Fault simulation-based TBM hob eccentric wear identification method, system and device

Abstract

The invention provides a TBM hob eccentric wear identification method, system and device based on fault simulation, and relates to the technical field of fault identification, and the method comprises the steps: carrying out the hob eccentric wear fault simulation of a target TBM under the constraint of a preset test condition, and obtaining a target simulation record; performing multi-domain feature extraction on the eccentric wear time sequence signal to obtain a hob eccentric wear feature set; introducing a feature screening mechanism to obtain a target eccentric wear feature set; output information is obtained through the hob eccentric wear fault recognition model; whether the target eccentric wear failure rate in the output information reaches a preset failure rate threshold or not is judged; if yes, an eccentric wear fault early warning instruction is sent out to carry out tool changing treatment on the target TBM. According to the method and the device, the problem that the existing method cannot integrate the influence of the multi-factor coupling effect to detect and identify the hob eccentric wear fault under the actual working condition can be solved, the accuracy of identifying the hob eccentric wear fault is improved, and the effect of improving the working efficiency and the construction safety of the heading machine is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of fault identification, and in particular to a method, system and device for identifying eccentric wear of a TBM cutter based on fault simulation. Background Art

[0002] In tunnel excavation projects, tunnel boring machines (TBMs) are the main construction equipment, and the cutter, as a key component of the TBM, is in direct contact with the rock mass, responsible for crushing the rock and pushing the tunnel forward. Its performance and status directly affect the safety, efficiency and quality of construction. At present, abnormal damage of TBM cutters is one of the key issues affecting construction safety and efficiency. Existing research focuses on the normal wear of cutters, including mechanism analysis, experience summary, and data-driven model prediction. However, in engineering practice, the problem of abnormal damage of cutters, especially eccentric wear failure, is insufficiently studied, but its harmfulness cannot be ignored. Different from the regular characteristics of gradual consumption of the surface material of the cutter ring in normal wear, the abnormal damage of the cutter is complex and diverse. Eccentric wear failure is one of the most common and harmful fault types. It is usually caused by damage to the cutter bearing or foreign matter such as rock chips that hinders the rotation of the cutter shaft, resulting in the cutter ring only partially contacting the rock mass, which in turn changes the relative motion mode between the cutter and the rock mass from rolling to sliding, and the geometric shape of the contact area between the cutter ring and the rock mass also changes. If the eccentrically worn hob is not identified and handled in time, it will not only aggravate the wear of the adjacent hobs, but may also lead to premature failure of the hobs and even endanger the overall structure of the cutterhead, causing major construction safety hazards.

[0003] In summary, existing studies mostly focus on the interaction between a single eccentrically worn disc cutter and the rock mass, which makes it difficult to fully consider the comprehensive impact of the number, distribution and degree of eccentric wear on the overall load of the TBM. In addition, the results of indoor cutting experiments are difficult to accurately reflect the multi-factor coupling characteristics in actual construction conditions. In addition, since the monitoring and recording of eccentric wear faults at the construction site has not yet formed a systematic standard, the relevant data samples under actual working conditions are extremely scarce, which greatly limits the development of disc cutter fault detection and identification technology based on field data. Summary of the invention

[0004] The purpose of this application is to provide a TBM cutter eccentric wear identification method, system and device based on fault simulation, so as to solve the problem that existing research mostly focuses on the interaction between a single eccentrically worn cutter and rock mass, and it is difficult to fully consider the comprehensive impact of the number, distribution and degree of eccentric wear of the cutter on the overall load of the TBM, and the indoor cutting test results are difficult to accurately reflect the multi-factor coupling characteristics in actual construction conditions. In addition, since the monitoring and recording of eccentric wear faults at the construction site has not yet formed a systematic standard, the relevant data samples under actual working conditions are extremely scarce, which greatly limits the development of cutter fault detection and identification technology based on field data.

[0005] In view of the above problems, the present application provides a TBM cutter eccentric wear identification method, system and device based on fault simulation.

[0006] In the first aspect, the present application provides a TBM cutter eccentric wear identification method based on fault simulation, and the TBM cutter eccentric wear identification method based on fault simulation is implemented by a TBM cutter eccentric wear identification system based on fault simulation, wherein the TBM cutter eccentric wear identification method based on fault simulation includes: obtaining preset test conditions, and performing cutter eccentric wear fault simulation on a target TBM under the constraints of the preset test conditions to obtain a target simulation record; analyzing the target simulation record to obtain an eccentric wear timing signal, and performing multi-domain feature extraction on the eccentric wear timing signal to obtain a cutter eccentric wear feature set; introducing a feature screening mechanism to screen and analyze the cutter eccentric wear feature set to obtain a target eccentric wear feature set; using the target eccentric wear feature set as input information of a cutter eccentric wear fault identification model, and obtaining output information through the cutter eccentric wear fault identification model; judging whether the target eccentric wear fault rate in the output information reaches a predetermined fault rate threshold; if the target eccentric wear fault rate reaches the predetermined fault rate threshold, issuing an eccentric wear fault warning instruction; and performing a cutter change process on the target TBM based on the eccentric wear fault warning instruction.

[0007] In the second aspect, the present application also provides a TBM cutter eccentric wear identification system based on fault simulation, which is used to execute the TBM cutter eccentric wear identification method based on fault simulation as described in the first aspect, wherein the TBM cutter eccentric wear identification system based on fault simulation includes: an eccentric wear simulation module, which is used to obtain preset test conditions, and perform cutter eccentric wear fault simulation on the target TBM under the constraints of the preset test conditions to obtain a target simulation record; a feature extraction module, which is used to analyze the target simulation record to obtain an eccentric wear timing signal, and perform multi-domain feature extraction on the eccentric wear timing signal to obtain a cutter eccentric wear feature set; a feature screening module, which is used to extract the eccentric wear timing signal from multiple domains to obtain a cutter eccentric wear feature set; and a feature screening module, which is used to extract the eccentric wear timing signal from multiple domains to obtain a cutter eccentric wear feature set. A feature screening mechanism is used to screen and analyze the roller cutter eccentric wear feature set to obtain a target eccentric wear feature set; an eccentric wear identification module is used to use the target eccentric wear feature set as input information of a roller cutter eccentric wear fault identification model, and obtain output information through the roller cutter eccentric wear fault identification model; a failure rate judgment module is used to judge whether the target eccentric wear failure rate in the output information reaches a predetermined failure rate threshold; an eccentric wear warning module is used to issue an eccentric wear fault warning instruction if the target eccentric wear failure rate reaches the predetermined failure rate threshold; and a tool change execution module is used to perform tool change processing on the target TBM based on the eccentric wear fault warning instruction.

