Production equipment fault diagnosis method for door plate production workshop and related device

Abstract

The invention discloses a production equipment fault diagnosis method for a door plate production workshop and a related device, and the method comprises the steps: carrying out the collection and processing of a vibration signal when the production equipment carries out the production operation, and obtaining a production vibration signal corresponding to each joint node; performing signal preprocessing on the production vibration signal corresponding to each joint node; performing vibration feature extraction processing on the preprocessed production vibration signal corresponding to each joint node; inputting the vibration feature vector corresponding to each joint node into a joint node fault diagnosis model for fault diagnosis prediction processing to obtain a fault diagnosis prediction result corresponding to each joint node; and carrying out fusion processing on the fault diagnosis prediction results corresponding to the joint nodes to obtain a fault diagnosis prediction result of the production equipment. In the embodiment of the invention, the fault condition of each joint node of the production equipment can be predicted, and the mechanical fault problem of the production equipment can be found in time.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to a method and related devices for diagnosing production equipment faults in a door panel production workshop. Background Art

[0002] There are several production equipment on the intelligent manufacturing production line. The management of these production equipment is generally carried out through manual inspection or robot inspection. In this way, it is impossible to discover possible faults in the production equipment in time, and it is impossible to maintain or repair the faults in the production equipment. As a result, the production equipment is operated with faults, and major production accidents such as shutdowns may occur at any time, which will bring great production losses. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a production equipment fault diagnosis method and related devices for a door panel production workshop, which can predict the fault conditions of each joint node of the production equipment and promptly discover the mechanical failure problems existing in the production equipment; and perform maintenance and repair in time according to the existing mechanical failure problems.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a method for diagnosing production equipment faults in a door panel production workshop, the method comprising:

[0005] Based on the vibration signal acquisition sensors arranged on each joint node of the production equipment, vibration signal acquisition and processing are performed when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node;

[0006] Perform signal preprocessing on the production vibration signal corresponding to each joint node to obtain the preprocessed production vibration signal corresponding to each joint node;

[0007] Performing vibration feature extraction processing on the pre-processed production vibration signal corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node;

[0008] The vibration characteristic vector corresponding to each joint node is input into the joint node fault diagnosis model to perform fault diagnosis prediction processing, and the fault diagnosis prediction result corresponding to each joint node is obtained;

[0009] The fault diagnosis prediction results corresponding to each joint node are fused to obtain the fault diagnosis prediction result of the production equipment.

[0010] Optionally, the vibration signal acquisition sensor provided on each joint node of the production equipment performs vibration signal acquisition processing when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node, including:

[0011] By setting vibration signal collection sensors on each joint node of the production equipment;

[0012] When the production equipment performs production operations, vibration signal collection and processing is performed on each joint node based on the vibration signal collection sensor on each joint node to obtain a production vibration signal corresponding to each joint node;

[0013] Optionally, performing signal preprocessing on the production vibration signal corresponding to each joint node to obtain the preprocessed production vibration signal corresponding to each joint node includes:

[0014] The production vibration signal corresponding to each joint node is filtered through a low-pass filter to obtain a filtered production vibration signal corresponding to each joint node;

[0015] The filtered production vibration signal corresponding to each joint node is converted into an electrical signal through a signal converter to obtain a pre-processed production vibration signal corresponding to each joint node, wherein the pre-processed production vibration signal is a production vibration electrical signal.

[0016] Optionally, the performing vibration feature extraction processing on the pre-processed production vibration signal corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node includes:

[0017] Performing signal extraction processing on the pre-processed production vibration signals corresponding to each joint node according to the vibration period to obtain N periodic production vibration signals corresponding to each joint node;

[0018] Obtaining multiple values ​​corresponding to each of the N periodic production vibration signals corresponding to each joint node, wherein the multiple values ​​at least include a maximum amplitude value and a minimum amplitude value in each first periodic production vibration signal, and each of the multiple values ​​corresponds to a time point;

[0019] Divide N values ​​corresponding to each time point in a plurality of values ​​corresponding to each of the N periodic production vibration signals corresponding to each joint node into a value set;

[0020] Calculate the median and absolute median difference of the values ​​in the value set corresponding to each time point, and obtain the median and absolute median difference corresponding to each time node;

[0021] Based on the median and absolute median difference corresponding to each time node and the numerical set corresponding to each time point, the vibration characteristic vector corresponding to each joint node at each time node is obtained.

[0022] Optionally, obtaining the vibration feature vector corresponding to each joint node at each time node based on the median and absolute median difference corresponding to each time node and the value set corresponding to each time point includes:

[0023] Add the median and absolute median difference corresponding to each time node to the corresponding value set to form an updated value set corresponding to each time node;

[0024] The updated value set corresponding to each time node is vector-converted to form the vibration feature vector corresponding to each joint node at each time node.

