Textile quality tracing method and system

Abstract

The invention provides a textile quality tracing method and system, and belongs to the technical field of control, firstly, a control terminal obtains a training set, the training set comprises a plurality of groups of training data, then the control terminal generates a neural network model based on the training set, and the neural network model is used for obtaining defect data according to the input defect data. And selectively outputting one or more of raw material batch data, production equipment data, operator data, process parameter data and production time data, finally, acquiring target defect data of a to-be-traced product by the control terminal, inputting the target defect data into the trained neural network model, and according to an output result of the neural network model, obtaining the target defect data of the to-be-traced product. And determining production reasons. According to the textile quality tracing method and system provided by the invention, by constructing the intelligent quality tracing system, whole-course data acquisition, analysis and tracing from raw materials to finished products can be realized, so that the troubleshooting efficiency of quality problems is improved, the production cost is reduced, and the product quality is improved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a method and system for tracing the quality of textiles. Background Art

[0002] Multiple links are involved in the production process of textiles, including raw material procurement, spinning, weaving, printing and dyeing, post-finishing, packaging, etc. Quality problems may be introduced in each link, such as raw material defects, equipment failures, operation errors, or process parameter deviations. Traditional quality tracing methods usually rely on manual records and inspections, with low efficiency and prone to errors, making it difficult to achieve fast and accurate positioning of quality problems. Summary of the Invention

[0003] Embodiments of this application provide a method and system for tracing the quality of textiles.

[0004] To achieve the above object, this application adopts the following technical solutions: In a first aspect, this application proposes a method for tracing the quality of textiles, which is applicable to a textile quality tracing system. The system includes a control terminal. The method includes: The control terminal obtains a training set, which includes multiple sets of training data. Among them, a set of training data consists of a corresponding set of defect data and tracing data. The tracing data includes raw material batch data, production equipment data, operator data, process parameter data, and production time data; The control terminal generates a neural network model based on the training set. The neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data; The control terminal obtains the target defect data of the product to be traced, and inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model.

[0005] Combined with the first aspect, in some embodiments, the textile quality tracing system further includes a detection terminal, which is used to detect and obtain the raw material batch data, production equipment data, operator data, process parameter data, and production time data. Before the control terminal obtains the target defect data of the product to be traced and inputs the target defect data into the trained neural network model and determines the production cause, it includes: The control terminal obtains the production equipment data, operator data, process parameter data, and production time data corresponding to the target defect data.

[0006] In combination with the first aspect, in some embodiments, the control terminal obtains the target defect data of the product to be traced, inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model. It further includes: The control terminal obtains the detection terminal corresponding to the production cause based on the production cause, and determines the detection terminal as the target detection terminal; The control terminal controls the target detection terminal to increase the detection frequency.

[0007] In combination with the first aspect, in some embodiments, the control terminal generates a neural network model based on the training set. The neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data. It includes: The control terminal controls the input layer of the neural network model to receive the defect data. The defect data includes features such as defect type, defect location, and defect severity. Among them, the number of nodes in the input layer matches the feature dimension of the defect data; The control terminal controls the output layer of the neural network model to generate one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, the number of nodes in the output layer matches the number of traceability data items to be output.

[0008] In combination with the first aspect, in some embodiments, the control terminal controls the output layer of the neural network model to generate one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, when the number of nodes in the output layer matches the number of traceability data items to be output, the activation function is Softmax or a linear function.

[0009] In combination with the first aspect, in some embodiments, the control terminal controls the output layer of the neural network model to generate one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, when the number of nodes in the output layer matches the number of traceability data items to be output, it further includes: The control terminal divides the training set into a target training set and a target validation set, uses the target training set to train the neural network model, and determines the stop training condition through the target validation set.

[0010] In combination with the first aspect, in some embodiments, the control terminal divides the training set into a target training set and a target validation set, uses the target training set to train the neural network model, and determines the stop training condition through the target validation set. It includes: The control terminal divides the training set into a target training set and a target validation set according to a preset ratio; The control terminal inputs the defect data in the target verification set into the neural network model and obtains the output result; The control terminal matches the output result of the neural network model with the production equipment data, operator data, process parameter data, and production time data in the target verification set, and determines whether to stop training according to the matching result.

[0011] In a second aspect, the present application proposes a textile quality traceability system, which includes a control terminal and is configured to: The control terminal obtains a training set, and the training set includes multiple groups of training data. Among them, a group of training data consists of a corresponding group of defect data and traceability data, and the traceability data includes raw material batch data, production equipment data, operator data, process parameter data, and production time data; The control terminal generates a neural network model based on the training set, and the neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data; The control terminal obtains the target defect data of the product to be traced, inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model.

