Cutting bed fault diagnosis method

Abstract

The invention discloses a cutting bed fault diagnosis method. The method comprises the following steps: step S10, defining a to-be-monitored fault diagnosis target type; step S20, defining a fault type; step S30, setting a fault diagnosis target priority type; step S40, constructing a fault diagnosis target priority decision tree and performing fault type diagnosis; and step S50, outputting the decision tree, and outputting the fault type and reason according to the branch logic and priority setting of the decision tree. According to the invention, monitoring and maintenance of the cutting bed equipment are realized, the cutting quality and the equipment stability are ensured, system feedback and diagnosis results are directly fed back to the equipment under the monitoring of various parameters, the cutting speed of the equipment is improved, the production efficiency is improved, and the maintenance cost is reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of textile processing, and in particular relates to a cutting bed fault diagnosis method. Background Art

[0002] In the field of textile processing, with the development of industrial automation and intelligence, higher requirements are placed on the fault diagnosis and early warning capabilities of cutting equipment. In the prior art, the fault diagnosis methods for cutting equipment include the following four methods:

[0003] 1) Fault judgment method based on expert system: This method relies on the experience and knowledge of experts, but it is difficult for expert systems to cover all possible fault conditions and variable combinations, and updating and maintaining expert systems requires a lot of time and resources.

[0004] 2) Fault judgment method based on artificial neural network: Although the fault judgment method based on artificial neural network can handle complex nonlinear relationships, neural network is usually regarded as a "black box" model, and it is difficult to explain its decision-making process. The training of neural network requires a large amount of data and computing resources, and it is difficult to handle abnormal data.

[0005] 3) Fault judgment method based on fuzzy theory: Although it can process fuzzy and uncertain information, the formulation and updating of fuzzy rules require more professional knowledge. The performance of fuzzy system is greatly affected by the quality of input data and the selection of fuzzy rules.

[0006] 4) Fault judgment methods based on traditional statistical methods: such as regression analysis, variance analysis, etc. This method usually assumes that the data obeys a certain distribution, but this assumption may not hold true in practical applications. Therefore, traditional statistical methods are difficult to handle high-dimensional data and complex nonlinear relationships.

[0007] In summary, existing diagnostic inventions have the problems of large data resource consumption, poor clarity and versatility. In order to meet the needs of the modern textile industry for rapid and accurate fault identification, a more efficient and adaptable fault diagnosis solution is urgently needed, which can provide clear and interpretable results while reducing data consumption and can be widely applied to different types of cutting equipment. Summary of the invention

[0008] The present invention provides a cutting table fault diagnosis method, so as to realize the purpose of quickly and accurately identifying equipment faults and improve production efficiency and product quality.

[0009] The technical solution of the present invention is as follows:

[0010] A method for diagnosing a cutting bed fault comprises the following steps:

[0011] Step S10, defining the fault diagnosis target type to be monitored;

[0012] Step S20, defining the fault type;

[0013] Step S30, setting the fault diagnosis target priority type;

[0014] Step S40, constructing a fault diagnosis target priority decision tree according to the fault diagnosis target priority type, and performing fault type diagnosis;

[0015] Step S50, outputting a decision tree, and outputting the fault type and cause according to the branch logic and priority setting of the decision tree.

[0016] Furthermore, the fault diagnosis target types in step S10 include: number of fabric layers, fabric size, fabric tightness, equipment status, vacuum level, vibration speed, cutting speed, knife loss, adsorption negative pressure value, air pressure positive pressure value, and knife width sensor;

[0017] The fabric size includes fabric length and fabric width.

[0018] Furthermore, the fault types in step S20 include abnormal cloth fault, equipment status fault, and cutting system fault.

[0019] Furthermore, the identification targets of the abnormal fabric failure include at least the number of fabric layers, fabric size and fabric tightness;

[0020] The number of fabric layers is controlled and monitored by the cutting bed height limit module. When the number exceeds the set value of the height limit module, the fabric feeding system stops feeding and the fault alarm module triggers an abnormal alarm.