[0025] Optionally, the step of inputting the vibration characteristic vectors corresponding to each joint node into a joint node fault diagnosis model to perform fault diagnosis prediction processing to obtain the fault diagnosis prediction results corresponding to each joint node includes:

[0026] The vibration characteristic vectors corresponding to each joint node are sequentially input into the corresponding joint node fault diagnosis model for fault diagnosis prediction processing to obtain the fault diagnosis prediction results corresponding to each joint node;

[0027] Each joint node fault diagnosis model is formed by training a preset deep neural network model using model training sample data corresponding to the joint node, and the model training data includes manually annotated normal vibration feature vectors and fault diagnosis feature vectors corresponding to the joint node.

[0028] Optionally, fusing the fault diagnosis prediction results corresponding to each joint node to obtain the fault diagnosis prediction result of the production equipment includes:

[0029] The fault diagnosis prediction result corresponding to each joint node in each joint node is marked in the corresponding position of the production equipment model diagram to form a fault prediction model diagram corresponding to the production equipment.

[0030] In addition, an embodiment of the present invention further provides a production equipment fault diagnosis device for a door panel production workshop, the device comprising:

[0031] Signal acquisition module: used to collect and process vibration signals based on vibration signal acquisition sensors arranged on each joint node of the production equipment when the production equipment performs production operations, and obtain production vibration signals corresponding to each joint node;

[0032] Signal processing module: used to perform signal preprocessing on the production vibration signal corresponding to each joint node to obtain the preprocessed production vibration signal corresponding to each joint node;

[0033] Feature extraction module: used to perform vibration feature extraction processing on the pre-processed production vibration signal corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node;

[0034] Fault prediction module: used to input the vibration characteristic vector corresponding to each joint node into the joint node fault diagnosis model to perform fault diagnosis prediction processing, and obtain the fault diagnosis prediction result corresponding to each joint node;

[0035] Fault fusion module: used to fuse the fault diagnosis prediction results corresponding to each joint node to obtain the fault diagnosis prediction results of the production equipment.

[0036] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the production equipment fault diagnosis method as described in any one of the above is implemented.

[0037] In addition, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0038] one or more processors;

[0039] Memory;

[0040] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: execute the production equipment fault diagnosis method according to any one of the above.

[0041] In an embodiment of the present invention, vibration signal collection and processing are performed when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node; then signal preprocessing is performed to obtain preprocessed production vibration signals corresponding to each joint node; vibration feature extraction processing is performed to obtain vibration feature vectors corresponding to each joint node; then the vibration feature vectors corresponding to each joint node are input into a joint node fault diagnosis model for fault diagnosis prediction processing to obtain fault diagnosis prediction results corresponding to each joint node; the fault diagnosis prediction results corresponding to each joint node are fused to obtain the fault diagnosis prediction results of the production equipment; the fault conditions of each joint node of the production equipment can be predicted, and mechanical fault problems existing in the production equipment can be discovered in time; and maintenance and repairs are performed in time according to the existing mechanical fault problems, effectively ensuring the normal operation of each production equipment on the intelligent production line and ensuring production progress. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 is a flow chart of a method for diagnosing production equipment failures in a door panel production workshop in an embodiment of the present invention;

[0044] Figure 2 It is a schematic diagram of the structure of a production equipment fault diagnosis device for a door panel production workshop in an embodiment of the present invention;

[0045] Figure 3 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] For example, see Figure 1 , Figure 1 It is a flow chart of a method for diagnosing production equipment faults in a door panel production workshop in an embodiment of the present invention.

[0048] like Figure 1 As shown, a method for diagnosing production equipment faults in a door panel production workshop comprises:

[0049] S11: performing vibration signal collection and processing based on vibration signal collection sensors provided on each joint node of the production equipment when the production equipment performs production operations, and obtaining production vibration signals corresponding to each joint node;

[0050] In the specific implementation process of the present invention, the vibration signal acquisition sensors arranged on each joint node on the production equipment perform vibration signal acquisition and processing when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node, including: by setting vibration signal acquisition sensors on each joint node on the production equipment; when the production equipment performs production operations, vibration signal acquisition and processing are performed on each joint node based on the vibration signal acquisition sensors on each joint node to obtain production vibration signals corresponding to each joint node.

[0051] Specifically, first, corresponding vibration signal acquisition sensors are set at the corresponding positions of each joint node on the production equipment; when the production equipment is executing production, the vibration signals generated by each joint node are used to trigger the vibration signal acquisition sensors on each joint node to start, and vibration signal acquisition and processing is performed on each joint node, so as to obtain the production vibration signals corresponding to each joint node.

