An intelligent water jet loom fault diagnosis method and system

Abstract

The present invention provides a fault diagnosis method and system for an intelligent water jet loom, belonging to the technical field of data processing, specifically including: determining a reference diagnosis model for the remaining textile type by using the similarity between the remaining textile type and the control parameters of different reference types, determining the identification deviation situation of the fault types in different dimensions based on the identification results of the reference diagnosis model for the matching data of the remaining textile type, and when it is determined that there is no reference diagnosis model with the identification reliability meeting the requirements by combining the matching data of the fault types in different dimensions, performing a combined processing on the reference diagnosis models to generate multiple groups of identification schemes, determining the identification schemes by using the identification deviation situations of the fault types in different dimensions of the remaining textile type for different identification schemes, and performing a fault identification process on the remaining textile type by using the selected identification schemes, ensuring the accuracy of the fault diagnosis results of the water jet loom.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to a fault diagnosis method and system for an intelligent water jet loom. Background Art

[0002] A water jet loom is a shuttleless loom that uses a jet of water to draw the weft yarn through the shed. In order to achieve fault identification of the water jet loom, in the patent application for invention CN202310636798.8, "Intelligent Water Jet Loom and Its Control System", automatic diagnosis of water jet loom faults is realized based on vibration signals and sound signals, so as to timely detect faults of the water jet loom and avoid equipment damage and production efficiency decline caused by faults. However, there are the following technical problems at the same time:

[0003] When processing different types of textiles, due to certain differences in the shedding amount, shedding time, cloth roller tension, water spraying time, water spraying amount, and water pressure of the water pump of the water jet loom, there will also be certain differences in its vibration signals and sound signals. This makes it difficult to meet the requirements for the accuracy of the processing results of fault diagnosis if a unified fault diagnosis model is adopted for the water jet loom.

[0004] In view of the above technical problems, the present invention provides a fault diagnosis method and system for an intelligent water jet loom. Summary of the Invention

[0005] To achieve the object of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a fault diagnosis method for an intelligent water jet loom is provided.

[0007] A fault diagnosis method for an intelligent water jet loom specifically includes:

[0008] S1 Determine the matching data of the water jet loom for different types of textiles, and determine the type of textile for constructing the fault diagnosis model through the analysis results of the matching data for different fault types, and use it as the reference type.

[0009] S2 Use the types of textiles other than the reference type as the remaining textile types, and based on the control parameters of the water jet loom for the remaining textile types, determine the similarity with the control parameters of different reference types, and use the similarity to determine the reference diagnosis model for the remaining textile types.

[0010] S3 determines the identification deviation of the fault types in different dimensions based on the identification results of the matching data of the remaining fabric types by the reference diagnostic model. When it is determined that there is no reference diagnostic model with the identification reliability meeting the requirements in combination with the matching data of the fault types in different dimensions, proceed to the next step;

[0011] S4 performs combined processing on the reference diagnostic model to generate multiple groups of identification schemes, determines the screening of the identification schemes by using the identification deviation of the fault types in different dimensions of the remaining fabric types for different identification schemes, and performs fault identification processing on the remaining fabric types by using the screened identification schemes.

[0012] The beneficial effects of the present invention are as follows:

[0013] By analyzing the results of the matching data for different fault types, the type of fabric for constructing the fault diagnosis model is determined, thereby realizing the determination of the type of fabric for constructing the fault diagnosis model from multiple perspectives such as the data volume of the matching data corresponding to different fault types and the similarity degree of the matching data, avoiding the technical problem of low accuracy of the construction result of the fault diagnosis model caused by less data volume of the matching data or more similar matching data, improving the reliability of the diagnosis result of the fault diagnosis model, and also laying a foundation for further determining the screening identification scheme.

[0014] Determine the screening of the identification schemes by using the identification deviation of the fault types in different dimensions of the remaining fabric types for different identification schemes, thereby realizing the identification of the fault types of the remaining fabric types from the identification schemes constructed by multiple fault diagnosis models, avoiding the technical problem of low accuracy of the identification result caused by using a single fault diagnosis type, and further combining the identification deviation of the fault types in different dimensions, thereby realizing the accurate determination of the identification scheme of the remaining fabric types from the perspective of the identification accuracy rate.

[0015] A further technical solution is that the matching data is the operation data of the water jet loom when processing the fabric of the type.

[0016] A further technical solution is that the input quantities of the fault diagnosis model include the vibration data and sound data of the water jet loom.

