A method for diagnosing faults of production equipment of a door panel production workshop and related devices

Abstract

The application discloses a kind of production equipment fault diagnosis method and related devices of door panel production workshop, wherein the method comprises: vibration signal acquisition processing is carried out when production equipment executes production job, obtains the production vibration signal corresponding to each joint node;Signal pre-processing is carried out to the production vibration signal corresponding to each joint node;Vibration feature extraction processing is carried out to the pre-processed production vibration signal corresponding to each joint node;The vibration feature vector corresponding to each joint node is input into joint node fault diagnosis model and carries out fault diagnosis prediction processing, obtains the fault diagnosis prediction result corresponding to each joint node;The fault diagnosis prediction result corresponding to each joint node is fused and processed, obtains the fault diagnosis prediction result of the production equipment.In the embodiment of the application, the fault condition of each joint node of production equipment can be predicted, and mechanical fault problems existing in production equipment can be found in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing, and in particular to a production equipment fault diagnosis method for a door panel production workshop and a related device. BACKGROUND

[0002] There are several production equipments on an intelligent manufacturing production line. The management of these production equipments is generally performed by manual inspection or robot inspection. As a result, the possible faults of the production equipments cannot be found in time, and the faults of the production equipments cannot be maintained or repaired, so that the production equipments are operated with faults, and a large production accident such as shutdown may occur at any time, which will cause great production loss. SUMMARY

[0003] The present application aims to overcome the deficiencies of the prior art, and provides a production equipment fault diagnosis method for a door panel production workshop and a related device, which can predict the fault conditions of each joint node of the production equipment, find the mechanical fault of the production equipment in time, and maintain and repair the production equipment in time according to the mechanical fault.

[0004] To solve the above technical problems, the present application provides a production equipment fault diagnosis method for a door panel production workshop, which comprises the following steps:

[0005] Vibration signal acquisition sensors arranged on each joint node of the production equipment perform vibration signal acquisition processing when the production equipment performs production operation, to obtain production vibration signals corresponding to each joint node.

[0006] The production vibration signals corresponding to each joint node are subjected to signal preprocessing, to obtain preprocessed production vibration signals corresponding to each joint node.

[0007] The preprocessed production vibration signals corresponding to each joint node are subjected to vibration feature extraction processing, to obtain vibration feature vectors corresponding to each joint node.

[0008] The vibration feature vectors corresponding to each joint node are input into a joint node fault diagnosis model for fault diagnosis and prediction processing, to obtain fault diagnosis and prediction results corresponding to each joint node.

[0009] The fault diagnosis and prediction results corresponding to each joint node are subjected to fusion processing, to obtain fault diagnosis and prediction results of the production equipment.

[0010] Optionally, the vibration signal acquisition sensors arranged on each joint node of the production equipment perform vibration signal acquisition processing when the production equipment performs production operation, to obtain production vibration signals corresponding to each joint node, which comprises the following steps:

[0011] vibration signal acquisition sensors are arranged on each joint node of the production equipment;

[0012] When the production equipment performs a production task, vibration signal acquisition sensors arranged on each joint node of the production equipment perform vibration signal acquisition processing on each joint node to obtain production vibration signals corresponding to each joint node;

[0013] Optionally, the production vibration signals corresponding to each joint node are preprocessed to obtain preprocessed production vibration signals corresponding to each joint node, including:

[0014] The production vibration signals corresponding to each joint node are filtered by a low-pass filter to obtain filtered production vibration signals corresponding to each joint node;

[0015] The filtered production vibration signals corresponding to each joint node are converted into electrical signals by a signal converter to obtain preprocessed production vibration signals corresponding to each joint node, the preprocessed production vibration signals being production vibration electrical signals.