[0052] S12: performing signal preprocessing on the production vibration signal corresponding to each joint node to obtain the preprocessed production vibration signal corresponding to each joint node;

[0053] In the specific implementation process of the present invention, the production vibration signal corresponding to each joint node is preprocessed to obtain the preprocessed production vibration signal corresponding to each joint node, including: filtering the production vibration signal corresponding to each joint node through a low-pass filter to obtain the filtered production vibration signal corresponding to each joint node; converting the filtered production vibration signal corresponding to each joint node into an electrical signal through a signal converter to obtain the preprocessed production vibration signal corresponding to each joint node, and the preprocessed production vibration signal is a production vibration electrical signal.

[0054] Specifically, after obtaining the production vibration signal corresponding to each joint node, in order to solve the influence of some subsequent mixed signals on the vibration signal, a filtering operation is required, that is, the production vibration signal corresponding to each joint node is input into a low-pass filter for filtering processing to obtain the filtered production vibration signal corresponding to each joint node. The low-pass filter can generally be an anti-aliasing filter circuit; since the collected production vibration signal is an analog signal, it is necessary to convert it into an electrical signal, so the filtered production vibration signal corresponding to each joint node needs to be converted into an electrical signal through a signal converter to obtain the pre-processed production vibration signal corresponding to each joint node. The signal converter is generally an analog-to-digital converter, and the pre-processed production vibration signal is a production vibration electrical signal.

[0055] S13: performing vibration feature extraction processing on the pre-processed production vibration signal corresponding to each joint node to obtain a vibration feature vector corresponding to each joint node;

[0056] In the specific implementation process of the present invention, the vibration feature extraction processing is performed on the pre-processed production vibration signal corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node, including: performing signal extraction processing on the pre-processed production vibration signal corresponding to each joint node according to the vibration period to obtain N periodic production vibration signals corresponding to each joint node; obtaining multiple numerical values ​​corresponding to each periodic production vibration signal in the N periodic production vibration signals corresponding to each joint node, wherein the multiple numerical values ​​at least include the maximum amplitude and the minimum amplitude in each first periodic production vibration signal, and each numerical value in the multiple numerical values ​​corresponds to a time point; dividing the N numerical values ​​corresponding to each time point in the multiple numerical values ​​corresponding to each periodic production vibration signal in the N periodic production vibration signals corresponding to each joint node into a numerical set; calculating the median and absolute median difference of the numerical values ​​in the numerical set corresponding to each time point to obtain the median and absolute median difference corresponding to each time node; based on the median and absolute median difference corresponding to each time node and the numerical set corresponding to each time point, obtaining the vibration feature vector corresponding to each joint node at each time node.

[0057] Furthermore, the method of obtaining the vibration characteristic vector corresponding to each joint node at each time node based on the median and absolute median difference corresponding to each time node and the numerical set corresponding to each time point includes: adding the median and absolute median difference corresponding to each time node to the corresponding numerical set to form an updated numerical set corresponding to each time node; performing vector conversion processing on the updated numerical set corresponding to each time node to form the vibration characteristic vector corresponding to each joint node at each time node.

[0058] Specifically, firstly, the pre-processed production vibration signal corresponding to each joint node is subjected to corresponding feature extraction processing. When the feature data is extracted, the vibration feature vector corresponding to each joint node is constructed according to the extracted feature data.

[0059] Firstly, the pre-processed production vibration signal corresponding to each joint node is extracted and processed according to the vibration period to obtain N periodic production vibration signals corresponding to each joint node; that is, the pre-processed production vibration signal corresponding to each joint node in each joint node is intercepted, and the signal is intercepted according to the vibration period, that is, the beginning of the vibration period is used as the starting point of signal interception, and the end of the period after several signal periods is used as the signal interception terminal; in this way, the pre-processed production vibration signal corresponding to each joint node is intercepted and processed, and N periodic production vibration signals corresponding to each joint node in each joint node can be obtained.

[0060] Then it is necessary to obtain multiple numerical values ​​corresponding to each of the N periodic production vibration signals corresponding to each joint node in each joint node. Generally, it is sufficient to select the extreme value of each periodic production vibration signal. In this embodiment, the multiple numerical values ​​can be the maximum amplitude value and the minimum amplitude value in each first periodic production vibration signal. In this way, each periodic production vibration signal will have a maximum amplitude value and a minimum amplitude value; the N periodic production vibration signals will have N maximum amplitude values ​​and N minimum amplitude values; that is, each of the multiple numerical values ​​corresponds to a time point.

[0061] Then, the N numerical values ​​corresponding to each time point in the multiple numerical values ​​corresponding to each periodic production vibration signal corresponding to each joint node can be divided into a numerical set. It can be understood that the N maximum amplitude values ​​in the N periodic production vibration signals corresponding to each joint node in each joint node are taken as a numerical set in turn, and the N minimum amplitude values ​​are taken as a numerical set in turn.