[0008] In the third aspect, the present application also provides a TBM cutter eccentric wear identification device based on fault simulation, which is used to execute the TBM cutter eccentric wear identification method based on fault simulation as described in the first aspect, wherein the TBM cutter eccentric wear identification device based on fault simulation includes: a cutter disc, wherein a plurality of grooves are distributed on the cutter disc; a cutter seat, wherein the cutter seat is installed to the plurality of grooves of the cutter disc by bolts; and a cutter, wherein the cutter is installed on the cutter seat.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: By obtaining preset test conditions, and simulating the roller cutter eccentric wear fault on the target TBM under the constraints of the preset test conditions, a target simulation record is obtained; the eccentric wear timing signal is obtained by analyzing the target simulation record, and multi-domain feature extraction is performed on the eccentric wear timing signal to obtain a roller cutter eccentric wear feature set; a feature screening mechanism is introduced to screen and analyze the roller cutter eccentric wear feature set to obtain a target eccentric wear feature set; the target eccentric wear feature set is used as input information of a roller cutter eccentric wear fault identification model, and output information is obtained through the roller cutter eccentric wear fault identification model; it is determined whether the target eccentric wear fault rate in the output information reaches a predetermined fault rate threshold; if the target eccentric wear fault rate reaches the predetermined fault rate threshold, an eccentric wear fault warning instruction is issued; and the target TBM is subjected to a cutter change process based on the eccentric wear fault warning instruction. That is to say, by simulating the eccentric wear fault of the TBM under preset conditions, analyzing the simulation results to obtain the eccentric wear timing signal, extracting and screening multi-domain features, and inputting the screened features into the recognition model, if the failure rate output by the model reaches the threshold, an early warning is issued and the cutter is replaced. By accurately simulating the eccentric wear fault of the TBM and effectively collecting and extracting the characteristic data of the eccentric wear fault of the TBM, and then machine learning and training to obtain the eccentric wear fault recognition model, it is helpful to accurately judge whether the TBM has eccentric wear fault and the degree of eccentric wear fault, so as to replace the damaged TBM in time. Furthermore, after accurately identifying the eccentric wear fault of the TBM, the problem of aggravated wear of adjacent TBMs, premature failure of TBMs, and even endangerment of the overall structure of the cutter disc caused by failure to timely discover the eccentric wear fault can be avoided, thereby extending the service life of the TBM and improving the utilization rate of the TBM. Furthermore, the construction interruption and equipment maintenance time caused by TBM failure can be reduced, the working efficiency and construction safety of the tunnel boring machine can be significantly improved, and important support can be provided for the intelligent development of TBM construction.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic diagram of the flow of a TBM cutter eccentric wear identification method based on fault simulation in this application; Figure 2 This is a schematic diagram of the structure of the TBM cutter eccentric wear identification system based on fault simulation in this application.

[0013] Description of reference numerals: Eccentric wear simulation module 11, feature extraction module 12, feature screening module 13, eccentric wear identification module 14, failure rate judgment module 15, eccentric wear warning module 16, tool change execution module 17. DETAILED DESCRIPTION

[0014] This application provides a method, system and device for identifying eccentric wear of TBM cutters based on fault simulation, which solves the problem that most existing studies focus on the interaction between a single eccentric wear cutter and the rock mass, and it is difficult to fully consider the comprehensive impact of the number, distribution and degree of eccentric wear of the cutters on the overall load of the TBM, and the indoor cutting test results are difficult to accurately reflect the multi-factor coupling characteristics in actual construction conditions. In addition, since the monitoring and recording of eccentric wear faults at the construction site have not yet formed a systematic standard, the relevant data samples under actual working conditions are extremely scarce, which greatly limits the development of cutter fault detection and identification technology based on field data. By accurately simulating the eccentric wear fault of the cutter and effectively collecting and extracting the characteristic data of the eccentric wear fault of the cutter, and then machine learning and training to obtain the eccentric wear fault identification model, it is helpful to accurately judge whether the cutter has eccentric wear fault and the degree of eccentric wear fault, so as to replace the damaged cutter in time. Furthermore, after accurately identifying the eccentric wear fault of the cutter, the problem of aggravated wear of adjacent cutters, premature failure of the cutter and even endangerment of the overall structure of the cutter disc due to failure to timely discover the eccentric wear fault can be avoided, thereby extending the service life of the cutter and improving the utilization rate of the cutter. Furthermore, it can reduce construction interruptions and equipment maintenance time caused by cutter failures, significantly improve the working efficiency and construction safety of the tunnel boring machine, and provide important support for the intelligent development of TBM construction.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] For example, please refer to the attached Figure 1 The present application provides a TBM cutter eccentric wear identification method based on fault simulation, wherein the method is applied to a TBM cutter eccentric wear identification system based on fault simulation, and the TBM cutter eccentric wear identification method based on fault simulation specifically comprises the following steps: Step P10: obtaining preset test conditions, and simulating the hob cutter eccentric wear fault on the target TBM under the constraints of the preset test conditions to obtain a target simulation record; Specifically, the preset test conditions are first determined. These conditions set a controllable environment for the simulation experiment, including geological conditions, excavation parameters, and the initial state of the cutter. Under these conditions, the target TBM is simulated for cutter eccentric wear failure. During the simulation, the cutter operates according to the set working conditions to reproduce the working conditions in actual construction. Through monitoring equipment and data acquisition systems, the operating parameters and performance of the cutter during the simulation are recorded in real time to form a target simulation record. These records contain detailed information such as cutter force, wear, and excavation speed, providing a basis for subsequent analysis. By analyzing these simulation records, the performance of the cutter under different working conditions can be evaluated, thereby optimizing the TBM design and construction plan and improving construction efficiency and safety.

[0017] Step P20: Analyze the target simulation record to obtain an eccentric wear timing signal, and perform multi-domain feature extraction on the eccentric wear timing signal to obtain a hob eccentric wear feature set; Specifically, the target simulation records are analyzed to obtain the eccentric wear timing signal, and multi-domain feature extraction is performed on the timing to obtain the eccentric wear feature set. This process aims to deeply mine the key information in the simulation data and provide a solid foundation for subsequent fault identification.

[0018] First, the target simulation record is carefully analyzed. This record contains various operating data of the hob during the simulation process. Through professional data analysis methods, the time series signals related to the eccentric wear of the hob are extracted from these data. This time series reflects the change of the eccentric wear state of the hob during the simulation process and is the key clue to analyze the performance of the hob. Then, multi-domain feature extraction is performed on the extracted eccentric wear time series signal. This means that it is necessary not only to analyze the amplitude, frequency and other characteristics of the signal from the time domain perspective, but also to expand to multiple dimensions such as the frequency domain and the time-frequency domain to fully capture the characteristics of the signal. In the time domain, the periodicity and trend changes of the signal can be observed; in the frequency domain, the frequency distribution of the signal can be analyzed to understand the proportion of different frequency components; the time-frequency domain analysis can consider the time and frequency factors at the same time and describe the dynamic characteristics of the signal more accurately. Through these multi-domain analyses, a series of features related to eccentric wear are collected, which together constitute the eccentric wear feature set. Among them, each feature reflects the characteristics of the eccentric wear of the hob from different aspects, providing rich input information for the subsequent fault identification model. Therefore, this process is a key step in achieving accurate fault identification. Through the comprehensive collection of multi-domain features, the state of hob eccentric wear can be more accurately characterized, thereby improving the accuracy and reliability of fault identification.

