A fault detection system for a smart wharf and a building method

Abstract

The present application relates to the technical field of fault detection, in particular to a fault detection system for a smart wharf and a building method, the fault detection system comprises: a data acquisition module for acquiring vibration signals of port equipment; a processing module for signal processing of the vibration signals, judging whether the vibration signals after signal processing are fault data; an extraction module for extracting fault features of the fault data according to a deep learning method, judging the fault type of the port equipment according to the fault features; a maintenance module for maintaining the port equipment according to the fault type, and changing the fault data after maintenance into normal data. The present application solves the problem of not timely discovering the fault of the port equipment in the prior art, which affects the safety of the equipment and the person or causes an accident.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault detection, in particular to a fault detection system for a smart wharf and a building method. BACKGROUND

[0002] As the key main drive equipment and supporting equipment on the port mechanical equipment, it is the key important part for the safe, efficient and stable operation of the port mechanical equipment. If these main drive equipment or supporting equipment has problems, it will directly lead to the failure, shutdown and even safety accidents of the whole port mechanical equipment. In the existing port, it is a common practice to set up a monitoring center to supervise the mechanical equipment. Although this method can basically realize the interconnection and intercommunication of the port mechanical equipment, there are still obvious defects in the collection, preservation and analysis technology of the port mechanical fault data.

[0003] The existing port mechanical equipment is repaired only after failure or equipment damage, and the maintenance of the port mechanical equipment is carried out according to the time specified in the maintenance manual. There is no similar maintenance warning method. The existing fault detection method discovers problems late, and usually the port mechanical equipment has affected or caused accidents to the wharf operation and production, even the equipment and personal safety. Therefore, how to provide a fault detection system for a smart wharf and a building method is a technical problem to be solved at present. SUMMARY

[0004] In view of the problems existing in the prior art, the purpose of the present application is to provide a fault detection system for a smart wharf and a building method. The present application builds a perfect sensor network through a platform, collects port equipment monitoring data, quickly judges whether a fault has occurred through a signal processing method, further extracts fault features through a deep learning method, makes an accurate judgment on the type of equipment fault, and gives maintenance suggestions for the port equipment according to the type and level of the fault, solving the problem of not timely discovering the port equipment fault in the prior art, which affects or causes accidents to the equipment and personal safety.

[0005] In order to achieve the above purpose, the present application provides a fault detection system for a smart wharf and a building method, which comprises:

[0006] A data acquisition module for acquiring vibration signals of port equipment;

[0007] A processing module for signal processing of the vibration signals, judging whether the vibration signals after signal processing are fault data;

[0008] An extraction module for extracting fault features of the fault data according to a deep learning method, judging the fault type of the port equipment according to the fault features;

[0009] a maintenance module for maintaining the port equipment according to the fault type, and changing the fault data after maintenance into normal data.

[0010] The vibration signal of the port equipment is a vibration signal of a motor and a gear box bearing.

[0011] In some embodiments of the present application, the signal processing of the vibration signal comprises:

[0012] collecting the vibration signal in a preset stable period t1-t2;

[0013] performing short-time Fourier transform on the vibration signal to obtain a first time-frequency spectrum, and determining a first amplitude a1 in the first time-frequency spectrum and a first frequency value a2 corresponding to the first amplitude a1.

[0014] In some embodiments of the present application, before determining whether the signal-processed vibration signal is fault data, the method comprises:

[0015] obtaining a preset normal vibration signal in historical operation data, performing signal processing on the preset normal vibration signal to obtain a second time-frequency spectrum, and determining a second amplitude b1 in the second time-frequency spectrum and a second frequency value b2 corresponding to the second amplitude b1.

[0016] calculating a difference value H of the first frequency value a2 and the second frequency value b2, and determining whether the vibration signal is fault data according to the difference value H.

