A method and system for processing data on shield component wear and repair

Abstract

The application relates to the technical field of shield machines, and provides a shield component wear and repair data processing method and system, which comprises the following steps: acquiring cutter head operation data of a cutter head of a shield machine and conveying operation data of a screw conveyor of the shield machine; detecting whether the screw conveyor is in a hard rock conveying state according to the cutter head operation data and the conveying operation data; in the case that it is detected that the screw conveyor is in the hard rock conveying state, determining a target wear correction coefficient of the screw conveyor according to the conveying operation data; determining a target health index of the screw conveyor according to the number of times that the screw conveyor is in the hard rock conveying state after the last maintenance of the screw conveyor and the target wear correction coefficient of the screw conveyor corresponding to each time that the screw conveyor is in the hard rock conveying state; and in the case that the target health index is less than a preset threshold value, determining a target repair strategy of the screw conveyor according to the target health index. The accuracy of shield component wear and repair data processing can be improved.

Description

Technical Field

[0001] This application relates to the field of tunnel boring machine technology, and in particular to a method and system for processing data on wear and repair of tunnel boring machine components. Background Technology

[0002] In underground engineering construction, tunnel boring machines (TBMs), as heavy equipment, face severe wear and tear on their core components, such as the cutterhead, cutting tools, and screw conveyor system, when operating continuously in complex geological environments. Accurately predicting component wear and developing timely repair plans are crucial for ensuring project progress and equipment safety. Currently, many maintenance decisions still rely on the experience and judgment of on-site personnel. This can not only lead to maintenance delays but also make it difficult to precisely control the timing of repairs and material consumption, thus affecting the overall service life of the equipment and construction efficiency.

[0003] In existing technologies, wear assessment methods for tunnel boring machines (TBMs) typically treat the cutterhead system and the auger conveyor system as relatively independent modules. When the TBM encounters hard rock layers that were not fully explored in the early stages, these hard rock fragments cut by the cutterhead enter the auger conveyor. Existing wear analysis methods for the auger conveyor cannot directly link this change to the fundamental reason that the upstream cutterhead is encountering hard rock layers. The system merely judges the auger conveyor to be in a "high-load wear" state in isolation, and its recommended repair strategy is still the traditional welded wear-resistant layer, failing to recognize that the wear characteristics have fundamentally changed. This failure to establish the intrinsic connection between cutterhead operating conditions and auger conveyor wear leads to serious misjudgments of auger conveyor damage, turning what could have been a more planned maintenance into a costly emergency repair. Therefore, the accuracy of existing TBM component wear and repair data processing is relatively low. Summary of the Invention

[0004] This application provides a method and system for processing data on wear and repair of tunnel boring machine (TBM) components, which can improve the accuracy of data processing on wear and repair of TBM components.

[0005] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application discloses a method for processing data on wear and repair of tunnel boring machine (TBM) components. The method includes: acquiring cutterhead operation data and conveying operation data of the TBM's cutterhead and screw conveyor; detecting whether the screw conveyor is in a hard rock transport state based on the cutterhead operation data and the conveying operation data; if the screw conveyor is detected to be in a hard rock transport state, determining a target wear correction coefficient for the screw conveyor based on the conveying operation data; determining a target health index for the screw conveyor based on the number of times the screw conveyor has been in a hard rock transport state since the last maintenance and the target wear correction coefficient corresponding to each instance of the screw conveyor being in a hard rock transport state; and determining a target repair strategy for the screw conveyor based on the target health index if the target health index is less than a preset threshold.

[0006] Furthermore, the detection of whether the screw conveyor is in hard rock transport mode is based on the cutterhead operation data and the conveying operation data, including: detecting whether the cutterhead is in hard rock cutting mode based on the cutterhead operation data; and if the cutterhead is detected to be in hard rock cutting mode, detecting whether the screw conveyor is in hard rock transport mode based on the conveying operation data.

[0007] More specifically, in some implementation schemes, the cutterhead operating data includes the drive torque of the cutterhead, the vibration data of the cutterhead hob, and the temperature of the hob. Based on the cutterhead operating data, it is determined whether the cutterhead is in a hard rock cutting state, including: determining whether the drive torque is within a first preset range, whether the vibration data is within a second preset range, and whether the temperature is within a third preset range; if all are, it is determined that the cutterhead is detected to be in a hard rock cutting state.

[0008] Based on the above, this application further proposes that the conveying operation data includes the drive current of the screw conveyor, the frequency and intensity of the sound collected by the sound acquisition device installed on the casing of the screw conveyor, and when the cutter head is detected to be in a hard rock cutting state, the screw conveyor is detected to be in a hard rock transport state based on the conveying operation data, including: determining whether the rate of change of the drive current is greater than a first threshold, whether the frequency is within a fourth preset range, and whether the intensity is greater than a second threshold within a preset time period after a first moment, where the first moment is the moment when the cutter head is detected to be in a hard rock cutting state; if all of these are true, it is determined that the screw conveyor is detected to be in a hard rock transport state.

[0009] Preferably, when the screw conveyor is detected to be in a hard rock transport state, the target wear correction coefficient of the screw conveyor is determined based on the transport operation data, including: determining a first duration; the first duration is the duration between a first moment and a second moment, and the second moment is the moment when the screw conveyor is detected to be in a hard rock transport state; and determining the target wear correction coefficient of the screw conveyor based on the current change rate at the first duration and the second moment.

[0010] As a technical improvement, the target wear correction coefficient for the screw conveyor is determined based on the current change rate at the first time interval and the second time interval. This includes: obtaining a first correspondence; the first correspondence includes a one-to-one correspondence between multiple pieces of first information and multiple wear correction coefficients, the first information including a time interval range and a current change rate range, the wear correction coefficient being negatively correlated with the minimum value in the corresponding time interval range, and positively correlated with the minimum value in the corresponding current change rate range; and using the wear correction coefficient corresponding to the first information at the first time interval and the current change rate at the second time interval in the first correspondence as the target wear correction coefficient.

[0011] Based on the above, this application further proposes to determine the target health index of the screw conveyor according to the number of times the screw conveyor has been in hard rock transportation mode since the last maintenance and the target wear correction coefficient of the screw conveyor corresponding to each time the screw conveyor is in hard rock transportation mode, including: using the product of a first difference and a first weight as a first sub-target health index; the first difference is the difference between 1 and the ratio of the number of times to the preset maximum number of times; using the product of a second difference and a second weight as a second sub-target health index; the second difference is the difference between 1 and the average of multiple target wear correction coefficients; and determining the target health index based on the first sub-target health index and the second sub-target health index.

[0012] Furthermore, the target health index is determined based on the first sub-target health index and the second sub-target health index, including: obtaining the wear resistance index of the screw conveyor; multiplying the wear resistance index by the third weight as the third sub-target health index; the sum of the first weight, the second weight, and the third weight is 1; and the sum of the first sub-target health index, the second sub-target health index, and the third sub-target health index is taken as the target health index.

[0013] To improve the solution, when the target health index is less than a preset threshold, a target repair strategy for the screw conveyor is determined based on the target health index. This includes: obtaining a second correspondence; the second correspondence includes a one-to-one correspondence between multiple target health indices and multiple repair strategies, where the repair strategy is used to repair the screw conveyor, and the repair intensity of the repair strategy is negatively correlated with the corresponding target health index; and the repair strategy corresponding to the target health index in the second correspondence is taken as the target repair strategy.