[0062] Calculate the median and absolute median difference of the values ​​in the set of values ​​corresponding to each time point, and obtain the median and absolute median difference corresponding to each time node; it can be understood that, through the values ​​in the set of values ​​corresponding to each time point, the median and absolute median difference corresponding to these values ​​can be calculated, and the median and absolute median difference corresponding to each time node can be obtained.

[0063] Finally, the vibration characteristic vector corresponding to each joint node at each time node can be obtained according to the median and absolute median difference corresponding to each time node and the numerical set corresponding to each time point.

[0064] When constructing the vibration feature vector, you first need to add the median and absolute median difference corresponding to each time node to the corresponding value set to form an updated value set corresponding to each time node; then identify the data in the updated value set corresponding to each time node in the form of a vector to complete the vector conversion process and form the vibration feature vector corresponding to each joint node at each time node.

[0065] S14: inputting the vibration characteristic vector corresponding to each joint node into the joint node fault diagnosis model to perform fault diagnosis prediction processing, and obtaining the fault diagnosis prediction result corresponding to each joint node;

[0066] In the specific implementation process of the present invention, the vibration characteristic vector corresponding to each joint node is input into the joint node fault diagnosis model for fault diagnosis prediction processing to obtain the fault diagnosis prediction result corresponding to each joint node, including: the vibration characteristic vector corresponding to each joint node is input into the corresponding joint node fault diagnosis model in turn for fault diagnosis prediction processing to obtain the fault diagnosis prediction result corresponding to each joint node; wherein each joint node fault diagnosis model is formed by training a preset deep neural network model using the model training sample data corresponding to the joint node, and the model training data includes the manually annotated normal vibration characteristic vector vector and fault diagnosis characteristic vector corresponding to the joint node.

[0067] Specifically, first, the joint node fault diagnosis model is generally formed by training a preset deep neural network model using the model training sample data corresponding to the joint node, and is a converged model, which can then directly perform fault diagnosis of the corresponding shutdown node; the model training data includes the manually annotated normal vibration feature vector vector and fault diagnosis feature vector corresponding to the joint node.

[0068] After obtaining the joint node fault diagnosis model corresponding to each joint node, it is necessary to input the vibration characteristic vectors corresponding to each joint node into the corresponding joint node fault diagnosis model in turn to perform fault diagnosis prediction processing to obtain the fault diagnosis prediction results corresponding to each joint node.

[0069] S15: Fusing the fault diagnosis prediction results corresponding to each joint node to obtain the fault diagnosis prediction result of the production equipment.

[0070] In the specific implementation process of the present invention, the fault diagnosis prediction results corresponding to each joint node are fused to obtain the fault diagnosis prediction results of the production equipment, including: marking the fault diagnosis prediction results corresponding to each joint node in the corresponding position of the production equipment model diagram to form a fault prediction model diagram corresponding to the production equipment.

[0071] Specifically, in order to facilitate fault maintenance users or management users to query or understand production equipment faults, it is necessary to further process the fault diagnosis prediction results corresponding to each joint node. In this embodiment, fusion processing is required, that is, the fault diagnosis prediction results corresponding to each joint node in each joint node are marked in the corresponding position of the production equipment model diagram to form a fault prediction model diagram corresponding to the production equipment. This will greatly facilitate subsequent viewing and improve the efficiency of fault viewing.

[0072] In an embodiment of the present invention, vibration signal collection and processing are performed when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node; then signal preprocessing is performed to obtain preprocessed production vibration signals corresponding to each joint node; vibration feature extraction processing is performed to obtain vibration feature vectors corresponding to each joint node; then the vibration feature vectors corresponding to each joint node are input into a joint node fault diagnosis model for fault diagnosis prediction processing to obtain fault diagnosis prediction results corresponding to each joint node; the fault diagnosis prediction results corresponding to each joint node are fused to obtain the fault diagnosis prediction results of the production equipment; the fault conditions of each joint node of the production equipment can be predicted, and mechanical fault problems existing in the production equipment can be discovered in time; and maintenance and repairs are performed in time according to the existing mechanical fault problems, effectively ensuring the normal operation of each production equipment on the intelligent production line and ensuring production progress.

[0073] For example 2, please refer to Figure 2 , Figure 2 It is a schematic diagram of the structural composition of a production equipment fault diagnosis device in a door panel production workshop in an embodiment of the present invention.