[0016] Optionally, the preprocessed production vibration signals corresponding to each joint node are subjected to vibration feature extraction processing to obtain vibration feature vectors corresponding to each joint node, including:

[0017] The preprocessed production vibration signals corresponding to each joint node are subjected to signal extraction processing according to vibration cycles to obtain N cycle production vibration signals corresponding to each joint node;

[0018] A plurality of values corresponding to each cycle production vibration signal of the N cycle production vibration signals corresponding to each joint node are obtained, wherein the plurality of values at least include a maximum amplitude and a minimum amplitude of each first cycle production vibration signal, and each value of the plurality of values corresponds to a time point;

[0019] N values corresponding to each time point of the plurality of values corresponding to each cycle production vibration signal of the N cycle production vibration signals corresponding to each joint node are divided into a value set;

[0020] The median and the absolute median difference of the values in the value set corresponding to each time point are calculated to obtain the median and the absolute median difference corresponding to each time node;

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

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

[0023] The median and the absolute median deviation of each time node are added 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 subjected to vector conversion processing to form the vibration feature vector of each joint node at each time node.

[0025] Optionally, the inputting of the vibration feature vector of each joint node into the joint node fault diagnosis model for fault diagnosis prediction processing to obtain the fault diagnosis prediction result of each joint node comprises:

[0026] The vibration feature vector of each joint node is sequentially input into the corresponding joint node fault diagnosis model for fault diagnosis prediction processing to obtain the fault diagnosis prediction result of 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, wherein the model training data contains artificially labeled normal vibration feature vector and fault diagnosis feature vector corresponding to the joint node.

[0028] Optionally, the fusion processing of the fault diagnosis prediction result of each joint node to obtain the fault diagnosis prediction result of the production equipment comprises:

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

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

[0031] The signal acquisition module is configured to perform vibration signal acquisition processing based on the vibration signal acquisition sensors arranged on each joint node of the production equipment when the production equipment performs production work to obtain the production vibration signal corresponding to each joint node.

[0032] The signal processing module is configured 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] The feature extraction module is configured to extract vibration features from the preprocessed production vibration signals corresponding to the joint nodes to obtain vibration feature vectors corresponding to the joint nodes.

[0034] The fault prediction module is configured to input the vibration feature vectors corresponding to the joint nodes into a joint node fault diagnosis model to perform fault diagnosis and prediction processing to obtain fault diagnosis and prediction results corresponding to the joint nodes.

[0035] The fault fusion module is configured to fuse the fault diagnosis and prediction results corresponding to the joint nodes to obtain fault diagnosis and prediction results of the production equipment.

[0036] In addition, the embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the production equipment fault diagnosis method in any one of the above.

[0037] In addition, the embodiment of the present application further provides an electronic device, which comprises:

[0038] one or more processors;

[0039] a memory;

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

[0041] In the embodiment of the present application, the vibration signal collection processing is performed when the production equipment performs the production operation to obtain the production vibration signals corresponding to the joint nodes, the signal preprocessing is performed to obtain the preprocessed production vibration signals corresponding to the joint nodes, the vibration feature extraction processing is performed to obtain the vibration feature vectors corresponding to the joint nodes, the vibration feature vectors corresponding to the joint nodes are input into the joint node fault diagnosis model to perform the fault diagnosis and prediction processing to obtain the fault diagnosis and prediction results corresponding to the joint nodes, and the fault diagnosis and prediction results corresponding to the joint nodes are fused to obtain the fault diagnosis and prediction results of the production equipment, so that the fault conditions of the joint nodes of the production equipment can be predicted, the mechanical fault problems existing in the production equipment can be found in time, the maintenance and repair can be performed in time according to the mechanical fault problems, the normal operation of each production equipment on the intelligent production line is effectively ensured, and the production progress is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0043] Figure 1 is a flowchart of a production equipment fault diagnosis method of a door panel production workshop in an embodiment of the present application.

[0044] Figure 2 is a structural composition schematic diagram of a production equipment fault diagnosis device of a door panel production workshop in an embodiment of the present application.

[0045] Figure 3 is a structural composition schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0047] Embodiment one, please refer to Figure 1 , Figure 1 is a flowchart of a production equipment fault diagnosis method of a door panel production workshop in an embodiment of the present application.

