Intelligent early warning method for typical faults of shield

Abstract

The invention provides a shield typical fault intelligent early warning method. The first data value is larger than the second data value, and the first data value and the second data value are determined according to the maximum value and the minimum value of a plurality of data values contained in the initial state data. Generally, the first data value is less than a maximum value in the initial state data and the second data value is greater than a minimum value in the initial state data. In initial state data, due to the fact that in the data transmission and data collection process, some information fluctuation situations possibly occur, and the situation often causes the situation that individual data values are extremely large or extremely small. The individual maximum or minimum numerical values can pollute the data, so that the first data value and the second data value need to be determined to remove the maximum or minimum numerical values so as to achieve the effect of purifying the data, and then the accuracy of fault diagnosis of the shield tunneling machine can be improved.

Description

Technical Field Technical Field

[0001] The present invention relates to the technical field of shield machine fault early warning, and particularly to an intelligent early warning method for typical shield machine faults. Background Art

[0002] With the vigorous development of China's infrastructure industry, shields are widely used in engineering fields such as highways, water conservancy, subways, and railways. At present, the total tunnel mileage in China has exceeded 50,000 kilometers, and the total scale of under-construction and in-service tunnels ranks first in the world. The health status of the key components of the shield TBM during the whole life cycle is related to the tunneling efficiency and has a great impact on the productivity of the entire tunnel construction.

[0003] At present, there is already monitoring of the core components of the shield TBM construction equipment, but the intelligent analysis and early warning technology for key components has not been implemented yet. Only the operating status of key components can be observed. Therefore, it is particularly necessary to deploy an intelligent algorithm model to realize the early warning of typical fault signals and ensure the safe and stable operation of the equipment.

[0004] In view of the problem that the on-line measurement of the bearing clearance of the main drive bearing cannot be carried out during the shield tunneling process, the present invention designs an intelligent early warning method for typical shield TBM faults to realize the real-time monitoring of typical shield TBM faults and ensure the safe and reliable operation of the equipment. Summary of the Invention

[0005] In view of the above problems, the present invention is proposed to provide an intelligent early warning method for typical shield machine faults that can overcome or at least partially solve the above problems, which can solve the problem of poor early warning effect of the shield machine fault early warning system and achieve the problem of improving the safety during the movement of the shield machine.

[0006] Specifically, the present invention provides an intelligent early warning method for typical shield machine faults, and the intelligent early warning method for typical shield machine faults includes: Obtain the initial motion state information of the shield machine and convert the initial operation state information into a plurality of initial state data; Eliminate the numerical values in the initial state data that are greater than the first data value and less than the second data value to obtain the first remaining data; Judge whether the continuous part of the first remaining data has repeated data values; If so, eliminate one of the repeated values to obtain the second remaining data, and convert the second remaining data into standard data; Obtain the operation state information of the shield machine and convert the operation state information into motion state data; Correspond the data values in the motion state data with the data values of the standard data, and determine whether the data values in the motion state data are greater than or less than the corresponding data values of the standard data; If so, a fault occurs at the corresponding position of the shield machine at the corresponding position of the motion state data.

[0007] Optionally, the intelligent early warning method for typical shield machine faults further includes: Store the motion state data at the fault position and mark it as fault data; Form an intelligent algorithm model with multiple pieces of the fault data; Use the intelligent algorithm model to monitor the operation state of the shield machine in real time.

[0008] Optionally, in the step of forming an intelligent algorithm model with multiple pieces of the fault data, it includes: Train multiple pieces of the fault data through yolov8 to form an intelligent algorithm model; Deploy the intelligent algorithm model to the cloud and electrically connect it to a remote monitoring device.

[0009] Optionally, in the step of obtaining the initial motion state information of the shield machine, it includes: Obtain the initial motion state information of each mechanism of the shield machine, so that each mechanism has a corresponding set of the initial motion state information, and each set of the initial motion state information corresponds to an initial state data.

[0010] Optionally, in the step of removing the values in the initial state data that are greater than the first data value and less than the second data value, it includes: Obtain the first data value and the second data value according to the multiple data values in the initial state data; Determine the standard data interval according to the interval between the first data value and the second data value; Judge whether the multiple data values in the initial state data are within the standard data interval; If so, remove this data value.