[0017] A further technical solution is that the method for determining the screening identification scheme is as follows:

[0018] Based on the identification deviation of the fault types in different dimensions of the remaining fabric types for the identification scheme, determine the number of identification deviations and the number of accurate identifications of the fault types in different dimensions;

[0019] Determine the deviation coefficient of the fault type in different dimensions based on the ratio of the number of recognition deviations to the number of accurate recognitions;

[0020] Determine the comprehensive deviation coefficient of different recognition schemes based on the average value of the deviation coefficients of the fault types in different dimensions, and determine the screening recognition scheme in the recognition scheme based on the comprehensive deviation coefficient.

[0021] A further technical solution is that the screening recognition scheme is the recognition scheme with the smallest comprehensive deviation coefficient.

[0022] On the other hand, the present invention provides a computer system, including: a memory and a processor connected by communication, and a computer program stored on the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned intelligent water-jet loom fault diagnosis method.

[0023] Other features and advantages will be described in the subsequent specification, and the objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0024] To make the above-mentioned objectives, features and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, is described in detail as follows. Description of the Drawings

[0025] By referring to the drawings and describing its exemplary embodiments in detail, the above and other features and advantages of the present invention will become more obvious;

[0026] Figure 1 is a flowchart of an intelligent water-jet loom fault diagnosis method;

[0027] Figure 2 is a flowchart of a method for determining the type of textile fabric for constructing a fault diagnosis model;

[0028] Figure 3 is a flowchart of a method for determining the reference diagnosis model of the remaining textile fabric types;

[0029] Figure 4 is a flowchart of a method for determining the recognition reliability of the reference diagnosis model;

[0030] Figure 5 is a framework diagram of a computer system. Detailed Embodiments

[0031] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification. Embodiment 1

[0032] To solve the above problems, according to one aspect of the present invention, as Figure 1 shown, a fault diagnosis method for an intelligent water jet loom is provided, which specifically includes:

[0033] S1 Determine the matching data of the water jet loom for different types of textiles, and determine the type of textile for constructing the fault diagnosis model through the analysis results of the matching data for different fault types, and use it as the reference type;

[0034] Further, the matching data is the operation data of the water jet loom when processing the type of textile.

[0035] It can be understood that the input quantities of the fault diagnosis model include the vibration data and sound data of the water jet loom.

[0036] Specifically, as Figure 2 shown, the method for determining the type of textile for constructing the fault diagnosis model is:

[0037] Based on the analysis results of the matching data for different fault types, determine the matching data under different fault types;

[0038] Determine the data volume of the matching data under different fault types with the matching data under different fault types, and use the data volume of the matching data under different fault types to determine the data matching coefficients of different fault types;

[0039] Based on the data matching coefficients of different fault types, determine the comprehensive matching coefficient of the matching data, and use the comprehensive matching coefficient to determine whether the type of textile is the type of textile for constructing the fault diagnosis model.

[0040] Further, the data matching coefficient of the fault type is determined according to the ratio of the data volume of the matching data of the fault type to the preset data volume.

[0041] It can be understood that the comprehensive matching coefficient is determined according to the average value of the data matching coefficients of different fault types of the matching data.

[0042] In addition, it should be noted that the method for determining the type of the textile for constructing the fault diagnosis model is as follows:

[0043] Based on the analysis results of the matching data for different fault types, determine the matching data for different fault types;

[0044] Determine the data volume of the matching data for different fault types with the matching data for different fault types, and use the data volume of the matching data for different fault types to determine whether the type of the textile is the type of the textile for constructing the fault diagnosis model.

[0045] In addition, it should be noted that when there is a fault type with the data volume of the matching data less than the matching data volume threshold, it is determined that the type of the textile does not belong to the type of the textile for constructing the fault diagnosis model.

[0046] Optionally, the method for determining the type of the textile for constructing the fault diagnosis model is as follows:

[0047] S11 Based on the analysis results of the matching data for different fault types, determine the matching data for different fault types;

[0048] Optionally, before entering step S12, the following content is also included:

[0049] Based on the matching data for different fault types, determine the data volume of the matching data for different fault types. When the total data volume of the matching data for different fault types is less than the preset data volume threshold, it is determined that the type of the textile does not belong to the type of the textile for constructing the fault diagnosis model. When the total data volume of the matching data for different fault types is not less than the preset data volume threshold, proceed to step S12.