[0017] In some embodiments of the present application, the determination of whether the vibration signal is fault data according to the difference value comprises:

[0018] a preset frequency difference standard value matrix W and a preset operation condition matrix C are set, for the preset frequency difference standard value matrix W, W (W1, W2, W3, W4) is set, wherein W1 is a first preset frequency difference standard value, W2 is a second preset frequency difference standard value, W3 is a third preset frequency difference standard value, and W4 is a fourth preset frequency difference standard value, and W1

[0019] for the preset operation condition matrix C, C (C1, C2, C3, C4) is set, wherein C1 is a first preset operation condition, C2 is a second preset operation condition, C3 is a third preset operation condition, and C4 is a fourth preset operation condition.

[0020] selecting the corresponding operation state of the equipment according to the relationship between the difference value H and the preset frequency difference standard value matrix W.

[0021] When H

[0022] When W1≤H

[0023] When W2≤H

[0024] When W3≤H

[0025] When W3≤H

[0026] In some embodiments of the present application, when the fault feature of the fault data is extracted according to the deep learning model, it comprises:

[0027] A first convolutional neural network is constructed, and the time-frequency spectrum set of the vibration signal in the historical database is obtained by short-time Fourier transform;

[0028] The time-frequency spectrum set is divided into a training set and a test set, the first convolutional neural network is trained according to the training set, a second convolutional neural network is obtained, the test set is identified according to the second convolutional neural network, and the operating condition of the port equipment is obtained;

[0029] The second convolutional neural network extracts the fault feature of the fault data, classifies the fault feature, and judges the fault type according to the fault feature.

[0030] In some embodiments of the present application, when the fault type of the port equipment is judged according to the fault feature, it comprises:

[0031] A preset fault feature matrix D and a preset fault type matrix Q are set, for the preset fault feature matrix D, D (D1, D2, D3, D4) is set, wherein D1 is a first preset fault feature, D2 is a second preset fault feature, D3 is a third preset fault feature, and D4 is a fourth preset fault feature;

[0032] For the preset fault type matrix Q, set Q (Q1, Q2, Q3, Q4), wherein Q1 is a first preset fault type, Q2 is a second preset fault type, Q3 is a third preset fault type, and Q4 is a fourth preset fault type;

[0033] When the fault feature of the port equipment is the first preset fault feature D1, it is determined that the fault type of the port equipment is the first preset fault type Q1;

[0034] When the fault feature of the port equipment is the second preset fault feature D2, it is determined that the fault type of the port equipment is the second preset fault type Q2;

[0035] When the fault feature of the port equipment is the third preset fault feature D3, it is determined that the fault type of the port equipment is the third preset fault type Q3;

[0036] When the fault feature of the port equipment is the fourth preset fault feature D4, it is determined that the fault type of the port equipment is the fourth preset fault type Q4.

[0037] In some embodiments of the present application, the fault detection system further comprises:

[0038] A preset alarm signal matrix F is set, for the preset alarm signal matrix F, set F (F1, F2, F3, F4), wherein F1 is a first preset alarm signal, F2 is a second preset alarm signal, F3 is a third preset alarm signal, and F4 is a fourth preset alarm signal, and F1

[0039] According to the fault type, a corresponding alarm signal is selected;

[0040] If the current port equipment fault type is the first preset fault type Q1, the first preset alarm signal F1 is selected as the current sent alarm signal;

[0041] If the current port equipment fault type is the second preset fault type Q2, the second preset alarm signal F2 is selected as the current sent alarm signal;

[0042] If the current port equipment fault type is the third preset fault type Q3, the third preset alarm signal F3 is selected as the current sent alarm signal;

[0043] If the current port equipment fault type is the fourth preset fault type Q4, the fourth preset alarm signal F4 is selected as the current sent alarm signal;

[0044] The alarm signal can determine the corresponding fault level according to the fault type of the port equipment.

[0045] In some embodiments of the present application, the fault detection system further comprises:

[0046] The maintenance module is further configured to receive an alarm signal sent according to the fault type, the alarm signal comprising a fault type and a fault level of the port equipment, and the maintenance module performs maintenance processing according to the fault level.

[0047] In some embodiments of the present application, the fault detection system further comprises:

[0048] The abnormal pre-vibration signal is obtained, and the abnormal pre-vibration signal is input into the second convolutional neural network for learning and training, and the second convolutional neural network is updated.