[0014] Secondly, this application also discloses a shield tunneling component wear and repair data processing system, which includes: an acquisition device and a processing device; the acquisition device is used to acquire cutterhead operation data of the shield tunneling machine and conveying operation data of the shield tunneling machine's screw conveyor; the processing device is used to detect whether the screw conveyor is in a hard rock transport state based on the cutterhead operation data and the conveying operation data; the processing device is used to determine a target wear correction coefficient for the screw conveyor based on the conveying operation data when the screw conveyor is detected to be in a hard rock transport state; the processing device is used to determine a target health index for the screw conveyor based on the number of times the screw conveyor has been in a hard rock transport state since the last maintenance and the target wear correction coefficient of the screw conveyor corresponding to each time the screw conveyor is in a hard rock transport state; the processing device is used to determine a target repair strategy for the screw conveyor based on the target health index when the target health index is less than a preset threshold.

[0015] Beneficial Effects: The shield tunneling component wear and repair data processing method disclosed in this application acquires the cutterhead operation data and the conveying operation data of the screw conveyor, and intelligently detects whether the screw conveyor is in hard rock transport mode based on this data. After confirming that it is in hard rock transport mode, the method can dynamically determine the target wear correction coefficient of the screw conveyor based on the conveying operation data. Furthermore, by combining the number of times the screw conveyor has been in hard rock transport mode since the last maintenance and the corresponding target wear correction coefficient each time, the system accurately calculates the target health index of the screw conveyor. When the target health index is lower than a preset threshold, the system will determine and recommend a corresponding target repair strategy based on the health index.

[0016] This method effectively solves the problems of inaccurate assessment of cutterhead and screw conveyor wear in existing tunnel boring machine (TBM) wear evaluation methods, as well as the failure to establish the intrinsic relationship between cutterhead operating conditions and screw conveyor wear. By correlating and analyzing the operating data of the cutterhead and screw conveyor, this application can more accurately identify the impact of hard rock conditions on screw conveyor wear, avoiding misjudgments caused by isolated assessments in traditional methods. This comprehensive evaluation approach makes the determination of wear correction coefficients more accurate and the assessment of health indices more comprehensive, thereby providing more targeted and forward-looking repair strategies. Compared with existing technologies, this application can significantly improve the accuracy and timeliness of TBM component maintenance, effectively avoid emergency repairs and high maintenance costs caused by misjudgments of wear, extend equipment service life, improve construction efficiency and safety, and enhance the accuracy of TBM component wear and repair data processing. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a method for processing data on wear and repair of tunnel boring machine components provided in this application; Figure 2A flowchart illustrating another method for processing data on wear and repair of tunnel boring machine components provided in this application; Figure 3 A flowchart illustrating another method for processing data on wear and repair of tunnel boring machine components provided in this application; Figure 4 This is a schematic diagram of the architecture of a shield tunnel component wear and repair data processing system provided in this application. Detailed Implementation

[0018] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0019] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0020] In underground engineering construction, tunnel boring machines (TBMs), as heavy equipment, face severe wear and tear on their core components, such as the cutterhead, cutting tools, and screw conveyor system, when operating continuously in complex geological environments. Accurately predicting component wear and developing timely repair plans are crucial for ensuring project progress and equipment safety. Currently, many maintenance decisions still rely on the experience and judgment of on-site personnel. This can not only lead to maintenance delays but also make it difficult to precisely control the timing of repairs and material consumption, thus affecting the overall service life of the equipment and construction efficiency.

[0021] In existing technologies, wear assessment methods for tunnel boring machines (TBMs) typically treat the cutterhead system and the auger conveyor system as relatively independent modules. When the TBM encounters hard rock layers that were not fully explored in the early stages, these hard rock fragments cut by the cutterhead enter the auger conveyor. Existing wear analysis methods for the auger conveyor cannot directly link this change to the fundamental reason that the upstream cutterhead is encountering hard rock layers. The system merely judges the auger conveyor to be in a "high-load wear" state in isolation, and its recommended repair strategy is still the traditional welded wear-resistant layer, failing to recognize that the wear characteristics have fundamentally changed. This failure to establish the intrinsic connection between cutterhead operating conditions and auger conveyor wear leads to serious misjudgments of auger conveyor damage, turning what could have been a more planned maintenance into a costly emergency repair. Therefore, the accuracy of existing TBM component wear and repair data processing is relatively low.

[0022] In this regard, such as Figure 1 As shown, this application proposes a method for processing data on wear and repair of tunnel boring machine components. The method includes: S101. Obtain the cutterhead operation data of the tunnel boring machine and the conveying operation data of the tunnel boring machine's screw conveyor.

[0023] S102. Detect whether the screw conveyor is in hard rock transportation mode based on the cutter head operation data and conveying operation data.

[0024] S103. When the screw conveyor is detected to be in a hard rock transport state, determine the target wear correction coefficient of the screw conveyor based on the transport operation data.

[0025] S104. Determine the target health index of the screw conveyor based on the number of times the screw conveyor has been in hard rock transport mode since the last maintenance and the target wear correction coefficient of the screw conveyor for each time it is in hard rock transport mode.

[0026] S105. When the target health index is less than the preset threshold, determine the target repair strategy for the screw conveyor based on the target health index.

[0027] This application aims to provide a data processing method for wear and repair of tunnel boring machine (TBM) components. By comprehensively analyzing cutterhead operating data and screw conveyor operating data, it achieves a more accurate assessment of the wear condition of the screw conveyor under hard rock transport conditions, and formulates targeted repair strategies accordingly. Cutterhead operating data refers to various parameters reflecting the working state of the TBM cutterhead, such as the drive torque of the cutterhead, the vibration data of the cutterhead, and the temperature of the cutterhead. Transport operating data refers to various parameters reflecting the working state of the screw conveyor, such as the drive current of the screw conveyor, and the frequency and intensity of sound collected by the sound acquisition equipment. Hard rock transport conditions refer to the working state of the screw conveyor when transporting hard rock fragments cut by the cutterhead; this state is typically accompanied by high load and severe wear. The target wear correction coefficient is a correction factor used to quantify the degree of wear of the screw conveyor under specific hard rock transport conditions. The target health index is an assessment indicator of the overall health status of the screw conveyor, comprehensively considering the number of hard rock transport operations and the wear correction coefficient under each hard rock transport condition. The target repair strategy is a specific plan for repairing the screw conveyor, determined based on the target health index.

[0028] The shield tunneling component wear and repair data processing method of this application first requires acquiring the cutterhead operation data and the conveying operation data of the shield tunneling machine's screw conveyor. The cutterhead operation data can be acquired through sensors installed on the cutterhead drive system, such as torque sensors, vibration sensors, and temperature sensors. These sensors monitor the drive torque of the cutterhead, the vibration amplitude and frequency of the cutterhead rollers, and the surface temperature of the cutterhead rollers in real time. The conveying operation data can be acquired through sensors installed on the screw conveyor, such as current sensors and acoustic sensors. The current sensor monitors the current changes of the screw conveyor drive motor, and the acoustic sensor collects the sound frequency and intensity during screw conveyor operation. This data can be acquired in real time and transmitted to a data processing system for subsequent analysis.

[0029] After acquiring the cutterhead operating data and conveyor operating data, it is necessary to detect whether the screw conveyor is in hard rock transport mode based on this data. One approach is to first determine whether the cutterhead is in hard rock cutting mode based on the cutterhead operating data. For example, this can be determined by analyzing the changing trends of cutterhead drive torque, cutter vibration data, and cutter temperature. When the cutterhead drive torque continuously increases and exceeds a preset threshold, the cutter vibration data increases abnormally, and the cutter temperature rises sharply, it can be preliminarily determined that the cutterhead may be in hard rock cutting mode. After confirming that the cutterhead is in hard rock cutting mode, further detection of whether the screw conveyor is in hard rock transport mode is performed based on the conveyor operating data. For example, when the screw conveyor drive current increases significantly and the acoustic sensor detects high-frequency, high-intensity noise, it can be determined that the screw conveyor is transporting hard rock, i.e., in hard rock transport mode.