[0012] Combined with the second aspect, in some embodiments, the system is configured to: The textile quality traceability system further includes a detection terminal, which is used to detect and obtain the raw material batch data, production equipment data, operator data, process parameter data, and production time data. Before the control terminal obtains the target defect data of the product to be traced and inputs the target defect data into the trained neural network model to determine the production cause, it includes: The control terminal obtains the production equipment data, operator data, process parameter data, and production time data corresponding to the target defect data.

[0013] Combined with the second aspect, in some embodiments, the system is configured to: After the control terminal obtains the target defect data of the product to be traced and inputs the target defect data into the trained neural network model to determine the production cause, it further includes: The control terminal obtains the detection terminal corresponding to the production cause based on the production cause, and determines the detection terminal as the target detection terminal; The control terminal controls the target detection terminal to increase the detection frequency.

[0014] Combined with the second aspect, in some embodiments, the system is configured to: The control terminal generates a neural network model based on a training set. The neural network model is used to selectively output one or more of raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data, including: The control terminal controls the input layer of the neural network model to receive defect data. The defect data includes features such as defect type, defect location, and defect severity. Among them, the number of nodes in the input layer matches the feature dimension of the defect data; The control terminal controls the output layer of the neural network model to generate one or more of raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, the number of nodes in the output layer matches the number of traceability data items to be output.

[0015] Combined with the second aspect, in some embodiments, the system is configured to: The control terminal controls the output layer of the neural network model to generate one or more of raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, the number of nodes in the output layer matches the number of traceability data items to be output. In this case, the activation function is Softmax or a linear function.

[0016] Combined with the second aspect, in some embodiments, the system is configured to: The control terminal controls the output layer of the neural network model to generate one or more of raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, the number of nodes in the output layer matches the number of traceability data items to be output, and further includes: The control terminal divides the training set into a target training set and a target validation set, uses the target training set to train the neural network model, and determines the stop training condition through the target validation set.

[0017] Combined with the second aspect, in some embodiments, the system is configured to: The control terminal divides the training set into a target training set and a target validation set, uses the target training set to train the neural network model, and determines the stop training condition through the target validation set, including: The control terminal divides the training set into a target training set and a target validation set according to a preset ratio; The control terminal inputs the defect data in the target validation set into the neural network model and obtains the output result; The control terminal matches the output result of the neural network model with the production equipment data, operator data, process parameter data, and production time data in the target validation set, and determines whether to stop training according to the matching result.

[0018] In a third aspect of the embodiments of the present invention, an electronic device is proposed. The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method proposed in the first aspect of the embodiments of the present invention.

[0019] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is proposed, on which a computer program is stored, and when the program is executed by a processor, it implements the method proposed in the first aspect of the embodiments of the present invention.

[0020] In summary, the above method and device have the following technical effects: The present application proposes a method for tracing the quality of textiles. First, the control terminal obtains a training set, which includes multiple sets of training data. Among them, a set of training data consists of a corresponding set of defect data and tracing data. The tracing data includes raw material batch data, production equipment data, operator data, process parameter data, and production time data. Then, the control terminal generates a neural network model based on the training set. The neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data. Finally, the control terminal obtains the target defect data of the product to be traced, inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model. A method and system for tracing the quality of textiles proposed in the present application can realize the whole-process data collection, analysis, and tracing from raw materials to finished products by constructing an intelligent quality tracing system, thereby improving the efficiency of troubleshooting quality problems, reducing production costs, and improving product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic flowchart of a method for tracing the quality of textiles proposed in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] The present application proposes a method for tracing the quality of textiles, which is applicable to a textile quality tracing system. The system includes a control terminal. Please refer to Figure 1, the method includes the following steps: S101: The control terminal obtains a training set, which includes multiple groups of training data. Among them, a group of training data consists of a corresponding group of defect data and traceability data. The traceability data includes raw material batch data, production equipment data, operator data, process parameter data, and production time data.

[0024] It can be understood that data at each link in the textile production process is collected through devices such as inspection terminals, sensors, and production management systems. The defect data can include defect types (such as color difference, broken yarn, stains, etc.), defect locations, defect severity levels, etc. In the training set, each group of defect data is associated with the corresponding traceability data to form a complete group of training data. For example, if a batch of textiles has a color difference defect in the dyeing link, then this defect data is associated with the raw material batch, equipment number, operator, process parameters, and production time in the dyeing link. In some embodiments, the data in the training set can also be cleaned and preprocessed, including removing duplicate data, filling in missing values, standardizing the data format, etc.

