Shield grease dosage intelligent early warning method and system based on AI algorithm

Abstract

The invention provides a shield grease consumption intelligent early warning method and system based on an AI algorithm. The grease consumption data of the shield grease pumping mechanism is obtained when the shield tunneling machine advances in rings with different diameters, and a native database is formed. And meanwhile, a historical experience database of the grease dosage of the shield grease pumping mechanism is obtained. And performing data aggregation on the native database and the experience database to obtain a multi-dimensional feature vector. And acquiring the safe use amount range of grease when the shield tunneling machine tunnels the plurality of rings by using an LSTM algorithm according to the multi-dimensional feature vector. And obtaining the actual grease dosage in the process of tunneling the plurality of rings by the shield tunneling machine. And judging whether the actual grease dosage is within the safe dosage range or not. If not, an abnormal alarm is given out for the shield grease pumping mechanism, so that the effect and efficiency of detecting the oil way of the shield tunneling machine are rapidly improved, the fault sensitivity detection is improved, and early warning is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of shield machines, in particular to a shield grease dosage intelligent early warning method and system based on an AI algorithm. BACKGROUND

[0002] As the core equipment of modern tunnel construction, the normal operation of the lubrication and sealing system of a shield machine is directly related to construction safety and engineering efficiency. During shield tunneling, the shield tail sealing system needs to continuously inject shield tail grease to fill the gap between the shield tail steel wire brush to prevent underground water and slurry from entering; the main bearing, as a key moving part, needs to rely on black grease to form a pressure barrier and maintain lubrication; and yellow grease is widely used for lubrication and protection of various moving pairs. In traditional construction, the injection of these greases often relies on manual experience judgment, and lacks precise measurement means and real-time monitoring systems. According to statistics, in a typical subway tunnel project, grease consumption can account for 15%-20% of the total cost of construction materials, and abnormal consumption may indicate major hidden dangers such as shield tail brush wear, sealing failure or bearing abnormalities.

[0003] The prior art mostly uses simple flow meters for cumulative measurement, which cannot distinguish the independent consumption characteristics of different grease systems, and it is difficult to establish a dynamic correlation model between tunneling parameters (such as thrust, torque, and ground conditions) and grease dosage. More notably, when there is a sudden change in grease consumption, the existing system can only provide a lagging alarm and cannot achieve early warning based on trend prediction. This technical defect makes it difficult for the construction party to optimize grease usage strategies to achieve cost reduction and efficiency improvement, and it is also impossible to identify potential equipment failures in a timely manner, which may lead to water and sand inrush accidents caused by sealing failure, resulting in significant economic losses and safety risks. Therefore, developing a grease consumption management system with multi-dimensional monitoring, intelligent analysis and forward-looking warning functions has become an urgent need for the intelligent transformation of shield construction. SUMMARY

[0004] In view of the above problems, the present application provides a shield grease dosage intelligent early warning method based on an AI algorithm, which can solve the problem of difficulty in detecting faults of the grease pumping mechanism during shield machine construction, and improve the detection sensitivity of the shield machine grease pumping mechanism to achieve early warning.

[0005] Specifically, the present application provides a shield grease dosage intelligent early warning method based on an AI algorithm, which comprises:

[0006] Obtaining the grease dosage data of the shield grease pumping mechanism when the shield machine travels in rings of different diameters, and forming a primary database; and simultaneously obtaining a historical experience database of the grease dosage of the shield grease pumping mechanism;

[0007] converging the original database and the experience database, and respectively acquiring a multi-dimensional feature vector according to data type, data time sequence, and data trend;

[0008] acquiring a safe grease consumption range of the shield tunneling machine during the multiple rings according to the multi-dimensional feature vector by using an LSTM algorithm;

[0009] acquiring an actual grease consumption during the process of the shield tunneling machine tunneling the multiple rings;

[0010] judging whether the actual grease consumption is within the safe consumption range;

[0011] if not, issuing an abnormal alarm information of the shield grease pumping mechanism.

[0012] Optionally, in the step of acquiring the grease consumption data of the shield grease pumping mechanism, the step comprises:

[0013] acquiring a stroke difference L of the shield grease pumping mechanism at an initial state and an end state of the shield tunneling machine in each ring; and an oil tank height H of the shield grease pumping mechanism, and a weight M of the grease in the oil tank at the initial state;

[0014] the grease consumption data = (L / H)*M.