[0030] When a screw conveyor is detected to be operating in hard rock conditions, a target wear correction factor needs to be determined based on the conveying operation data. One approach is to continuously monitor conveying operation data such as drive current, sound frequency, and intensity during the hard rock transport phase. By analyzing the variation range, duration, and peak values ​​of these data under hard rock transport conditions, a correction factor reflecting the current degree of wear can be calculated. For example, the average value, maximum value, and rate of change of the drive current can all be used as a basis for calculating the wear correction factor. Longer durations and larger rates of change in current generally indicate more severe wear, and the corresponding wear correction factor should be larger.

[0031] Subsequently, the target health index of the screw conveyor is determined based on the number of times the screw conveyor has been in hard rock transport mode since the last maintenance, and the target wear correction coefficient corresponding to each hard rock transport mode. One implementation method is to record the number of hard rock transport cycles since the last maintenance and store the target wear correction coefficient determined for each hard rock transport mode. The calculation of the target health index can comprehensively consider these two factors. For example, the more hard rock transport cycles, the lower the screw conveyor's health index; the larger the target wear correction coefficient for each hard rock transport mode, the more severe the wear, and the lower the health index. These factors can be integrated through weighted averaging or other mathematical models to obtain a comprehensive health index.

[0032] Finally, when the target health index is less than a preset threshold, the target repair strategy for the screw conveyor is determined based on the target health index. One implementation is that the system presets a health index threshold; when the calculated target health index is lower than this threshold, it indicates that the screw conveyor needs repair. In this case, the system selects the most suitable repair solution from a preset repair strategy library based on the specific value of the target health index. For example, when the health index is slightly below the threshold, localized welding repair might be recommended; when the health index is significantly below the threshold, large-area wear-resistant layer replacement or component replacement might be recommended. The strength of the repair strategy is negatively correlated with the target health index; that is, the lower the health index, the greater the repair strength.

[0033] The shield tunneling component wear and repair data processing method of this application acquires the cutterhead operation data and the conveying operation data of the screw conveyor, and uses this data to detect whether the screw conveyor is in a hard rock transport state. If the screw conveyor is detected to be in a hard rock transport state, a target wear correction coefficient for the screw conveyor is determined based on the conveying operation data. Subsequently, a target health index for the screw conveyor is determined based on the number of times the screw conveyor has been in a hard rock transport state since the last maintenance and the target wear correction coefficient corresponding to each instance of the screw conveyor being in a hard rock transport state. Finally, if the target health index is less than a preset threshold, a target repair strategy for the screw conveyor is determined based on the target health index.

[0034] The core of this method lies in establishing the intrinsic relationship between the cutterhead's operating conditions and the wear of the screw conveyor, thus solving the problems of isolated and misjudged wear analysis in existing technologies. By comprehensively analyzing the operating data of the cutterhead and the screw conveyor, the wear characteristics of the screw conveyor under hard rock transport conditions can be identified more accurately, and its wear degree can be quantified. This linked analysis makes the assessment of screw conveyor damage more precise, avoiding misjudgments caused by traditional methods that fail to consider the upstream cutterhead's operating conditions.

[0035] Compared with existing technologies, this application has the following advantages: First, it can identify the wear risk of the screw conveyor under hard rock transportation conditions earlier and more accurately because it considers the impact of the cutterhead's hard rock cutting condition on the screw conveyor. Second, by introducing a target wear correction coefficient and a target health index, it achieves a quantitative assessment of the wear degree of the screw conveyor, enabling maintenance decisions to shift from experience-based judgment to data-driven approaches. Finally, determining the target repair strategy based on the quantified health index provides more targeted and economical repair solutions, avoiding over-repair or under-repair, thereby extending the service life of the screw conveyor, reducing maintenance costs, and improving the overall operating efficiency and safety of the tunnel boring machine. This method can effectively avoid emergency repairs caused by misjudgment of wear, achieving more planned maintenance and demonstrating significant technological advancement.

[0036] Specifically, such as Figure 2 As shown, the steps described above for detecting whether the screw conveyor is in hard rock transport mode based on cutterhead operation data and conveying operation data can be further refined into the following methods.

[0037] Based on the aforementioned method for processing shield component wear and repair data, the screw conveyor is checked for hard rock transport status based on cutterhead operation data and conveyor operation data, including: S201. Detect whether the cutterhead is in hard rock cutting state based on the cutterhead operation data.

[0038] S202. When the cutterhead is detected to be in a hard rock cutting state, the screw conveyor is detected to be in a hard rock transport state based on the conveying operation data.

[0039] Specifically, this step aims to improve the accuracy of determining whether a screw conveyor is in a hard rock transport state through phased testing. First, by analyzing the cutterhead's operating data, it is determined whether the cutterhead is engaged in hard rock cutting. The cutterhead's hard rock cutting state is a prerequisite for the screw conveyor to potentially be in a hard rock transport state. Only when the cutterhead is confirmed to be in a hard rock cutting state is further testing of the screw conveyor's actual transport state based on the conveying operation data. This step-by-step testing method effectively avoids misjudgments and ensures the accuracy of subsequent wear correction coefficient and health index determination.

[0040] This application's solution establishes a logically rigorous judgment mechanism by first detecting whether the cutterhead is in a hard rock cutting state, and then further detecting whether the screw conveyor is in a hard rock transport state. Hard rock cutting by the cutterhead is the source of hard rock entering the screw conveyor; therefore, the screw conveyor can only transport hard rock when the cutterhead is in a hard rock cutting state. This pre-judgment avoids unnecessary hard rock transport state detection of the screw conveyor under non-hard rock cutting conditions, thereby improving detection efficiency and accuracy. Once the cutterhead is confirmed to be in a hard rock cutting state, combining this with the screw conveyor's transport operation data allows for a more accurate identification of whether the screw conveyor is experiencing wear risks associated with hard rock transport.

[0041] The above technical solution enables more accurate and reliable detection of the hard rock transport status of the screw conveyor. This phased judgment logic effectively reduces the misjudgment rate and ensures the accuracy of subsequent wear correction coefficient and health index calculations, thus providing a more solid data foundation for the wear and repair of tunnel boring machine components and helping to improve the overall intelligence level of tunnel boring machine operation and maintenance.

[0042] Specifically, such as Figure 3 As shown, in some of the above embodiments, the step of detecting whether the cutterhead is in a hard rock cutting state based on the cutterhead operation data is further refined.

[0043] The cutterhead operating data includes the drive torque of the cutterhead, the vibration data of the cutterhead hobs, and the temperature of the hobs. Based on this operating data, the determination of whether the cutterhead is in a hard rock cutting state includes: S301. Determine whether the driving torque is within the first preset range, whether the vibration data is within the second preset range, and whether the temperature is within the third preset range.

[0044] S302. If both are true, it is confirmed that the cutter head is in a hard rock cutting state.

[0045] Among them, cutterhead operation data refers to real-time or historical data related to the working status of the cutterhead during the tunneling process of the tunnel boring machine. Specifically, driving torque refers to the torque required to drive the cutterhead to rotate, and its magnitude directly reflects the resistance encountered by the cutterhead during the cutting process. Hob vibration data refers to the vibration signals generated by the hobs mounted on the cutterhead when cutting rock, usually collected by vibration sensors; changes in their frequency and amplitude can indicate the hardness of the cutting medium. Hob temperature refers to the heat generated by the hobs due to friction and compression during the cutting process, monitored by temperature sensors; abnormally high temperatures are often related to cutting hard rock or accelerated wear.