[0021] The cloth size is controlled and monitored by the analytical cutting module. When the analytical cutting module identifies that the rectangular area of ​​the cloth where a certain piece is located exceeds the cutting range of the cutting table, the cloth cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm.

[0022] The tightness of the fabric is controlled and monitored by a signal monitoring module, and the tightness of the fabric is controlled by adsorption of a vacuum adsorption unit. The signal monitoring module monitors the negative pressure sensor connected to the vacuum adsorption unit in real time. When the signal monitoring module detects through the negative pressure sensor that the pressure value of the vacuum adsorption unit is reduced to the set threshold value of the fabric tightness pressure, the fabric cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm.

[0023] Furthermore, the target of judging the device status fault includes at least the device status, and the device status includes at least the device model, device verification code, device working status and running time; wherein

[0024] When determining equipment status faults, at least the following aspects need to be monitored, including:

[0025] The information identification module reads the device model, reads the parameter configuration corresponding to the device model, and checks whether the device model and the parameter configuration corresponding to the device model maintain integrity and consistency. When the parameter configuration of the device model is abnormal, the fabric cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm; and / or,

[0026] The information identification module reads the encryption lock information to obtain the device verification code, and detects whether the encryption lock information reading process is abnormal. When the encryption lock information reading process is abnormal and the device verification code cannot be obtained, the fabric cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm; and / or,

[0027] The signal monitoring module reads the IO status of each component sensor of the device to determine whether there is an abnormality in each component; and / or,

[0028] During the running time, the signal monitoring module initiates a trigger instruction for one or more target components, records the sensor triggering duration and scans the sensor status of the target component, and determines whether the sensor triggering duration exceeds the preset time period. If the sensor of the target component is not triggered within the preset time period, the running time monitoring module will judge it as abnormal, triggering the stop instruction of the material cutting system, and the fault alarm module will trigger an abnormal alarm.

[0029] Furthermore, the types of cutting system faults include at least vacuum level, blade vibration speed, cutting speed and blade wear; wherein,

[0030] The vacuum level is achieved by real-time monitoring of the negative pressure sensor by the signal monitoring module. When the signal monitoring module detects through the negative pressure sensor that the negative pressure value of the vacuum adsorption unit is lower than the set minimum threshold of the cloth adsorption pressure, the cloth cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm.

[0031] The vibration knife speed is realized by real-time monitoring and reading the vibration knife motor encoder feedback through the signal monitoring module. When it is detected that the vibration knife speed is lower than the minimum value, the cutting is stopped and an abnormal alarm is triggered;

[0032] The cutting speed is achieved by real-time detection of interpolation feedback of each axis by the signal monitoring module. When an abnormal axis interpolation state is detected, the cloth cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm.

[0033] The knife wear is achieved by real-time monitoring of the knife sharpening times by a signal monitoring module or by measuring the knife width by a displacement sensor. When the knife sharpening times reaches a maximum threshold or the knife width reaches a minimum threshold, the cloth cutting system suspends cutting and a fault alarm module triggers an abnormal alarm.

[0034] Furthermore, the fault diagnosis target priority types in step S30 are divided into the highest priority target type, the second highest priority target type, the third priority target type and other target types, wherein the highest priority target type is the vacuum level, the second highest priority target type is the fabric tightness, the third priority target type is the knife loss, and other target types include at least the number of fabric layers, fabric size, equipment status, knife vibration speed and cutting speed.

[0035] Furthermore, the specific steps of step S40 are as follows:

[0036] S41: Setting the root node and starting fault type diagnosis;

[0037] S42: Build the first-level branch, the highest priority target type, specifically:

[0038] Based on the vacuum index, the signal monitoring module monitors the negative pressure sensor to determine whether the negative pressure value of the vacuum adsorption unit is lower than the set minimum threshold of the fabric adsorption pressure, and diagnose whether the vacuum level is abnormal;

[0039] If so, a vacuum adsorption unit failure alarm is output and the judgment process is interrupted;

[0040] If not, continue monitoring the next highest priority target type;

[0041] S43: construct the second-level branch to diagnose the second-highest priority target type;