[0015] Optionally, in the step of acquiring the safe grease consumption range of the shield tunneling machine during the multiple rings according to the feature vector by using the LSTM algorithm, the step further comprises:

[0016] acquiring a future grease consumption and a fluctuation range of the future grease consumption of the shield tunneling machine during the multiple rings according to the feature vector;

[0017] acquiring a maximum threshold and a minimum threshold of the future grease consumption according to the future grease consumption and the fluctuation range, and recording a range greater than the minimum threshold and smaller than the maximum threshold as the safe consumption range.

[0018] Optionally, in the step of acquiring the safe grease consumption range of the shield tunneling machine during the multiple rings according to the feature vector by using the LSTM algorithm, the step further comprises:

[0019] classifying the safe consumption range according to the size of the ring diameter of the shield tunneling machine, so as to constitute the safe consumption range related to the ring diameter.

[0020] Optionally, in the step of converging the original database and the experience database, and respectively acquiring a multi-dimensional feature vector according to data type, data time sequence, and data trend, the step comprises:

[0021] The feature vectors of the data types, the feature vectors of the data time sequences and the feature vectors of the data trends are fused by using an AI algorithm to form a multi-dimensional feature vector.

[0022] The application provides an AI algorithm-based intelligent early warning system for shield grease consumption.

[0023] The acquisition and calculation module is used to acquire the original grease consumption data of the shield grease pumping mechanism when the shield machine is tunneling in each ring.

[0024] The original database module is connected with the acquisition and calculation module and is used to record the original grease consumption data corresponding to the rings of different diameters tunnelled by the shield machine.

[0025] The experience database module stores a plurality of shield engineering historical data, and acquires experience grease consumption data corresponding to the rings of different diameters tunnelled by a plurality of shield machines according to the shield engineering historical data.

[0026] The intelligent early warning module acquires the maximum threshold and the minimum threshold of the safe grease consumption of the shield machine according to the original grease consumption data and the experience grease consumption data, and judges the abnormal information of the shield machine according to the maximum threshold and the minimum threshold.

[0027] Optionally, the original data module comprises a data storage module and a historical data query module.

[0028] The data storage module is used to record and store the original grease consumption data.

[0029] The historical data query module is used to quickly query the original grease consumption data corresponding to the rings of different diameters.

[0030] Optionally, the acquisition and calculation module comprises a TOF acquisition module and a consumption conversion module.

[0031] The TOF acquisition module is arranged at the top of the grease barrel of the shield grease pumping mechanism and is used to acquire the oil consumption information in the shield grease pumping mechanism.

[0032] The consumption conversion module is used to acquire the original grease consumption data according to the oil consumption information.

[0033] Optionally, the experience database module includes a big data analysis module;

[0034] The big data analysis module is used to classify the rings of different diameters excavated by the tunnel boring machine.

[0035] This invention presents an AI-based intelligent early warning method for shield tunneling grease usage. It achieves real-time, accurate collection and storage of grease usage information through automation, overcoming the limitations of traditional manual recording and improving data integrity and efficiency. By leveraging AI algorithms to deeply analyze historical experience data and equipment parameters, it accurately identifies abnormal fluctuations in usage, such as surges caused by leaks or equipment malfunctions, enabling intelligent early warning. This constructs a fully intelligent closed-loop process from data collection and analysis to early warning, promoting the digital and intelligent transformation of grease management in shield tunneling construction. It helps maintenance personnel respond quickly to problems, reduces equipment downtime, lowers maintenance costs, and comprehensively improves the intelligence level and overall efficiency of tunnel construction.

[0036] Furthermore, the actual grease usage refers to the grease usage of the shield grease pumping mechanism during actual tunneling. The step of determining whether the actual grease usage falls within the safe usage range can quickly confirm whether there is a fault in the oil circuit of the shield grease pumping mechanism of the shield machine in operation by using the original data of the shield machine and the historical experience data of other shield machines to form a safe usage range. This improves the effectiveness and efficiency of detecting the shield machine's oil circuit and increases the sensitivity of fault detection, so as to achieve early warning.