[0046] The first, second, and third preset ranges are threshold intervals pre-set based on historical experience data, experimental test results, or expert knowledge. For example, when the cutter head cuts hard rock, the driving torque usually increases significantly, so the first preset range can be set to a torque range higher than that used when cutting soft rock normally. When the hob cuts in hard rock, the vibration is more intense and has specific frequency characteristics, so the second preset range can correspond to the vibration mode during hard rock cutting. At the same time, the frictional heat generated during hard rock cutting is greater, and the hob temperature will rise accordingly, so the third preset range can be set to indicate the high temperature range. When the driving torque, vibration data, and temperature all meet their respective preset ranges, it can be comprehensively determined that the cutter head is in a hard rock cutting state.

[0047] This application's solution, through comprehensive analysis of three key operating parameters—the cutterhead's driving torque, the cutterhead's vibration data, and the cutterhead's temperature—can more accurately identify whether the cutterhead is in a hard rock cutting state. During tunnel boring machine (TBM) excavation, when the cutterhead encounters hard rock, its driving torque increases due to increased cutting resistance; the intense friction and impact between the cutterhead and the hard rock causes a significant change in its vibration mode, generating specific vibration frequencies and amplitudes; simultaneously, the enormous frictional heat generated by hard rock cutting causes the cutterhead's temperature to rise rapidly. By setting and judging whether these parameters are simultaneously within their respective preset ranges, misjudgments caused by fluctuations in a single parameter can be effectively eliminated, thereby improving the accuracy and reliability of the cutterhead's hard rock cutting state detection. This multi-parameter collaborative judgment mechanism makes the perception of the cutterhead's working environment more comprehensive and refined.

[0048] Through the above technical solution, this application enables accurate and reliable detection of the hard rock cutting condition of the tunnel boring machine cutterhead. Compared to methods that rely on only a single or a few parameters for judgment, comprehensively considering the drive torque, cutterhead vibration data, and cutterhead temperature, and setting corresponding preset ranges for coordinated judgment, significantly improves the accuracy of detection and reduces the risk of false alarms and missed alarms. Therefore, it provides a more solid and accurate foundation for subsequent judgment of whether the screw conveyor is in a hard rock transport state, thereby optimizing the effectiveness of the entire tunnel boring machine component wear and repair data processing method.

[0049] Specifically, when the cutterhead is detected to be in a hard rock cutting state, the following method can be used to detect whether the screw conveyor is in a hard rock transport state based on the above-mentioned transport operation data.

[0050] The conveying operation data includes the drive current of the screw conveyor, the frequency and intensity of the sound collected by the sound acquisition device installed on the casing of the screw conveyor, and, when the cutterhead is detected to be in a hard rock cutting state, the conveying operation data is used to determine whether the screw conveyor is in a hard rock transport state, including: Determine whether, within a preset time period after the first moment, the rate of change of the driving current is greater than the first threshold, the frequency is within the fourth preset range, and the intensity is greater than the second threshold. The first moment is the moment when the cutter head is detected to be in hard rock cutting state. If all of these conditions are met, it is determined that the screw conveyor is detected to be in hard rock transport state.

[0051] Among these parameters, conveying operation data are key parameters used to characterize the working status of the screw conveyor. Specifically, the drive current reflects the load borne by the screw conveyor when transporting materials, and its rate of change indicates abrupt changes in material hardness. Sound acquisition equipment can be configured on the screw conveyor's casing to monitor the acoustic characteristics generated during operation in real time. The frequency and intensity of the sound are key acoustic parameters collected by the sound acquisition equipment; their changes effectively reflect the properties of the material inside the screw conveyor, such as the presence of hard rock friction or impact.

[0052] The first moment refers to the precise point in time when the cutterhead is detected to be in hard rock cutting mode. After this first moment, the operating data of the screw conveyor needs to be continuously monitored for a preset duration. The preset duration can be set based on actual engineering experience or experimental data to ensure that there is a sufficient time window to capture the characteristic performance of the screw conveyor under hard rock transport conditions.

[0053] Specifically, determining whether the rate of change of the driving current exceeds a first threshold aims to identify whether the load on the screw conveyor has increased significantly in a short period of time, which is usually a signal of encountering hard rock. The first threshold can be set based on the design parameters of the screw conveyor and actual operating experience. Determining whether the frequency is within a fourth preset range and whether the intensity exceeds a second threshold further confirms the presence of hard rock through acoustic characteristics. When hard rock is transported in a screw conveyor, it usually generates noise within a specific frequency range and a high sound intensity. The fourth preset range and the second threshold can be determined based on the analysis results of the acoustic characteristics of the screw conveyor under hard rock transport conditions.

[0054] This application's solution, through comprehensive analysis of three key conveying operation data—the rate of change of the screw conveyor's drive current, the frequency of sound, and the intensity of sound—can more accurately determine whether the screw conveyor is in a hard rock transport state. When the cutterhead is already in a hard rock cutting state, it means that the tunnel boring machine is dealing with hard rock strata. At this time, if the rate of change of the screw conveyor's drive current increases significantly, and the sound frequency detected by the sound acquisition device on its casing falls within a specific range and the sound intensity is high, it indicates that the screw conveyor is also under the transport load of hard rock material. This multi-dimensional data cross-validation mechanism effectively avoids misjudgments that may arise from a single data source, thereby improving the accuracy and reliability of hard rock transport status detection.

[0055] Through the above technical solution, this application can utilize multi-source heterogeneous conveying operation data to make a refined and multi-dimensional judgment on whether the screw conveyor is in hard rock transport mode. This judgment method not only considers the change in mechanical load (driving current change rate) but also introduces acoustic characteristics (sound frequency and intensity), making the detection results more comprehensive and reliable. Therefore, it can effectively avoid excessive wear of the screw conveyor caused by misjudgment or omission of hard rock transport mode, providing more accurate basic data for the subsequent determination of the target wear correction coefficient, thereby improving the overall accuracy and efficiency of shield component wear and repair data processing.

[0056] In some embodiments described above, when the screw conveyor is detected to be in a hard rock transport state, a target wear correction coefficient for the screw conveyor needs to be determined based on transport operation data. While the above approach can identify the hard rock transport state and use transport operation data to initially determine the wear correction coefficient, it may not fully consider the dynamic characteristics of the hard rock transport process, such as the duration of the hard rock transport state and the instantaneous load changes upon entering this state. This deficiency may result in an insufficiently precise wear correction coefficient, thus affecting the accurate assessment of the actual wear degree of the screw conveyor.

[0057] In this regard, this application further proposes determining the target wear correction coefficient for the screw conveyor based on conveying operation data when the screw conveyor is detected to be in a hard rock transport state, including: Determine the first duration; the first duration is the time between the first moment and the second moment, and the second moment is the moment when the screw conveyor is detected to be in hard rock transport mode; determine the target wear correction coefficient of the screw conveyor based on the current change rate at the first duration and the second moment.

[0058] Specifically, the first moment refers to the moment when the cutterhead is detected to be in hard rock cutting mode, while the second moment refers to the moment when the screw conveyor is detected to be in hard rock transport mode. The first duration is defined as the time interval from when the cutterhead begins hard rock cutting to when the screw conveyor is confirmed to be in hard rock transport mode. The current change rate can be understood as the instantaneous change rate of the screw conveyor drive current at the second moment, reflecting the load change rate of the screw conveyor when entering the hard rock transport mode. In practical applications, the determination of the target wear correction coefficient no longer relies solely on the overall judgment of the conveyor operation data, but combines the duration of the hard rock transport mode (first duration) and the instantaneous load change upon entering this mode (current change rate at the second moment).