[0048] As shown in Figure 1 , a production equipment fault diagnosis method of a door panel production workshop, the method comprises:

[0049] S11: based on the vibration signal acquisition sensors arranged on each joint node of the production equipment, performing vibration signal acquisition processing when the production equipment performs production work, to obtain production vibration signals corresponding to each joint node;

[0050] In the specific implementation process of the present application, the vibration signal acquisition sensors arranged on each joint node of the production equipment perform vibration signal acquisition processing when the production equipment performs production work, to obtain production vibration signals corresponding to each joint node, comprising: arranging vibration signal acquisition sensors on each joint node of the production equipment; based on the vibration signal acquisition sensors on each joint node, performing vibration signal acquisition processing on each joint node when the production equipment performs production work, to obtain production vibration signals corresponding to each joint node.

[0051] Specifically, first, corresponding vibration signal collection sensors are arranged at corresponding positions of each joint node on the production equipment; when the production equipment performs production, the vibration signal collection sensors on each joint node are triggered to start by the vibration signals generated by each joint node, and vibration signal collection and processing are performed on each joint node, so that the production vibration signals corresponding to each joint node are obtained.

[0052] S12: Signal pre-processing is performed on the production vibration signals corresponding to each joint node to obtain pre-processed production vibration signals corresponding to each joint node.

[0053] In the specific implementation process of the present application, the signal pre-processing on the production vibration signals corresponding to each joint node to obtain the pre-processed production vibration signals corresponding to each joint node comprises: filtering the production vibration signals corresponding to each joint node through a low-pass filter to obtain filtered production vibration signals corresponding to each joint node; and performing electrical signal conversion processing on the filtered production vibration signals corresponding to each joint node through a signal converter to obtain the pre-processed production vibration signals corresponding to each joint node, wherein the pre-processed production vibration signals are production vibration electrical signals.

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

[0055] S13: Vibration feature extraction processing is performed on the pre-processed production vibration signals corresponding to each joint node to obtain vibration feature vectors corresponding to each joint node.

[0056] In the implementation of the present application, the vibration feature extraction processing is performed on the pretreated production vibration signals corresponding to each joint node to obtain the vibration feature vectors corresponding to each joint node, which includes: performing signal extraction processing on the pretreated 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 a plurality of values corresponding to each periodic production vibration signal of the N periodic production vibration signals corresponding to each joint node, wherein the plurality of values at least include the maximum amplitude and the minimum amplitude in each first periodic production vibration signal, and each value in the plurality of values corresponds to a time point; dividing the N values corresponding to each time point in the plurality of values corresponding to each periodic production vibration signal of the N periodic production vibration signals corresponding to each joint node into a value set; calculating the median and the absolute median difference of the values in the value set corresponding to each time point to obtain the median and the absolute median difference corresponding to each time node; and obtaining the vibration feature vector of each joint node at each time node based on the median and the absolute median difference corresponding to each time node and the value set corresponding to each time point.

[0057] Further, the vibration feature vector of each joint node at each time node is obtained based on the median and the absolute median difference corresponding to each time node and the value set corresponding to each time point, which includes: adding the median and the absolute median difference corresponding to each time node into the corresponding value set to form an updated value set corresponding to each time node; and performing vector conversion processing on the updated value set corresponding to each time node to form the vibration feature vector of each joint node at each time node.

[0058] Specifically, first, the corresponding feature extraction processing is performed on the pretreated production vibration signals corresponding to each joint node, and when the feature data is extracted, the vibration feature vector corresponding to each joint node is constructed according to the extracted feature data.

[0059] First, the signal extraction processing is performed on the pretreated 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; that is, the signal interception is performed on the pretreated production vibration signals corresponding to each joint node, and the signal interception is performed according to the vibration period, that is, the beginning of the vibration period is taken as the starting point of the signal interception, and the end of the period after a plurality of signal periods is taken as the terminal of the signal interception; in this way, the signal interception processing is performed on the pretreated production vibration signals corresponding to each joint node, and N periodic production vibration signals corresponding to each joint node are obtained.