[0074] like Figure 2 As shown, a production equipment fault diagnosis device for a door panel production workshop, the device comprises:

[0075] Signal acquisition module 21: used to collect and process vibration signals based on vibration signal acquisition sensors arranged on each joint node of the production equipment when the production equipment performs production operations, and obtain production vibration signals corresponding to each joint node;

[0076] In the specific implementation process of the present invention, the vibration signal acquisition sensors arranged on each joint node on the production equipment perform vibration signal acquisition and processing when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node, including: by setting vibration signal acquisition sensors on each joint node on the production equipment; when the production equipment performs production operations, vibration signal acquisition and processing are performed on each joint node based on the vibration signal acquisition sensors on each joint node to obtain production vibration signals corresponding to each joint node.

[0077] Specifically, first, corresponding vibration signal acquisition sensors are set at the corresponding positions of each joint node on the production equipment; when the production equipment is executing production, the vibration signals generated by each joint node are used to trigger the vibration signal acquisition sensors on each joint node to start, and vibration signal acquisition and processing is performed on each joint node, so as to obtain the production vibration signals corresponding to each joint node.

[0078] Signal processing module 22: used for performing signal preprocessing on the production vibration signal corresponding to each joint node to obtain the preprocessed production vibration signal corresponding to each joint node;

[0079] In the specific implementation process of the present invention, the production vibration signal corresponding to each joint node is preprocessed to obtain the preprocessed production vibration signal corresponding to each joint node, including: filtering the production vibration signal corresponding to each joint node through a low-pass filter to obtain the filtered production vibration signal corresponding to each joint node; converting the filtered production vibration signal corresponding to each joint node into an electrical signal through a signal converter to obtain the preprocessed production vibration signal corresponding to each joint node, and the preprocessed production vibration signal is a production vibration electrical signal.

[0080] Specifically, after obtaining the production vibration signal corresponding to each joint node, in order to solve the influence of some subsequent mixed signals on the vibration signal, a filtering operation is required, that is, the production vibration signal corresponding to each joint node is input into a low-pass filter for filtering processing to obtain the filtered production vibration signal corresponding to each joint node. The low-pass filter can generally be an anti-aliasing filter circuit; since the collected production vibration signal is an analog signal, it is necessary to convert it into an electrical signal, so the filtered production vibration signal corresponding to each joint node needs to be converted into an electrical signal through a signal converter to obtain the pre-processed production vibration signal corresponding to each joint node. The signal converter is generally an analog-to-digital converter, and the pre-processed production vibration signal is a production vibration electrical signal.

[0081] Feature extraction module 23: used to perform vibration feature extraction processing on the pre-processed production vibration signal corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node;

[0082] In the specific implementation process of the present invention, the vibration feature extraction processing is performed on the pre-processed production vibration signal corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node, including: performing signal extraction processing on the pre-processed production vibration signal corresponding to each joint node according to the vibration period to obtain N periodic production vibration signals corresponding to each joint node; obtaining multiple numerical values ​​corresponding to each periodic production vibration signal in the N periodic production vibration signals corresponding to each joint node, wherein the multiple numerical values ​​at least include the maximum amplitude and the minimum amplitude in each first periodic production vibration signal, and each numerical value in the multiple numerical values ​​corresponds to a time point; dividing the N numerical values ​​corresponding to each time point in the multiple numerical values ​​corresponding to each periodic production vibration signal in the N periodic production vibration signals corresponding to each joint node into a numerical set; calculating the median and absolute median difference of the numerical values ​​in the numerical set corresponding to each time point to obtain the median and absolute median difference corresponding to each time node; based on the median and absolute median difference corresponding to each time node and the numerical set corresponding to each time point, obtaining the vibration feature vector corresponding to each joint node at each time node.

[0083] Furthermore, the method of obtaining the vibration characteristic vector corresponding to each joint node at each time node based on the median and absolute median difference corresponding to each time node and the numerical set corresponding to each time point includes: adding the median and absolute median difference corresponding to each time node to the corresponding numerical set to form an updated numerical set corresponding to each time node; performing vector conversion processing on the updated numerical set corresponding to each time node to form the vibration characteristic vector corresponding to each joint node at each time node.

[0084] Specifically, firstly, the pre-processed production vibration signal corresponding to each joint node is subjected to corresponding feature extraction processing. When the feature data is extracted, the vibration feature vector corresponding to each joint node is constructed according to the extracted feature data.

[0085] Firstly, the pre-processed production vibration signal corresponding to each joint node is extracted and processed according to the vibration period to obtain N periodic production vibration signals corresponding to each joint node; that is, the pre-processed production vibration signal corresponding to each joint node in each joint node is intercepted, and the signal is intercepted according to the vibration period, that is, the beginning of the vibration period is used as the starting point of signal interception, and the end of the period after several signal periods is used as the signal interception terminal; in this way, the pre-processed production vibration signal corresponding to each joint node is intercepted and processed, and N periodic production vibration signals corresponding to each joint node in each joint node can be obtained.