[0049] When the second convolutional neural network identifies that the current vibration signal is the abnormal pre-vibration signal, a pre-warning signal is sent.

[0050] The abnormal pre-vibration signal is a vibration signal before a preset time length of the fault data.

[0051] In some embodiments of the present application, a method for building a fault detection system for a smart terminal is further provided.

[0052] The vibration signals of the motor and the gear box bearing of the port are collected.

[0053] The vibration signals are processed, and it is determined whether the processed vibration signals are fault data.

[0054] The fault features of the fault data are extracted according to a deep learning method, and the fault type of the port equipment is determined according to the fault features.

[0055] The port equipment is maintained according to the fault type, and the fault data after maintenance is changed into normal data.

[0056] The present application provides a fault detection system for a smart terminal and a building method, which has the following advantages compared with the prior art:

[0057] The application discloses a fault detection system for a smart wharf and a building method. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 A structure schematic diagram of a fault detection system for a smart wharf is shown in the embodiment of the application;

[0059] Figure 2 A flow schematic diagram of a building method of a fault detection system for a smart wharf is shown in the embodiment of the application. DETAILED DESCRIPTION

[0060] The specific embodiments of the application will be further described in detail below with reference to the accompanying drawings and embodiments. The following embodiments are used to illustrate the application, but are not used to limit the scope of the application.

[0061] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0062] The terms "first", "second" are only used for description purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0063] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; 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; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0064] The following is a description of preferred embodiments of the present invention in conjunction with the accompanying drawings.

[0065] like Figure 1 As shown, an embodiment of the present invention discloses a fault detection system and a method for building a smart port. The fault detection system includes:

[0066] Data acquisition module 101 is used to acquire vibration signals from port equipment;

[0067] Processing module 102 is used to process the vibration signal and determine whether the processed vibration signal is fault data;

[0068] Extraction module 103 is used to extract fault features from the fault data using deep learning methods, and to determine the fault type of the port equipment based on the fault features;

[0069] The maintenance module 104 is used to maintain the port equipment according to the fault type and change the maintained fault data to normal data.

[0070] The vibration signals of the port equipment are the vibration signals of the motor and gearbox bearings.

[0071] In this embodiment, key components of the port machinery are inspected by installing vibration sensors on the motor and gearbox bearings of the port machinery. The vibration frequency of the bearings is one of the important characteristics for determining whether the equipment has a fault.

[0072] In some embodiments of this application, the signal processing of the vibration signal includes:

[0073] The vibration signal is collected during a preset stable period t1-t2;

[0074] The vibration signal is subjected to a short-time Fourier transform to obtain a first time spectrum, and a first amplitude a1 and a first frequency value a2 corresponding to the first amplitude a1 are determined in the first time spectrum.

[0075] In the embodiment, the short-time Fourier transform introduces a window function, which is stationary in the time interval t1-t2. The Fourier transform is performed on the signal truncated by the window function, and the spectrum analysis of the signal in the time interval is completed by the sliding window.

[0076] In some embodiments of the present application, before determining whether the signal-processed vibration signal is fault data, the method comprises:

[0077] obtaining a preset normal vibration signal in historical operation data, and performing signal processing according to the preset normal vibration signal to obtain a second time-frequency spectrum and determine a second amplitude b1 in the second time-frequency spectrum and a second frequency value b2 corresponding to the second amplitude b1;

[0078] calculating a difference value H of the first frequency value a2 and the second frequency value b2, and determining whether the vibration signal is fault data according to the difference value H.