[0060] Then, the multiple values corresponding to each of the periodic production vibration signals corresponding to each of the joint nodes need to be obtained. In general, the extreme values of each of the periodic production vibration signals can be selected. In this embodiment, the multiple values can be the maximum amplitude and the minimum amplitude of each of the first periodic production vibration signals. In this way, each of the periodic production vibration signals has a maximum amplitude and a minimum amplitude. The N periodic production vibration signals have N maximum amplitudes and N minimum amplitudes. That is, each of the multiple values corresponds to a time point.

[0061] Then, the N values corresponding to each time point in the multiple values corresponding to each of the periodic production vibration signals corresponding to each of the joint nodes can be divided into a value set. It can be understood that the N maximum amplitudes in the N periodic production vibration signals corresponding to each of the joint nodes are sequentially taken as a value set, and the N minimum amplitudes are sequentially taken as a value set.

[0062] The median and the absolute median difference of the values in the value set corresponding to each time point are calculated to obtain the median and the absolute median difference corresponding to each time node. It can be understood that the median and the absolute median difference corresponding to each time node can be obtained by calculating the median and the absolute median difference of the values in the value set corresponding to each time point.

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

[0064] When constructing the vibration feature vector, the median and the absolute median difference corresponding to each time node are first added to the corresponding value set to form an updated value set corresponding to each time node. Then, the data in the updated value set corresponding to each time node are identified in the form of a vector to complete the vector conversion processing and form the vibration feature vector of each joint node at each time node.

[0065] S14: The vibration feature vectors corresponding to each of the joint nodes are input into a joint node fault diagnosis model for fault diagnosis and prediction processing to obtain fault diagnosis and prediction results corresponding to each of the joint nodes.

[0066] In the implementation of the present application, the vibration feature vector corresponding to each joint node is input into the joint node fault diagnosis model for fault diagnosis and prediction processing, and the fault diagnosis and prediction result corresponding to each joint node is obtained, which includes: sequentially inputting the vibration feature vector corresponding to each joint node into the corresponding joint node fault diagnosis model for fault diagnosis and prediction processing, and obtaining the fault diagnosis and 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 contains the normal vibration feature vector and the fault diagnosis feature vector artificially labeled corresponding to the joint node.

[0067] Specifically, 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, and subsequent fault diagnosis of the corresponding joint node can be directly performed; the model training data contains the normal vibration feature vector and the fault diagnosis feature vector artificially labeled corresponding to the joint node.

[0068] After obtaining the joint node fault diagnosis model corresponding to each joint node in each joint node, the vibration feature vector corresponding to each joint node is sequentially input into the corresponding joint node fault diagnosis model for fault diagnosis and prediction processing, and the fault diagnosis and prediction result corresponding to each joint node is obtained.

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

[0070] In the implementation of the present application, the fault diagnosis and prediction result corresponding to each joint node is fused to obtain the fault diagnosis and prediction result of the production equipment, which includes: marking the fault diagnosis and prediction result corresponding to each joint node in each joint node in the corresponding position of the production equipment model graph to form the fault prediction model graph corresponding to the production equipment.

[0071] Specifically, in order to facilitate the fault query or understanding of the production equipment by the fault maintenance user or the management user, the fault diagnosis and prediction result corresponding to each joint node needs to be further processed, and in the present embodiment, fusion processing is required, that is, the fault diagnosis and prediction result corresponding to each joint node in each joint node is marked in the corresponding position of the production equipment model graph to form the fault prediction model graph corresponding to the production equipment, which greatly facilitates subsequent viewing and improves the efficiency of fault viewing.