[0050] Optionally, step S11 in the above includes steps S111 - S113, specifically:

[0051] Based on the analysis results of the matching data for different fault types, determine the matching data for different fault types

[0052] S111 Obtain the data volume of the matching data of the type of the textile. When the data volume of the matching data of the type of the textile is less than the preset matching data volume threshold, it is determined that the type of the textile does not belong to the type of the textile for constructing the fault diagnosis model. When the data volume of the matching data of the type of the textile is not less than the preset matching data volume threshold, proceed to step S112;

[0053] S112 uses the matching data of the type of the textile to calculate the data similarity coefficient of the matching data of the type of the textile. When the data similarity coefficient of the matching data of the type of the textile does not meet the requirements, it is determined that the type of the textile does not belong to the type of the textile for constructing the fault diagnosis model. When the data similarity coefficient of the matching data of the type of the textile meets the requirements, go to step S113;

[0054] S113 is based on the matching data under different fault types to determine the data volume of the matching data under different fault types. When the total data volume of the matching data under different fault types is less than the preset data volume threshold, it is determined that the type of the textile does not belong to the type of the textile for constructing the fault diagnosis model. When the total data volume of the matching data under different fault types is not less than the preset data volume threshold, go to step S12.

[0055] S12 uses the matching data under different fault types to determine the data volume of the matching data under different fault types, and combines the data deviation situation between the matching data under different fault types to determine the data matching coefficient of different fault types;

[0056] Optionally, step S12 above includes steps S121 - S123, specifically:

[0057] S121 uses the matching data under different fault types to determine the data volume of the matching data under different fault types. When there is a fault type with the data volume of the matching data less than the matching data volume threshold, it is determined that the type of the textile does not belong to the type of the textile for constructing the fault diagnosis model. When the data volume of the matching data of different fault types is not less than the matching data volume threshold, go to step S122;

[0058] S122 uses the data deviation situation between the matching data under different fault types to calculate the data similarity coefficient of the matching data under different fault types. When there is a fault type with the data similarity coefficient greater than the preset similarity coefficient, it is determined that the type of the textile does not belong to the type of the textile for constructing the fault diagnosis model. When there is no fault type with the data similarity coefficient greater than the preset similarity coefficient, go to step S123;

[0059] S123 determines the data matching coefficient of different fault types according to the data volume of the matching data under different fault types and the data deviation situation between the matching data under different fault types. When there is a fault type with the data matching coefficient not meeting the requirements, it is determined that the type of the textile does not belong to the type of the textile for constructing the fault diagnosis model. When there is no fault type with the data matching coefficient not meeting the requirements, go to step S13.

[0060] S13 determines the comprehensive matching coefficient of the matching data based on the data matching coefficients of different fault types, and uses the comprehensive matching coefficient to determine whether the type of the textile is the type of the textile for constructing the fault diagnosis model.

[0061] S2 uses the type of the textile excluding the reference type of the textile as the remaining textile types, and based on the control parameters of the water jet loom for the remaining textile types, determines the similarity of the control parameters with different reference types, and uses the similarity to determine the reference diagnosis model of the remaining textile types;

[0062] Furthermore, the data similarity coefficient of the matching data under the fault type is determined according to the proportion of the amount of data within the preset range of the data deviation amount of the matching data under the fault type.

[0063] Specifically, the control parameters include the shedding amount and shedding time of the water jet loom, the cloth roller tension, the water spraying time, water spraying amount and water pressure of the water pump.

[0064] It can be understood that the similarity of the control parameters includes the parameter deviation amount of different control parameters.

[0065] It should be noted that as Figure 3 shown, the method for determining the reference diagnosis model of the remaining textile types is:

[0066] Use the similarity to determine the parameter deviation amount of the remaining textile types and the reference type for different control parameters;

[0067] Determine the control parameter deviation coefficient according to the average value of the parameter deviation amounts of different control parameters, and determine whether the fault diagnosis model of the reference type is the reference diagnosis model of the remaining textile types through the control parameter deviation coefficient.

[0068] Furthermore, the control parameter deviation coefficient is determined according to the average value of the ratios of the parameter deviation amounts of different control parameters to the control parameters of the remaining textile types.

[0069] It can be understood that when the control parameter deviation coefficient of the remaining textile types and the reference type is less than the preset deviation threshold, it is determined that the fault diagnosis model of the reference type is the reference diagnosis model of the remaining textile types.