[0042] The signal monitoring module monitors the negative pressure sensor to determine whether the negative pressure value of the vacuum adsorption unit is lower than the set threshold of the fabric tightness pressure, and diagnose whether the fabric tightness is abnormal. Specifically:

[0043] If so, it outputs a fabric abnormality fault alarm and interacts with the fabric cutting system to confirm whether to interrupt the process;

[0044] No, continue monitoring the third priority target type;

[0045] S44: Construct the third-level branch to diagnose the third-priority target type, specifically:

[0046] The signal monitoring module monitors whether the number of times the knife is sharpened has reached the highest threshold or whether the knife width has reached the lowest threshold, and diagnoses whether the knife wear has reached the usage threshold.

[0047] If so, the output cutting system fails and interacts with the fabric cutting system to confirm whether to interrupt the process;

[0048] No, continue to check other target types;

[0049] S45, diagnose other monitoring quantities, specifically:

[0050] Monitor the number of fabric layers, fabric size, equipment status, vibration speed, and cutting speed to see if there are any abnormalities.

[0051] The fault diagnosis target type is output according to the abnormal monitoring quantity monitored, and it is decided whether to perform fault diagnosis target processing.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] Observability and explainability: The structure of the decision tree is intuitive and easy to understand and operate. At the same time, the branch logic of the decision tree can clearly show the process and basis of fault judgment.

[0054] Ability to integrate multiple variables: The decision tree can comprehensively consider multiple monitoring variables and make fault judgments based on the priority and importance of the variables.

[0055] Real-time and accuracy: The decision tree method can quickly respond to changes in input data and give accurate fault judgment results.

[0056] Easy to update and maintain: The structure and rules of the decision tree can be adjusted and optimized according to actual conditions to adapt to changes in equipment characteristics and changes in production needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 The present invention is a flowchart of the cutting bed fault diagnosis method. DETAILED DESCRIPTION

[0058] 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.

[0059] The invention discloses a cutting bed fault diagnosis method, comprising the following steps:

[0060] Step S10, defining the fault diagnosis target type to be monitored;

[0061] In this embodiment, the fault diagnosis target types include at least: number of fabric layers, fabric size, fabric tightness, equipment status, vacuum level, vibration speed, cutting speed, and blade wear;

[0062] The fabric size includes fabric length and fabric width.

[0063] Step S20, defining the fault type;

[0064] In this embodiment, the fault types in step S20 at least include abnormal cloth fault, equipment status fault, and cutting system fault.

[0065] In this embodiment, the determination targets of abnormal fabric failure include at least the number of fabric layers, fabric size, and fabric tightness;

[0066] The number of fabric layers is controlled and monitored by the cutting bed height limit module. When the number exceeds the set value of the height limit module, the fabric feeding system stops feeding and the fault alarm module triggers an abnormal alarm.

[0067] The cloth size is controlled and monitored by the analytical cutting module. When the analytical cutting module identifies that the rectangular area of ​​a cloth piece is beyond the cutting range of the cutting table, the cloth cutting system stops cutting and the fault alarm module triggers an abnormal alarm.

[0068] The tightness of the fabric is controlled and monitored by the signal monitoring module. The tightness of the fabric is controlled by the vacuum adsorption unit. The signal monitoring module monitors the negative pressure sensor connected to the vacuum adsorption unit in real time. When the signal monitoring module detects through the negative pressure sensor that the pressure value of the vacuum adsorption unit is reduced to the set threshold of the fabric tightness pressure, the fabric cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm.

[0069] The identification target of the equipment status failure includes at least the equipment status, and the equipment status includes at least the equipment model, equipment verification code, equipment working status and running time.