[0079] In some embodiments of the present application, when determining whether the vibration signal is fault data according to the difference value, the method comprises:

[0080] a preset frequency difference standard value matrix W and a preset operation condition matrix C are set, for the preset frequency difference standard value matrix W, W (W1, W2, W3, W4) is set, wherein W1 is a first preset frequency difference standard value, W2 is a second preset frequency difference standard value, W3 is a third preset frequency difference standard value, and W4 is a fourth preset frequency difference standard value, and W1

[0081] for the preset operation condition matrix C, C (C1, C2, C3, C4) is set, wherein C1 is a first preset operation condition, C2 is a second preset operation condition, C3 is a third preset operation condition, and C4 is a fourth preset operation condition;

[0082] selecting the operation condition of the device according to the relationship between the difference value H and the preset frequency difference standard value matrix W;

[0083] when H

[0084] when W1≤H

[0085] When W2≤H<W3, the third preset operating condition C3 is selected as the operating condition of the current port equipment, wherein the third preset operating condition indicates that the equipment is in a medium damage state and needs to be checked and replaced regularly;

[0086] When W3≤H<W4, the fourth preset operating condition C4 is selected as the operating condition of the current port equipment, wherein the fourth preset operating condition indicates that the equipment is in a late damage state and needs to be checked and replaced immediately;

[0087] When W3≤H<W4, it is indicated that the corresponding vibration signal is fault data.

[0088] In some embodiments of the present application, when the fault feature of the fault data is extracted according to the deep learning model, it includes:

[0089] A first convolutional neural network is constructed, and time-frequency spectrum sets of the vibration signals in the historical database are obtained by short-time Fourier transform;

[0090] The time-frequency spectrum sets are divided into a training set and a test set, the first convolutional neural network is trained according to the training set, a second convolutional neural network is obtained, the second convolutional neural network identifies the test set, and the operating condition of the port equipment is obtained;

[0091] The second convolutional neural network extracts the fault feature of the fault data, and classifies the fault feature, and judges the fault type according to the fault feature.

[0092] In the present embodiment, the convolutional neural network can identify the time-frequency spectrum through training, and can judge different fault types. The second convolutional neural network that meets the training standard can judge the fault type according to different fault features, and has high accuracy.

[0093] In some embodiments of the present application, when the fault type of the port equipment is judged according to the fault feature, it includes:

[0094] A preset fault feature matrix D and a preset fault type matrix Q are set, for the preset fault feature matrix D, D (D1, D2, D3, D4) is set, wherein D1 is a first preset fault feature, D2 is a second preset fault feature, D3 is a third preset fault feature, and D4 is a fourth preset fault feature;

[0095] For the preset fault type matrix Q, Q (Q1, Q2, Q3, Q4) is set, wherein Q1 is a first preset fault type, Q2 is a second preset fault type, Q3 is a third preset fault type, and Q4 is a fourth preset fault type;

[0096] When the fault feature of the port equipment is the first preset fault feature D1, it is judged that the fault type of the port equipment is a first preset fault type Q1;

[0097] When the fault feature of the port equipment is the second preset fault feature D2, it is judged that the fault type of the port equipment is a second preset fault type Q2;

[0098] When the fault feature of the port equipment is the third preset fault feature D3, it is judged that the fault type of the port equipment is a third preset fault type Q3;

[0099] When the fault feature of the port equipment is the fourth preset fault feature D4, it is judged that the fault type of the port equipment is a fourth preset fault type Q4.

[0100] In some embodiments of the present application, the fault detection system further comprises:

[0101] A preset alarm signal matrix F is set, for the preset alarm signal matrix F, F (F1, F2, F3, F4) is set, wherein F1 is a first preset alarm signal, F2 is a second preset alarm signal, F3 is a third preset alarm signal, and F4 is a fourth preset alarm signal, and F1

[0102] According to the fault type, a corresponding alarm signal is selected;

[0103] If the current port equipment fault type is the first preset fault type Q1, the first preset alarm signal F1 is selected as the current sent alarm signal;

[0104] If the current port equipment fault type is the second preset fault type Q2, the second preset alarm signal F2 is selected as the current sent alarm signal;

[0105] If the current port equipment fault type is the third preset fault type Q3, the third preset alarm signal F3 is selected as the current sent alarm signal;

[0106] If the current port equipment fault type is the fourth preset fault type Q4, the fourth preset alarm signal F4 is selected as the current sent alarm signal;

[0107] Wherein, the alarm signal can judge the corresponding fault level according to the fault type of the port equipment.

[0108] In some embodiments of the present application, the fault detection system further comprises:

[0109] The maintenance module is also configured to receive an alarm signal sent according to the fault type, the alarm signal comprising the fault type and a fault level of the port equipment, and the maintenance module is configured to perform maintenance processing according to the fault level.