[0070] In addition, it should be noted that the method for determining the reference diagnosis model of the remaining textile types is:

[0071] Use the similarity to determine the parameter deviation amount of the remaining textile types and the reference type for different control parameters;

[0072] Determine the deviation coefficients of different control parameters according to the parameter deviation amounts of different control parameters;

[0073] Use the deviation coefficients to determine whether the fault diagnosis model of the reference type is the reference diagnosis model of the remaining textile type.

[0074] Further, when there are control parameters whose deviation coefficients do not meet the requirements, it is determined that the fault diagnosis model of the reference type does not belong to the reference diagnosis model of the remaining textile type.

[0075] S3 uses the recognition result of the reference diagnosis model for the matching data of the remaining textile type to determine the recognition deviation situation of the fault types in different dimensions, and when it is determined that there is no reference diagnosis model with the recognition reliability meeting the requirements by combining the matching data of the fault types in different dimensions, proceed to the next step;

[0076] Further, the recognition deviation situation of the fault types in different dimensions includes the number of recognition deviations of the fault types in different dimensions.

[0077] Specifically, as Figure 4 shown, the method for determining the recognition reliability of the reference diagnosis model is:

[0078] Determine the number of recognition deviations of the fault types in different dimensions based on the recognition deviation situation of the fault types in different dimensions by the reference diagnosis model;

[0079] Determine the data volume of the matching data of the fault types in different dimensions with the matching data of the fault types in different dimensions, and use the proportion of the data volume of the matching data of the fault types in different dimensions in the data volume of the remaining textile type to determine the weight coefficient of the matching data of the fault types in different dimensions;

[0080] Based on the weight coefficient of the matching data of the fault types in different dimensions and the number of recognition deviations of the fault types in different dimensions, determine the corrected number of deviations of the reference diagnosis model, and use the corrected number of deviations to determine the recognition reliability of the reference diagnosis model.

[0081] Further, the recognition reliability of the reference diagnosis model is determined according to the preset reliability coefficient corresponding to the corrected number of deviations.

[0082] In addition, it should be noted that the value range of the recognition reliability of the reference diagnosis model is between 0 and 1, where when the recognition reliability of the reference diagnosis model is greater than the preset reliability threshold, it is determined that the recognition reliability of the reference diagnosis model meets the requirements.

[0083] It is understandable that when there is a reference diagnosis model with recognition reliability meeting the requirements, the reference diagnosis model with the highest recognition reliability is used to perform the fault recognition process for the remaining textile types.

[0084] Optionally, the method for determining the recognition reliability of the reference diagnosis model is as follows:

[0085] S31 Determine the number of recognition deviations of the fault types in different dimensions based on the recognition deviation situations of the fault types in different dimensions of the reference diagnosis model, and calculate the recognition reliability coefficients of the fault types in different dimensions according to the number of recognition deviations and the number of accurate recognitions;

[0086] S32 Determine the data volume of the matching data of the fault types in different dimensions with the matching data of the fault types in different dimensions, and use the data volume of the matching data of the fault types in different dimensions to determine the weight coefficients of the matching data of the fault types in different dimensions in the proportion of the data volume of the remaining textile types;

[0087] S33 Determine the recognition reliability of the reference diagnosis model based on the weight coefficients of the matching data of the fault types in different dimensions and the recognition reliability coefficients of the fault types in different dimensions.

[0088] S4 Combine the reference diagnosis models to generate multiple sets of recognition schemes, use the recognition deviation situations of the fault types in different dimensions of the remaining textile types with different recognition schemes to determine the screening of the recognition schemes, and use the screened recognition schemes to perform the fault recognition process for the remaining textile types.

[0089] Furthermore, the recognition scheme is constructed based on multiple reference diagnosis models.

[0090] Specifically, the method for determining the screened recognition scheme is as follows:

[0091] Based on the recognition deviation situations of the fault types in different dimensions of the remaining textile types with the recognition scheme, determine the number of recognition deviations and the number of accurate recognitions of the fault types in different dimensions;

[0092] Determine the deviation coefficients of the fault types in different dimensions based on the ratio of the number of recognition deviations to the number of accurate recognitions;

[0093] Determine the comprehensive deviation coefficients of different recognition schemes according to the average values of the deviation coefficients of the fault types in different dimensions, and determine the screened recognition scheme in the recognition scheme based on the comprehensive deviation coefficients.