[0086] Then it is necessary to obtain multiple numerical values ​​corresponding to each of the N periodic production vibration signals corresponding to each joint node in each joint node. Generally, it is sufficient to select the extreme value of each periodic production vibration signal. In this embodiment, the multiple numerical values ​​can be the maximum amplitude value and the minimum amplitude value in each first periodic production vibration signal. In this way, each periodic production vibration signal will have a maximum amplitude value and a minimum amplitude value; the N periodic production vibration signals will have N maximum amplitude values ​​and N minimum amplitude values; that is, each of the multiple numerical values ​​corresponds to a time point.

[0087] Then, the N numerical values ​​corresponding to each time point in the multiple numerical values ​​corresponding to each periodic production vibration signal corresponding to each joint node can be divided into a numerical set. It can be understood that the N maximum amplitude values ​​in the N periodic production vibration signals corresponding to each joint node in each joint node are taken as a numerical set in turn, and the N minimum amplitude values ​​are taken as a numerical set in turn.

[0088] Calculate the median and absolute median difference of the values ​​in the set of values ​​corresponding to each time point, and obtain the median and absolute median difference corresponding to each time node; it can be understood that, through the values ​​in the set of values ​​corresponding to each time point, the median and absolute median difference corresponding to these values ​​can be calculated, and the median and absolute median difference corresponding to each time node can be obtained.

[0089] Finally, the vibration characteristic vector corresponding to each joint node at each time node can be obtained according to the median and absolute median difference corresponding to each time node and the numerical set corresponding to each time point.

[0090] When constructing the vibration feature vector, you first need to add the median and absolute median difference corresponding to each time node to the corresponding value set to form an updated value set corresponding to each time node; then identify the data in the updated value set corresponding to each time node in the form of a vector to complete the vector conversion process and form the vibration feature vector corresponding to each joint node at each time node.

[0091] Fault prediction module 24: used to input the vibration characteristic vector corresponding to each joint node into the joint node fault diagnosis model to perform fault diagnosis prediction processing, and obtain the fault diagnosis prediction result corresponding to each joint node;

[0092] In the specific implementation process of the present invention, the vibration characteristic vector corresponding to each joint node is input into the joint node fault diagnosis model for fault diagnosis prediction processing to obtain the fault diagnosis prediction result corresponding to each joint node, including: the vibration characteristic vector corresponding to each joint node is input into the corresponding joint node fault diagnosis model in turn for fault diagnosis prediction processing to obtain the fault diagnosis prediction result corresponding to each joint node; wherein each joint node fault diagnosis model is formed by training a preset deep neural network model using the model training sample data corresponding to the joint node, and the model training data includes the manually annotated normal vibration characteristic vector vector and fault diagnosis characteristic vector corresponding to the joint node.

[0093] Specifically, first, the joint node fault diagnosis model is generally formed by training a preset deep neural network model using the model training sample data corresponding to the joint node, and is a converged model, which can then directly perform fault diagnosis of the corresponding shutdown node; the model training data includes the manually annotated normal vibration feature vector vector and fault diagnosis feature vector corresponding to the joint node.

[0094] After obtaining the joint node fault diagnosis model corresponding to each joint node, it is necessary to input the vibration characteristic vectors corresponding to each joint node into the corresponding joint node fault diagnosis model in turn to perform fault diagnosis prediction processing to obtain the fault diagnosis prediction results corresponding to each joint node.

[0095] Fault fusion module 25: used for fusing the fault diagnosis prediction results corresponding to each joint node to obtain the fault diagnosis prediction result of the production equipment.

[0096] In the specific implementation process of the present invention, the fault diagnosis prediction results corresponding to each joint node are fused to obtain the fault diagnosis prediction results of the production equipment, including: marking the fault diagnosis prediction results corresponding to each joint node in the corresponding position of the production equipment model diagram to form a fault prediction model diagram corresponding to the production equipment.

[0097] Specifically, in order to facilitate fault maintenance users or management users to query or understand production equipment faults, it is necessary to further process the fault diagnosis prediction results corresponding to each joint node. In this embodiment, fusion processing is required, that is, the fault diagnosis prediction results corresponding to each joint node in each joint node are marked in the corresponding position of the production equipment model diagram to form a fault prediction model diagram corresponding to the production equipment. This will greatly facilitate subsequent viewing and improve the efficiency of fault viewing.