[0019] In summary, the eccentric wear time series signal is obtained by analyzing the target simulation records, and multi-domain feature extraction is performed to form the cutter eccentric wear feature set, which lays the foundation for the accurate identification of cutter eccentric wear faults and helps to improve the safety and efficiency of TBM construction.

[0020] Step P30: introducing a feature screening mechanism to screen and analyze the hob eccentric wear feature set to obtain a target eccentric wear feature set; Specifically, after obtaining the eccentric wear feature set containing rich information, in order to improve the efficiency and accuracy of subsequent analysis, these features need to be screened. This process is achieved by introducing a feature screening mechanism, the purpose of which is to select the most representative and influential features for the identification of hob eccentric wear faults from a large number of features, thereby forming a target eccentric wear feature set, which provides key input for establishing an efficient and accurate fault identification model.

[0021] First, the collected eccentric wear feature sets are comprehensively reviewed. These feature sets cover various parameters obtained from multi-domain analysis. Although they are theoretically related to hob eccentric wear, in practical applications, some features may contribute little to fault identification, or even introduce noise, affecting the performance of the model. Therefore, an effective screening mechanism is needed to distinguish the importance of these features. Then, the eccentric wear feature set is screened and analyzed using methods such as statistical analysis and machine learning algorithms. For example, the correlation coefficient between the feature and the eccentric wear fault can be calculated to screen out the features that are highly correlated with the fault; or feature importance evaluation methods, such as feature importance ranking based on decision tree models, can be used to determine which features play a key role in predicting eccentric wear faults. In addition, dimensionality reduction techniques, such as principal component analysis (PCA), can be used to remove redundant features, retain the main components, and further streamline the feature set. Through these screening and analysis steps, irrelevant or redundant features can be effectively eliminated, leaving the features that are truly valuable for fault identification. Finally, the screened features are combined to form the target eccentric wear feature set. This feature set is more refined and highlights the features closely related to the hob eccentric wear fault, providing high-quality data support for the subsequent construction of the fault identification model, which helps to improve the recognition accuracy and generalization ability of the model.

[0022] In summary, the feature screening mechanism is introduced to screen and analyze the eccentric wear feature set to obtain the target eccentric wear feature set. This process is crucial to improving the efficiency and accuracy of hob eccentric wear fault identification and can ensure that the fault identification model is more reliable and effective in practical applications.

[0023] Step P40: using the target eccentric wear feature set as input information of a roller cutter eccentric wear fault identification model, and obtaining output information through the roller cutter eccentric wear fault identification model; Specifically, the target eccentric wear feature set is input into the cutter eccentric wear fault identification model to obtain the output information of the model. This process is a key link in achieving accurate diagnosis of cutter eccentric wear fault. It aims to transform the feature set into results with clear diagnostic significance through model analysis and processing, thereby providing decision support for TBM maintenance and operation.

[0024] First, prepare the selected target eccentric wear feature sets. These feature sets are obtained through in-depth analysis of simulation records and multi-domain feature extraction in the early stage, and then refined by feature screening mechanism. They contain information that is crucial to the identification of hob eccentric wear faults. Then, these feature sets are used as input information and input into a specially constructed hob eccentric wear fault identification model. The model is trained based on a large amount of sample data and can identify and understand the complex relationship between input features and hob eccentric wear faults. Inside the model, the input feature set will go through a series of calculation and analysis processes, including but not limited to the evaluation of feature weights, pattern matching, and calculation of fault probabilities. Through these complex operations, the model can comprehensively evaluate the eccentric wear state of the hob. Next, the model will generate output information, which is usually the diagnosis result of the hob eccentric wear fault, which may include the probability of fault occurrence, the severity level of the fault, or the specific fault type. These output information are the model's interpretation and judgment of the input feature set, which provides a direct basis for subsequent decision-making. Therefore, this process is a key step in converting abstract feature data into specific and practical diagnostic results. Through the intelligent analysis of the model, fault identification is made more scientific and accurate.

[0025] In summary, by inputting the target eccentric wear feature set into the cutter eccentric wear fault identification model and obtaining the output information, the transformation from feature data to fault diagnosis results is realized, which provides strong technical support for the maintenance and management of TBM cutters, helps to timely discover and deal with cutter eccentric wear faults, and ensures the smooth progress of tunnel excavation projects.

[0026] Step P50: determining whether the target eccentric wear failure rate in the output information reaches a predetermined failure rate threshold; Step P60: If the target eccentric wear failure rate reaches the predetermined failure rate threshold, issuing an eccentric wear failure warning instruction; Step P70: Performing a tool change process on the target TBM based on the eccentric wear fault warning instruction.

[0027] Specifically, in the process of identifying the eccentric wear fault of the hob, the target eccentric wear fault rate in the output information of the hob eccentric wear fault identification model is first judged to see whether it has reached the preset fault rate threshold. This threshold is determined based on actual engineering experience and safety standards, and is used to distinguish between normal wear and fault status of the hob. If the target eccentric wear fault rate does not reach the threshold, it is considered that the hob is currently within an acceptable wear range and no special measures are required; on the contrary, if it reaches or exceeds the threshold, it means that the hob may have a more serious eccentric wear fault and needs further processing. Then, when it is confirmed that the target eccentric wear fault rate has reached the predetermined fault rate threshold, an eccentric wear fault warning instruction is issued. The warning instruction is a signal used to notify the operator or the automatic control system that there is a potential failure risk of the hob. The issuance of the warning instruction is the start signal of the fault handling process, triggering a series of subsequent maintenance operations to ensure that the fault can be responded to in a timely manner. Finally, the target TBM is replaced based on the eccentric wear fault warning instruction. Cutter replacement is a practical maintenance operation, the purpose of which is to replace severely worn or faulty cutters with new ones, thereby restoring the normal excavation capacity of the TBM. This treatment measure is part of preventive maintenance. By replacing faulty cutters in a timely manner, further expansion of the fault can be avoided, the impact on the overall performance of the TBM can be reduced, and the continuity and safety of the tunnel excavation project can be ensured.

[0028] In summary, from the judgment of the failure rate to the issuance of early warning instructions, and then to the final cutter change processing, each link is closely linked to ensure the stable operation of the TBM during the excavation process and effectively reduce the construction risks caused by eccentric cutter wear failure.

[0029] Furthermore, the present application comprises the following steps: Use sand as the upper stratum; The crushed soft rock is taken as the underlying stratum; forming a composite stratum based on the upper stratum and the lower stratum, and using the composite stratum as a preset geological condition; Get the preset fault ratio; Get the preset excavation mode; The preset test conditions are formed based on the preset geological conditions, the preset fault ratio and the preset excavation mode.