[0037] The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments of the invention in conjunction with the accompanying drawings. Attached Figure Description

[0038] The following sections will describe some specific embodiments of the invention in detail by way of example and not limitation, with reference to the accompanying drawings. The same reference numerals in the drawings denote the same or similar parts or portions. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0039] Figure 1 This is a schematic flowchart of an intelligent early warning method for shield tunnel grease usage based on an AI algorithm according to an embodiment of the present invention.

[0040] Figure 2 This is a schematic flowchart of an intelligent early warning method for shield tunnel grease usage based on an AI algorithm according to an embodiment of the present invention.

[0041] Figure 3 This is a schematic flowchart of an intelligent early warning method for shield tunnel grease usage based on an AI algorithm according to an embodiment of the present invention.

[0042] Figure 4 This is a schematic structural diagram of an intelligent early warning system for shield tunnel grease usage based on an AI algorithm according to an embodiment of the present invention. Detailed Implementation

[0043] The following reference Figures 1 to 4 This invention describes an AI-based intelligent early warning method for tunnel boring machine grease usage according to an embodiment of the present invention. In this description, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature, that is, include one or more of that feature. In the description of the present invention, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. When a feature "includes or contains" one or more of the features it encompasses, unless otherwise specifically described, this indicates that other features are not excluded and may be further included.

[0044] Unless otherwise expressly specified and limited, the terms "set up," "install," "connect," "link," "fix," and "couple" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art should be able to understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0045] Furthermore, in the description of this embodiment, "above" or "below" the second feature can include direct contact between the first and second features, or it can include contact between the first and second features through another feature between them. That is, in the description of this embodiment, "above," "over," and "on top" of the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," or "below" of the second feature can mean the first feature is directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0046] In the description of this embodiment, the terms "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0047] Figure 1 This is a schematic flowchart illustrating the AI ​​algorithm-based intelligent early warning method for tunnel boring machine grease usage, such as... Figure 1 As shown, and with reference Figures 2 to 4 This invention provides an AI-based intelligent early warning method for shield tunneling grease usage, which includes:

[0048] S100: Obtain grease consumption data of the shield grease pumping mechanism when the shield machine travels through rings of different diameters, and construct a native database; at the same time, obtain a historical experience database of grease consumption of the shield grease pumping mechanism.

[0049] S200. Aggregate the data from the native database and the experience database, and obtain multi-dimensional feature vectors based on data type, data time series and data trend respectively.

[0050] S300: Use the LSTM algorithm to obtain the safe range of grease usage when the tunnel boring machine is excavating multiple rings based on multi-dimensional feature vectors;

[0051] S400: Obtain the actual grease usage during multiple stages of tunneling by the tunnel boring machine;

[0052] S500, Determine whether the actual amount of oil used is within the safe usage range;

[0053] S600, if not, issue an alarm message for abnormality in the shield tunnel grease pumping mechanism.

[0054] Specifically, the shield tunneling grease pump mechanism delivers grease to specific locations via grease pumping pipelines during shield machine operation. Therefore, the amount of grease used during shield tunneling is constant. However, the amount of grease used varies depending on the ring diameter during tunneling. Thus, grease usage data can be categorized based on ring diameter. It should be noted that when the shield machine operates in areas with larger ring diameters, the shield diameter is larger, and consequently, the grease usage is lower, and vice versa. Furthermore, using the base of the grease tank of the shield tunneling grease pump mechanism as the target point, the travel distance of the grease pump mechanism is continuously measured from top to bottom, and then this travel distance is converted into grease usage. It should be noted that the original database contains the grease usage data for this specific shield machine.

[0055] Furthermore, the historical experience database is a collection of data on grease usage generated by tunnel boring machines (TBMs) other than this one during excavation within rings of different diameters in previous tunnel projects. This historical experience database can also be connected to the cloud or the internet to upload or embed grease usage data from TBMs in different tunnel projects, thereby expanding the reference sample.

