the first abnormal marker.

[0060] The first anomaly marker refers to the record made by the monitoring system for vibration signal segments that exceed the preset vibration feature vector range, used to identify vibration signal segments that may be abnormal.

[0061] After removing interfering data segments, the monitoring system initially detects abnormal signals in the vibration signal segments. Specifically, the system compares the vibration feature vector corresponding to each remaining vibration signal segment with a preset range of vibration feature vectors. This preset range can be determined through statistical analysis of historical normal data or machine learning methods, and is typically represented as a hypercube or ellipsoid in a multi-dimensional space. If the vibration feature vector of a particular vibration signal segment falls outside this range, it indicates a significant difference between the characteristics of the vibration signal and those under normal operating conditions, and the monitoring system records this vibration signal segment as the first anomaly marker.

[0062] S207. When the acoustic emission characteristic parameter corresponding to the acoustic emission signal segment exceeds the preset acoustic emission characteristic parameter threshold, the acoustic emission signal segment is recorded as a second abnormal marker.

[0063] The second anomaly marker refers to the record made by the monitoring system for acoustic emission signal segments that exceed the preset acoustic emission characteristic parameter threshold, which is used to identify acoustic emission signal segments that may be abnormal.

[0064] After removing interfering data segments, the monitoring system detects anomalies in the acoustic emission signal. Specifically, the system compares the acoustic emission characteristic parameters corresponding to each remaining acoustic emission signal segment with preset acoustic emission characteristic parameter thresholds. These thresholds are determined through statistical analysis of historical normal data or machine learning methods, representing a reasonable range for acoustic emission characteristic parameters under normal operating conditions. If the acoustic emission characteristic parameters of a particular signal segment exceed these thresholds, it indicates a significant difference between the characteristics of that signal and those under normal operating conditions, and the monitoring system records this signal segment as a second anomaly.

[0065] S208. If the duration of the first abnormal marker exceeds a preset duration and the number density of the second abnormal marker exceeds a preset density threshold, the cutter head of the tunnel boring machine is determined to be damaged and an early warning signal is issued.

[0066] Among them, the preset duration refers to a time limit set in advance by the monitoring system, which is used to determine whether the duration of the vibration signal abnormality of the first abnormal marker is long enough; the number density refers to the ratio of the number of occurrences of the second abnormal marker to the length of the window within a certain time window, which is used to measure the frequency of acoustic emission signal abnormalities.

[0067] After recording the first and second anomaly markers, the monitoring system comprehensively determines whether the tunnel boring machine's cutterhead is damaged and whether to issue an early warning. Specifically, the monitoring system first counts the duration of the first anomaly marker, that is, the time span from the appearance of the first anomaly marker to the end of the last one. Simultaneously, the monitoring system calculates the quantity density of the second anomaly markers within a sliding time window; for example, if 5 second anomaly markers appear within a 10-second time window, the quantity density is 0.5 markers / second. Then, the monitoring system compares the duration of the first anomaly markers with a preset duration and the quantity density of the second anomaly markers with a preset density threshold. Only when the duration of the first anomaly marker exceeds the preset duration and the quantity density of the second anomaly markers exceeds the preset density threshold will the monitoring system determine that the cutterhead is damaged and issue an early warning signal. The early warning signal can be conveyed to the operator through audible and visual alarms, SMS notifications, or monitoring system interface prompts, so that timely measures such as cutterhead replacement can be taken to avoid further equipment damage and project delays.

[0068] By adopting the above technical solution, this embodiment captures abnormal changes in the operating status of the tunnel boring machine's cutterhead from multiple angles through joint analysis of vibration and acoustic emission signals, effectively improving the accuracy and reliability of anomaly detection. Through signal segmentation and feature extraction based on the cutterhead rotation cycle, the differences between adjacent segments are dynamically calculated, and interfering data is eliminated. By combining threshold analysis of vibration feature vectors and acoustic emission feature parameters, the cutterhead damage status is comprehensively judged, achieving precise monitoring. This ensures the safety and continuity of tunnel construction, improving project efficiency and economic benefits.

[0069] In the above embodiments, this application collects vibration and acoustic emission signals from the tunnel boring machine's cutterhead during operation, removes interference signals, determines whether the cutterhead is damaged, and triggers an early warning. In practical applications, during the interference signal removal process, abnormal signals caused by cutterhead damage may be mistakenly identified as interference and rejected. In some embodiments, a verification mechanism can be introduced during the interference signal removal process to avoid mistakenly deleting abnormal signals.