[0072] In the embodiment of the present application, the production vibration signals corresponding to each joint node are obtained by collecting and processing vibration signals when the production equipment performs production work, the preprocessed production vibration signals corresponding to each joint node are obtained by preprocessing signals, the vibration feature vectors corresponding to each joint node are obtained by performing vibration feature extraction processing, the fault diagnosis prediction results corresponding to each joint node are obtained by inputting the vibration feature vectors corresponding to each joint node into the joint node fault diagnosis model for fault diagnosis prediction processing, and the fault diagnosis prediction results of the production equipment are obtained by fusing the fault diagnosis prediction results corresponding to each joint node. The fault conditions of each joint node of the production equipment can be predicted, mechanical fault problems existing in the production equipment can be found in time, maintenance and repair can be performed in time according to the existing mechanical fault problems, the normal operation of each production equipment on the intelligent production line is effectively ensured, and the production progress is ensured.

[0073] Embodiment two, please refer to Figure 2 , Figure 2 is a structural composition schematic diagram of the production equipment fault diagnosis device of the door plate production workshop in the embodiment of the present application.

[0074] As Figure 2 shown, a production equipment fault diagnosis device of a door plate production workshop comprises:

[0075] The signal collection module 21 is configured to collect and process vibration signals based on vibration signal collection sensors arranged on each joint node of the production equipment when the production equipment performs production work, and obtain production vibration signals corresponding to each joint node.

[0076] In the embodiment, the vibration signal collection sensors arranged on each joint node of the production equipment collect and process vibration signals when the production equipment performs production work, and obtain production vibration signals corresponding to each joint node, including: arranging vibration signal collection sensors on each joint node of the production equipment; based on the vibration signal collection sensors on each joint node, collecting and processing vibration signals of each joint node when the production equipment performs production work, and obtaining production vibration signals corresponding to each joint node.

[0077] Specifically, first, vibration signal collection sensors are arranged on the corresponding positions of each joint node of the production equipment; when the production equipment performs production, the vibration signal collection sensors on each joint node are triggered to start by the vibration signals generated by each joint node, and vibration signals of each joint node are collected and processed, so as to obtain production vibration signals corresponding to each joint node.

[0078] The signal processing module 22 is used for signal pre-processing of the production vibration signals corresponding to each joint node, to obtain pre-processed production vibration signals corresponding to each joint node.

[0079] In the embodiment of the present application, the signal pre-processing of the production vibration signals corresponding to each joint node to obtain the pre-processed production vibration signals corresponding to each joint node comprises: filtering the production vibration signals corresponding to each joint node through a low-pass filter to obtain filtered production vibration signals corresponding to each joint node; and converting the filtered production vibration signals corresponding to each joint node into electrical signals through a signal converter to obtain the pre-processed production vibration signals corresponding to each joint node, wherein the pre-processed production vibration signals are production vibration electrical signals.

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

[0081] The feature extraction module 23 is used for vibration feature extraction processing of the pre-processed production vibration signals corresponding to each joint node, to obtain vibration feature vectors corresponding to each joint node.

[0082] In the implementation of the present application, the vibration feature extraction processing is performed on the pretreated production vibration signals corresponding to each joint node to obtain the vibration feature vectors corresponding to each joint node, which includes: performing signal extraction processing on the pretreated 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 a plurality of values corresponding to each periodic production vibration signal of the N periodic production vibration signals corresponding to each joint node, wherein the plurality of values at least include the maximum amplitude and the minimum amplitude in each first periodic production vibration signal, and each value in the plurality of values corresponds to a time point; dividing the N values corresponding to each time point in the plurality of values corresponding to each periodic production vibration signal of the N periodic production vibration signals corresponding to each joint node into a value set; calculating the median and the absolute median difference of the values in the value set corresponding to each time point to obtain the median and the absolute median difference corresponding to each time node; and obtaining the vibration feature vector of each joint node at each time node based on the median and the absolute median difference corresponding to each time node and the value set corresponding to each time point.