[0056] Furthermore, the data type represents the grease consumption corresponding to tunnel boring machines (TBMs) with different ring diameters; the data time series represents the grease consumption corresponding to the length of the TBM's operating time or the length of its lifespan; and the data trend represents the corresponding changes in grease consumption as the TBM's operating time, lifespan, or ring diameter changes. For example, the grease consumption of the TBM's grease pumping mechanism is positively correlated with the diameter of the working ring. Moreover, the multidimensional feature vector can comprehensively and accurately reveal the optimal grease consumption under complex and variable conditions, and can be used to determine the safe grease consumption range.

[0057] Furthermore, the actual grease usage refers to the grease usage of the shield grease pumping mechanism during actual tunneling. The step of determining whether the actual grease usage falls within the safe usage range can quickly confirm whether there is a malfunction in the oil circuit of the shield grease pumping mechanism of the shield machine in operation by using the original data of the shield machine and the historical experience data of other shield machines to form a safe usage range. This can quickly improve the effectiveness and efficiency of testing the shield machine's oil circuit.

[0058] In some embodiments of the present invention, such as Figure 2 and Figure 3 As shown, the steps for obtaining grease usage data of the shield tunneling grease pumping mechanism include:

[0059] S110. Obtain the stroke difference L between the initial state and the end state of the tunnel boring machine in each ring of the shield grease pumping mechanism; and the height of the oil tank of the shield grease pumping mechanism is H, and the weight of the grease in the oil tank in the initial state is M.

[0060] S120, Oil usage data = (L / H)*M.

[0061] Specifically, multiple oil usage data are stored and form a historical experience database.

[0062] In some embodiments of the present invention, such as Figure 2 and Figure 3 As shown, the step of using the LSTM algorithm to obtain the safe range of grease usage when a tunnel boring machine is excavating multiple rings based on the feature vector also includes:

[0063] S310. Obtain the future grease usage and fluctuation range of future grease usage when the tunnel boring machine is excavating multiple rings based on the feature vector;

[0064] S320. Based on the future oil consumption and fluctuation range, obtain the maximum and minimum thresholds for future oil consumption, and record the ranges greater than the minimum threshold and less than the maximum threshold as the safe consumption range.

[0065] Specifically, the future grease usage is a prediction of the grease usage during the pre-construction phase of the tunnel boring machine. Furthermore, based on the LSTM algorithm, through time-series data feature extraction, anomaly detection model construction, and alarm strategy generation, the system identifies and issues alarms regarding abnormal grease usage information.

[0066] In some embodiments of the present invention, such as Figure 2 and Figure 3 As shown, the step of using the LSTM algorithm to obtain the safe range of grease usage when a tunnel boring machine is excavating multiple rings based on the feature vector also includes:

[0067] S330, the size of the construction ring diameter of the foundation shield machine, classifies the safe usage range to form a safe usage range related to the ring diameter.

[0068] Specifically, the ring diameter during tunnel boring machine excavation is used as the classification basis. Combined with the analysis of historical experience data by experts, threshold classification recommends usage warning thresholds for different diameters, which serve as another criterion for intelligent early warning, thereby enabling more accurate judgment.

[0069] In some embodiments of the present invention, the step of aggregating the native database and the empirical database, and extracting feature vectors based on data type, data time series, and data trend, respectively, includes:

[0070] S210. Using AI algorithms, feature vectors of data types, feature vectors of data time series, and feature vectors of data trends are fused from multiple sources to form multi-dimensional feature vectors.

[0071] Specifically, the AI ​​algorithm, based on algorithms such as LSTM and random forest, identifies and judges abnormal information on oil usage and abnormal events in oil pumping pipelines step by step. Finally, through the early warning output module, it outputs early warning information on oil usage and early warning information on abnormal events in oil pumping pipelines.

[0072] This invention provides an intelligent early warning system for shield tunneling grease usage based on AI algorithms, such as... Figure 4 As shown, according to any of the above embodiments, the intelligent early warning method for shield tunneling grease usage based on AI algorithm includes an early warning system comprising a data acquisition and calculation module, a native database module, an experience database module, and an intelligent early warning module.

[0073] The data acquisition and calculation module obtains the raw grease usage data of the shield grease pumping mechanism during tunneling within each ring. The raw grease database, connected to the acquisition and calculation module, records the raw grease usage data corresponding to multiple rings of different diameters tunneled by the shield machine. The experience database module stores historical data from multiple shield tunneling projects and, based on this data, obtains the experience grease usage data corresponding to multiple rings of different diameters tunneled by the shield machine. The intelligent early warning module analyzes and processes the raw and experience grease usage data to obtain the maximum and minimum thresholds for safe grease usage for the shield machine, and uses these thresholds to identify any abnormal information about the shield machine.