[0110] In some embodiments of the present application, the fault detection system further comprises:

[0111] The abnormality-preceding vibration signal is put into the second convolutional neural network for learning and training, and the second convolutional neural network is updated;

[0112] When the second convolutional neural network identifies that the current vibration signal is the abnormality-preceding vibration signal, a pre-warning signal is sent.

[0113] The abnormality-preceding vibration signal is a vibration signal before a preset time length of the fault data.

[0114] In the present embodiment, the vibration signal before the fault data is collected and a collection period is set, the vibration signal is taken as pre-fault data, and the pre-fault feature is extracted in the second convolutional neural network, and when the pre-fault feature is identified again, a pre-warning signal is sent.

[0115] In some embodiments of the present application, as shown in Figure 2 The present application also provides a fault detection system for a smart port.

[0116] Step S201: collecting vibration signals of motors and gear box bearings of the port;

[0117] Step S202: performing signal processing on the vibration signals, and determining whether the vibration signals after signal processing are fault data;

[0118] Step S203: extracting fault features of the fault data according to a deep learning method, and determining a fault type of the port equipment according to the fault features;

[0119] Step S204: performing maintenance on the port equipment according to the fault type, and changing the fault data after maintenance into normal data.

[0120] In conclusion, the application discloses a fault detection system for a smart wharf and a building method, the fault detection system comprises: a data acquisition module, used for acquiring vibration signals of a motor and a gear box bearing of a port; a processing module, used for signal processing on the vibration signals, and judging whether the vibration signals after signal processing are fault data; an extraction module, used for extracting fault features of the fault data according to a deep learning method, and judging a fault type of a port equipment according to the fault features; a maintenance module, used for maintaining the port equipment according to the fault type, and changing the fault data after maintenance into normal data; the application builds a perfect sensor network through a platform, acquires port equipment monitoring data, quickly judges whether a fault occurs through a signal processing method, further extracts fault features through a deep learning method, makes an accurate judgment on a device fault type, and gives a maintenance suggestion of the port equipment according to a fault type and a fault level, analyzes data before the fault data, and sends an early warning signal when the same vibration signal is identified, so that the port equipment can timely detect the occurrence of a fault, identify the type and level of the fault, and solve the problem that a port equipment fault is not discovered in time in the prior art, and the problem of influence on equipment and personal safety or accidents.

[0121] In the description of the above-described embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0122] Although the application has been described with reference to the embodiments above, various modifications can be made to the application and equivalents thereof without departing from the scope of the application. In particular, features of the disclosed embodiments can be combined in any manner without structural conflict, and the combinations are not all described in the specification only for the purpose of saving space and resources. Therefore, the application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

[0123] Those skilled in the art can understand that the above are only preferred embodiments of the application, and are not used to limit the application, although the application has been described in detail with reference to the foregoing embodiments, and those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments or make equivalent replacements for part of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the application shall be included in the protection scope of the application.