[0059] This application's solution, by introducing the current change rate at a first time interval and a second time interval, can more precisely capture the actual operating conditions of the screw conveyor under hard rock transport conditions. Specifically, the first time interval reflects the time interval from when the cutterhead begins hard rock cutting to when the screw conveyor is confirmed to be in hard rock transport conditions. This helps to assess the persistence of hard rock transport events and their cumulative impact on component wear. Simultaneously, the current change rate at the second time interval directly quantifies the instantaneous load impact of the screw conveyor when entering hard rock transport conditions, which is crucial for assessing instantaneous wear under sudden hard rock conditions. Because this solution comprehensively considers the persistence and instantaneous load characteristics of hard rock transport, the calculation of the target wear correction coefficient can more closely approximate the wear mechanism of the screw conveyor under actual hard rock conditions, thereby improving the accuracy of wear assessment.

[0060] Through the above technical solution, this application can more accurately determine the target wear correction coefficient of the screw conveyor. Compared with making a general judgment based solely on conveying operation data, this application considers the current change rate at the first and second time points, making the calculation of the wear correction coefficient more refined and dynamic. This effectively avoids the deviation in health index assessment caused by inaccurate wear correction coefficients, providing more reliable data support for subsequent repair strategy formulation, and significantly improving the intelligence and accuracy of shield component wear and repair data processing.

[0061] In some preferred embodiments, it is assumed that during a tunnel boring machine (TBM) operation, the cutterhead is detected to be in hard rock cutting mode at time T1, and subsequently, the screw conveyor is detected to be in hard rock transport mode at time T2. The first duration is then T2-T1. Simultaneously, at time T2, the rate of change of the screw conveyor's drive current is measured as ΔI. The system can pre-define a lookup table or model that associates different ranges of the first duration and the rate of change of current with corresponding target wear correction coefficients. For example, if the first duration is short and the rate of change of current is high, it may indicate that the screw conveyor has suddenly experienced a large impact from hard rock; in this case, the corresponding target wear correction coefficient will be relatively large to reflect a more severe wear risk. Conversely, if the first duration is long and the rate of change of current is low, it may indicate that the hard rock transport process is relatively smooth; the corresponding target wear correction coefficient will be relatively small. In this way, the target wear correction coefficient can be dynamically and accurately determined based on specific operating parameters.

[0062] In some embodiments described above in this application, a scheme is proposed to determine the target wear correction coefficient for a screw conveyor based on the current change rate at a first duration and a second moment. However, in practical applications, how to accurately and systematically establish a quantitative relationship between duration, current change rate, and wear correction coefficient to ensure the accuracy of the wear correction coefficient is a problem that requires further refinement. Determining the wear correction coefficient solely based on experience or a simple linear relationship may result in insufficient accuracy, thereby affecting subsequent health index assessments and the formulation of repair strategies.

[0063] In this regard, this application further proposes a step for determining the target wear correction coefficient of the screw conveyor based on the current change rate at the first time period and the second time period, including: Obtain the first correspondence; the first correspondence includes a one-to-one correspondence between multiple pieces of first information and multiple wear correction coefficients. The first information includes a duration range and a current change rate range. The wear correction coefficient is negatively correlated with the minimum value in the corresponding duration range and positively correlated with the minimum value in the corresponding current change rate range. The wear correction coefficient corresponding to the first information in the first correspondence, where the current change rate is at the first duration and the second moment, is taken as the target wear correction coefficient.

[0064] Specifically, the first correspondence can be understood as a pre-established mapping table or mathematical model, which aims to associate the duration of the screw conveyor in hard rock transport mode (i.e., the first duration) and the rate of change of the driving current in this mode (i.e., the rate of change of current at the second moment) with a quantified wear correction coefficient. The first information is the basic unit constituting this correspondence; it consists of a specific duration range and a current change rate range, used to define the operating characteristics of the screw conveyor under specific working conditions. The wear correction coefficient is a value calculated or found based on these operating characteristics, used to quantify the degree of wear of the screw conveyor in hard rock transport mode.

[0065] The wear correction coefficient is negatively correlated with the minimum value within the corresponding time range. This means that, all other things being equal, the wear correction coefficient decreases as the minimum value of the time range increases, and vice versa. Simultaneously, the wear correction coefficient is positively correlated with the minimum value within the corresponding current change rate range. This means that the wear correction coefficient increases as the minimum value of the current change rate range increases, and vice versa. This design aims to quantify the degree of wear correction by comprehensively considering the duration and severity of the working conditions of the screw conveyor in hard rock transport.

[0066] This application's solution systematically solves the problem of accurately quantifying the wear correction coefficient of a screw conveyor by introducing a first correspondence relationship. Specifically, by pre-establishing a one-to-one correspondence between first information including a time range and a current change rate range and the wear correction coefficient, after detecting that the screw conveyor is in a hard rock transport state, the corresponding wear correction coefficient can be found or calculated from the first correspondence relationship based on the actually measured first time period and the current change rate at the second moment. This method based on a pre-defined correspondence relationship avoids errors caused by subjective judgment or simple estimation, ensuring higher accuracy and reliability in determining the wear correction coefficient. The wear correction coefficient is negatively correlated with the minimum value of the time range and positively correlated with the minimum value of the current change rate range, reflecting the complexity of the screw conveyor's wear degree under different operating conditions, making the determination of the wear correction coefficient more refined and consistent with reality.

[0067] Through the above technical solution, this application provides a more accurate and systematic method for determining the target wear correction coefficient of the screw conveyor. Compared with solutions that do not clearly define the quantitative relationship, this application establishes a first correspondence, effectively linking complex operating parameters (such as hard rock transport time and current variation rate) with the wear correction coefficient, thereby improving the accuracy and reliability of the wear correction coefficient determination. This not only helps to more accurately assess the health status of the screw conveyor, but also provides a solid data foundation for subsequently developing more reasonable and effective repair strategies, thereby extending the service life of the tunnel boring machine components and reducing operating costs.

[0068] Specifically, the steps described above for determining the target health index of the screw conveyor based on the number of times the screw conveyor was in hard rock transport mode after the last maintenance and the target wear correction coefficient of the screw conveyor for each time it was in hard rock transport mode can be further refined as follows.

[0069] The target health index of the screw conveyor is determined based on the number of times the screw conveyor has been in hard rock transport mode since the last maintenance, and the target wear correction coefficient of the screw conveyor for each time it is in hard rock transport mode. This includes: The product of the first difference and the first weight is used as the first sub-target health index; the first difference is the difference between 1 and the ratio of the number of times to the preset maximum number of times; the product of the second difference and the second weight is used as the second sub-target health index; the second difference is the difference between 1 and the average of multiple target wear correction coefficients; the target health index is determined based on the first sub-target health index and the second sub-target health index.

[0070] The first difference refers to the difference between 1 and the ratio of the number of times the screw conveyor was in hard rock transport mode to the preset maximum number of times. This first difference aims to quantify the relationship between the cumulative workload of the screw conveyor in hard rock transport mode and its design life or maximum bearing capacity. The more times the screw conveyor is in hard rock transport mode, the larger this ratio and the smaller the first difference, indicating a higher cumulative load and potentially worse health status. The first weight is a configurable parameter used to adjust the importance of this cumulative load factor in the overall health index calculation. The first sub-target health index is obtained by multiplying the first difference by the first weight and is used to reflect the health status of the screw conveyor due to cumulative workload.