[0025] S102: The control terminal generates a neural network model based on the training set. The neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data.

[0026] Specifically, the control terminal controls the input layer of the neural network model to receive the defect data. The defect data includes features such as defect type, defect location, and defect severity level. Among them, the number of nodes in the input layer matches the feature dimension of the defect data. The control terminal controls the output layer of the neural network model to generate one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, the number of nodes in the output layer matches the number of traceability data items to be output.

[0027] Exemplarily, the input layer receives the defect data, including features such as defect type, defect location, and defect severity level.

[0028] The number of nodes in the input layer matches the feature dimension of the defect data. For example, if the defect data contains 10 features, the input layer is designed with 10 nodes. The hidden layer is used to extract the non-linear relationship between the defect data and the traceability data. The hidden layer can be designed as a multi-layer structure, each layer containing several neurons. The activation function can be selected from ReLU, Sigmoid, or Tanh, etc. Of course, it can also be Softmax or a linear function. The number of nodes in the output layer matches the number of traceability data items to be output. For example, if 5 items of traceability data need to be output, the output layer is designed with 5 nodes.

[0029] It is understandable that the target training set is input into the neural network model, and the output result is calculated through forward propagation. The gradient of the loss function with respect to the model parameters is calculated through backpropagation, and the parameters are updated until the model reaches the preset accuracy or convergence condition.

[0030] Exemplarily, as an implementation manner, the control terminal divides the training set into a target training set and a target validation set, uses the target training set to train the neural network model, and determines the stop training condition through the target validation set.

[0031] Specifically, the control terminal divides the training set into a target training set and a target validation set according to a preset ratio; The control terminal inputs the defective data in the target validation set into the neural network model and obtains the output result; The control terminal matches the output result of the neural network model with the production equipment data, operator data, process parameter data, and production time data in the target validation set, and determines whether to stop training according to the matching result.

[0032] In this embodiment, the neural network model can also selectively output the traceability data items most relevant to the defect through the calculation of internal weights and biases according to the input defective data. For example: If the defect is mainly caused by raw material problems, the model preferentially outputs the raw material batch data. If the defect is related to the production equipment, the production equipment data is output. The output result can be a single data item or a combination of multiple data items, depending on the characteristics of the defective data and the learning ability of the model.

[0033] S103: The control terminal obtains the target defective data of the product to be traced, inputs the target defective data into the trained neural network model, and determines the production cause according to the output result of the neural network model.

[0034] The neural network model can be used for real-time prediction. When the target defective data of the product to be traced is input, the model automatically outputs the relevant traceability data items to help quickly locate the production cause.

[0035] For example: Input defective data: {Defect type: color difference, defect location: dyeing area, defect severity: high}.

[0036] Output traceability data: {Raw material batch data: batch A, production equipment data: dyeing machine X, process parameter data: temperature too high}.

[0037] In this embodiment, after determining the production cause, the control terminal can also obtain the detection terminal corresponding to the production cause based on the production cause, and determine the detection terminal as the target detection terminal, and the control terminal controls the target detection terminal to increase the detection frequency.

[0038] It can be understood that the standard detection terminal collects data in real time according to the adjusted detection frequency and uploads it to the control terminal.

[0039] The control terminal analyzes the collected data to determine whether the production problem has been improved. For example: If the raw material detection terminal finds that the quality of a new batch is qualified, the detection frequency is reduced.

[0040] If the dyeing machine status detection terminal finds that the equipment is running normally, the original detection frequency is restored.

[0041] A textile quality traceability method proposed in this application. First, the control terminal obtains a training set, and the training set includes multiple groups of training data. Among them, a group of training data consists of a corresponding group of defect data and traceability data. The traceability data includes raw material batch data, production equipment data, operator data, process parameter data, and production time data. Then, the control terminal generates a neural network model based on the training set. The neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data. Finally, the control terminal obtains the target defect data of the product to be traced and inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model. A textile quality traceability method and system proposed in this application can realize the whole-process data collection, analysis, and traceability from raw materials to finished products by constructing an intelligent quality traceability system, thereby improving the troubleshooting efficiency of quality problems, reducing production costs, and improving product quality.