[0070] The following provides supplementary information regarding the scenario in this embodiment. Based on the above scenario, the method provided in this embodiment will be described in more detail below. Please refer to... Figure 2 This is another flowchart illustrating the method for monitoring cutterhead damage in tunnel boring machines in this application.

[0071] S301. Obtain the vibration signal and acoustic emission signal of the tunnel boring machine cutter head. The acoustic emission signal refers to the transient elastic wave generated when the tunnel boring machine cutter head contacts and rolls the tunnel.

[0072] Step S301 is similar to step S201 in the above embodiments, and can be referred to the above description, so it will not be repeated here.

[0073] S302. Obtain the real-time rotational speed and angular position information of the tunnel boring machine cutterhead;

[0074] Among them, the real-time rotation speed of the tunnel boring machine cutterhead indicates the rotation speed of the cutterhead at the current moment, usually measured in revolutions per minute (RPM), and is used to measure how fast the cutterhead rotates; the angular position information refers to the angle value of the cutterhead relative to a certain reference position during rotation, usually measured in degrees (°), and is used to determine the specific position of the cutterhead on the circumference.

[0075] After acquiring the vibration and acoustic emission signals of the tunnel boring machine cutterhead, the system provides time and position references for subsequent signal segmentation. Specifically, the monitoring system monitors the cutterhead's rotation speed in real time using speed sensors (such as photoelectric encoders and Hall effect sensors) installed on the cutterhead drive shaft or related transmission components. This converts the mechanical rotation into electrical signals, which are then processed to obtain accurate real-time speed data. Simultaneously, angle encoders and other devices are used to acquire the cutterhead's angular position information, which precisely indicates the cutterhead's rotation angle relative to its initial reference position at any given time.

[0076] S303. Based on the real-time rotation speed, calculate the rotation cycle required for the cutter head to complete one full rotation;

[0077] The rotation cycle represents the time required for the cutterhead of the tunnel boring machine to complete one full 360° rotation, measured in seconds (s). It is inversely proportional to the real-time rotation speed.

[0078] After acquiring the real-time rotational speed of the cutterhead, the time window for signal segmentation is determined. Specifically, the monitoring system calculates the time required for the cutterhead to complete one full rotation based on the real-time rotational speed data using the formula: Rotation period = 60 / Real-time rotational speed. For example, if the real-time rotational speed is 3 RPM, then the rotation period is 60 / 3 = 20 seconds. The system continuously updates the rotation period data to adapt to changes in the cutterhead rotational speed under different operating conditions of the tunnel boring machine, ensuring the accuracy and real-time performance of subsequent signal segmentation.

[0079] S304. Based on the rotation period and angular position information, the vibration signal is divided into multiple vibration signal segments of equal length, and each vibration signal segment contains a corresponding timestamp.

[0080] Based on the rotation period and angular position information, the acoustic emission signal is divided into multiple acoustic emission signal segments of equal length. Each acoustic emission signal segment contains a corresponding timestamp, and the timestamps of the vibration signal segments correspond one-to-one.

[0081] After calculating the rotation period, signal preprocessing is performed. Specifically, the monitoring system first determines the time length of the signal segments based on the rotation period. For example, if the rotation period is 20 seconds, the vibration signal and acoustic emission signal are divided into equal-length 20-second time windows. Simultaneously, combined with angular position information, it ensures that each signal segment corresponds to a specific angular interval of the cutterhead on the circumference.

[0082] During the segmentation process, the system adds precise timestamps to each vibration signal segment and acoustic emission signal segment. These timestamps are calculated based on the start time of signal acquisition and the segment's position within the continuous signal. For example, the timestamp of the first signal segment is the acquisition start time, and the timestamps of subsequent segments increment sequentially by the duration of the rotation cycle. In this way, the system achieves strict temporal synchronization between the vibration and acoustic emission signal segments, providing an accurate data foundation for subsequent feature extraction and anomaly detection.