Claims

1. A fault detection system for a smart port, characterized in that, include: The data acquisition module is used to collect vibration signals from port equipment. The processing module is used to process the vibration signal and determine whether the processed vibration signal is fault data. The extraction module is used to extract fault features from the fault data using deep learning methods, and to determine the fault type of the port equipment based on the fault features. The maintenance module is used to maintain the port equipment according to the fault type and change the maintained fault data to normal data. The vibration signals of the port equipment are the vibration signals of the motor and gearbox bearings; The signal processing of the vibration signal includes: The vibration signal is collected during a preset stable period t1-t2; The vibration signal is subjected to short-time Fourier transform to obtain a first time spectrum, and a first amplitude a1 and a first frequency value a2 corresponding to the first amplitude a1 are determined in the first time spectrum. Before determining whether the processed vibration signal is fault data, the following steps are included: A preset normal vibration signal is obtained from historical operating data, and signal processing is performed based on the preset normal vibration signal to obtain a second time spectrum diagram, and a second amplitude b1 and a second frequency value b2 corresponding to the second amplitude b1 are determined in the second time spectrum diagram. Calculate the difference H between the first frequency value a2 and the second frequency value b2, and determine whether the vibration signal is fault data based on the difference H; When determining whether the vibration signal is fault data based on the difference, the following are included: A preset frequency difference standard value matrix W and a preset operating status matrix C are set. For the preset frequency difference standard value matrix W, W(W1, W2, W3, W4) is set, where W1 is the first preset frequency difference standard value, W2 is the second preset frequency difference standard value, W3 is the third preset frequency difference standard value, W4 is the fourth preset frequency difference standard value, and W1 < W2 < W3 < W4. For the preset operating status matrix C, C(C1, C2, C3, C4) is defined, where C1 is the first preset operating status, C2 is the second preset operating status, C3 is the third preset operating status, and C4 is the fourth preset operating status. The corresponding operating state of the device is selected based on the relationship between the difference H and the preset frequency difference standard value matrix W. When H < W1, the first preset operating status C1 is selected as the current operating status of the port equipment, wherein the first preset operating status indicates that the equipment is operating well and continues to be monitored normally. When W1≤H<W2, the second preset operating condition C2 is selected as the current operating condition of the port equipment. The second preset operating condition indicates that the equipment is in the initial stage of damage and needs to be monitored more closely. When W2≤H<W3, the third preset operating condition C3 is selected as the current operating condition of the port equipment. The third preset operating condition indicates that the equipment is damaged in the middle stage and needs to be inspected and replaced regularly. When W3≤H<W4, the fourth preset operating condition C4 is selected as the current operating condition of the port equipment. The fourth preset operating condition indicates that the equipment is in the late stage of damage and needs to be stopped immediately for inspection and replacement. When W3≤H<W4, it indicates that the corresponding vibration signal is fault data.

2. The fault detection system for smart terminals according to claim 1, characterized in that, When extracting fault features from the fault data using a deep learning model, the following steps are included: The first convolutional neural network was constructed, and the vibration signals in the historical database were subjected to short-time Fourier transform to obtain the time-spectrum atlas; The time-spectrum image set is divided into a training set and a test set. The first convolutional neural network is trained based on the training set to obtain a second convolutional neural network. The second convolutional neural network identifies the test set to obtain the operating status of the port equipment. The second convolutional neural network extracts the fault features from the fault data, performs feature classification on the fault features, and determines the fault type based on the fault features.

3. The fault detection system for smart terminals according to claim 2, characterized in that, When determining the fault type of port equipment based on the fault characteristics, the following are included: A preset fault feature matrix D and a preset fault type matrix Q are set. For the preset fault feature matrix D, D(D1, D2, D3, D4) are set, where D1 is the first preset fault feature, D2 is the second preset fault feature, D3 is the third preset fault feature, and D4 is the fourth preset fault feature. For the preset fault type matrix Q, set Q(Q1, Q2, Q3, Q4), where Q1 is the first preset fault type, Q2 is the second preset fault type, Q3 is the third preset fault type, and Q4 is the fourth preset fault type. When the fault characteristic of the port equipment is the first preset fault characteristic D1, the fault type of the port equipment is determined to be the first preset fault type Q1; When the fault characteristic of the port equipment is the second preset fault characteristic D2, the fault type of the port equipment is determined to be the second preset fault type Q2; When the fault characteristic of the port equipment is the third preset fault characteristic D3, the fault type of the port equipment is determined to be the third preset fault type Q3; When the fault characteristic of the port equipment is the fourth preset fault characteristic D4, the fault type of the port equipment is determined to be the fourth preset fault type Q4.