[0011] Optionally, in the step of determining the standard data interval according to the interval between the first data value and the second data value, it includes: Convert the interval between the first data value and the second data value into frequency data and / or waveform data; Determine the standard data interval according to the frequency data and / or waveform data.

[0012] In the intelligent early warning method for typical shield tunneling machine failures of the present invention, the first data value is greater than the second data value, and the first data value and the second data value are determined based on the maximum and minimum values among the multiple data values included in the initial state data. Generally speaking, the first data value is less than the maximum value in the initial state data, and the second data value is greater than the minimum value in the initial state data. In the initial state data, due to information fluctuations that may occur during data transmission and data collection, individual data values may be extremely large or extremely small. These individual extremely large or extremely small values will contaminate the data. Therefore, it is necessary to determine the first data value and the second data value to eliminate the extremely large or extremely small values, thereby achieving the effect of purifying the data, and further improving the accuracy of shield tunneling machine failure diagnosis. Since the acquired data is periodic, there may be overlapping parts in the data of two adjacent cycles. Therefore, it is necessary to eliminate one of the duplicate data values to further purify the data and avoid interference from duplicate values on subsequent failure diagnosis. In summary, this method can eliminate interference data, thereby improving the accuracy of monitoring shield tunneling machine failures, and further ensuring the safety and reliability of shield tunneling machine operation.

[0013] From the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more clearly aware of the above and other objects, advantages, and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Some specific embodiments of the present invention will be described in detail hereinafter with reference to the accompanying drawings in an exemplary and non-limiting manner. The same reference numerals in the drawings denote the same or similar components or parts. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings: Figure 1 is a schematic flowchart of an intelligent early warning method for typical shield tunneling machine failures according to an embodiment of the present invention; Figure 2 is a schematic partial flowchart of an intelligent early warning method for typical shield tunneling machine failures according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] The following refers to Figures 1 to 2The intelligent early warning method for typical shield tunneling failures in the embodiments of the present invention will be described. In the description of the embodiments of the present invention, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one of such features, that is, include one or more of such features. In the description of the present invention, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise specifically defined. When a certain feature "includes or contains" a certain or certain features it covers, unless otherwise specifically described, this indicates that other features are not excluded and other features may be further included.

[0016] Unless otherwise clearly specified and defined, the terms "arranged", "installed", "connected", "coupled", "fixed", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two components or the interaction relationship between two components, unless otherwise clearly defined. Those of ordinary skill in the art should be able to understand the specific meanings of the above terms in the present invention according to specific circumstances.

[0017] In addition, in the description of the embodiments, the first feature being "above" or "below" the second feature may include the first and second features being in direct contact, or may include the first and second features not being in direct contact but in contact through additional features therebetween. That is, in the description of the embodiments, the first feature being "above", "over", and "on" the second feature includes the first feature being directly above and obliquely above the second feature, or merely indicating that the first feature has a higher horizontal height than the second feature. The first feature being "under", "beneath", or "underneath" the second feature may be the first feature being directly below or obliquely below the second feature, or merely indicating that the first feature has a lower horizontal height than the second feature.

[0018] In the description of the embodiments, the description with reference to terms such as "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples.

[0019] Figure 1 is a schematic flowchart of the intelligent early warning method for typical shield tunneling failures, as Figure 1As shown in and referring to Figure 2 , an embodiment of the present invention provides an intelligent early warning method for typical shield tunneling machine failures. The intelligent early warning method for typical shield tunneling machine failures includes: S100. Obtain the initial motion state information of the shield tunneling machine and convert the initial operating state information into a plurality of initial state data; S200. Eliminate the numerical values in the initial state data that are greater than the first data value and less than the second data value to obtain the first remaining data; S300. Determine whether there are duplicate values in the continuous part of the plurality of first remaining data; S400. If so, eliminate one of the duplicate values to obtain the second remaining data and convert the second remaining data into standard data; S500. Obtain the operating state information of the shield tunneling machine and convert the operating state information into motion state data; S600. Corresponding the data values in the motion state data with the data values in the standard data, and determine whether the data values in the motion state data are greater than or less than the corresponding data values in the standard data; S700. If so, a failure occurs at the corresponding position of the shield tunneling machine at the position corresponding to the data value of the motion state data; S710. If not, the motion state of the shield tunneling machine is normal.

