Intelligent yarn detection system and method based on charge

By acquiring the time series of yarn charge signals and using deep learning algorithms to analyze the potential temporal correlation features of yarn motion state, the problem of high error rate in photoelectric detection systems when monitoring ultra-fine yarns is solved, and more accurate monitoring of yarn motion state is achieved.

CN118348274BActive Publication Date: 2024-11-08HANGZHOU GOLDEN TECH M&E
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410470493.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-18
Publication Date
2024-11-08
Estimated Expiration
2044-04-18

AI Technical Summary

Technical Problem

Existing photoelectric detection systems suffer from high error rates when monitoring ultra-fine yarns, especially due to insensitivity in monitoring yarn movement or false alarms.

Method used

By acquiring the time series of yarn charge signals, signal processing is performed, and deep learning algorithms are used to analyze the potential temporal correlation features of the yarn motion state. Prior information is also introduced for comprehensive characterization to estimate the yarn's motion speed.

Benefits of technology

This improved the accuracy of yarn movement monitoring, reduced the false alarm rate, and ensured the stability and consistency of the weaving process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118348274B_ABST
    Figure CN118348274B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a charge-based yarn intelligent detection system and method. The method comprises: obtaining a time series of yarn charge quantity signals; performing signal processing on the time series of the yarn charge quantity signals to obtain a time series of the processed yarn charge quantity; and determining the movement speed value of the yarn based on the time series of the processed yarn charge quantity. In this way, a deep learning algorithm is used to analyze the potential temporal correlation characteristics of the yarn movement state contained in the time series of the processed yarn charge quantity, and a priori information is introduced as a reasoning clue to comprehensively characterize the yarn movement speed, thereby estimating the yarn movement speed value by decoding regression.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of yarn intelligent detection, and in particular, to a charge-based yarn intelligent detection system and method. Background Art

[0002] As living standards improve, people's requirements for clothing fabrics are also gradually increasing. However, when extremely fine yarn fabrics are applied to fabrics, underwear machines usually need to accurately monitor the movement of the yarn during the weaving process.

[0003] According to current feedback, the error rate of photoelectric detection of ultra-fine yarns on underwear machines is relatively high, and there are problems such as insensitivity to ultra-fine yarn monitoring or false alarms. Therefore, an optimized yarn detection system and method are expected. Summary of the invention

[0004] This disclosure section is provided to introduce concepts in a brief form, which will be described in detail in the detailed description section below. This disclosure section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a charge-based intelligent yarn detection method, the method comprising:

[0006] Obtaining the time series of yarn charge signal;

[0007] Performing signal processing on the time series of the yarn charge signal to obtain a time series of the processed yarn charge; and

[0008] Based on the time series of the charge amount of the yarn after the treatment, the moving speed value of the yarn is determined.

[0009] Optionally, signal processing is performed on the time series of the yarn charge signal to obtain the time series of the processed yarn charge, including: performing first-level differential amplification processing and bandpass filtering amplification processing on each yarn charge signal in the time series of the yarn charge signal to obtain the time series of the processed yarn charge.

[0010] Optionally, based on the time series of the yarn charge after processing, the movement speed value of the yarn is determined, including: arranging the time series of the yarn charge after processing according to the time dimension to obtain a yarn charge time series input vector; performing local time series correlation analysis on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge; using an inferencer based on prior information on the sequence of local time series implicit feature vectors of the yarn charge to obtain an implicit characterization feature vector of the yarn movement speed; and determining the movement speed value of the yarn based on the implicit characterization feature vector of the yarn movement speed.

[0011] Optionally, a local time series correlation analysis is performed on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge, including: performing data regularization on the yarn charge time series input vector to obtain a sequence of local time series input vectors of the yarn charge; and passing the sequence of local time series input vectors of the yarn charge through a yarn charge time series context encoder based on a bidirectional LSTM model to obtain a sequence of local time series implicit feature vectors of the yarn charge.

[0012] Optionally, data regularization is performed on the yarn charge time series input vector to obtain a sequence of local time series input vectors of the yarn charge, including: sequence segmentation of the yarn charge time series input vector based on a predetermined time scale to obtain a sequence of local time series input vectors of the yarn charge.