[0083] S305. Based on the preset standard operating frequency, extract the effective vibration signal from each vibration signal segment;

[0084] The effective vibration signal is subjected to wavelet transform to obtain effective vibration sub-signals in multiple frequency bands;

[0085] Among them, the preset standard working frequency represents the frequency at which a single cutter completes one full contact and compacts the tunnel under the current shield machine operating conditions, and the unit is Hertz (Hz). It is preset by factors such as shield machine design parameters and geological conditions; the effective vibration signal refers to the signal component that is directly related to the normal or abnormal state of the cutter and is selected from the vibration signal segment, excluding irrelevant interference such as environmental noise; wavelet transform is a mathematical method that decomposes a time-domain signal into sub-signals of different frequency bands. It extracts the characteristics of the signal at different frequencies through multi-resolution analysis. For example, it decomposes the vibration signal into high-frequency (reflecting impact characteristics) and low-frequency (reflecting steady-state vibration characteristics) sub-signals.

[0086] After the vibration signal segments are divided, effective features are extracted from them. Specifically, the monitoring system first performs bandpass filtering on each vibration signal segment according to a preset standard operating frequency, filtering out noise signals that are unrelated to the standard operating frequency and retaining effective vibration signals that contain the working characteristics of the hobbing cutter.

[0087] Subsequently, the system performs wavelet transform on the effective vibration signal, selects an appropriate wavelet basis function (such as Daubechies wavelet) and decomposition level (such as 3 levels), and decomposes the signal into multiple effective vibration sub-signals of different frequency bands. Each sub-signal corresponds to a specific frequency range. For example, the first level decomposes the high frequency band and the low frequency band, the second level further decomposes the low frequency band, and so on.

[0088] S306. Arrange the energy values ​​of the effective vibration sub-signals of each frequency band according to the frequency band to obtain the vibration feature vector; where, the frequency band represents the frequency range obtained by decomposing the signal after wavelet transform, such as high frequency band (100-200Hz), mid frequency band (20-100Hz), etc.; the effective vibration sub-signal refers to the signal of each frequency band decomposed from the effective vibration signal through wavelet transform, and each sub-signal contains the vibration energy characteristics of the corresponding frequency band; the energy value is used to represent the energy magnitude of the signal of each frequency band, which is obtained by calculating the root mean square value or power spectral density of the signal in that frequency band.

[0089] After extracting the effective features of the vibration signal segments, the corresponding frequency domain features are transformed into a computable vector form. Specifically, the monitoring system performs energy calculations on the effective vibration sub-signals for each frequency band.

[0090] For example, calculating the root mean square energy of a high-frequency sub-signal within a time window:

[0091]

[0092] Where x i denoted as the sampling point value of the sub-signal, and N as the number of sampling points.

[0093] After the calculation is completed, the system arranges the energy values ​​of each frequency band into a vector according to the frequency band from low to high (or from high to low), forming a vibration characteristic vector. For example, if the signal is decomposed into three frequency bands: low frequency (0-20Hz), mid frequency (20-50Hz), and high frequency (50-100Hz), then the vibration characteristic vector is [low frequency energy, mid frequency energy, high frequency energy], which comprehensively reflects the energy distribution characteristics of the vibration signal.

[0094] S307. Calculate the Euclidean distance between the vibration feature vectors corresponding to adjacent vibration signal segments.

[0095] Here, adjacent vibration signal segments represent two consecutive vibration signal segments in the time series, such as the nth and (n+1)th segments; Euclidean distance is used to measure the geometric distance between two vibration feature vectors in multidimensional space, reflecting the degree of difference in features between adjacent segments; the larger the distance, the more significant the feature change. The calculation formula is:

[0096]

[0097] Where v n,i and v n+1,i Let be the i-th component of the nth and (n+1)th eigenvectors, respectively, and m be the vector dimension.

[0098] After generating the vibration feature vectors, the temporal changes of the vibration signal feature vectors are analyzed. Specifically, the monitoring system traverses all vibration signal segments in chronological order and calculates the Euclidean distance for each pair of adjacent vibration feature vectors.

[0099] S308. Extract the spectrum data corresponding to each acoustic emission signal segment;

[0100] Based on the spectrum data, the frequency component with the highest amplitude in the acoustic emission signal is determined as the main frequency component, and the frequency component with the second highest amplitude is determined as the secondary frequency component.