[0030] Specifically, first, sand is set as the upper stratum, which is a common stratum material with certain water permeability and low bearing capacity. Then, the crushed soft rock is set as the lower stratum. This rock is relatively easy to crush and together with the sand layer, it constitutes a stratum structure with specific engineering characteristics. Then, a composite stratum is constructed based on these two strata. The composite stratum simulates the complex geological environment that may be encountered in actual tunnel excavation, and it is used as a preset geological condition to provide a background close to the actual working conditions for subsequent tests. The geological conditions of the exemplary eccentric wear fault simulation test are a composite stratum with an upper layer of sand and a lower layer of crushed soft rock. The data acquisition system records parameters including cutter head speed, propulsion speed, cutter head torque and thrust at a sampling frequency of 1Hz. The specific process of the test includes: first, the upper soft and lower hard composite stratum is filled in the prepared rock box, and then the test bench is adjusted and the cutter head is assembled. When assembling the cutter head, the faulty rollers are arranged according to the different fault ratios set. After completing these steps, the console selects the full-section excavation mode and sets the cutter head speed and propulsion speed.

[0031] Obtain the preset fault ratio, which is predetermined according to the research purpose or engineering experience, and is used to simulate different degrees of eccentric wear failure of the cutter in the test, so as to study the impact of different fault degrees on the TBM excavation performance. For example, the test group of the simulation test includes different eccentric wear failure rates, where the ratios are 0%, 25%, 50% and 75% respectively. At the same time, obtain the preset excavation mode, which includes the settings of parameters such as the cutter head speed and the propulsion speed, which directly affect the excavation efficiency of the TBM and the force of the cutter.

[0032] Finally, the preset geological conditions, preset fault ratios and preset excavation modes are comprehensively considered to form complete preset test conditions. These conditions together constitute a control variable, ensuring that the test is carried out under a unified standard, making the test results comparable and reliable, and providing an accurate test basis for studying the eccentric wear of the cutter and its impact on the excavation performance of the TBM.

[0033] Furthermore, the present application comprises the following steps: Extracting a thrust simulation timing signal from the target simulation record, and using the thrust simulation timing signal as the eccentric wear timing signal; Reading a predetermined time domain feature, and extracting a time domain feature of the eccentric wear timing signal based on the predetermined time domain feature to obtain a first time domain feature set; Reading a predetermined frequency domain feature, and extracting a frequency domain feature of a first eccentric wear signal spectrum obtained after fast Fourier transforming the eccentric wear time series signal based on the predetermined frequency domain feature, to obtain a first frequency domain feature set; Retrieving a predetermined time-domain and frequency-domain feature extraction strategy, and obtaining a first time-domain and frequency-domain feature set of the eccentric wear timing signal according to the predetermined time-domain and frequency-domain feature extraction strategy; The roller cutter eccentric wear feature set is constructed based on the first time domain feature set, the first frequency domain feature set and the first time domain and frequency domain feature set.

[0034] Specifically, first, the thrust simulation time series signal is extracted from the target simulation record and used as the representative of the eccentric wear time series signal. This is because the thrust signal can directly reflect the force of the roller cutter during the excavation process and is an important basis for evaluating the eccentric wear state of the roller cutter. Next, the predetermined time domain features are read. The time domain features include mean value, standard deviation, root mean square, root square amplitude, peak value, skewness, kurtosis, waveform factor, peak factor, pulse factor, margin factor and energy, which can provide information about the overall trend, discrete degree, periodicity and morphology of the parameters, that is, they can reflect the basic characteristics of the signal in the time dimension. Based on these predetermined time domain features, the time domain features of the eccentric wear time series signal are extracted to obtain the first time domain feature set, which provides key information on the time series for subsequent analysis. Then, the predetermined frequency domain features are read, and the eccentric wear time series signal is fast Fourier transformed to convert it from the time domain to the frequency domain to obtain the first eccentric wear signal spectrum. Based on the predetermined frequency domain features, the frequency domain features of this spectrum are extracted to obtain the first frequency domain feature set, which provides data support for analyzing the frequency characteristics of the signal. Exemplary frequency domain features include centroid frequency, average frequency, frequency standard deviation, and root mean square frequency, which are helpful in understanding the frequency distribution of the signal.

[0035] In addition, the predetermined time-domain and frequency-domain feature extraction strategy is called. This strategy comprehensively considers the correlation characteristics of the signal in the time domain and frequency domain. According to this strategy, the first time-domain and frequency-domain feature set of the eccentric wear timing signal is obtained. This feature set integrates the information of the two dimensions of time and frequency, and can more comprehensively describe the characteristics of the signal. For example, the time-domain and frequency-domain features are decomposed into two layers of wavelet packets by using the db4 wavelet basis function to decompose the tunneling parameters, obtain four sub-band signals, and extract the average energy of the wavelet packet coefficients of each sub-band as the feature parameter, thereby obtaining four time-frequency domain features.

[0036] Finally, based on the first time domain feature set, the first frequency domain feature set, and the first time domain frequency domain feature set, the features in these three sets are integrated to form a complete eccentric wear feature set. This eccentric wear feature set contains features extracted from different angles, providing a rich and comprehensive data basis for subsequent fault identification and analysis, and helping to more accurately identify and evaluate the eccentric wear fault state of the hob.

[0037] Furthermore, the present application comprises the following steps: Performing a 2-layer wavelet packet decomposition on the eccentric wear time series signal based on the db4 wavelet basis function to obtain an eccentric wear signal decomposition result, wherein the eccentric wear signal decomposition result includes four sub-band signals; Extracting any sub-band signal from the four sub-band signals, and obtaining average energy of any wavelet packet coefficients of the arbitrary sub-band signal; The first time-domain and frequency-domain feature set is established based on the average energy of the arbitrary wavelet packet coefficients.

[0038] Specifically, firstly, the eccentric wear timing signal is decomposed into two layers of wavelet packets based on the db4 wavelet basis function. This process decomposes the signal into multiple sub-band signals, and specifically obtains four sub-band signals. These four sub-band signals represent the characteristics of the signal in different frequency bands, respectively, and provide a basis for subsequent feature extraction. Then, any sub-band signal is extracted from these four sub-band signals, and the average energy of any wavelet packet coefficient of the sub-band signal is calculated. The average energy of the wavelet packet coefficient is obtained by calculating the sum of the squares of each wavelet packet coefficient in the sub-band signal and then calculating its average value, which reflects the energy distribution of the signal in the frequency band. Finally, based on the calculated average energy of any wavelet packet coefficient, the first time domain and frequency domain feature set is formed. This feature set integrates the information of the time domain and frequency domain, can more comprehensively describe the characteristics of the eccentric wear signal, and provides important data support for subsequent fault identification and analysis.