[0070] In this embodiment, when performing device status fault identification, the following aspects need to be monitored, including:

[0071] The information identification module reads the device model and the parameter configuration corresponding to the device model, and checks whether the device model and the parameter configuration corresponding to the device model maintain integrity and consistency. When the parameter configuration of the device model is abnormal, the fabric cutting system will be restricted, and the fault alarm module will trigger an abnormal alarm; and / or,

[0072] The information identification module reads the encryption lock information to obtain the device verification code, and detects whether the encryption lock information is abnormal. When the encryption lock information is abnormal and the device verification code cannot be obtained, the cloth cutting system will be restricted, and the fault alarm module triggers an abnormal alarm; and / or,

[0073] The signal monitoring module reads the IO status of each component sensor of the device to determine whether there is an abnormality in each component; and / or,

[0074] During the running time, the signal monitoring module initiates a trigger instruction for one or more target components, records the sensor triggering duration and scans the sensor status of the target component, and determines whether the sensor triggering duration exceeds the preset time period. If the sensor of the target component is not triggered within the preset time period, the running time monitoring module will judge it as abnormal, triggering the stop instruction of the material cutting system, and the fault alarm module will trigger an abnormal alarm.

[0075] In this embodiment, the types of cutting system faults include at least vacuum level, blade vibration speed, cutting speed and blade wear;

[0076] The vacuum level is achieved by real-time monitoring of the negative pressure sensor by the signal monitoring module. When the signal monitoring module detects through the negative pressure sensor that the negative pressure value of the vacuum adsorption unit is lower than the minimum threshold set for the fabric adsorption pressure, the fabric cutting system will be restricted and the fault alarm module will trigger an abnormal alarm.

[0077] The oscillating knife speed is realized by real-time monitoring and reading the feedback of the oscillating knife motor encoder by the signal monitoring module. When it is detected that the oscillating knife speed is lower than the minimum value, the cloth cutting system will be restricted and the fault alarm module will trigger an abnormal alarm.

[0078] The cutting speed is achieved by real-time detection of interpolation feedback of each axis by the signal monitoring module. When an abnormal axis interpolation state is detected, the cloth cutting system will be restricted and the fault alarm module will trigger an abnormal alarm.

[0079] Knife wear is detected by real-time monitoring of knife sharpening times through a signal monitoring module or by measuring knife width through a displacement sensor. When the knife sharpening times reach the highest threshold or the knife width reaches the lowest threshold, the fabric cutting system will be restricted and the fault alarm module will trigger an abnormal alarm.

[0080] Step S30, setting the fault diagnosis target priority type;

[0081] In this embodiment, the fault diagnosis target priority types are divided into the highest priority target type, the second highest priority target type, the third priority target type and other target types. The highest priority target type is the vacuum level, the second highest priority target type is the fabric tightness, the third priority target type is the knife loss, and other target types include at least the number of fabric layers, fabric size, equipment status, knife vibration speed and cutting speed.

[0082] Step S40, constructing a fault diagnosis target priority decision tree and performing fault type diagnosis; the specific steps are as follows:

[0083] S41: Setting the root node and starting fault type diagnosis;

[0084] S42: Build the first-level branch, the highest priority target type, specifically:

[0085] Based on the vacuum index, the signal monitoring module monitors the negative pressure sensor to determine whether the negative pressure value of the vacuum adsorption unit is lower than the set minimum threshold of the fabric adsorption pressure, and diagnose whether the vacuum level is abnormal;

[0086] If so, a vacuum adsorption unit failure alarm is output and the judgment process is interrupted;

[0087] If not, continue monitoring the next highest priority target type;

[0088] S43: construct the second-level branch to diagnose the second-highest priority target type;

[0089] The signal monitoring module monitors the negative pressure sensor to determine whether the negative pressure value of the vacuum adsorption unit is lower than the set threshold of the fabric tightness pressure, and diagnose whether the fabric tightness is abnormal. Specifically:

[0090] If so, it outputs a fabric abnormality fault alarm and interacts with the fabric cutting system to confirm whether to interrupt the process;

[0091] No, continue monitoring the third priority target type;

[0092] S44: Construct the third-level branch to diagnose the third-priority target type, specifically:

[0093] The signal monitoring module monitors whether the number of times the knife is sharpened has reached the highest threshold or whether the knife width has reached the lowest threshold, and diagnoses whether the knife wear has reached the usage threshold.