[0101] Among them, the dominant frequency component refers to the frequency component with the highest amplitude in the spectrum data, representing the main energy concentration band of the acoustic emission signal. For example, if the amplitude of the 200Hz frequency is the largest in a certain segment, then 200Hz is the dominant frequency component of that segment. The secondary frequency component refers to the frequency component with the second highest amplitude in the spectrum data, which is an important auxiliary indicator of signal characteristics. For example, if the amplitude of the 150Hz frequency is second only to 200Hz, then it is the secondary frequency component.

[0102] After segmenting the acoustic emission signal, the frequency domain features corresponding to each segment are extracted. Specifically, the monitoring system performs a Fast Fourier Transform (FFT) on each acoustic emission signal segment, converting the time-domain signal into frequency-domain data and generating a spectrum. The system traverses all frequency points in the spectrum, identifying the frequency with the largest amplitude as the dominant frequency component, and then finding the frequency with the second largest amplitude as the secondary frequency component. For example, in the spectrum of a certain acoustic emission signal segment, the amplitude corresponding to the 180Hz frequency is 60mV, the amplitude corresponding to the 120Hz frequency is 45mV, and the amplitudes of other frequencies are all less than 45mV. Therefore, the dominant frequency component is 180Hz, and the secondary frequency component is 120Hz.

[0103] S309. Calculate the amplitude ratio of the dominant frequency component to the secondary frequency component to obtain the acoustic emission characteristic parameters;

[0104] Among them, the amplitude ratio represents the ratio of the amplitude of the main frequency component to the amplitude of the secondary frequency component, which is used to quantify the frequency characteristic distribution of the acoustic emission signal; the acoustic emission characteristic parameter refers to the signal characteristic quantity characterized by the amplitude ratio, which is used to reflect the degree of abnormality in the working state of the hob.

[0105] After determining the dominant and secondary frequency components, acoustic emission characteristic parameters are generated. Specifically, the monitoring system extracts the amplitudes of the dominant and secondary frequency components from the spectral data, calculates the amplitude ratio, and obtains the acoustic emission characteristic parameters. For example, if the dominant frequency component amplitude is 50mV and the secondary frequency component amplitude is 25mV, then the amplitude ratio is 2.0. The monitoring system generates corresponding acoustic emission characteristic parameters for each acoustic emission signal segment and stores them in chronological order.

[0106] S310. Based on the acoustic emission characteristic parameters arranged in time sequence, calculate the rate of change between the acoustic emission characteristic parameters corresponding to each adjacent acoustic emission signal segment.

[0107] Among them, temporal arrangement refers to arranging the acoustic emission characteristic parameters according to the acquisition time sequence of the signal segments to form time series data;

[0108] After generating the acoustic emission characteristic parameters, the dynamic changes of these parameters are quantified. Specifically, the monitoring system iterates through all acoustic emission characteristic parameters in chronological order, calculating the rate of change for each pair of adjacent parameters using the following formula:

[0109]

[0110] Among them, P i Let be the acoustic emission characteristic parameters corresponding to the i-th acoustic emission signal segment.

[0111] S311. Input two adjacent vibration signal segments and two adjacent acoustic emission signal segments into the data processing queue according to the time sequence.

[0112] After completing the calculation of the Euclidean distance of the vibration feature vector and the rate of change of the acoustic emission feature parameters, the monitoring system takes each group of adjacent vibration signal segments (the nth and n+1th segments) and their corresponding acoustic emission signal segments (timestamps correspond one-to-one) as a data group and inputs them into the data processing queue in chronological order.

[0113] S312. Compare the Euclidean distance with the preset Euclidean distance threshold, and compare the rate of change with the preset rate of change threshold;

[0114] After the signal segments are stored in the data processing queue, abnormal signal segments are initially screened.

[0115] The monitoring system retrieves data from each group of adjacent signal segments from the data processing queue, and obtains the Euclidean distance and rate of change for that group. The Euclidean distance is compared to a preset Euclidean distance threshold, and the rate of change is also compared to a preset rate of change threshold.

[0116] S313. When the Euclidean distance exceeds the preset Euclidean distance threshold, or / and the rate of change exceeds the preset rate of change threshold, obtain the vibration feature vector corresponding to the vibration signal segment with the later time sequence, and the acoustic emission feature parameters corresponding to the acoustic emission signal segment.

[0117] When the Euclidean distance or rate of change exceeds the corresponding threshold, the abnormal signal segment is located.