[0020] Specifically, the initial motion state of the shield tunneling machine is the motion state in the normal working state within the preset time after the shield tunneling machine starts, that is, it means that each mechanism of the shield tunneling machine is in a healthy state. Therefore, the initial motion state information of the shield tunneling machine is the healthy state information in the normal working state of the shield tunneling machine. That is to say, the initial state data is the corresponding data in the normal working state of the shield tunneling machine, and each or each group of data is composed of a plurality of corresponding numerical values.

[0021] Furthermore, the first data value is greater than the second data value, and the first data value and the second data value are determined according to the maximum and minimum values of the multiple data values included in the initial state data. Generally speaking, the first data value is less than the maximum value in the initial state data, and the second data value is greater than the minimum value in the initial state data. In the initial state data, due to information fluctuations that may occur during data transmission and data collection, this situation often causes individual data values to be extremely large or extremely small. These individual extremely large or extremely small numerical values will contaminate the data. Therefore, it is necessary to determine the first data value and the second data value to eliminate the extremely large or extremely small numerical values so as to achieve the effect of purifying the data, and further improve the accuracy of the shield tunneling machine failure diagnosis.

[0022] Furthermore, since the acquired data is periodic, there may be overlapping parts in the data of two adjacent periods. Therefore, one of the duplicate data values needs to be removed to further purify the data, so as to avoid the interference of duplicate values on later fault diagnosis.

[0023] Specifically, the motion state information of the shield machine is the motion state information during the shield tunneling operation. Therefore, the motion state data can reflect the motion state information of each mechanism of the shield machine. When the numerical value in the motion state data is within the data interval formed by the standard data, it indicates that the states of each mechanism of the shield machine are normal. If individual data values are greater than or less than the data interval formed by the standard data, it means that the corresponding mechanism of the shield machine has a fault, so that the fault location of the shield machine can be quickly judged to achieve the effect of early warning and avoid further damage to the shield machine due to motion.

[0024] Furthermore, one of the duplicate values is removed. Use the Pandas library to read the data and check for missing values, use duplicated() to identify duplicate values, and use drop_duplicates() to delete duplicate values.

[0025] In some embodiments of the present invention, as Figure 1 and Figure 2 shown, the intelligent early warning method for typical shield machine faults further includes: S800. Store the motion state data of the fault location and mark it as fault data; S900. Form an intelligent algorithm model from multiple pieces of fault data; S910. Use the intelligent algorithm model to monitor the running state of the shield machine in real time.

[0026] Specifically, the fault data is uploaded to the cloud for storage, thus realizing cloud deployment. Connect the server for locally monitoring the running state of the shield machine to the server. Furthermore, the intelligent algorithm model is deployed at the edge side to realize real-time monitoring and early warning of the shield machine state at the edge side.

[0027] In some embodiments of the present invention, as Figure 1 and Figure 2 shown, in forming an intelligent algorithm model from multiple pieces of fault data, it includes: S920. Train multiple pieces of fault data through yolov8 to form an intelligent algorithm model; S930. Deploy the intelligent algorithm model to the cloud and electrically connect it to the remote monitoring device.

[0028] Specifically, cloud deployment enables data sharing, thereby expanding the training samples and further enhancing the intelligence level of the intelligent algorithm model. Further, remote monitoring enables the control center to quickly and constantly grasp the motion state of the shield machine.

[0029] In some embodiments of the present invention, as Figure 1 and Figure 2 shown, in obtaining the initial motion state information of the shield machine, it includes: S110. Obtain the initial motion state information of each mechanism of the shield machine, so that each mechanism has a corresponding set of initial motion state information, and each set of initial motion state information corresponds to an initial state data.