4. The fault detection system for smart terminals according to claim 3, characterized in that, Also includes: A preset alarm signal matrix F is set. For the preset alarm signal matrix F, F(F1, F2, F3, F4) is set, where F1 is the first preset alarm signal, F2 is the second preset alarm signal, F3 is the third preset alarm signal, and F4 is the fourth preset alarm signal, and F1 < F2 < F3 < F4. Select the appropriate alarm signal based on the fault type; If the current port equipment fault type is the first preset fault type Q1, then the first preset alarm signal F1 is selected as the alarm signal to be sent. If the current port equipment fault type is the second preset fault type Q2, then the second preset alarm signal F2 is selected as the alarm signal to be sent. If the current port equipment fault type is the third preset fault type Q3, then the third preset alarm signal F3 is selected as the alarm signal to be sent. If the current port equipment fault type is the fourth preset fault type Q4, then the fourth preset alarm signal F4 is selected as the alarm signal to be sent. The alarm signal can be used to determine the corresponding fault level based on the fault type of the port equipment.

5. The fault detection system for smart terminals according to claim 4, characterized in that, Also includes: The maintenance module is also used to receive alarm signals sent according to the fault type, the alarm signals including the fault type and fault level of the port equipment, and the maintenance module performs maintenance processing according to the fault level.

6. The fault detection system for smart terminals as described in claim 5, characterized in that, Also includes: Obtain the pre-abnormal vibration signal, feed the pre-abnormal vibration signal into the second convolutional neural network for learning and training, and update the second convolutional neural network; When the second convolutional neural network identifies the current vibration signal as the abnormal pre-vibration signal, it sends an early warning signal; The pre-abnormal vibration signal is the vibration signal prior to the preset time period of the fault data.

7. A method for constructing a fault detection system for a smart port, characterized in that, include: Collect vibration signals from the bearings of motors and gearboxes in the port; The vibration signal is processed to determine whether the processed vibration signal is fault data. The fault features of the fault data are extracted using deep learning methods, and the fault type of the port equipment is determined based on the fault features. Repair the port equipment according to the fault type, and change the repaired fault data to normal data; The vibration signals of the port equipment are the vibration signals of the motor and gearbox bearings; The signal processing of the vibration signal includes: The vibration signal is collected during a preset stable period t1-t2; The vibration signal is subjected to short-time Fourier transform to obtain a first time spectrum, and a first amplitude a1 and a first frequency value a2 corresponding to the first amplitude a1 are determined in the first time spectrum. Before determining whether the processed vibration signal is fault data, the following steps are included: A preset normal vibration signal is obtained from historical operating data, and signal processing is performed based on the preset normal vibration signal to obtain a second time spectrum diagram, and a second amplitude b1 and a second frequency value b2 corresponding to the second amplitude b1 are determined in the second time spectrum diagram. Calculate the difference H between the first frequency value a2 and the second frequency value b2, and determine whether the vibration signal is fault data based on the difference H; When determining whether the vibration signal is fault data based on the difference, the following are included: A preset frequency difference standard value matrix W and a preset operating status matrix C are set. For the preset frequency difference standard value matrix W, W(W1, W2, W3, W4) is set, where W1 is the first preset frequency difference standard value, W2 is the second preset frequency difference standard value, W3 is the third preset frequency difference standard value, W4 is the fourth preset frequency difference standard value, and W1 < W2 < W3 < W4. For the preset operating status matrix C, C(C1, C2, C3, C4) is defined, where C1 is the first preset operating status, C2 is the second preset operating status, C3 is the third preset operating status, and C4 is the fourth preset operating status. The corresponding operating state of the device is selected based on the relationship between the difference H and the preset frequency difference standard value matrix W. When H < W1, the first preset operating status C1 is selected as the current operating status of the port equipment, wherein the first preset operating status indicates that the equipment is operating well and continues to be monitored normally. When W1≤H<W2, the second preset operating condition C2 is selected as the current operating condition of the port equipment. The second preset operating condition indicates that the equipment is in the initial stage of damage and needs to be monitored more closely. When W2≤H<W3, the third preset operating condition C3 is selected as the current operating condition of the port equipment. The third preset operating condition indicates that the equipment is damaged in the middle stage and needs to be inspected and replaced regularly. When W3≤H<W4, the fourth preset operating condition C4 is selected as the current operating condition of the port equipment. The fourth preset operating condition indicates that the equipment is in the late stage of damage and needs to be stopped immediately for inspection and replacement. When W3≤H<W4, it indicates that the corresponding vibration signal is fault data.

Images