[0118] When the Euclidean distance between adjacent signal segments in a group exceeds a preset threshold, or the rate of change exceeds a preset threshold, the monitoring system determines that the later-timed vibration signal segment (the (n+1)th segment) and its corresponding acoustic emission signal segment in that group may be interference data. The vibration feature vector of the (n+1)th vibration signal segment and the feature parameters of the corresponding acoustic emission signal segment are extracted for further judgment.

[0119] S314. Determine whether the vibration feature vector exceeds the preset vibration feature vector range, or whether the acoustic emission feature parameter exceeds the preset acoustic emission feature parameter threshold.

[0120] After locating a possible abnormal signal segment, the subsequent abnormality verification process is initiated to avoid directly rejecting possible real abnormal signals.

[0121] The monitoring system first compares the feature vector of the later vibration signal segment with a preset range of vibration feature vectors. For example, if the feature vector is [15, 65, 25], and the lower limit of low-frequency energy is 20, then the vibration feature is determined to be out of range. At the same time, the system compares the corresponding acoustic emission feature parameters with a preset threshold. If the parameter is 2.8 (exceeding the upper limit of 2.5), then the acoustic emission feature is determined to be abnormal.

[0122] S315. If any or all of the judgment results are yes, the vibration signal segment and acoustic emission signal segment with the later timing sequence shall be retained.

[0123] The monitoring system uses "OR" logic for judgment, that is, if the vibration characteristic vector is out of range or the acoustic emission characteristic parameter is out of threshold, the signal segment is considered to be abnormal (including interference or actual damage).

[0124] If any judgment result in step S314 is "yes" (such as vibration characteristics exceeding the range, or acoustic emission parameters exceeding the threshold), the monitoring system considers that the signal segment with the later timing sequence may reflect the actual abnormality of the hob (such as wear or cracks), rather than simply external interference. In this case, the system retains the vibration signal segment and the acoustic emission signal segment in the temporary storage area without performing a rejection operation.

[0125] S316. The vibration signal segment and acoustic emission signal segment with the later timing sequence are identified as interference data segments and removed.

[0126] If all the judgment results in step S314 are "no", that is, the vibration feature vector does not exceed the preset range and the acoustic emission feature parameter does not exceed the preset threshold, the monitoring system determines that the signal segment with the later timing is an interference data segment.

[0127] At this point, the monitoring system removes the vibration signal segment and acoustic emission signal segment from the data processing queue and marks them as interference data segments. For example, if the Euclidean distance of a segment is 6.0 (exceeding the threshold of 5.0), but its vibration characteristic vector and acoustic emission parameters are within the normal range after inspection, the system will determine that the segment is a feature mutation caused by temporary sensor interference and remove it. The removal operation will simultaneously update the time sequence index of subsequent signal segments to ensure data continuity.

[0128] S317. Determine whether the vibration feature vector corresponding to the vibration signal segment exceeds the preset vibration feature vector range; after completing the removal of interference data, continuously monitor the characteristic anomalies of the vibration signal segment. Specifically, the monitoring system traverses all vibration signal segments that have not been removed and compares the vibration feature vector of each segment with the preset range. For example, if the feature vector of a certain vibration signal segment is [15, 65, 25], where the low-frequency energy 15 is lower than the preset lower limit 20 and the mid-frequency energy 65 is higher than the preset upper limit 60, then it is determined that the vector exceeds the normal range.

[0129] S318. When the vibration feature vector corresponding to the vibration signal segment exceeds the preset vibration feature vector range, the vibration signal segment is recorded as the first abnormal marker.

[0130] Steps S318 and S320 are similar to steps S206 and S207 in the above embodiments, and can be referred to the above description, so they will not be repeated here.

[0131] S319. Determine whether the acoustic emission characteristic parameter corresponding to the acoustic emission signal segment exceeds the preset acoustic emission characteristic parameter threshold.

[0132] After removing interfering data, the system continuously monitors for anomalies in the acoustic emission signal segments. Specifically, the monitoring system iterates through all remaining acoustic emission signal segments and compares the acoustic emission characteristic parameters of each segment with preset thresholds. For example, if a segment's parameter value is 2.8 (exceeding the upper limit of 2.5) or 0.5 (below the lower limit of 0.8), it is considered an anomaly. When a parameter is abnormal, the system generates a second anomaly marker, which includes: segment timestamp, specific parameter value (e.g., 3.0), and anomaly direction (upper limit exceeded).