[0042] Based on the same inventive concept, this application also proposes a textile quality traceability system, which includes a control terminal, and the system is configured to: The control terminal obtains a training set, and the training set includes multiple groups of training data. Among them, a group of training data consists of a corresponding group of defect data and traceability data. The traceability data includes raw material batch data, production equipment data, operator data, process parameter data, and production time data; The control terminal generates a neural network model based on the training set. The neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data; The control terminal obtains the target defect data of the product to be traced, inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model.

[0043] In some embodiments, the system is configured to: The textile quality traceability system further includes a detection terminal. The detection terminal is used to detect and obtain raw material batch data, production equipment data, operator data, process parameter data, and production time data. Before the control terminal obtains the target defect data of the product to be traced and inputs the target defect data into the trained neural network model and determines the production cause, it includes: The control terminal obtains the production equipment data, operator data, process parameter data, and production time data corresponding to the target defect data.

[0044] In some embodiments, the system is configured to: The control terminal obtains the target defect data of the product to be traced, inputs the target defect data into the trained neural network model, and determines the production cause. It further includes: The control terminal obtains the detection terminal corresponding to the production cause based on the production cause, and determines the detection terminal as the target detection terminal; The control terminal controls the target detection terminal to increase the detection frequency.

[0045] In some embodiments, the system is configured to: The control terminal generates a neural network model based on the training set. The neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data, including: The control terminal controls the input layer of the neural network model to receive the defect data. The defect data includes features such as defect type, defect location, and defect severity. Among them, the number of nodes in the input layer matches the feature dimension of the defect data; The control terminal controls the output layer of the neural network model to generate one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, the number of nodes in the output layer matches the number of traceability data items to be output.

[0046] In some embodiments, the system is configured to: The control terminal controls the output layer of the neural network model to generate one or more of raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, the number of nodes in the output layer matches the number of traceability data items to be output, and the activation function is Softmax or a linear function.

[0047] In some embodiments, the system is configured to: The control terminal controls the output layer of the neural network model to generate one or more of raw material batch data, production equipment data, operator data, process parameter data, and production time data. Among them, the number of nodes in the output layer matches the number of traceability data items to be output, and further includes: The control terminal divides the training set into a target training set and a target validation set, uses the target training set to train the neural network model, and determines the stop training condition through the target validation set.

[0048] In some embodiments, the system is configured to: The control terminal divides the training set into a target training set and a target validation set, uses the target training set to train the neural network model, and determines the stop training condition through the target validation set, including: The control terminal divides the training set into a target training set and a target validation set according to a preset ratio; The control terminal inputs the defect data in the target validation set into the neural network model and obtains the output result; The control terminal matches the output result of the neural network model with the production equipment data, operator data, process parameter data, and production time data in the target validation set, and determines whether to stop training according to the matching result.

[0049] This application proposes a textile quality traceability system. First, the control terminal obtains a training set, which includes multiple sets of training data. Among them, a set of training data consists of a corresponding set of defect data and traceability data. The traceability data includes raw material batch data, production equipment data, operator data, process parameter data, and production time data. Then, the control terminal generates a neural network model based on the training set. The neural network model is used to selectively output one or more of the raw material batch data, production equipment data, operator data, process parameter data, and production time data according to the input defect data. Finally, the control terminal obtains the target defect data of the product to be traced and inputs the target defect data into the trained neural network model. According to the output result of the neural network model, the production cause is determined. The textile quality traceability system proposed in this application can realize the whole-process data collection, analysis, and traceability from raw materials to finished products by constructing an intelligent quality traceability system, thereby improving the troubleshooting efficiency of quality problems, reducing production costs, and improving product quality.

[0050] Based on the same inventive concept, an embodiment of this application also proposes an electronic device, which includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the textile quality traceability method of the embodiment of this application.

[0051] In addition, to achieve the above object, an embodiment of this application also proposes a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it implements the textile quality traceability method of the embodiment of this application.

[0052] The following specifically introduces each component of the electronic device: Among them, the processor is the control center of the electronic device, which can be a single processor or a collective term for multiple processing elements. For example, the processor is one or more central processing units (CPUs), or can be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as: one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0053] Optionally, the processor can perform various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0054] The memory is used to store the software program for implementing the solution of the present invention and is controlled by the processor for execution. The specific implementation manner can refer to the above method embodiments and will not be elaborated herein.

[0055] Optionally, the memory can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory can be integrated with the processor or exist independently and be coupled to the processor through the interface circuit of the electronic device. The embodiments of the present invention do not make specific limitations in this regard.

[0056] The transceiver is used to communicate with a network device or with a terminal device.