[0098] In an embodiment of the present invention, vibration signal collection and processing are performed when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node; then signal preprocessing is performed to obtain preprocessed production vibration signals corresponding to each joint node; vibration feature extraction processing is performed to obtain vibration feature vectors corresponding to each joint node; then the vibration feature vectors corresponding to each joint node are input into a joint node fault diagnosis model for fault diagnosis prediction processing to obtain fault diagnosis prediction results corresponding to each joint node; the fault diagnosis prediction results corresponding to each joint node are fused to obtain the fault diagnosis prediction results of the production equipment; the fault conditions of each joint node of the production equipment can be predicted, and mechanical fault problems existing in the production equipment can be discovered in time; and maintenance and repairs are performed in time according to the existing mechanical fault problems, effectively ensuring the normal operation of each production equipment on the intelligent production line and ensuring production progress.

[0099] A computer-readable storage medium provided in an embodiment of the present invention stores a computer program on the computer-readable storage medium, and when the program is executed by a processor, the production equipment fault diagnosis method of any one of the above embodiments is implemented. The computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (EraSable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or optical card. That is, the storage device includes any medium that can store or transmit information in a readable form by a device (for example, a computer, a mobile phone), which can be a read-only memory, a disk or an optical disk, etc.

[0100] An embodiment of the present invention further provides a computer application program, which runs on a computer and is used to execute the production equipment fault diagnosis method of any one of the above embodiments.

[0101] also, Figure 3 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention.

[0102] The embodiment of the present invention further provides an electronic device, such as Figure 3 The electronic device includes a processor 302, a memory 303, an input unit 304, a display unit 305 and other devices. Those skilled in the art will understand that Figure 3 The electronic device structure device shown does not constitute a limitation on all devices, and may include more or fewer components than shown, or combine certain components. The memory 303 can be used to store the application 301 and various functional modules, and the processor 302 runs the application 301 stored in the memory 303, thereby executing various functional applications and data processing of the device. The memory can be an internal memory or an external memory, or include both internal and external memories. The internal memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, or a random access memory. The external memory may include a hard disk, a floppy disk, a ZIP disk, a U disk, a magnetic tape, etc. The memory disclosed in the present invention includes but is not limited to these types of memories. The memory disclosed in the present invention is only used as an example and not as a limitation.

[0103] The input unit 304 is used to receive the input of the signal and the keyword input by the user. The input unit 304 may include a touch panel and other input devices. The touch panel can collect the user's touch operation on or near it (such as the user's operation on or near the touch panel using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program; other input devices may include but are not limited to one or more of a physical keyboard, a function key (such as a playback control key, a switch key, etc.), a trackball, a mouse, a joystick, etc. The display unit 305 can be used to display the information input by the user or the information provided to the user and various menus of the terminal device. The display unit 305 can be in the form of a liquid crystal display, an organic light emitting diode, etc. The processor 302 is the control center of the terminal device, which uses various interfaces and lines to connect the various parts of the entire device, and executes various functions and processes data by running or executing software programs and / or modules stored in the memory 303, and calling the data stored in the memory.

[0104] As an embodiment, the electronic device includes: one or more processors 302, a memory 303, and one or more applications 301, wherein the one or more applications 301 are stored in the memory 303 and are configured to be executed by the one or more processors 302, and the one or more applications 301 are configured to execute the production equipment fault diagnosis method in any one of the above-mentioned embodiments.

[0105] In an embodiment of the present invention, vibration signal collection and processing are performed when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node; then signal preprocessing is performed to obtain preprocessed production vibration signals corresponding to each joint node; vibration feature extraction processing is performed to obtain vibration feature vectors corresponding to each joint node; then the vibration feature vectors corresponding to each joint node are input into a joint node fault diagnosis model for fault diagnosis prediction processing to obtain fault diagnosis prediction results corresponding to each joint node; the fault diagnosis prediction results corresponding to each joint node are fused to obtain the fault diagnosis prediction results of the production equipment; the fault conditions of each joint node of the production equipment can be predicted, and mechanical fault problems existing in the production equipment can be discovered in time; and maintenance and repairs are performed in time according to the existing mechanical fault problems, effectively ensuring the normal operation of each production equipment on the intelligent production line and ensuring production progress.

[0106] In addition, the above is a detailed introduction to a method for diagnosing production equipment faults in a door panel production workshop and related devices provided in an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for diagnosing production equipment faults in a door panel production workshop, characterized in that: The method comprises: Based on the vibration signal acquisition sensors arranged on each joint node of the production equipment, vibration signal acquisition and processing are performed when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node; Perform signal preprocessing on the production vibration signal corresponding to each joint node to obtain the preprocessed production vibration signal corresponding to each joint node; Performing vibration feature extraction processing on the pre-processed production vibration signal corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node; The vibration characteristic vector corresponding to each joint node is input into the joint node fault diagnosis model to perform fault diagnosis prediction processing, and the fault diagnosis prediction result corresponding to each joint node is obtained; The fault diagnosis prediction results corresponding to each joint node are fused to obtain the fault diagnosis prediction result of the production equipment.