[0039] Furthermore, the present application comprises the following steps: Extracting a torque simulation timing signal from the target simulation record, and using the torque simulation timing signal as the eccentric wear timing signal; Extracting and obtaining a second time domain feature set of the eccentric wear timing signal based on the predetermined time domain feature; A second frequency domain feature set of a second eccentric wear signal spectrum obtained by fast Fourier transforming the eccentric wear time series signal is extracted based on the predetermined frequency domain feature; Obtaining a second time-domain and frequency-domain feature set of the eccentric wear timing signal according to the predetermined time-domain and frequency-domain feature extraction strategy; The second time domain feature set, the second frequency domain feature set and the second time domain and frequency domain feature set are added to the roller cutter eccentric wear feature set.

[0040] Specifically, first, the torque simulation time series signal is extracted from the target simulation record and used as another important data source of the eccentric wear time series signal. The torque time series signal can reflect the change of the torsional torque that the roller cutter bears during the excavation process, and is one of the key indicators for evaluating the eccentric wear state of the roller cutter. Then, based on the predetermined time domain features, the time domain features of the torque simulation time series signal are extracted. These features may include the mean, variance, peak value, etc. of the signal, so as to obtain the second time domain feature set, which provides detailed information on the time series for analyzing the eccentric wear state of the roller cutter. Then, based on the predetermined frequency domain features, the torque simulation time series signal is fast Fourier transformed and converted into a frequency domain signal to obtain the second eccentric wear signal spectrum. By extracting the frequency domain features of the spectrum, such as calculating the center frequency and bandwidth of the spectrum, the second frequency domain feature set is obtained, which further enriches the description of the eccentric wear state of the roller cutter, especially the information on the frequency distribution. In addition, according to the predetermined time domain and frequency domain feature extraction strategy, the torque simulation time series signal is comprehensively analyzed to obtain the second time domain and frequency domain feature set. This feature set combines the features of the time domain and frequency domain, and can more comprehensively reflect the changes in the torque signal at different times and frequencies, providing a richer data dimension for fault identification.

[0041] Finally, the second time domain feature set, the second frequency domain feature set, and the second time domain frequency domain feature set are integrated into the existing eccentric wear feature set. In this way, the eccentric wear feature set not only contains the relevant features of the thrust signal, but also adds the multi-dimensional features of the torque signal, making the entire feature set more comprehensive and rich, providing more powerful data support for the subsequent identification and analysis of hob eccentric wear faults, and helping to improve the accuracy and reliability of fault diagnosis.

[0042] Furthermore, the present application includes the following steps: the feature screening mechanism refers to a mechanism for performing correlation screening on the eccentric wear feature set based on a predetermined correlation analysis method, and the predetermined correlation analysis method includes a Pearson correlation analysis method and a copula entropy theory analysis method.

[0043] Specifically, first of all, the core of the feature screening mechanism is to use the predetermined correlation analysis method to screen the eccentric wear feature set. This process aims to identify and retain the features that are most relevant to the diagnosis of hob eccentric wear fault, thereby improving the efficiency and accuracy of the fault identification model. Specifically, the predetermined correlation analysis methods include the Pearson correlation analysis method and the copula entropy theory analysis method, which evaluate the degree of correlation between features and faults from different perspectives.

[0044] Next, the Pearson correlation analysis method measures the linear correlation between the features and the eccentric wear failure rate by calculating the Pearson correlation coefficient between them. The value range of the correlation coefficient is between -1 and 1. The closer the value is to 1 or -1, the stronger the linear relationship between the feature and the failure rate; the closer the value is to 0, the weaker the linear relationship. In this way, features with strong linear correlation with the eccentric wear failure rate can be screened out, providing direct linear clues for fault diagnosis. Among them, the Pearson correlation analysis calculates the Pearson correlation coefficient between the extracted features and the eccentric wear failure rate. The results show that there is a strong linear correlation between the frequency domain and time-frequency domain features and the fault eccentric wear rate, and the correlation coefficient values ​​are all over 0.5. However, for some time domain features, such as skewness, kurtosis, waveform factor, peak factor, margin factor, pulse factor and other 12 features, the absolute value of the correlation coefficient is less than 0.2, or close to 0.2, indicating that the linear relationship between these features and the eccentric wear failure rate is weak or even non-existent.

[0045] In addition, the copula entropy theory analysis method focuses on evaluating the nonlinear correlation between features and faults. It reveals the complex nonlinear relationship between the features and the fault state by calculating the copula value between the features and the fault state. This method can capture nonlinear associations that may be overlooked in the Pearson correlation analysis, thereby more comprehensively understanding the intrinsic connection between features and faults. Among them, the Copula entropy theory calculates the Copula value of the extracted features and the eccentric wear failure rate. The results show that there is a complex nonlinear relationship between the features and the fault state in the frequency domain, time-frequency domain, and time domain. Only the waveform factor, a time domain feature, still shows a very low level of nonlinear correlation. Therefore, the effective features finally screened out can be used to identify the eccentric wear failure rate of the hob.

[0046] Finally, the two predetermined correlation analysis methods are used in combination to comprehensively screen the eccentric wear feature set. The features that show strong linear correlation in the Pearson correlation analysis and significant nonlinear correlation in the copula entropy theory analysis are retained to form the target eccentric wear feature set. This target feature set is concise and efficient, laying a solid foundation for building an accurate hob eccentric wear fault identification model and helping to improve the model's sensitivity and accuracy in fault diagnosis.

[0047] Furthermore, the present application comprises the following steps: Matching the eccentric wear failure rate corresponding to the eccentric wear timing signal in the target simulation record; Based on the Stacking ensemble learning principle, ensemble learning training is performed on the training data group formed according to the eccentric wear feature set and the eccentric wear failure rate to obtain the hob eccentric wear fault identification model.

[0048] Specifically, first, the eccentric wear failure rate corresponding to the eccentric wear timing signal is accurately matched in the target simulation record. This process is to find the failure rate indicator that matches the eccentric wear timing signal by analyzing the data in the simulation record, which directly reflects the degree of eccentric wear of the hob. Next, based on the principle of Stacking ensemble learning, this is an advanced machine learning method that combines the advantages of multiple different models to improve the accuracy and stability of prediction. Specifically, the eccentric wear feature set and the corresponding eccentric wear failure rate are used to form a training data set, which contains rich feature information and accurate fault labels, providing a solid foundation for model training. Then, these training data sets are trained by ensemble learning. During the training process, the Stacking method first trains multiple base models, such as decision trees and support vector machines, each of which learns the rules in the data from different perspectives. The prediction results of these base models are then used as new features and input into a meta-model, which is usually a simple model such as logistic regression. It is responsible for integrating the prediction results of the base models and outputting the final fault identification results. In this way, Stacking ensemble learning can fully utilize the advantages of each base model while reducing the bias and variance problems that may exist in a single model.