[0074] In a further embodiment, the intelligent early warning system for shield tunneling grease usage based on AI algorithms also includes an AI algorithm module. Specifically, the intelligent early warning module includes a multi-criteria fusion module. This module aggregates data from the native database and the empirical database through an API interface, and extracts feature vectors based on data type, data time series, and data trend, respectively, to provide the AI ​​algorithm module with a multi-dimensional feature vector after multi-source data fusion.

[0075] The AI ​​algorithm module includes two functions: identification and judgment of abnormal grease usage and identification and judgment of pipeline abnormal events in the shield grease pumping mechanism. For the identification and judgment of abnormal grease usage, the LSTM algorithm is adopted. The multi-dimensional feature vector of the original data processed by the multi-criteria fusion module is used as the data input. The LSTM model predicts the grease usage and fluctuation range of the shield machine in the next three rings. Based on the shield machine diameter, the corresponding threshold in the experience database is called. If the current usage or future usage exceeds or falls below the upper or lower limit of the threshold, the usage is judged to be abnormal.

[0076] Furthermore, the judgment result is transmitted to the intelligent early warning module. For the identification and judgment of abnormal events in the grease pumping pipeline, the multi-dimensional feature vector of the original data processed by the multi-criteria fusion module and the historical usage data are used as data input. At the same time, based on the diameter of the tunnel boring machine, the corresponding threshold in the experience database is called, and a decision tree of current usage, historical usage and experience usage is constructed using the random forest algorithm. If the grease usage is consistently lower than the threshold, it can be preliminarily judged as an abnormality in the pumping pipeline.

[0077] Furthermore, by optimizing parameters, training models, and evaluating the feedback between predicted and actual results, the accuracy of abnormal event detection is improved, and the detection results are transmitted to the intelligent early warning module.

[0078] In some embodiments of the present invention, such as Figure 4 As shown, the native data module includes a data storage module and a historical data query module. The data storage module is used to record and store multiple native oil usage data, while the historical data query module is used to quickly query the oil usage data corresponding to different diameter rings.

[0079] In some embodiments of the present invention, such as Figure 4 As shown, the data acquisition and calculation module includes a Time-of-Flight (TOF) acquisition module and a usage conversion module. The TOF acquisition module is installed on top of the grease tank of the shield tunneling grease pumping mechanism to acquire grease usage information within the mechanism. The usage conversion module calculates the raw grease usage data based on this information.

[0080] In some embodiments of the present invention, such as Figure 4 As shown, the experience database module includes a big data analytics module. This module is used to classify rings of different diameters excavated by the tunnel boring machine.

[0081] Specifically, the big data analysis module in the experience database module is based on massive amounts of data from historical projects. It uses methods such as classification statistics and expert evaluation to conduct analysis. Since the amount of shield grease used by the tunnel boring machine is directly related to the diameter of the tunnel boring machine, the diameter of the tunnel boring machine is used as the classification basis. The maximum threshold, minimum threshold and average value of grease usage are used as targets to carry out grease usage threshold analysis, and the results are transmitted to the threshold classification module.

[0082] In this embodiment, the experience database module also includes a threshold classification module. The threshold classification module stores the maximum threshold, minimum threshold, and average value of grease usage for shield machines of different diameters and has a corresponding API interface to provide data for the multi-criteria fusion module in the intelligent early warning module.

[0083] Therefore, those skilled in the art should recognize that although numerous exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications conforming to the principles of the present invention can be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Thus, the scope of the present invention should be understood and construed as covering all such other variations or modifications.