[0133] S320. When the acoustic emission characteristic parameter corresponding to the acoustic emission signal segment exceeds the preset acoustic emission characteristic parameter threshold, the acoustic emission signal segment is recorded as a second abnormal marker.

[0134] S321. Obtain all first and second abnormal markers within the signal segment to be processed, the signal segment to be processed including the unprocessed vibration signal segment and acoustic emission signal segment after removing the interference data segment;

[0135] Among them, the signal segments to be processed refer to the vibration signal segments and acoustic emission signal segments remaining after removing interference data, including normal signal segments that are not marked as interference and possible abnormal signal segments.

[0136] After removing interference data and generating anomaly markers, the anomaly markers to be analyzed are summarized. Specifically, the monitoring system first determines the time window of the signal segment to be processed, and then extracts all first and second anomaly markers within that window from the anomaly database. For example, if the system sets the processing window to the duration of 10 cycles of the cutter head rotation, and the current cutter head rotation cycle is 20 seconds, then the window duration is 200 seconds, and the system will extract all anomaly markers within that 200 seconds. The extracted markers contain information such as the signal segment timestamp and characteristic parameter values ​​corresponding to each anomaly, so as to calculate the duration and number density of the anomalies in subsequent calculations.

[0137] S322. Calculate the duration of the first anomaly marker in the signal segment to be processed;

[0138] The number of occurrences of the second anomaly marker in the signal segment to be processed is counted, and the number density of the second anomaly marker per unit time is calculated.

[0139] The duration of the first anomaly marker refers to the time interval from the appearance of the first anomaly marker to the end of the last consecutive first anomaly marker. For example, the time span of three consecutive markers is 60 seconds. The preset duration is a time threshold set by the system to judge the validity of the anomaly's persistence, such as 30 seconds. If the duration exceeds this, the anomaly is considered persistent. The number density of the second anomaly marker refers to the number of times the second anomaly marker appears per unit time. The calculation formula is number density = number of markers / time window length. For example, if five markers appear within 10 seconds, the density is 0.5 times / second. The preset density threshold is an upper limit set by the system for the frequency of normal anomalies, such as 0.3 times / second. If the threshold is exceeded, the anomaly is considered frequent.

[0140] After acquiring the anomaly markers within the signal segment to be processed, the temporal and frequency characteristics of the anomaly signals are quantified. Specifically, the monitoring system first sorts the first anomaly markers by time, finds consecutively occurring anomaly segments, and calculates their duration. For example, if the first anomaly marker starts at 10:30:00 and ends at 10:30:45, the duration is 45 seconds. If the anomaly markers are not consecutive, the duration is calculated segment by segment. Simultaneously, the system counts the total number of second anomaly markers within the processing window and divides this count by the window duration to obtain the frequency density. For example, if the window duration is 50 seconds and there are 20 second anomaly markers, the density is 20 / 50 = 0.4 times / second.

[0141] S323. If the duration of the first abnormal marker exceeds a preset duration and the number density of the second abnormal marker exceeds a preset density threshold, it is determined that the cutter head of the tunnel boring machine is damaged and an early warning signal is issued.

[0142] After calculating the duration of the first anomaly marker and the quantity density of the second anomaly marker, the system comprehensively determines whether the hob is damaged and triggers an early warning. Specifically, the monitoring system simultaneously checks whether the duration of the first anomaly marker exceeds a preset duration and whether the quantity density of the second anomaly marker exceeds a preset density threshold. For example, if the duration is 45 seconds (exceeding the preset 40 seconds) and the quantity density is 0.4 times / second (exceeding the preset 0.3 times / second), the hob is determined to be damaged, and an early warning signal is immediately generated. The early warning signal includes information such as the hob number, damage type (e.g., cutter ring wear, crack), and anomaly start time. If only a single condition is met (e.g., the duration meets the standard but the density does not), the system continues to accumulate data and re-evaluate to avoid false alarms. The system improves the accuracy and reliability of hob damage monitoring through dual-condition cross-validation.

[0143] S324. If all judgment results are negative, then the current working status of the tunnel boring machine cutter head is normal.