[0071] Furthermore, the second difference refers to the difference between 1 and the average of multiple target wear correction coefficients. The average of the multiple target wear correction coefficients reflects the average wear degree of the screw conveyor under each hard rock transport condition. The larger the average wear correction coefficient, the more severe the average wear; the smaller the second difference, the worse the health condition may be. The second weight is also a configurable parameter used to adjust the importance of this average wear degree factor in the overall health index calculation. The second sub-target health index is obtained by multiplying the second difference by the second weight and is used to reflect the health condition of the screw conveyor due to the average wear degree.

[0072] Therefore, the target health index is determined by comprehensively considering both the first and second sub-target health indices. This combination approach ensures that the health assessment of the screw conveyor considers not only its cumulative usage frequency under hard rock transport conditions but also the severity of wear during each use, thus providing a more comprehensive and refined health assessment result.

[0073] The proposed solution decomposes the health index of a screw conveyor into two or more sub-target health indices and assigns them different weights, thus providing a more comprehensive reflection of the screw conveyor's health status across different dimensions. Specifically, the first sub-target health index focuses on assessing the impact of the cumulative usage frequency of the screw conveyor under hard rock transport conditions on health, while the second sub-target health index focuses on assessing the impact of the severity of wear during each hard rock transport condition on health. This multi-dimensional assessment mechanism makes the calculation results of the health index more refined, capturing health change trends that are difficult to reflect with a single indicator. By reasonably setting the first and second weights, the contribution ratio of different factors in the overall health assessment can be flexibly adjusted according to actual working conditions, material characteristics, or historical data, making the calculation of the health index more targeted and accurate.

[0074] The above technical solution enables a more comprehensive and accurate assessment of the health status of screw conveyors. By introducing a first sub-target health index and a second sub-target health index, the health status is quantitatively assessed from two dimensions: the number of times the screw conveyor operates in hard rock transport mode and the degree of wear during each hard rock transport mode. This avoids the potential bias of a single indicator. Furthermore, by introducing weights, the contribution of different factors to the health index can be flexibly adjusted based on actual working conditions and experience, making the calculation results more targeted and instructive, thus providing a more reliable basis for subsequent repair strategy formulation.

[0075] In some embodiments described above in this application, a scheme is proposed to determine the target health index of the screw conveyor based on the number of times the screw conveyor has been in hard rock transport mode since its last maintenance and the target wear correction coefficient of the screw conveyor for each instance of being in hard rock transport mode. However, in its implementation, considering only the frequency of use and the degree of wear may not fully reflect the wear resistance of the screw conveyor itself, resulting in a certain degree of one-sidedness in the assessment of the component's health status, and failing to fully take into account the influence of inherent factors such as the material properties and structural design of the screw conveyor on its wear life.

[0076] In this regard, this application further proposes the following steps for determining the target health index based on the first sub-target health index and the second sub-target health index: Obtain the wear resistance index of the screw conveyor; multiply the wear resistance index by the third weight as the third sub-target health index; the sum of the first weight, the second weight, and the third weight is 1; the sum of the first sub-target health index, the second sub-target health index, and the third sub-target health index is taken as the target health index.

[0077] Specifically, the wear resistance index can be understood as the wear resistance capability determined by the inherent properties of the screw conveyor's materials and structural design. Its purpose is to quantify the wear resistance characteristics of the screw conveyor itself, compensating for the shortcomings of health assessments based solely on operational data. In practical applications, this wear resistance index can be obtained in various ways. For example, it can be comprehensively evaluated based on parameters such as the hardness, toughness, and surface treatment process of the blade material used in the screw conveyor, or it can be predicted by modeling based on historical wear life data of the same model of screw conveyor under different operating conditions. The third weight is used to balance the importance of the wear resistance index in the overall health index assessment. To ensure the reasonable allocation and normalization of each assessment dimension in the calculation of the total health index, the sum of the first, second, and third weights is set to 1. Therefore, the final target health index can comprehensively reflect the screw conveyor's usage intensity (reflected by the number of uses), wear degree (reflected by the target wear correction coefficient), and inherent wear resistance capability (reflected by the wear resistance index).

[0078] This application's solution effectively addresses the potential one-sidedness of existing methods in assessing the health status of screw conveyors by introducing the wear resistance index of the screw conveyor as a third sub-target health index into the calculation of the target health index. The wear resistance index of the screw conveyor directly reflects its intrinsic factors such as material properties, manufacturing processes, and structural design, which have a decisive impact on the actual wear life of the screw conveyor. By quantifying this inherent attribute and assigning corresponding weights, the calculation of the target health index no longer relies solely on external operating data but incorporates the intrinsic quality of the component itself. Therefore, when the screw conveyor operates under hard rock transport conditions, even if its number of runs and wear correction coefficient show a certain wear trend, a high wear resistance index indicates that the component has stronger wear resistance, and the rate of decline in its health index will be reasonably corrected, thus avoiding misjudgments caused by a single-dimensional assessment.

[0079] Through the above technical solutions, this application provides a more comprehensive, accurate, and scientific health assessment model for tunnel boring machine (TBM) components. By integrating the inherent wear resistance of the screw conveyor, the target health index can more realistically reflect the actual wear state and remaining life of the components, significantly improving the reliability and predictive accuracy of the health assessment. This helps maintenance personnel identify potential wear risks earlier and more accurately, thereby developing more targeted and forward-looking maintenance and repair strategies, effectively extending the service life of the screw conveyor, reducing operating costs, and improving the safety and efficiency of TBM construction.

[0080] In some preferred embodiments, a specific example is given below. Assume a screw conveyor was in hard rock transport mode 50 times after its last maintenance, with a preset maximum of 100 times. According to the above scheme, the first difference is calculated as 1 - (50 / 100) = 0.5. If the first weight is set to 0.4, the first sub-target health index is 0.5 * 0.4 = 0.2. Simultaneously, assuming the average of the multiple target wear correction coefficients corresponding to each instance of the screw conveyor being in hard rock transport mode is 0.8, the second difference is calculated as 1 - 0.8 = 0.2. If the second weight is set to 0.3, the second sub-target health index is 0.2 * 0.3 = 0.06. Further, in this embodiment, the wear resistance index of the screw conveyor is obtained as 0.9. Since the sum of the first weight, second weight, and third weight is 1, and the first weight is 0.4 and the second weight is 0.3, the third weight is determined to be 1 - 0.4 - 0.3 = 0.3. Therefore, the third sub-target health index was calculated as 0.9 * 0.3 = 0.27. Ultimately, the target health index of the screw conveyor was determined as the sum of the first, second, and third sub-target health indices, i.e., 0.2 + 0.06 + 0.27 = 0.53. In this way, the target health index comprehensively considers the screw conveyor's usage intensity, wear level, and inherent wear resistance, providing a more comprehensive health assessment result.

[0081] Traditional methods for processing wear and repair data of tunnel boring machine (TBM) components can identify the need for repair when the target health index of the screw conveyor is below a preset threshold. However, they do not elaborate on how to systematically and accurately determine the most suitable repair strategy based on the target health index. This lack of specific guidance in strategy determination may lead to suboptimal repair options that fail to adequately address the actual needs of the screw conveyor under different wear levels, thus affecting repair effectiveness and efficiency.

[0082] In response, this application further proposes a method for determining the target repair strategy for a screw conveyor, which aims to achieve intelligent and refined selection of repair strategies by establishing a correspondence between the target health index and the repair strategy.

[0083] If the target health index is less than a preset threshold, the target repair strategy for the screw conveyor is determined based on the target health index, including: Obtain the second correspondence; the second correspondence includes a one-to-one correspondence between multiple target health indices and multiple repair strategies. The repair strategies are used to repair the screw conveyor, and the repair intensity of the repair strategy is negatively correlated with the corresponding target health index. The repair strategy corresponding to the target health index in the second correspondence is taken as the target repair strategy.