Claims

1. A method for intelligent early warning of grease usage in tunnel boring machines based on AI algorithms, characterized in that, include: Data on grease usage of the shield grease pumping mechanism is obtained when the shield machine travels through tunnels of different diameters, and a native database is constructed. At the same time, a historical empirical database of grease usage of the shield grease pumping mechanism is also obtained. The native database and the experience database are aggregated, and multi-dimensional feature vectors are obtained based on data type, data time series and data trend, respectively. The LSTM algorithm is used to obtain the safe range of grease usage when the tunnel boring machine is excavating multiple rings based on the multidimensional feature vector. Obtain the actual amount of grease used during the tunneling process of the tunnel boring machine in multiple rings; Determine whether the actual amount of oil used is within the safe usage range; If not, issue an alarm message for the abnormality of the shield grease pumping mechanism.

2. The intelligent early warning method for shield tunneling grease usage based on AI algorithm according to claim 1, characterized in that, The step of obtaining grease usage data for the shield tunneling grease pumping mechanism includes: Obtain the stroke difference L between the initial state and the end state of the tunnel boring machine in each ring of the shield grease pumping mechanism; and the height of the oil tank of the shield grease pumping mechanism is H, and the weight of the grease in the oil tank in the initial state is M; The amount of oil used is calculated as (L / H) * M.

3. The intelligent early warning method for shield tunneling grease usage based on AI algorithm according to claim 1, characterized in that, The step of obtaining the safe grease usage range when the tunnel boring machine is excavating multiple rings using the LSTM algorithm based on the feature vector further includes: Based on the feature vector, the future grease usage and the fluctuation range of future grease usage are obtained when the tunnel boring machine is excavating multiple rings. Based on the future oil consumption and the fluctuation range, the maximum and minimum thresholds of the future oil consumption are obtained, and the ranges greater than the minimum threshold and less than the maximum threshold are recorded as the safe consumption range.

4. The intelligent early warning method for shield tunneling grease usage based on AI algorithm according to claim 1, characterized in that, The step of obtaining the safe grease usage range when the tunnel boring machine is excavating multiple rings using the LSTM algorithm based on the feature vector further includes: Based on the size of the ring diameter constructed by the tunnel boring machine, the safety allowance range is classified to form the safety allowance range related to the ring diameter.

5. The intelligent early warning method for shield tunneling grease usage based on AI algorithm according to claim 1, characterized in that, The steps of aggregating the native database and the empirical database, and extracting feature vectors based on data type, data time series, and data trend, respectively, include: AI algorithms are used to fuse feature vectors of the data type, feature vectors of the data time series, and feature vectors of the data trend from multiple sources to form a multi-dimensional feature vector.

6. An intelligent early warning system for shield tunneling grease usage based on AI algorithms, wherein the intelligent early warning method for shield tunneling grease usage based on AI algorithms according to any one of claims 1-5 is characterized in that, include: The data acquisition and calculation module is used to acquire the original grease usage data of the shield grease pumping mechanism when the shield machine is tunneling in each ring; A native database module, which is connected to the acquisition and calculation module, is used to record the amount of native grease used for the multiple rings of different diameters excavated by the tunnel boring machine; An experience database module stores multiple historical data of shield tunneling projects, and obtains experience grease usage data corresponding to multiple rings of different diameters excavated by the shield machine based on the historical data of shield tunneling projects. The intelligent early warning module analyzes and processes multiple sets of original grease usage data and multiple sets of empirical grease usage data to obtain the maximum and minimum thresholds for the safe grease usage of the tunnel boring machine, and uses the maximum and minimum thresholds to determine abnormal information of the tunnel boring machine.

7. The intelligent early warning system for shield tunneling grease usage based on AI algorithm according to claim 6, characterized in that, The native data module includes a data storage module and a historical data query module; The data storage module is used to record and store multiple data points on the amount of the original oil used; The historical data query module is used to quickly query the amount of native oil used for rings of different diameters.

8. The intelligent early warning system for shield tunneling grease usage based on AI algorithm according to claim 6, characterized in that, The data acquisition and calculation module includes a TOF data acquisition module and a usage conversion module; The TOF acquisition module is located on top of the grease tank of the shield grease pumping mechanism and is used to acquire information on the amount of oil used in the shield grease pumping mechanism. The dosage conversion module calculates and obtains the raw oil dosage data based on the oil usage information.

9. The intelligent early warning system for shield tunneling grease usage based on AI algorithm according to claim 6, characterized in that, The experience database module includes a big data analysis module; The big data analysis module is used to classify the rings of different diameters excavated by the tunnel boring machine.

Images