[0144] By adopting the above technical solution, this embodiment achieves precise signal segmentation by introducing cutter head rotation speed and angular position information. Wavelet transform and spectral analysis are used to extract multi-band features of the vibration signal and frequency features of the acoustic emission signal, respectively. A dual verification mechanism is designed: first, abnormal signals are screened based on Euclidean distance and rate of change thresholds; then, it is determined whether the features exceed a preset range, avoiding the false deletion of genuine abnormal signals. Simultaneously, a cross-verification mechanism is established by combining the duration of vibration anomalies and the quantity density of acoustic emission anomalies, achieving more accurate hobbing damage monitoring and effectively reducing the false alarm rate.

[0145] The following describes the hobbing cutter damage monitoring system in the embodiments of this invention from the perspective of hardware processing. Please refer to [link / reference]. Figure 4 This is a schematic diagram of the physical device structure of the hobbing cutter damage monitoring system in this application embodiment.

[0146] It should be noted that, Figure 4 The structure of the hob damage monitoring system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0147] like Figure 4As shown, the electronic device includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in Read-Only Memory (ROM) 402 or a program loaded from storage portion 408 into Random Access Memory (RAM) 403, such as performing the methods described in the above embodiments. The Random Access Memory (RAM) 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0148] The following components are connected to the input / output (I / O) interface 405: an input section 406 including audio input devices, push-button switches, etc.; an output section 407 including displays, audio output devices, indicator lights, etc.; a storage section 408 including hard disks, etc.; and a communication section 409 including network interface cards such as LAN (Local Area Network) cards, modems, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output (I / O) interface 405 as needed. Removable media 411, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive 410 as needed so that computer programs read from them can be installed into the storage section 408 as needed.

[0149] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by the Central Processing Unit (CPU) 401, it performs the various functions defined in this application. It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this invention, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0150] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0151] Specifically, the cutterhead damage monitoring system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the tunnel boring machine cutterhead damage monitoring method provided in the above embodiment.

[0152] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the cutterhead damage monitoring system described in the above embodiments; or it may exist independently and not assembled into the cutterhead damage monitoring system. The storage medium carries one or more computer programs, which, when executed by a processor of the cutterhead damage monitoring system, cause the cutterhead damage monitoring system to implement the tunnel boring machine cutterhead damage monitoring method provided in the above embodiments.

[0153] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0154] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for monitoring cutterhead damage in a tunnel boring machine, characterized in that, The method, applied to a hob damage monitoring system, includes: The vibration signal and acoustic emission signal of the tunnel boring machine cutter are obtained, wherein the acoustic emission signal refers to the transient elastic wave generated when the tunnel boring machine cutter contacts and crushes the tunnel; The vibration signal is divided into multiple vibration signal segments, and the acoustic emission signal is divided into multiple acoustic emission signal segments. The vibration signal segments and the corresponding acoustic emission signal segments are time-synchronized with each other in the rotation cycle of the tunnel boring machine cutterhead. Based on a preset standard operating frequency, the vibration feature vectors corresponding to each vibration signal segment are extracted, and the Euclidean distance between the vibration feature vectors corresponding to adjacent vibration signal segments is calculated. The preset standard operating frequency refers to the frequency at which a single tunnel boring machine cutter makes a complete contact with and compacts the tunnel under the current tunnel boring machine operating conditions. Based on the spectral data corresponding to each of the acoustic emission signal segments, the acoustic emission characteristic parameters corresponding to each of the acoustic emission signal segments are determined, and the rate of change between the acoustic emission characteristic parameters corresponding to adjacent acoustic emission signal segments is calculated. The acoustic emission characteristic parameters refer to the amplitude ratio of the dominant frequency component to the secondary frequency component determined based on the spectral data. Two adjacent vibration signal segments and two adjacent acoustic emission signal segments are input into the data processing queue according to the time sequence. The Euclidean distance is compared with a preset Euclidean distance threshold, and the rate of change is compared with a preset rate of change threshold; When the Euclidean distance exceeds the preset Euclidean distance threshold, or / and the rate of change exceeds the preset rate of change threshold, the vibration feature vector corresponding to the vibration signal segment with the later time sequence and the acoustic emission feature parameters corresponding to the acoustic emission signal segment are obtained; Determine whether the vibration feature vector exceeds a preset vibration feature vector range, or whether the acoustic emission feature parameter exceeds a preset acoustic emission feature parameter threshold. If any or all of the judgment results are yes, the vibration signal segment and acoustic emission signal segment with the later timing sequence will be retained; If all the judgment results are negative, the vibration signal segment and acoustic emission signal segment with the later timing sequence are identified as interference data segments and removed. When the vibration feature vector corresponding to the vibration signal segment exceeds the preset vibration feature vector range, the vibration signal segment is recorded as a first anomaly marker. When the acoustic emission feature parameter corresponding to the acoustic emission signal segment exceeds the preset acoustic emission feature parameter threshold, the acoustic emission signal segment is recorded as a second anomaly marker. If the duration of the first abnormal marker exceeds a preset duration and the number density of the second abnormal marker exceeds a preset density threshold, the cutter head of the tunnel boring machine is determined to be damaged and an early warning signal is issued.