[0094] If so, the cutting system failure is output, and the fabric cutting system is interacted with to confirm whether to interrupt the process; the cutting system failure is specifically that the tool is severely worn and needs to be replaced;

[0095] No, continue to check other target types;

[0096] S45, diagnose other monitoring quantities, specifically:

[0097] Monitor the number of fabric layers, fabric size, equipment status, vibration speed, and cutting speed to see if there are any abnormalities.

[0098] The fault diagnosis target type is output according to the abnormal monitoring quantity monitored, and it is decided whether to perform fault diagnosis target processing.

[0099] Step S50, outputting a decision tree, and outputting possible fault types and specific causes according to the branch logic and priority settings of the decision tree.

[0100] The cutting table fault diagnosis method of the present invention realizes the monitoring and maintenance of the cutting table equipment, ensures the cutting quality and equipment stability, and directly feeds back the system feedback and diagnosis results to the equipment under the monitoring of various parameters to improve the cutting speed of the equipment, improve production efficiency and reduce maintenance costs.

[0101] The present invention also discloses a cutting bed fault diagnosis system, which is connected to a fabric feeding system and a fabric cutting system respectively, and the cutting bed fault diagnosis system, the fabric feeding system and the fabric cutting system are all connected to a control system and controlled by the control system. The cutting bed fault diagnosis system includes a plurality of submodules, mainly including a cutting bed height limit module, an analytical cutting module, a pressure monitoring module, an information identification module, a signal monitoring module, a sensor monitoring module, etc., and each submodule of the cutting bed fault diagnosis system is connected to the control system.

[0102] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for diagnosing cutting bed faults, characterized in that: The following steps are involved: Step S10, defining the fault diagnosis target type to be monitored; Step S20, defining the fault type; Step S30, setting the fault diagnosis target priority type; Step S40, constructing a fault diagnosis target priority decision tree according to the fault diagnosis target priority type, and performing fault type diagnosis; Step S50, outputting a decision tree, and outputting the fault type and cause according to the branch logic and priority setting of the decision tree.

2. A cutting bed fault diagnosis method as claimed in claim 1, characterized in that: The fault diagnosis target types in step S10 include: number of fabric layers, fabric size, fabric tightness, equipment status, vacuum level, vibration speed, cutting speed, blade loss, adsorption negative pressure value, air pressure positive pressure value, and blade width sensor; The fabric size includes fabric length and fabric width.

3. A cutting bed fault diagnosis method as claimed in claim 1, characterized in that: The fault types in step S20 include abnormal cloth fault, equipment status fault, and cutting system fault.

4. A cutting bed fault diagnosis method as claimed in claim 3, characterized in that: The determination targets of the abnormal fabric failure at least include the number of fabric layers, fabric size and fabric tightness; The number of fabric layers is controlled and monitored by the cutting bed height limit module. When the number exceeds the set value of the height limit module, the fabric feeding system stops feeding and the fault alarm module triggers an abnormal alarm. The cloth size is controlled and monitored by the analytical cutting module. When the analytical cutting module identifies that the rectangular area of ​​the cloth where a certain piece is located exceeds the cutting range of the cutting table, the cloth cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm. The tightness of the fabric is controlled and monitored by a signal monitoring module, and the tightness of the fabric is controlled by adsorption of a vacuum adsorption unit. The signal monitoring module monitors the negative pressure sensor connected to the vacuum adsorption unit in real time. When the signal monitoring module detects through the negative pressure sensor that the pressure value of the vacuum adsorption unit is reduced to the set threshold value of the fabric tightness pressure, the fabric cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm.