[0094] It should be noted that the screened recognition scheme is the recognition scheme with the smallest comprehensive deviation coefficient. Embodiment 2

[0095] On the other hand, as Figure 5 shown, the present invention provides a computer system, comprising: a memory and a processor connected by communication, and a computer program stored on the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned intelligent water-jet loom fault diagnosis method.

[0096] In another embodiment, the method for determining the reference diagnosis model of the remaining fabric type is as follows:

[0097] Use the similar situation to determine the parameter deviation amount of the remaining fabric type and the reference type under different control parameters. When there are control parameters with parameter deviation amounts not meeting the requirements, it is determined that the fault diagnosis model of the reference type does not belong to the reference diagnosis model of the remaining fabric type;

[0098] When there are no control parameters with parameter deviation amounts not meeting the requirements:

[0099] Determine the deviation coefficient of different control parameters according to the ratio of the parameter deviation amount of different control parameters to the control parameters of the remaining fabric type. When there are control parameters with deviation coefficients not meeting the requirements: it is determined that the fault diagnosis model of the reference type does not belong to the reference diagnosis model of the remaining fabric type;

[0100] When there are no control parameters with deviation coefficients not meeting the requirements:

[0101] Based on the deviation coefficients of different control parameters, determine the average value of the deviation coefficients of different control parameters. When the average value of the deviation coefficients of different control parameters is less than the preset coefficient threshold:

[0102] It is determined that the fault diagnosis model of the reference type does not belong to the reference diagnosis model of the remaining fabric type;

[0103] When the average value of the deviation coefficients of different control parameters is not less than the preset coefficient threshold:

[0104] According to the deviation coefficients of different control parameters, divide the control parameters into different deviation coefficient intervals. When the number of control parameters in the preset deviation coefficient interval does not meet the requirements:

[0105] It is determined that the fault diagnosis model of the reference type does not belong to the reference diagnosis model of the remaining fabric type;

[0106] When the number of control parameters in the preset deviation coefficient interval meets the requirements:

[0107] Determine the interval deviation coefficient in different deviation coefficient intervals based on the number of control parameters in different deviation coefficient intervals and the deviation coefficients of different control parameters. When the interval deviation coefficient in the preset deviation coefficient interval is less than the preset deviation coefficient, it is determined that the fault diagnosis model of the reference type does not belong to the reference diagnosis model of the remaining fabric type;

[0108] When the interval deviation coefficient in the preset deviation coefficient interval is not less than the preset deviation coefficient:

[0109] Determine the comprehensive deviation coefficient based on the interval deviation coefficients in different deviation coefficient intervals, and determine whether the fault diagnosis model of the reference type is the reference diagnosis model of the remaining fabric type according to the comprehensive deviation coefficient.

[0110] Optionally, the above step S31 includes steps S311 - S313, specifically:

[0111] S311 Determine the number of identification deviations of fault types in different dimensions based on the identification deviation situations of fault types in different dimensions of the reference diagnosis model. When there are fault types with the number of identification deviations not meeting the requirements, it is determined that the identification reliability of the reference diagnosis model does not meet the requirements. When there are no fault types with the number of identification deviations not meeting the requirements, proceed to step S312;

[0112] S312 Determine the total number of identification deviations based on the number of identification deviations of similar faults in different dimensions. When the total number of identification deviations does not meet the requirements, it is determined that the identification reliability of the reference diagnosis model does not meet the requirements. When the total number of identification deviations meets the requirements, proceed to step S313;

[0113] S313 Calculate the identification reliability coefficient of fault types in different dimensions according to the number of identification deviations and the number of accurate identifications. When there are fault types with the identification reliability coefficient not meeting the requirements, it is determined that the identification reliability of the reference diagnosis model does not meet the requirements. When there are no fault types with the identification reliability coefficient not meeting the requirements, proceed to step S314;

[0114] S314 Determine the average value of the identification reliability coefficients of fault types in different dimensions based on the identification reliability coefficients of fault types in different dimensions. When the average value of the identification reliability coefficients of fault types in different dimensions does not meet the requirements, it is determined that the identification reliability of the reference diagnosis model does not meet the requirements. When the average value of the identification reliability coefficients of fault types in different dimensions meets the requirements, proceed to step S32.