[0030] Specifically, the various mechanisms of the shield machine are respectively the shield TBM cutter head, the main drive, the main bearing, etc. Each main mechanism forms an initial motion state information, that is, an initial state data corresponds to a mechanism of the shield machine. Further, the shield machine includes a motion sensing system and a signal collector. The motion sensing system is used to receive and obtain the initial motion state information, and convey the obtained initial state information to the signal collector. The signal collector classifies the initial motion state information corresponding to different mechanisms.

[0031] In some embodiments of the present invention, as Figure 1 and Figure 2 shown, in eliminating the numerical values greater than the first data value and less than the second data value in the initial state data, it includes: S210. According to multiple data values in the initial state data, obtain the first data value and the second data value; S220. Determine the standard data interval according to the interval between the first data value and the second data value; S230. Judge whether the multiple data values in the initial state data are within the standard data interval; S240. If so, eliminate this data value.

[0032] Specifically, the abnormal data that is too large or too small in the initial state data is eliminated through the standard data interval to complete data cleaning. Further, data normalization processing is performed on the data after eliminating duplicate data values to realize the processing and classification of data training samples.

[0033] In some embodiments of the present invention, as Figure 1 and Figure 2 shown, in determining the standard data interval according to the interval between the first data value and the second data value, it includes: S221. Convert the interval between the first data value and the second data value into frequency data and / or waveform data; S222. Determine the standard data interval according to the frequency data and / or waveform data.

[0034] Specifically, the frequency data and / or waveform data can intuitively reflect individual data that is too large or too small, thereby improving the efficiency of data processing.

[0035] At this point, those skilled in the art should recognize that, although multiple exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications that conform to the principles of the present invention can still be directly determined or derived based on the content disclosed in the present invention without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention should be understood and recognized as covering all these other variations or modifications.

Claims

1. An intelligent early warning method for typical faults of shield machines, characterized in that: include: Acquiring initial motion state information of the shield machine, and converting the initial motion state information into a plurality of initial state data; Eliminate values ​​greater than the first data value and less than the second data value in the initial state data to obtain first remaining data; determining whether a continuous portion of the first remaining data has a repeated data value; If so, remove one of the data values ​​in the repeated values ​​to obtain second remaining data, and convert the second remaining data into standard data; Acquiring the operating status information of the shield machine and converting the operating status information into motion status data; Comparing the data value in the motion state data with the data value of the standard data, and determining whether the data value in the motion state data is greater than or less than the corresponding data value of the standard data; If so, a fault occurs at a corresponding position of the shield machine corresponding to the motion state data.

2. The intelligent early warning method for typical faults of shield machines according to claim 1 is characterized in that: Also includes: The motion state data of the fault position is stored and marked as fault data; Forming an intelligent algorithm model with the plurality of fault data; The intelligent algorithm model is used to monitor the operating status of the shield machine in real time.

3. The intelligent early warning method for typical faults of shield machines according to claim 2 is characterized in that: In forming the intelligent algorithm model from the plurality of fault data, it includes: Training the plurality of fault data through yolov8 to form an intelligent algorithm model; The intelligent algorithm model is deployed in the cloud and electrically connected to the remote monitoring equipment.

4. The intelligent early warning method for typical faults of shield machines according to claim 1 is characterized in that: The obtaining of the initial motion state information of the shield machine includes: The initial motion state information of each mechanism of the shield machine is obtained, so that each mechanism has a corresponding set of the initial motion state information, and each set of the initial motion state information corresponds to one initial state data.

5. The intelligent early warning method for typical faults of shield machines according to claim 1 is characterized in that: The step of eliminating values ​​greater than the first data value and less than the second data value in the initial state data includes: Acquire a first data value and a second data value according to a plurality of data values ​​in the initial state data; Determine a standard data interval according to an interval between the first data value and the second data value; Determining whether a plurality of data values ​​in the initial state data are within the standard data interval; If so, remove the data value.

6. The intelligent early warning method for typical faults of shield machines according to claim 5 is characterized in that: In the step of determining the standard data interval according to the interval between the first data value and the second data value, the method includes: converting the first data value and the second data value into frequency data and / or waveform data; The standard data interval is determined according to frequency data and / or waveform data.

Images