2. The method according to claim 1, characterized in that, If the duration of the first abnormal marker exceeds a preset duration and the number density of the second abnormal marker exceeds a preset density threshold, the shield machine cutterhead is determined to be damaged and an early warning signal is issued. Specifically, this includes: Obtain all first and second anomaly markers within the signal segment to be processed, wherein the signal segment to be processed includes the unprocessed vibration signal segment and acoustic emission signal segment after removing the interference data segment; Calculate the duration of the first anomaly marker in the signal segment to be processed; The number of occurrences of the second anomaly marker in the signal segment to be processed is counted, and the number density of the second anomaly marker per unit time is calculated. If the duration of the first abnormal marker exceeds a preset duration and the number density of the second abnormal marker exceeds a preset density threshold, the cutter head of the tunnel boring machine is determined to be damaged and an early warning signal is issued.

3. The method according to claim 1, characterized in that, The process of dividing the vibration signal into multiple vibration signal segments and the acoustic emission signal into multiple acoustic emission signal segments specifically includes: Obtain the real-time rotational speed and angular position information of the tunnel boring machine cutterhead; Based on the real-time rotation speed, calculate the rotation cycle required for the cutter head to complete one full rotation; Based on the rotation period and angular position information, the vibration signal is divided into multiple vibration signal segments of equal length, and each vibration signal segment contains a corresponding timestamp; Based on the rotation period and angular position information, the acoustic emission signal is divided into multiple acoustic emission signal segments of equal length. Each acoustic emission signal segment contains a corresponding timestamp, and the timestamps of the vibration signal segments correspond one-to-one.

4. The method according to claim 1, characterized in that, The step of extracting vibration feature vectors corresponding to each vibration signal segment based on a preset standard operating frequency, and calculating the Euclidean distance between the vibration feature vectors corresponding to adjacent vibration signal segments, specifically includes: Based on a preset standard operating frequency, the effective vibration signal is extracted from each vibration signal segment; The effective vibration signal is subjected to wavelet transform to obtain effective vibration sub-signals in multiple frequency bands; The energy values ​​of the effective vibratory sub-signals in each frequency band are arranged according to the frequency band to obtain the vibration feature vector; Calculate the Euclidean distance between the vibration feature vectors corresponding to adjacent vibration signal segments.

5. The method according to claim 1, characterized in that, The step of determining the acoustic emission characteristic parameters corresponding to each acoustic emission signal segment based on the spectral data corresponding to each of the acoustic emission signal segments, and calculating the rate of change between the acoustic emission characteristic parameters corresponding to adjacent acoustic emission signal segments, specifically includes: Extract the spectral data corresponding to each of the acoustic emission signal segments; Based on the spectrum data, the frequency component with the highest amplitude in the acoustic emission signal segment is determined as the main frequency component, and the frequency component with the second highest amplitude is determined as the secondary frequency component. The amplitude ratio of the dominant frequency component to the secondary frequency component is calculated to obtain the acoustic emission characteristic parameters; Based on the acoustic emission characteristic parameters arranged in time sequence, the rate of change between the acoustic emission characteristic parameters corresponding to each adjacent acoustic emission signal segment is calculated.

6. A hob damage monitoring system, characterized in that, The hob damage monitoring system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the hob damage monitoring system to perform the method as described in any one of claims 1-5.

7. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the hob damage monitoring system, the hob damage monitoring system performs the method as described in any one of claims 1-5.

8. A computer program product, characterized in that, When the computer program product is run on the hob damage monitoring system, the hob damage monitoring system performs the method as described in any one of claims 1-5.

Images