[0013] Optionally, the sequence of the local temporal implicit feature vectors of the yarn charge is processed based on a priori information inference to obtain the implicit characterization feature vector of the yarn movement speed, including: processing the sequence of the local temporal implicit feature vectors of the yarn charge with the following inference formula to obtain the implicit characterization feature vector of the yarn movement speed; wherein the inference formula is: ;in, and are the first weight coefficient and the second weight coefficient respectively, and are the first random coefficient and the second random coefficient randomly sampled from the standard normal distribution, is the mean eigenvector of the sequence of the local temporal implicit eigenvectors of the yarn charge, is the number of the sequence of the local temporal implicit feature vectors of the yarn charge The local time series implicit eigenvector of the yarn charge, is the number of sequences of implicit characteristic vectors of the local time series of the yarn charge, is a local time series implicit feature vector of the yarn charge randomly selected from the sequence of the local time series implicit feature vectors of the yarn charge, is the implicit characteristic vector representing the yarn movement speed.

[0014] Optionally, determining the movement speed value of the yarn based on the implicit characterization feature vector of the yarn movement speed includes: performing characteristic distribution correction on the implicit characterization feature vector of the yarn movement speed to obtain a corrected implicit characterization feature vector of the yarn movement speed; and passing the corrected implicit characterization feature vector of the yarn movement speed through a decoder-based motion speed estimator to obtain the movement speed value of the yarn.

[0015] Optionally, the corrected implicit characterization feature vector of the yarn movement speed is passed through a decoder-based motion speed estimator to obtain the motion speed value of the yarn, which is used to: use the decoder-based motion speed estimator to decode and regress the corrected implicit characterization feature vector of the yarn movement speed using the following decoding formula to obtain the motion speed value of the yarn; wherein the decoding formula is: ;in, represents the implicit characteristic vector of the corrected yarn speed, represents the moving speed value of the yarn, represents the weight matrix, represents the bias vector, Represents matrix multiplication.

[0016] In a second aspect, the present disclosure provides a charge-based yarn intelligent detection system, the system comprising:

[0017] A yarn charge signal acquisition module is used to acquire the time series of the yarn charge signal;

[0018] A signal processing module, used for performing signal processing on the time series of the yarn charge signal to obtain a time series of the processed yarn charge; and

[0019] The yarn movement speed value determination module is used to determine the yarn movement speed value based on the time series of the yarn charge amount after the treatment.

[0020] Optionally, the signal processing module is used to: perform a first-order differential amplification process and a bandpass filter amplification process on each yarn charge signal in the time series of the yarn charge signal to obtain the processed yarn charge time series.

[0021] The above technical solution is adopted to obtain the time series of the yarn charge signal; perform signal processing on the time series of the yarn charge signal to obtain the time series of the processed yarn charge; and determine the yarn movement speed value based on the time series of the processed yarn charge. In this way, the deep learning algorithm is used to analyze the potential time series correlation characteristics of the yarn movement state contained in the time series of the processed yarn charge, and the prior information is introduced as the reasoning clue to comprehensively characterize the yarn movement speed, so as to estimate the yarn movement speed value by decoding regression.

[0022] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0024] Figure 1 The figure is a flow chart of a method for monitoring changes in yarn charge according to an exemplary embodiment.

[0025] Figure 2 The present invention is a flow chart of a charge-based intelligent yarn detection method according to an exemplary embodiment.

[0026] Figure 3 It is a block diagram of a charge-based intelligent yarn detection system according to an exemplary embodiment.

[0027] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0028] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0029] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0030] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0034] With the development of economy and the improvement of people's living standards, consumers' demand for clothing fabrics is also constantly upgrading. People pay more and more attention to the comfort, health, environmental protection and aesthetics of clothing. In this context, ultra-fine yarn fabrics have gradually become the new favorite of the market due to their softness, skin-friendliness and good breathability. In the textile industry, underwear machines are important production equipment. It is particularly important to accurately monitor the movement state of yarn during the weaving process. This is not only related to product quality and production efficiency, but also directly affects the economic benefits and market competitiveness of enterprises.