[0049] Finally, after ensemble learning training, a disc cutter eccentric wear fault identification model was obtained. This model can accurately predict the disc cutter eccentric wear failure rate based on the input eccentric wear feature set, providing scientific decision support for TBM maintenance and operation. Through this training method based on the Stacking ensemble learning principle, the obtained model not only has high prediction accuracy, but also can better adapt to different working conditions and data changes, improving the practicality and reliability of the model.

[0050] Furthermore, the present application comprises the following steps: extracting a first base model from predetermined base models; Performing machine learning on the first data group in the training data group using the first base model after hyperparameter optimization to obtain a first target base model; Acquire a predetermined meta-model, and integrate it with the first target base model to obtain the hob cutter eccentric wear fault identification model; The predetermined base models include at least a K-nearest neighbor model, a random forest model, a support vector classification model and a multivariate perceptron model.

[0051] Specifically, first, the first base model is extracted from the predetermined base model set. These base models are the basis for building an integrated learning model, including K-nearest neighbor model, random forest model, support vector classification model and multivariate perceptron model, etc. These models each have unique algorithms and advantages, and can analyze and predict data from different angles.

[0052] Next, the extracted first base model is subjected to hyperparameter optimization. Hyperparameter optimization is to improve the performance of the model by adjusting the parameter settings of the model, such as the number of neighbors in the K-nearest neighbor model, the number and depth of trees in the random forest model, etc. The optimized first base model can better adapt to the training data and improve the accuracy of prediction. Then, the first data group in the training data group is machine learned using the optimized first base model. The training process includes the hyperparameter optimization of the base model. The hyperparameter of the KNN model contains only one parameter, namely the number of neighbors (n_neighbors). When the number of neighbors is 7, the classification accuracy of the KNN model reaches the highest. For the RF model, the best performance is obtained by setting the number of decision trees (n_estimators) to 40 and the maximum depth of each tree (max_depth) to 4. For the SVC model, the best combination is found by adjusting the penalty parameter (C) and kernel width parameter (gamma) of the Gaussian kernel. When the penalty parameter is set to 1000 and the kernel width parameter is set to 0.001, the accuracy of the SVC model reaches the best. The MLP model achieved an accuracy of 88.16% in both single and double hidden layer configurations when the number of neurons was set to 60 and Adam was chosen as the solver. On the other hand, in the double hidden layer configuration, when the number of neurons was set to (40, 40) and the Adam solver was used, the accuracy slightly decreased to 88.05%, which is slightly lower than the accuracy of the single hidden layer configuration. Logistic regression has a hyperparameter, the penalty coefficient (CLR). When the value of CLR was set to 1.0, the model achieved the best classification performance with an accuracy of 91.69%. This process involves the model learning and training the data in order to enable the model to recognize patterns and regularities in the data and make accurate predictions about unknown data. Through this learning process, the first target base model is obtained, which has the ability to make predictions for a specific data set.

[0053] Next, obtain the predetermined meta-model. The meta-model is a high-level model in ensemble learning, which is responsible for integrating the outputs of each base model and making the final decision. For example, the meta-model is selected to use the logistic regression model (LR). The selection and design of the meta-model is crucial to the effect of ensemble learning.

[0054] Finally, the first target base model is combined with the meta-model to obtain the final disc cutter eccentric wear fault identification model. This model integrates the advantages of multiple base models and achieves high-precision identification of disc cutter eccentric wear faults through the coordination of the meta-model. This integration method not only improves the prediction ability of the model, but also enhances the stability and generalization ability of the model, so that it can be better applied to actual engineering scenarios and provide reliable fault warning and diagnosis support for TBM maintenance and operation.

[0055] In summary, the TBM cutter eccentric wear identification method based on fault simulation provided by the present application has the following technical effects: One or more technical solutions provided in this application have at least the following technical effects or advantages: By obtaining preset test conditions, and simulating the roller cutter eccentric wear fault on the target TBM under the constraints of the preset test conditions, a target simulation record is obtained; the eccentric wear timing signal is obtained by analyzing the target simulation record, and multi-domain feature extraction is performed on the eccentric wear timing signal to obtain a roller cutter eccentric wear feature set; a feature screening mechanism is introduced to screen and analyze the roller cutter eccentric wear feature set to obtain a target eccentric wear feature set; the target eccentric wear feature set is used as input information of a roller cutter eccentric wear fault identification model, and output information is obtained through the roller cutter eccentric wear fault identification model; it is determined whether the target eccentric wear fault rate in the output information reaches a predetermined fault rate threshold; if the target eccentric wear fault rate reaches the predetermined fault rate threshold, an eccentric wear fault warning instruction is issued; and the target TBM is subjected to a cutter change process based on the eccentric wear fault warning instruction. That is to say, by simulating the eccentric wear fault of the TBM under preset conditions, analyzing the simulation results to obtain the eccentric wear timing signal, extracting and screening multi-domain features, and inputting the screened features into the recognition model, if the failure rate output by the model reaches the threshold, an early warning is issued and the cutter is replaced. By accurately simulating the eccentric wear fault of the TBM and effectively collecting and extracting the characteristic data of the eccentric wear fault of the TBM, and then machine learning and training to obtain the eccentric wear fault recognition model, it is helpful to accurately judge whether the TBM has eccentric wear fault and the degree of eccentric wear fault, so as to replace the damaged TBM in time. Furthermore, after accurately identifying the eccentric wear fault of the TBM, the problem of aggravated wear of adjacent TBMs, premature failure of TBMs, and even endangerment of the overall structure of the cutter disc caused by failure to timely discover the eccentric wear fault can be avoided, thereby extending the service life of the TBM and improving the utilization rate of the TBM. Furthermore, the construction interruption and equipment maintenance time caused by TBM failure can be reduced, the working efficiency and construction safety of the tunnel boring machine can be significantly improved, and important support can be provided for the intelligent development of TBM construction.

[0056] Embodiment 2: Based on the same inventive concept as the TBM cutter eccentric wear identification method based on fault simulation in the above embodiment, the present application also provides a TBM cutter eccentric wear identification system based on fault simulation, please refer to the attached Figure 2 The TBM cutter eccentric wear identification system based on fault simulation includes: The eccentric wear simulation module 11 is used to obtain preset test conditions, and simulate the eccentric wear fault of the cutter on the target TBM under the constraints of the preset test conditions to obtain a target simulation record; A feature extraction module 12 is used to analyze the target simulation record to obtain an eccentric wear timing signal, and perform multi-domain feature extraction on the eccentric wear timing signal to obtain a hob eccentric wear feature set; A feature screening module 13 is used to introduce a feature screening mechanism to screen and analyze the hob eccentric wear feature set to obtain a target eccentric wear feature set; An eccentric wear identification module 14, used for using the target eccentric wear feature set as input information of a roller cutter eccentric wear fault identification model, and obtaining output information through the roller cutter eccentric wear fault identification model; A failure rate determination module 15 is used to determine whether the target eccentric wear failure rate in the output information reaches a predetermined failure rate threshold; An eccentric wear warning module 16 is used to issue an eccentric wear fault warning instruction if the target eccentric wear fault rate reaches the predetermined fault rate threshold; The tool change execution module 17 is used to perform a tool change process on the target TBM based on the eccentric wear fault warning instruction.