5. A cutting bed fault diagnosis method as claimed in claim 3, characterized in that: The target for judging the equipment status fault includes at least the equipment status, and the equipment status includes at least the equipment model, equipment verification code, equipment working status and running time; in When determining equipment status faults, at least the following aspects need to be monitored, including: The information identification module reads the device model, reads the parameter configuration corresponding to the device model, and checks whether the device model and the parameter configuration corresponding to the device model maintain integrity and consistency. When the parameter configuration of the device model is abnormal, the fabric cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm; and / or, The information identification module reads the encryption lock information to obtain the device verification code, and detects whether the encryption lock information reading process is abnormal. When the encryption lock information reading process is abnormal and the device verification code cannot be obtained, the fabric cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm; and / or, The signal monitoring module reads the IO status of each component sensor of the device to determine whether there is an abnormality in each component; and / or, The run time signal monitoring module initiates a trigger instruction for one or more target components, records the sensor trigger duration and scans the sensor status of the target component, and determines whether the sensor trigger duration exceeds the preset time period. If the sensor of the target component is not triggered within the preset time period, the run time monitoring module determines it as abnormal, triggers the stop instruction of the fabric cutting system, and the fault alarm module triggers an abnormal alarm.

6. A method for diagnosing cutting machine faults as claimed in claim 3, characterized in that: The types of cutting system faults include at least vacuum level, blade vibration speed, cutting speed and blade wear; wherein, The vacuum level is achieved by real-time monitoring of the negative pressure sensor by the signal monitoring module. When the signal monitoring module detects through the negative pressure sensor that the negative pressure value of the vacuum adsorption unit is lower than the set minimum threshold of the cloth adsorption pressure, the cloth cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm. The vibration knife speed is realized by real-time monitoring and reading the vibration knife motor encoder feedback through the signal monitoring module. When it is detected that the vibration knife speed is lower than the minimum value, the cutting is stopped and an abnormal alarm is triggered; The cutting speed is achieved by real-time detection of interpolation feedback of each axis by the signal monitoring module. When an abnormal axis interpolation state is detected, the cloth cutting system suspends cutting, and the fault alarm module triggers an abnormal alarm. The knife wear is achieved by real-time monitoring of the knife sharpening times by a signal monitoring module or by measuring the knife width by a displacement sensor. When the knife sharpening times reaches a maximum threshold or the knife width reaches a minimum threshold, the cloth cutting system suspends cutting and a fault alarm module triggers an abnormal alarm.

7. A cutting bed fault diagnosis method as claimed in claim 1, characterized in that: The fault diagnosis target priority types in step S30 are divided into the highest priority target type, the second highest priority target type, the third priority target type and other target types, wherein the highest priority target type is the vacuum level, the second highest priority target type is the fabric tightness, the third priority target type is the knife loss, and other target types include at least the number of fabric layers, fabric size, equipment status, knife vibration speed and cutting speed.

8. A method for diagnosing cutting machine faults as claimed in claim 1, characterized in that: The specific steps of step S40 are as follows: S41: Setting the root node and starting fault type diagnosis; S42: Build the first-level branch, the highest priority target type, specifically: Based on the vacuum index, the signal monitoring module monitors the negative pressure sensor to determine whether the negative pressure value of the vacuum adsorption unit is lower than the set minimum threshold of the fabric adsorption pressure, and diagnose whether the vacuum level is abnormal; If so, a vacuum adsorption unit failure alarm is output and the judgment process is interrupted; If not, continue monitoring the next highest priority target type; S43: construct the second-level branch to diagnose the second-highest priority target type; The signal monitoring module monitors the negative pressure sensor to determine whether the negative pressure value of the vacuum adsorption unit is lower than the set threshold of the fabric tightness pressure, and diagnose whether the fabric tightness is abnormal. Specifically: If so, it outputs a fabric abnormality fault alarm and interacts with the fabric cutting system to confirm whether to interrupt the process; No, continue monitoring the third priority target type; S44: Construct the third-level branch to diagnose the third-priority target type, specifically: The signal monitoring module monitors whether the number of times the knife is sharpened has reached the highest threshold or whether the knife width has reached the lowest threshold, and diagnoses whether the knife wear has reached the usage threshold. If so, the output cutting system fails and interacts with the fabric cutting system to confirm whether to interrupt the process; No, continue to check other target types; S45, diagnose other monitoring quantities, specifically: Monitor the number of fabric layers, fabric size, equipment status, vibration speed, and cutting speed to see if there are any abnormalities. The fault diagnosis target type is output according to the abnormal monitoring quantity monitored, and it is decided whether to perform fault diagnosis target processing.

Images