[0083] Further, the vibration feature vector of each joint node at each time node is obtained based on the median and the absolute median difference corresponding to each time node and the value set corresponding to each time point, which includes: adding the median and the absolute median difference corresponding to each time node into the corresponding value set to form an updated value set corresponding to each time node; and performing vector conversion processing on the updated value set corresponding to each time node to form the vibration feature vector of each joint node at each time node.

[0084] Specifically, first, the corresponding feature extraction processing is performed on the pretreated production vibration signals corresponding to each joint node, and when the feature data is extracted, the vibration feature vector corresponding to each joint node is constructed according to the extracted feature data.

[0085] First, the signal extraction processing is performed on the pretreated 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; that is, the signal interception is performed on the pretreated production vibration signals corresponding to each joint node, and the signal interception is performed according to the vibration period, that is, the beginning of the vibration period is taken as the starting point of the signal interception, and the end of the period after a plurality of signal periods is taken as the terminal of the signal interception; in this way, the signal interception processing is performed on the pretreated production vibration signals corresponding to each joint node, and N periodic production vibration signals corresponding to each joint node are obtained.

[0086] Then the corresponding multiple values of each of the N periodic production vibration signals corresponding to each of the joint nodes are needed, and in general case, the extreme values of each of the periodic production vibration signals can be selected, and in the embodiment, the multiple values can be the amplitude maximum value and the amplitude minimum value in each of the first periodic production vibration signals, so that each of the periodic production vibration signals has an amplitude maximum value and an amplitude minimum value, and the N periodic production vibration signals have N amplitude maximum values and N amplitude minimum values, that is, each of the multiple values corresponds to a time point.

[0087] Then the N values corresponding to each time point in the multiple values of each of the N periodic production vibration signals corresponding to each of the joint nodes can be divided into a value set, and it can be understood that the N amplitude maximum values in the N periodic production vibration signals corresponding to each of the joint nodes are sequentially taken as a value set, and the N amplitude minimum values are sequentially taken as a value set.

[0088] The median and the absolute median difference of the values in the value set corresponding to each time point are calculated to obtain the median and the absolute median difference corresponding to each time node, and it can be understood that the median and the absolute median difference corresponding to each time node can be obtained by calculating the median and the absolute median difference of the values in the value set corresponding to each time point.

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

[0090] When constructing the vibration feature vector, the median and the absolute median difference corresponding to each time node are first added to the corresponding value set to form an updated value set corresponding to each time node, and then the data in the updated value set corresponding to each time node is identified in the form of a vector to complete the vector conversion processing and form the vibration feature vector of each joint node corresponding to each time node.

[0091] The fault prediction module 24 is used for inputting the vibration feature vector of each joint node into a joint node fault diagnosis model to perform fault diagnosis and prediction processing, and obtaining the fault diagnosis and prediction result of each joint node;

[0092] In the implementation of the present application, the vibration feature vector corresponding to each joint node is input into the joint node fault diagnosis model for fault diagnosis and prediction processing, and the fault diagnosis and prediction result corresponding to each joint node is obtained, which includes: sequentially inputting the vibration feature vector corresponding to each joint node into the corresponding joint node fault diagnosis model for fault diagnosis and prediction processing, and obtaining the fault diagnosis and 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 contains the normal vibration feature vector and the fault diagnosis feature vector artificially labeled corresponding to the joint node.

[0093] Specifically, 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, and subsequent fault diagnosis of the corresponding joint node can be directly performed; the model training data contains the normal vibration feature vector and the fault diagnosis feature vector artificially labeled corresponding to the joint node.

[0094] After obtaining the joint node fault diagnosis model corresponding to each joint node in each joint node, the vibration feature vector corresponding to each joint node is sequentially input into the corresponding joint node fault diagnosis model for fault diagnosis and prediction processing, and the fault diagnosis and prediction result corresponding to each joint node is obtained.

[0095] The fault fusion module 25 is used for fusion processing of the fault diagnosis and prediction result corresponding to each joint node, and obtaining the fault diagnosis and prediction result of the production equipment.