[0057] Furthermore, the eccentric wear simulation module 11 in the TBM cutter eccentric wear identification system based on fault simulation is also used for: Use sand as the upper stratum; The crushed soft rock is taken as the underlying stratum; forming a composite stratum based on the upper stratum and the lower stratum, and using the composite stratum as a preset geological condition; Get the preset fault ratio; Get the preset excavation mode; The preset test conditions are formed based on the preset geological conditions, the preset fault ratio and the preset excavation mode.

[0058] Furthermore, the feature extraction module 12 in the fault simulation-based TBM cutter eccentric wear identification system is also used for: Extracting a thrust simulation timing signal from the target simulation record, and using the thrust simulation timing signal as the eccentric wear timing signal; Reading a predetermined time domain feature, and extracting a time domain feature of the eccentric wear timing signal based on the predetermined time domain feature to obtain a first time domain feature set; Reading a predetermined frequency domain feature, and extracting a frequency domain feature of a first eccentric wear signal spectrum obtained after fast Fourier transforming the eccentric wear time series signal based on the predetermined frequency domain feature, to obtain a first frequency domain feature set; Retrieving a predetermined time-domain and frequency-domain feature extraction strategy, and obtaining a first time-domain and frequency-domain feature set of the eccentric wear timing signal according to the predetermined time-domain and frequency-domain feature extraction strategy; The roller cutter eccentric wear feature set is constructed based on the first time domain feature set, the first frequency domain feature set and the first time domain and frequency domain feature set.

[0059] Furthermore, the feature extraction module 12 in the fault simulation-based TBM cutter eccentric wear identification system is also used for: Performing a 2-layer wavelet packet decomposition on the eccentric wear time series signal based on the db4 wavelet basis function to obtain an eccentric wear signal decomposition result, wherein the eccentric wear signal decomposition result includes four sub-band signals; Extracting any sub-band signal from the four sub-band signals, and obtaining average energy of any wavelet packet coefficients of the arbitrary sub-band signal; The first time-domain and frequency-domain feature set is established based on the average energy of the arbitrary wavelet packet coefficients.

[0060] Furthermore, the feature extraction module 12 in the fault simulation-based TBM cutter eccentric wear identification system is also used for: Extracting a torque simulation timing signal from the target simulation record, and using the torque simulation timing signal as the eccentric wear timing signal; Extracting and obtaining a second time domain feature set of the eccentric wear timing signal based on the predetermined time domain feature; A second frequency domain feature set of a second eccentric wear signal spectrum obtained by fast Fourier transforming the eccentric wear time series signal is extracted based on the predetermined frequency domain feature; Obtaining a second time-domain and frequency-domain feature set of the eccentric wear timing signal according to the predetermined time-domain and frequency-domain feature extraction strategy; The second time domain feature set, the second frequency domain feature set and the second time domain and frequency domain feature set are added to the roller cutter eccentric wear feature set.

[0061] Furthermore, the feature screening module 13 in the TBM cutter eccentric wear identification system based on fault simulation is also used for, and the feature screening mechanism refers to a mechanism for performing correlation screening on the cutter eccentric wear feature set based on a predetermined correlation analysis method, and the predetermined correlation analysis method includes a Pearson correlation analysis method and a copula entropy theory analysis method.

[0062] Furthermore, the eccentric wear identification module 14 in the TBM cutter eccentric wear identification system based on fault simulation is also used for: Matching the eccentric wear failure rate corresponding to the eccentric wear timing signal in the target simulation record; Based on the Stacking ensemble learning principle, ensemble learning training is performed on the training data group formed according to the eccentric wear feature set and the eccentric wear failure rate to obtain the hob eccentric wear fault identification model.

[0063] Furthermore, the eccentric wear identification module 14 in the TBM cutter eccentric wear identification system based on fault simulation is also used for: extracting a first base model from predetermined base models; Performing machine learning on the first data group in the training data group using the first base model after hyperparameter optimization to obtain a first target base model; Acquire a predetermined meta-model, and integrate it with the first target base model to obtain the hob cutter eccentric wear fault identification model; The predetermined base models include at least a K-nearest neighbor model, a random forest model, a support vector classification model and a multivariate perceptron model.

[0064] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The TBM cutter eccentric wear identification method based on fault simulation and the specific examples in the first embodiment are also applicable to the TBM cutter eccentric wear identification system based on fault simulation in the present embodiment. Through the above detailed description of the TBM cutter eccentric wear identification method based on fault simulation, those skilled in the art can clearly know the TBM cutter eccentric wear identification system based on fault simulation in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0065] Embodiment 3, based on the same inventive concept as the TBM cutter eccentric wear identification method based on fault simulation in the above embodiment, the present application also provides a TBM cutter eccentric wear identification device based on fault simulation, which is used to execute the steps of the TBM cutter eccentric wear identification method based on fault simulation in any one of the above embodiment 1, wherein the TBM cutter eccentric wear identification device based on fault simulation comprises: a cutter disc, the cutter disc is provided with a plurality of grooves; a cutter holder, the cutter holder is installed on the plurality of grooves of the cutter disc by bolts; a cutter, the cutter is installed on the cutter holder. There are 15 cutter holder grooves distributed on the TBM cutter disc. 12 inner cutters are installed with 12 positive cutters, arranged at an angle of 60 degrees. 3 cutters are installed with 3 side cutters on the outer ring of the cutter disc, arranged at an angle of 120 degrees and inclined 10 degrees with the horizontal plane. The installation radius of different cutters is different. For the convenience of description, the 15 cutters in the cutter disc are numbered, and numbers 1 to 12 are positive cutters, and numbers 13 to 15 are side cutters. In addition, the cutter disc is equipped with 3 sets of scrapers, arranged at an angle of 120 degrees, 8 in each set, and bolted to the edge area of ​​the hob opening. In addition, the cylindrical end of the cutter shaft of a normal hob is designed as a square structure, and the corresponding hob seat is also modified accordingly to achieve the hob trapped state. When the hob just enters the trapped state, the cutter ring has not yet worn. Based on the trapped hob, the cutter ring thickness of different degrees is gradually cut off to simulate different eccentric wear states.