[0084] Specifically, the second correspondence refers to a pre-established data structure or rule set used to guide the selection of repair strategies. This correspondence maps a series of possible target health index values ​​to a series of predefined repair strategies. The target health index is a key indicator for assessing the wear condition of the screw conveyor, while the repair strategy is a specific maintenance measure taken for different degrees of wear. The repair intensity of a repair strategy is negatively correlated with its corresponding target health index. This means that the lower the target health index of the screw conveyor (i.e., the more severe the wear), the greater the repair intensity of the corresponding repair strategy. For example, slight wear may correspond to local repairs, moderate wear may correspond to component replacement, while severe wear may require a complete overhaul. This negative correlation ensures the targetedness and effectiveness of repair measures, avoiding over-repair or under-repair. In practical applications, once the target health index of the screw conveyor is calculated, the system queries the pre-established second correspondence to find a repair strategy that matches the current target health index and uses it as the final target repair strategy.

[0085] This application's solution addresses the arbitrariness and inaccuracy that may exist in the basic solution mentioned above when determining the repair strategy by introducing a second correspondence. Specifically, when the target health index of the screw conveyor is determined to be lower than a preset threshold, this solution no longer simply "determines" a repair strategy. Instead, it systematically and accurately selects the most suitable repair strategy by querying a pre-established second correspondence that contains a one-to-one correspondence between the target health index and repair strategies. The negative correlation between the repair intensity of the repair strategy and the target health index ensures that the selected strategy matches the actual wear level of the screw conveyor; that is, the lower the health index, the more severe the wear, and the greater the required repair intensity. Therefore, this solution can provide targeted and customized repair suggestions based on the actual health condition of the screw conveyor, avoiding the uncertainty brought about by experience-based judgment.

[0086] Through the above technical solution, this application enables refined management of the wear condition of the tunnel boring machine's screw conveyor and intelligent decision-making regarding repair strategies. Compared to the relatively general approach to determining repair strategies in basic solutions, this application establishes a second correspondence between the target health index and the repair strategy, and clarifies the negative correlation between repair intensity and the health index, making the determined repair strategy more targeted and scientific. This not only effectively avoids resource waste or insufficient repair due to inappropriate repair strategies, but also significantly improves the maintenance efficiency and service life of the screw conveyor, thereby reducing the overall operating cost of the tunnel boring machine and enhancing construction reliability.

[0087] In some preferred embodiments, it is assumed that the target health index of the screw conveyor ranges from 0 to 100, where 0 represents complete damage and 100 represents brand new condition. A second correspondence can be preset, for example: When the target health index is between 80 and 100, the corresponding repair strategy is "no repair needed, continuous monitoring".

[0088] When the target health index is between 60 and 79, the corresponding repair strategy is "light maintenance, such as local welding repair and fastener inspection".

[0089] When the target health index is between 40 and 59, the corresponding repair strategy is "moderate repair, such as partial replacement of worn blades, bearing lubrication and inspection".

[0090] When the target health index is between 20 and 39, the corresponding repair strategy is "major overhaul, such as replacement of major worn parts, inspection and adjustment of the transmission system".

[0091] When the target health index is between 0 and 19, the corresponding repair strategy is "scrap or complete replacement".

[0092] When the system detects that the target health index of the screw conveyor is 35, based on the second correspondence mentioned above, the target repair strategy will be determined as "major overhaul, such as replacement of major worn parts, and inspection and adjustment of the transmission system." This ensures that the most appropriate repair measures are taken based on the actual wear level of the screw conveyor.

[0093] In underground engineering construction, tunnel boring machines (TBMs), as heavy equipment, face severe wear and tear on their core components, such as the cutterhead, cutting tools, and auger conveyor system, when operating continuously in complex geological environments. Accurately predicting component wear and developing timely repair plans are crucial for ensuring project progress and equipment safety. Currently, many maintenance decisions still rely on the experience and judgment of on-site personnel. This can lead to maintenance delays and make it difficult to precisely control repair timing and material consumption, thus affecting the overall service life of the equipment and construction efficiency. Existing wear assessment methods for TBMs typically treat the cutterhead system and auger conveyor system as relatively independent modules, failing to establish the intrinsic link between cutterhead operating conditions and auger conveyor wear. This results in serious misjudgments of auger conveyor damage, turning what could have been a more planned maintenance into costly emergency repairs.

[0094] In this regard, a specific embodiment of this application also discloses a shield tunneling component wear and repair data processing system, the system comprising: an acquisition device and a processing device; the acquisition device is used to acquire cutterhead operation data of the shield tunneling machine and conveying operation data of the shield tunneling machine's screw conveyor; the processing device is used to detect whether the screw conveyor is in a hard rock transport state based on the cutterhead operation data and the conveying operation data; the processing device is used to determine a target wear correction coefficient for the screw conveyor based on the conveying operation data when the screw conveyor is detected to be in a hard rock transport state; the processing device is used to determine a target health index for the screw conveyor based on the number of times the screw conveyor has been in a hard rock transport state since the last maintenance and the target wear correction coefficient of the screw conveyor corresponding to each time the screw conveyor is in a hard rock transport state; the processing device is used to determine a target repair strategy for the screw conveyor based on the target health index when the target health index is less than a preset threshold.

[0095] The shield tunneling machine component wear and repair data processing system of this application aims to overcome the limitations of existing shield machine component wear assessment technologies through an integrated data acquisition and processing mechanism, particularly addressing the problem of misjudgment of wear on the screw conveyor under hard rock transport conditions. This system acquires real-time operating data from the cutterhead and screw conveyor via an acquisition device, and then the processing device comprehensively analyzes this data to achieve accurate detection, quantitative assessment, and intelligent recommendation of repair strategies for the screw conveyor's wear condition. By establishing an intrinsic correlation between cutterhead operating conditions and screw conveyor wear, this system can provide more forward-looking and targeted maintenance decisions, effectively improving the operating efficiency and safety of the shield machine.

[0096] Specifically, the acquisition device may include, but is not limited to, various sensors, data acquisition modules, and communication interfaces. For example, sensors used to acquire cutter head operating data may include torque sensors mounted on the cutter head drive system, vibration sensors for monitoring cutter vibration, and temperature sensors for measuring cutter temperature. These sensors can monitor the cutter head drive torque, cutter vibration data, and cutter temperature in real time. Sensors used to acquire screw conveyor operation data may include current sensors for monitoring the screw conveyor drive motor current, and acoustic sensors mounted on the screw conveyor housing for sound acquisition. These sensors transmit the raw data to the data acquisition module via wired or wireless means. The data acquisition module then performs preliminary processing and formatting before sending the data to the processing device via the communication interface. As a preferred embodiment, the acquisition device can be configured to automatically and continuously acquire the aforementioned operating data, ensuring the real-time nature and accuracy of the data.

[0097] The processing device can be one or more processors, such as a central processing unit (CPU), graphics processing unit (GPU), digital signal processor (DSP), or other programmable logic devices, and may include memory, such as random access memory (RAM), read-only memory (ROM), flash memory, or hard disk. The processing device processes data transmitted from the acquisition device by executing program instructions stored in the memory. The functions of the processing device include, but are not limited to: detecting whether the screw conveyor is in a hard rock transport state based on cutter head operation data and conveyor operation data; determining the target wear correction coefficient of the screw conveyor based on the conveyor operation data when the screw conveyor is detected to be in a hard rock transport state; determining the target health index of the screw conveyor based on the number of times the screw conveyor has been in a hard rock transport state since the last maintenance and the target wear correction coefficient corresponding to each time the screw conveyor is in a hard rock transport state; and determining the target repair strategy of the screw conveyor based on the target health index when the target health index is less than a preset threshold. The specific implementation methods of these functions have been described in the above embodiments and will not be repeated here. It should be emphasized that the processing device, through the fusion analysis of multi-source heterogeneous data, can more comprehensively and accurately assess the wear condition of the screw conveyor.