[0096] In the implementation of the present application, the fault diagnosis and prediction result corresponding to each joint node is fusion processed, and the fault diagnosis and prediction result of the production equipment is obtained, which includes: marking the fault diagnosis and prediction result corresponding to each joint node in each joint node in the corresponding position of the production equipment model graph to form the fault prediction model graph corresponding to the production equipment.

[0097] Specifically, in order to facilitate the fault query or understanding of the production equipment by the fault maintenance user or the management user, the fault diagnosis and prediction result corresponding to each joint node needs to be further processed, and in the present embodiment, fusion processing is needed, that is, the fault diagnosis and prediction result corresponding to each joint node in each joint node is marked in the corresponding position of the production equipment model graph to form the fault prediction model graph corresponding to the production equipment, which greatly facilitates subsequent viewing and improves the efficiency of fault viewing.

[0098] In the embodiment of the present application, the production vibration signals corresponding to each joint node are obtained by collecting and processing vibration signals when the production equipment performs production work, and then the production vibration signals corresponding to each joint node are obtained by performing signal preprocessing, and then the vibration feature vectors corresponding to each joint node are obtained by performing vibration feature extraction processing, and then the fault diagnosis prediction result corresponding to each joint node is obtained by inputting the vibration feature vectors corresponding to each joint node into the joint node fault diagnosis model for fault diagnosis prediction processing, and then the fault diagnosis prediction result of the production equipment is obtained by performing fusion processing on the fault diagnosis prediction result corresponding to each joint node. 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 found in time. Maintenance and repair can be performed in time according to the existing mechanical fault problems, and the normal operation of each production equipment on the intelligent production line is effectively ensured, and the production progress is ensured.

[0099] The computer readable storage medium provided by the embodiment of the present application stores a computer program, and the program is executed by a processor to implement the production equipment fault diagnosis method of any one of the above embodiments. 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 magnetic disk or an optical disk, etc.

[0100] The embodiment of the present application also provides a computer application program running on a computer, which is used to execute the production equipment fault diagnosis method of any one of the above embodiments.

[0101] In addition, Figure 3 is a structural composition diagram of an electronic device in the embodiment of the present application.

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

[0103] The input unit 304 is used to receive the input of signals and receive the keyword input by the user. The input unit 304 can include a touch panel and other input devices. The touch panel can collect the touch operation of the user on or near it (such as the operation of the user using a finger, a stylus, etc. or any suitable object or accessory on or near the touch panel), and drive the corresponding connection device according to the pre-set program; other input devices can include but are not limited to one or more of a physical keyboard, function keys (such as play control buttons, switch buttons, etc.), trackballs, mice, joysticks, 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 take 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 connects all parts of the device through various interfaces and lines, executes various functions and processes data by running or executing the software program and / or module 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 application programs 301, wherein the one or more application programs 301 are stored in the memory 303 and configured to be executed by the one or more processors 302, and the one or more application programs 301 are configured to execute the production equipment fault diagnosis method in any one of the above embodiments.

[0105] In the embodiment of the present application, by collecting and processing vibration signals when the production equipment performs production work, production vibration signals corresponding to each joint node are obtained; 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 the joint node fault diagnosis model for fault diagnosis and prediction processing to obtain fault diagnosis and prediction results corresponding to each joint node; the fault diagnosis and prediction results corresponding to each joint node are fused to obtain the fault diagnosis and prediction result 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 found in time; and maintenance and repair can be 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 the production progress.