[0057] Optionally, the transceiver can include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0058] Optionally, the transceiver can be integrated with the processor or exist independently and be coupled to the processor through the interface circuit of the router. The embodiments of the present invention do not make specific limitations in this regard.

[0059] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiments and will not be elaborated herein.

[0060] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0061] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0062] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0063] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0064] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0065] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0066] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

Claims

1. A textile quality tracing method, characterized in that: Applicable to a textile quality tracing system, the system includes a control terminal, and the method includes: The control terminal obtains a training set, the training set includes multiple groups of training data, wherein a group of the training data consists of a corresponding group of defect data and traceability data, and the traceability data includes raw material batch data, production equipment data, operator data, process parameter data and production time data; The control terminal generates a neural network model based on the training set, and the neural network model is used to selectively output one or more of the raw material batch data, the production equipment data, the operator data, the process parameter data and the production time data according to the input defect data; The control terminal obtains target defect data of the product to be traced, and inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model.

2. A textile quality tracing method according to claim 1, characterized in that: The textile quality traceability system further includes a detection terminal, which is used to detect and obtain the raw material batch data, the production equipment data, the operator data, the process parameter data and the production time data. The control terminal obtains the target defect data of the product to be traced, and inputs the target defect data into the trained neural network model. According to the output result of the neural network model, before determining the production cause, it includes: The control terminal obtains the production equipment data, the operator data, the process parameter data and the production time data corresponding to the target defect data.

3. A textile quality tracing method according to claim 2, characterized in that: The control terminal obtains target defect data of the product to be traced, and inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model, further comprising: The control terminal acquires, based on the production reason, the detection terminal corresponding to the production reason, and determines the detection terminal as a target detection terminal; The control terminal controls the target detection terminal to increase the detection frequency.

4. A textile quality tracing method according to claim 1, characterized in that: The control terminal generates a neural network model based on the training set, and the neural network model is used to selectively output one or more of the raw material batch data, the production equipment data, the operator data, the process parameter data, and the production time data according to the input defect data, including: The control terminal controls the input layer of the neural network model to receive the defect data, wherein the defect data includes characteristics such as defect type, defect location, and defect severity, wherein the number of nodes in the input layer matches the characteristic dimension of the defect data; The control terminal controls the output layer of the neural network model to generate one or more of the raw material batch data, the production equipment data, the operator data, the process parameter data and the production time data, wherein the number of nodes in the output layer matches the traceability data items that need to be output.

5. A textile quality tracing method according to claim 4, characterized in that: The control terminal controls the output layer of the neural network model to generate one or more of the raw material batch data, the production equipment data, the operator data, the process parameter data and the production time data, wherein the number of nodes in the output layer matches the traceability data items to be output, and the activation function is Softmax or a linear function.

6. A textile quality tracing method according to claim 4, characterized in that: The control terminal controls the output layer of the neural network model to generate one or more of the raw material batch data, the production equipment data, the operator data, the process parameter data and the production time data, wherein the number of nodes in the output layer matches the traceability data items to be output, and further includes: The control terminal divides the training set into a target training set and a target verification set, uses the target training set to train the neural network model, and determines a training stop condition through the target verification set.

7. A textile quality tracing method according to claim 6, characterized in that: The control terminal divides the training set into a target training set and a target verification set, and uses the target training set to train the neural network model, and determines a stop training condition through the target verification set, including: The control terminal divides the training set into the target training set and the data target verification set according to a preset ratio; The control terminal inputs the defect data in the target verification set into the neural network model and obtains an output result; The control terminal matches the output result of the neural network model with the production equipment data, the operator data, the process parameter data and the production time data in the target verification set, and determines whether to stop training based on the matching result.

8. A textile quality tracing system, the system comprising a control terminal, characterized in that: The system is configured to: The control terminal obtains a training set, the training set includes multiple groups of training data, wherein a group of the training data consists of a corresponding group of defect data and traceability data, and the traceability data includes raw material batch data, production equipment data, operator data, process parameter data and production time data; The control terminal generates a neural network model based on the training set, and the neural network model is used to selectively output one or more of the raw material batch data, the production equipment data, the operator data, the process parameter data and the production time data according to the input defect data; The control terminal obtains target defect data of the product to be traced, and inputs the target defect data into the trained neural network model, and determines the production cause according to the output result of the neural network model.

9. An electronic device, comprising: at least one processor; and, a memory communicatively coupled to at least one of the processors; The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that at least one processor can execute the method proposed in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method as claimed in any one of claims 1 to 7.

Images