[0098] The shield tunneling component wear and repair data processing system of this application achieves intelligent and data-driven management of the wear status of shield tunneling components through the coordinated operation of the acquisition and processing devices. Compared with the maintenance methods of the prior art that rely on experience-based judgment or isolated analysis, this system can identify the wear risk of the screw conveyor under hard rock transportation conditions earlier and more accurately because it considers the impact of the cutterhead's hard rock cutting condition on the screw conveyor, thus establishing an intrinsic link between the cutterhead's working condition and the screw conveyor's wear. By introducing a target wear correction coefficient and a target health index, this system achieves a quantitative assessment of the wear degree of the screw conveyor, enabling maintenance decisions to shift from experience-based judgment to data-driven approaches. In addition, determining the target repair strategy based on the quantified health index can provide more targeted and economical repair solutions, avoiding over-repair or under-repair, thereby extending the service life of the screw conveyor, reducing maintenance costs, and improving the overall operating efficiency and safety of the shield tunneling machine. This system can effectively avoid emergency repairs caused by misjudgment of wear, achieving more planned maintenance and demonstrating significant technological advancements.

[0099] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for processing data on wear and repair of tunnel boring machine components, characterized in that, The methods include: Acquire the cutterhead operation data of the tunnel boring machine and the conveying operation data of the tunnel boring machine's screw conveyor; The screw conveyor is detected as being in hard rock transport mode based on the cutter head operation data and the conveying operation data. When the screw conveyor is detected to be in a hard rock transport state, the target wear correction coefficient of the screw conveyor is determined based on the transport operation data; The target health index of the screw conveyor is determined based on the number of times the screw conveyor has been in hard rock transport mode since the last maintenance and the target wear correction coefficient of the screw conveyor for each time it is in hard rock transport mode. If the target health index is less than a preset threshold, a target repair strategy for the screw conveyor is determined based on the target health index.

2. The method for processing data on wear and repair of tunnel boring machine components according to claim 1, characterized in that, Detecting whether the screw conveyor is in hard rock transport mode based on the cutterhead operation data and the conveying operation data includes: Detect whether the cutter head is in a hard rock cutting state based on the cutter head operation data; If the cutterhead is detected to be in a hard rock cutting state, the screw conveyor is detected to be in a hard rock transport state based on the transport operation data.

3. The method for processing data on wear and repair of tunnel boring machine components according to claim 2, characterized in that, The cutterhead operating data includes the drive torque of the cutterhead, the vibration data of the cutterhead's hobbing cutter, and the temperature of the hobbing cutter. Detecting whether the cutterhead is in a hard rock cutting state based on the cutterhead operating data includes: Determine whether the driving torque is within a first preset range, whether the vibration data is within a second preset range, and whether the temperature is within a third preset range; If both are true, it is determined that the cutter head is in a hard rock cutting state.

4. The method for processing data on wear and repair of tunnel boring machine components according to claim 2, characterized in that, The conveying operation data includes the drive current of the screw conveyor, the frequency and intensity of the sound collected by the sound acquisition device installed on the casing of the screw conveyor, and, when the cutterhead is detected to be in a hard rock cutting state, detecting whether the screw conveyor is in a hard rock transport state based on the conveying operation data, including: Determine whether, within a preset time period after the first moment, the rate of change of the driving current is greater than a first threshold, the frequency is within a fourth preset range, and the intensity is greater than a second threshold. The first moment is the moment when the cutter head is detected to be in a hard rock cutting state. If both are true, it is determined that the screw conveyor is in a hard rock transport state.

5. The method for processing data on wear and repair of tunnel boring machine components according to claim 4, characterized in that, When the screw conveyor is detected to be in a hard rock transport state, a target wear correction coefficient for the screw conveyor is determined based on the transport operation data, including: A first duration is determined; the first duration is the duration between a first moment and a second moment, where the second moment is the moment when the screw conveyor is detected to be in hard rock transport mode; The target wear correction coefficient for the screw conveyor is determined based on the current change rate at the first time interval and the second time interval.

6. The method for processing data on wear and repair of tunnel boring machine components according to claim 5, characterized in that, The target wear correction coefficient for the screw conveyor is determined based on the current change rate at the first time interval and the second time interval, including: Obtain the first correspondence; the first correspondence includes a one-to-one correspondence between multiple pieces of first information and multiple wear correction coefficients, the first information includes a duration range and a current change rate range, the wear correction coefficient is negatively correlated with the minimum value in the corresponding duration range, and the wear correction coefficient is positively correlated with the minimum value in the corresponding current change rate range; The wear correction coefficient corresponding to the first information in the first correspondence relationship, where the current change rate at the first time and the second time is located, is taken as the target wear correction coefficient.

7. The method for processing data on wear and repair of tunnel boring machine components according to claim 1, characterized in that, The target health index of the screw conveyor is determined based on the number of times the screw conveyor has been in hard rock transport mode since its last maintenance, and the target wear correction coefficient of the screw conveyor for each instance of being in hard rock transport mode. This includes: The product of the first difference and the first weight is used as the first sub-target health index; the first difference is the difference between 1 and the ratio of the number of times to the preset maximum number of times; The product of the second difference and the second weight is used as the second sub-target health index; the second difference is the difference between 1 and the average of multiple target wear correction coefficients; The target health index is determined based on the first sub-target health index and the second sub-target health index.

8. The method for processing data on wear and repair of tunnel boring machine components according to claim 7, characterized in that, Determining the target health index based on the first sub-target health index and the second sub-target health index includes: Obtain the wear resistance index of the screw conveyor; The product of the wear resistance index and the third weight is taken as the third sub-target health index; the sum of the first weight, the second weight and the third weight is 1; The sum of the first sub-target health index, the second sub-target health index, and the third sub-target health index is taken as the target health index.

9. The method for processing data on wear and repair of tunnel boring machine components according to claim 1, characterized in that, If the target health index is less than a preset threshold, a target repair strategy for the screw conveyor is determined based on the target health index, including: Obtain a second correspondence; the second correspondence includes a one-to-one correspondence between multiple target health indices and multiple repair strategies, wherein the repair strategies are used to repair the screw conveyor, and the repair intensity of the repair strategy is negatively correlated with the corresponding target health index; The repair strategy corresponding to the target health index in the second correspondence is taken as the target repair strategy.

10. A data processing system for wear and repair of tunnel boring machine components, characterized in that, The system includes: an acquisition device and a processing device; The acquisition device is used to acquire the cutterhead operation data of the tunnel boring machine and the conveying operation data of the screw conveyor of the tunnel boring machine. The processing device is used to detect whether the screw conveyor is in a hard rock transport state based on the cutter head operation data and the conveying operation data. The processing device is used to determine the target wear correction coefficient of the screw conveyor based on the conveying operation data when the screw conveyor is detected to be in a hard rock transport state. The processing device is used to determine the target health index of the screw conveyor based on the number of times the screw conveyor has been in hard rock transport mode since the last maintenance and the target wear correction coefficient of the screw conveyor corresponding to each time the screw conveyor is in hard rock transport mode. The processing device is used to determine a target repair strategy for the screw conveyor based on the target health index when the target health index is less than a preset threshold.

Images