[0066] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A TBM cutter eccentric wear identification method based on fault simulation, characterized in that: The method comprises: Acquire preset test conditions, and perform a hob cutter eccentric wear fault simulation on a target TBM under the constraints of the preset test conditions to obtain a target simulation record; Analyze the target simulation record to obtain an eccentric wear timing signal, and perform multi-domain feature extraction on the eccentric wear timing signal to obtain a hob eccentric wear feature set; A feature screening mechanism is introduced to screen and analyze the hob eccentric wear feature set to obtain a target eccentric wear feature set; Using the target eccentric wear feature set as input information of a roller cutter eccentric wear fault identification model, and obtaining output information through the roller cutter eccentric wear fault identification model; Determining whether the target eccentric wear failure rate in the output information reaches a predetermined failure rate threshold; If the target eccentric wear failure rate reaches the predetermined failure rate threshold, issuing an eccentric wear failure warning instruction; The target TBM is subjected to tool change processing based on the eccentric wear fault warning instruction.

2. The method according to claim 1, characterized in that Obtaining preset test conditions, and simulating the hob cutter eccentric wear fault on the target TBM under the constraints of the preset test conditions, and obtaining a target simulation record, including: Use sand as the upper stratum; The crushed soft rock is taken as the underlying stratum; forming a composite stratum based on the upper stratum and the lower stratum, and using the composite stratum as a preset geological condition; Get the preset fault ratio; Get the preset excavation mode; The preset test conditions are formed based on the preset geological conditions, the preset fault ratio and the preset excavation mode.

3. The method according to claim 1, characterized in that The target simulation record is analyzed to obtain an eccentric wear timing signal, and multi-domain feature extraction is performed on the eccentric wear timing signal to obtain a hob eccentric wear feature set, including: Extracting a thrust simulation timing signal from the target simulation record, and using the thrust simulation timing signal as the eccentric wear timing signal; Reading a predetermined time domain feature, and extracting a time domain feature of the eccentric wear timing signal based on the predetermined time domain feature to obtain a first time domain feature set; Reading a predetermined frequency domain feature, and extracting a frequency domain feature of a first eccentric wear signal spectrum obtained after fast Fourier transforming the eccentric wear time series signal based on the predetermined frequency domain feature, to obtain a first frequency domain feature set; Retrieving a predetermined time-domain and frequency-domain feature extraction strategy, and obtaining a first time-domain and frequency-domain feature set of the eccentric wear timing signal according to the predetermined time-domain and frequency-domain feature extraction strategy; The roller cutter eccentric wear feature set is constructed based on the first time domain feature set, the first frequency domain feature set and the first time domain and frequency domain feature set.

4. The method according to claim 3, characterized in that Retrieving a predetermined time domain and frequency domain feature extraction strategy, and obtaining a first time domain and frequency domain feature set of the eccentric wear timing signal according to the predetermined time domain and frequency domain feature extraction strategy, including: Performing a 2-layer wavelet packet decomposition on the eccentric wear time series signal based on the db4 wavelet basis function to obtain an eccentric wear signal decomposition result, wherein the eccentric wear signal decomposition result includes four sub-band signals; Extracting any sub-band signal from the four sub-band signals, and obtaining average energy of any wavelet packet coefficients of the arbitrary sub-band signal; The first time-domain and frequency-domain feature set is established based on the average energy of the arbitrary wavelet packet coefficients.

5. The method according to claim 4, characterized in that After the hob cutter eccentric wear feature set is formed based on the first time domain feature set, the first frequency domain feature set and the first time domain and frequency domain feature set, the method further includes: Extracting a torque simulation timing signal from the target simulation record, and using the torque simulation timing signal as the eccentric wear timing signal; Extracting and obtaining a second time domain feature set of the eccentric wear timing signal based on the predetermined time domain feature; A second frequency domain feature set of a second eccentric wear signal spectrum obtained by fast Fourier transforming the eccentric wear time series signal is extracted based on the predetermined frequency domain feature; Obtaining a second time-domain and frequency-domain feature set of the eccentric wear timing signal according to the predetermined time-domain and frequency-domain feature extraction strategy; The second time domain feature set, the second frequency domain feature set and the second time domain and frequency domain feature set are added to the roller cutter eccentric wear feature set.

6. The method according to claim 1, characterized in that The feature screening mechanism refers to a mechanism for performing correlation screening on the hob cutter eccentric wear feature set based on a predetermined correlation analysis method, wherein the predetermined correlation analysis method includes a Pearson correlation analysis method and a copula entropy theory analysis method.

7. The method according to claim 1, characterized in that The target eccentric wear feature set is used as input information of a roller cutter eccentric wear fault identification model, and output information is obtained through the roller cutter eccentric wear fault identification model, including: Matching the eccentric wear failure rate corresponding to the eccentric wear timing signal in the target simulation record; Based on the Stacking ensemble learning principle, ensemble learning training is performed on the training data group formed according to the eccentric wear feature set and the eccentric wear failure rate to obtain the hob eccentric wear fault identification model.

8. The method according to claim 7, characterized in that Based on the Stacking ensemble learning principle, ensemble learning training is performed on the training data group formed according to the eccentric wear feature set and the eccentric wear failure rate to obtain the hob eccentric wear fault identification model, including: extracting a first base model from predetermined base models; Performing machine learning on the first data group in the training data group using the first base model after hyperparameter optimization to obtain a first target base model; Acquire a predetermined meta-model, and integrate it with the first target base model to obtain the hob cutter eccentric wear fault identification model; The predetermined base models include at least a K-nearest neighbor model, a random forest model, a support vector classification model and a multivariate perceptron model.

9. The TBM cutter eccentric wear identification system based on fault simulation is characterized by: The system is used to perform the method according to any one of claims 1 to 8, and the system comprises: An eccentric wear simulation module is used to obtain preset test conditions and simulate the eccentric wear fault of the cutter on the target TBM under the constraints of the preset test conditions to obtain a target simulation record; A feature extraction module, used for analyzing the target simulation record to obtain an eccentric wear timing signal, and performing multi-domain feature extraction on the eccentric wear timing signal to obtain a hob eccentric wear feature set; A feature screening module is used to introduce a feature screening mechanism to screen and analyze the hob eccentric wear feature set to obtain a target eccentric wear feature set; An eccentric wear identification module, used for taking the target eccentric wear feature set as input information of a roller cutter eccentric wear fault identification model, and obtaining output information through the roller cutter eccentric wear fault identification model; A failure rate judgment module, used to judge whether the target eccentric wear failure rate in the output information reaches a predetermined failure rate threshold; An eccentric wear warning module is used to issue an eccentric wear fault warning instruction if the target eccentric wear failure rate reaches the predetermined failure rate threshold; The tool change execution module is used to perform tool change processing on the target TBM based on the eccentric wear fault warning instruction.

10. A TBM cutter eccentric wear identification device based on fault simulation, characterized in that: The device is used to perform the method according to any one of claims 1 to 8, and the device comprises: A cutter disc, wherein a plurality of grooves are distributed on the cutter disc; A knife seat, the knife seat is mounted on the plurality of grooves of the knife disc by bolts; A hob is installed on the cutter seat.

Images