[0115] Optionally, the above step S32 includes steps S321 - S323, specifically:

[0116] S321 determines the data volume of the matching data of the fault types in different dimensions, and uses the data volume of the matching data of the fault types in different dimensions to determine the weight coefficient of the matching data of the fault types in the proportion of the data volume of the remaining fabric types;

[0117] S322 determines the corrected reliability coefficient of the fault types in different dimensions based on the weight coefficient and the recognition reliability coefficient of the fault types in different dimensions. When there is a fault type whose corrected reliability coefficient does not meet the requirements, it is determined that the recognition reliability of the reference diagnosis model does not meet the requirements. When there is no fault type whose corrected reliability coefficient does not meet the requirements, it proceeds to step S323;

[0118] S323 determines the average value of the corrected reliability coefficients of the fault types in different dimensions with the corrected reliability coefficients of the fault types in different dimensions. When the average value of the corrected reliability coefficients of the fault types in different dimensions does not meet the requirements, it is determined that the recognition reliability of the reference diagnosis model does not meet the requirements. When the average value of the corrected reliability coefficients of the fault types in different dimensions meets the requirements, it proceeds to step S32.

[0119] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the embodiments of the device, equipment, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0120] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0121] The above is only one or more embodiments of this specification and is not used to limit this specification. For those skilled in the art, one or more embodiments of this specification can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. An intelligent water-jet loom fault diagnosis method, characterized in that, Specifically include: Determine the matching data of water jet looms for different types of textiles. Based on the analysis results of the matching data for different failure types, determine the type of textile for constructing the fault diagnosis model, and use it as the reference type; Take the types of textiles excluding the reference type as the remaining textile types. Based on the control parameters of the water jet loom for the remaining textile types, determine the similarity of the control parameters for different reference types, and use the similarity to determine the reference diagnosis model for the remaining textile types; Based on the recognition results of the reference diagnosis model for the matching data of the remaining textile types, determine the recognition deviation situations for failure types in different dimensions. When it is determined that there is no reference diagnosis model with the recognition reliability meeting the requirements in combination with the matching data of failure types in different dimensions, proceed to the next step; Perform combined processing on the reference diagnosis model to generate multiple sets of recognition schemes. Use the recognition deviation situations of different recognition schemes for failure types in different dimensions of the remaining textile types to determine the screening of recognition schemes, and use the screened recognition schemes to perform fault recognition processing on the remaining textile types; The method for determining the type of textile for constructing the fault diagnosis model is as follows: Based on the analysis results of the matching data for different failure types, determine the matching data under different failure types; Based on the matching data under different failure types, determine the data volume of the matching data under different failure types, and use the data volume of the matching data under different failure types to determine the data matching coefficients for different failure types; Based on the data matching coefficients for different failure types, determine the comprehensive matching coefficient of the matching data, and use the comprehensive matching coefficient to determine whether the type of textile is the type of textile for constructing the fault diagnosis model; The method for determining the screening of recognition schemes is as follows: Based on the recognition deviation situations of the recognition scheme for failure types in different dimensions of the remaining textile types, determine the number of recognition deviation times and the number of accurate recognition times for failure types in different dimensions; Based on the ratio of the number of recognition deviation times to the number of accurate recognition times, determine the deviation coefficients for failure types in different dimensions; According to the average value of the deviation coefficients for failure types in different dimensions, determine the comprehensive deviation coefficient of different recognition schemes, and based on the comprehensive deviation coefficient, determine the screening recognition scheme in the recognition scheme.

2. The intelligent water-jet loom fault diagnosis method according to claim 1, characterized in that, The matching data is the operation data of the water jet loom when processing textiles of this type.

3. The intelligent water-jet loom fault diagnosis method according to claim 1, wherein, The input quantities of the fault diagnosis model include the vibration data and sound data of the water jet loom.

4. The intelligent water-jet loom fault diagnosis method according to claim 1, wherein, The data matching coefficient for the failure type is determined according to the ratio of the data volume of the matching data for the failure type to the preset data volume.

5. The intelligent water-jet loom fault diagnosis method according to claim 1, wherein, The comprehensive matching coefficient is determined according to the average value of the data matching coefficients for different failure types of the matching data.

6. The intelligent water jet loom fault diagnosis method according to claim 1, characterized in that, The control parameters include the shedding amount and shedding time of the water jet loom, the cloth roller tension, the water spraying time, water spraying amount, and water pressure of the water pump.

7. The intelligent water-jet loom fault diagnosis method according to claim 1, characterized in that, The similarity of the control parameters includes the parameter deviation amounts for different control parameters.

8. A computer system, comprising: A memory and a processor in communication connection, and a computer program stored on the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes an intelligent water-jet loom fault diagnosis method according to any one of claims 1-7.

Images