2. The method for diagnosing production equipment faults according to claim 1, characterized in that: The vibration signal acquisition sensor provided on each joint node of the production equipment performs vibration signal acquisition processing when the production equipment performs production operations to obtain production vibration signals corresponding to each joint node, including: By setting vibration signal collection sensors on each joint node of the production equipment; When the production equipment performs production operations, vibration signal collection and processing is performed on each joint node based on the vibration signal collection sensors on each joint node to obtain production vibration signals corresponding to each joint node.

3. The method for diagnosing production equipment faults according to claim 1, characterized in that: The signal preprocessing is performed on the production vibration signal corresponding to each joint node to obtain the preprocessed production vibration signal corresponding to each joint node, including: The production vibration signal corresponding to each joint node is filtered through a low-pass filter to obtain a filtered production vibration signal corresponding to each joint node; The filtered production vibration signal corresponding to each joint node is converted into an electrical signal through a signal converter to obtain a pre-processed production vibration signal corresponding to each joint node, wherein the pre-processed production vibration signal is a production vibration electrical signal.

4. The method for diagnosing production equipment faults according to claim 1, characterized in that: The step of performing vibration feature extraction processing on the pre-processed production vibration signal corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node includes: Performing signal extraction processing on the pre-processed production vibration signals corresponding to each joint node according to the vibration period to obtain N periodic production vibration signals corresponding to each joint node; Obtaining multiple values ​​corresponding to each of the N periodic production vibration signals corresponding to each joint node, wherein the multiple values ​​at least include a maximum amplitude value and a minimum amplitude value in each first periodic production vibration signal, and each of the multiple values ​​corresponds to a time point; Divide N values ​​corresponding to each time point in a plurality of values ​​corresponding to each of the N periodic production vibration signals corresponding to each joint node into a value set; Calculate the median and absolute median difference of the values ​​in the value set corresponding to each time point, and obtain the median and absolute median difference corresponding to each time node; Based on the median and absolute median difference corresponding to each time node and the numerical set corresponding to each time point, the vibration characteristic vector corresponding to each joint node at each time node is obtained.

5. The method for diagnosing production equipment faults according to claim 4, characterized in that: The method of obtaining the vibration characteristic vector corresponding to each joint node at each time node based on the median and absolute median difference corresponding to each time node and the value set corresponding to each time point includes: Add the median and absolute median difference corresponding to each time node to the corresponding value set to form an updated value set corresponding to each time node; The updated value set corresponding to each time node is vector-converted to form the vibration feature vector corresponding to each joint node at each time node.

6. The method for diagnosing production equipment faults according to claim 1, characterized in that: The step of inputting the vibration characteristic vector corresponding to each joint node into the joint node fault diagnosis model to perform fault diagnosis prediction processing to obtain the fault diagnosis prediction result corresponding to each joint node includes: The vibration characteristic vectors corresponding to each joint node are sequentially input into the corresponding joint node fault diagnosis model for fault diagnosis prediction processing to obtain the fault diagnosis prediction results corresponding to each joint node; Each joint node fault diagnosis model is formed by training a preset deep neural network model using model training sample data corresponding to the joint node, and the model training data includes manually annotated normal vibration feature vectors and fault diagnosis feature vectors corresponding to the joint node.

7. The method for diagnosing production equipment faults according to claim 1, characterized in that: The fusing the fault diagnosis prediction results corresponding to each joint node to obtain the fault diagnosis prediction result of the production equipment includes: The fault diagnosis prediction result corresponding to each joint node in each joint node is marked in the corresponding position of the production equipment model diagram to form a fault prediction model diagram corresponding to the production equipment.

8. A production equipment fault diagnosis device for a door panel production workshop, characterized in that: The device comprises: Signal acquisition module: used to collect and process vibration signals based on vibration signal acquisition sensors arranged on each joint node of the production equipment when the production equipment performs production operations, and obtain production vibration signals corresponding to each joint node; Signal processing module: used to perform signal preprocessing on the production vibration signal corresponding to each joint node to obtain the preprocessed production vibration signal corresponding to each joint node; Feature extraction module: used to extract vibration features from pre-processed production vibration signals corresponding to each joint node, and obtain vibration feature vectors corresponding to each joint node; Fault prediction module: used to input the vibration characteristic vector corresponding to each joint node into the joint node fault diagnosis model to perform fault diagnosis prediction processing, and obtain the fault diagnosis prediction result corresponding to each joint node; Fault fusion module: used to fuse the fault diagnosis prediction results corresponding to each joint node to obtain the fault diagnosis prediction results of the production equipment.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the production equipment fault diagnosis method as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The electronic device comprises: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to: execute the production equipment fault diagnosis method according to any one of claims 1 to 7.

Images