[0106] In addition, the above describes in detail a door panel production workshop production equipment fault diagnosis method and related device provided by the embodiment of the present application, and the principle and implementation mode of the present application are described by using specific examples in this paper, and the above embodiment is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed; in view of the above, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for diagnosing production equipment faults in a door panel production workshop, characterized in that, The method includes: Vibration signal acquisition sensors installed on various joint nodes of the production equipment are used to collect and process vibration signals when the production equipment performs production operations, thereby obtaining the production vibration signals corresponding to each joint node. The production vibration signals corresponding to each joint node are preprocessed to obtain the preprocessed production vibration signals corresponding to each joint node. Vibration feature extraction is performed on the preprocessed production vibration signals corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node. The vibration feature vectors corresponding to each joint node are input into the joint node fault diagnosis model for fault diagnosis and prediction processing to obtain the fault diagnosis and 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 vibration signal acquisition sensors installed on each joint node of the production equipment collect and process vibration signals when the production equipment performs production operations, obtaining the production vibration signals corresponding to each joint node, including: Vibration signal acquisition sensors are installed at various joints of the production equipment; When the production equipment performs production operations, vibration signal acquisition sensors on each joint node are used to collect and process vibration signals of each joint node to obtain the production vibration signal corresponding to each joint node. The step of preprocessing the production vibration signals corresponding to each joint node to obtain preprocessed production vibration signals corresponding to each joint node includes: The production vibration signal corresponding to each joint node is filtered by a low-pass filter to obtain the filtered production vibration signal corresponding to each joint node. The filtered production vibration signals corresponding to each joint node are converted into electrical signals by a signal converter to obtain the pre-processed production vibration signals corresponding to each joint node. The pre-processed production vibration signals are production vibration electrical signals. The step of extracting vibration features from the preprocessed production vibration signals corresponding to each joint node to obtain the vibration feature vector corresponding to each joint node includes: The pre-processed production vibration signals corresponding to each joint node are processed by signal extraction according to the vibration period to obtain N periodic production vibration signals corresponding to each joint node. Obtain multiple values ​​corresponding to each cycle of the N cycle production vibration signals for each joint node, wherein the multiple values ​​include at least the maximum and minimum amplitude values ​​in each first cycle production vibration signal, and each of the multiple values ​​corresponds to a time point. The N values ​​corresponding to each time point in the N-cycle vibration signals produced by each joint node are divided into a set of values. Calculate the median and absolute median difference of the values ​​in the set corresponding to each time point to obtain the median and absolute median difference for each time point; The vibration feature vector of each joint node at each time node is obtained based on the median and absolute median difference at each time node and the numerical set at each time node.

2. The method for diagnosing production equipment faults according to claim 1, characterized in that, The vibration feature vector of each joint node at each time node is obtained based on the median and absolute median difference at each time node and the numerical set at each time node, including: The median and absolute median difference for each time point are added to the corresponding set of values ​​to form the updated set of values ​​for each time point. The updated numerical set corresponding to each time node is processed by vector transformation to form the vibration feature vector of each joint node at each time node.

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

4. The method for diagnosing production equipment faults according to claim 1, characterized in that, The step of 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 results corresponding to each joint node are marked in the corresponding position of the production equipment model diagram to form the fault prediction model diagram corresponding to the production equipment.

5. A fault diagnosis device for production equipment in a door panel production workshop, characterized in that, The apparatus is used to perform the production equipment fault diagnosis method according to any one of claims 1-4, the apparatus comprising: Signal acquisition module: used to acquire and process vibration signals based on vibration signal acquisition sensors installed on various joint nodes of the production equipment when the production equipment performs production operations, and obtain the production vibration signals corresponding to each joint node; Signal processing module: used to preprocess the production vibration signals corresponding to each joint node to obtain the preprocessed production vibration signals corresponding to each joint node; Feature extraction module: used to extract vibration features from the preprocessed production vibration signals corresponding to each joint node, and obtain the vibration feature vector corresponding to each joint node; Fault prediction module: This module is used to input the vibration feature vectors corresponding to each joint node into the joint node fault diagnosis model for fault diagnosis and prediction processing, and to obtain the fault diagnosis and prediction results 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.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the production equipment fault diagnosis method as described in any one of claims 1-4.

7. An electronic device, characterized in that, The electronic device includes: One or more processors; Memory; 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, the one or more applications being configured to: perform the production equipment fault diagnosis method according to any one of claims 1 to 4.

Images