[0035] However, according to user feedback, the current photoelectric detection system has a certain error rate when monitoring ultra-fine yarns, which is mainly manifested in the problem of insensitive monitoring of the yarn's motion state or false alarms. Photoelectric detection technology usually uses light sources and photoelectric sensors to detect the motion state of the yarn. When the yarn passes through a specific area, the photoelectric sensor will detect the change in light and determine whether the yarn is broken or in other abnormal conditions. However, due to its small diameter, ultra-fine yarns may affect the detection accuracy of the photoelectric detection system.

[0036] Furthermore, if the light source intensity is insufficient or the stability is poor, the light changes produced by the very fine yarn when passing through the detection area may not be obvious, thus affecting the detection sensitivity. The sensitivity of the photoelectric sensor directly affects the detection effect. For very fine yarns, a sensor with higher sensitivity is required to capture subtle light changes. Factors such as ambient light and dust may interfere with the normal operation of the photoelectric detection system and cause false alarms. The material and surface condition of the yarn (such as oil stains, cotton shell residues, etc.) will also affect the reflection and scattering of light, thereby affecting the detection results.

[0037] In order to ensure the stability and consistency of the yarn during the weaving process, the following methods can be used for monitoring:

[0038] Sensor technology: Various sensors are used to monitor the motion state of the yarn in real time, such as yarn tension sensors, yarn break sensors, etc. The data collected by these sensors can be used to adjust the motion state of the yarn in time to ensure the smooth progress of the weaving process.

[0039] Machine vision technology: The camera installed on the machine can capture the movement of the yarn in real time and analyze it through image processing technology. This can timely detect problems such as yarn breakage and entanglement, so that corresponding measures can be taken to deal with them.

[0040] Intelligent control system: By applying advanced control algorithms to textile equipment, the yarn motion state can be automatically adjusted. For example, fuzzy control, neural network and other technologies can be used to adjust the yarn tension in real time to ensure the stability of the weaving process.

[0041] In order to solve the above problems, the present disclosure provides a charge-based yarn intelligent detection system and method, which obtains the time series of the yarn charge signal; processes the time series of the yarn charge signal to obtain the time series of the processed yarn charge; and determines the yarn movement speed value based on the time series of the processed yarn charge. In this way, a deep learning algorithm is used to analyze the potential time-series correlation characteristics of the yarn movement state contained in the time series of the processed yarn charge, and a priori information is introduced as a reasoning clue to comprehensively characterize the yarn movement speed, so as to estimate the yarn movement speed value by decoding regression.

[0042] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0043] The present invention belongs to the field of electronic technology of circular knitting machines, and relates to an innovative yarn intelligent detection system and method for monitoring the motion state of yarn, which can determine the motion state of yarn according to the change of electric charge when the yarn is moving or stationary.

[0044] As living standards improve, people's requirements for clothing fabrics are also gradually increasing. However, when ultra-fine yarn fabrics are applied to fabrics, underwear machines need to accurately monitor the movement of the yarn during the weaving process. At present, feedback shows that the error rate of photoelectric detection for ultra-fine yarns on underwear machines is relatively high, and the monitoring of ultra-fine yarns is not sensitive or there are false alarms. In this case, a device is designed to monitor the charge on the yarn, and the movement state of the yarn is obtained through monitoring and calculation based on the change of the charge. The design principle is that there is a certain amount of electrostatic charge on the yarn itself. The change law of the charge is calculated by hardware circuits and software to determine whether the yarn is stationary or moving, and the movement speed of the yarn is calculated based on the monitored charge change.

[0045] The present invention is to overcome the defects in the prior art and provide a method for monitoring the change of yarn charge. Figure 1 As shown, it includes:

[0046] 1: Detect the weak charge of the yarn and monitor the change of the charge when the yarn is moving and stationary.

[0047] 2: Hardware module: The waveform changes caused by the charge changes on the yarn are amplified through a two-stage filtering and amplifying hardware circuit, and the low-frequency 50HZ industrial interference waveform and clutter above 10kHZ are filtered at the same time.

[0048] 3: MCU software algorithm module: Analyze the stillness, movement and speed of the yarn according to the sampled waveform. Perform a low-pass digital filter on the AD sampling data, perform threshold separation on the filtered data, and then perform statistical calculations on the separated data to analyze the running status of the yarn.

[0049] 4: Communication interface: Through the CAN communication interface and related protocols, the status data can be uploaded to the host computer, and the host computer can also set various parameters.

[0050] Furthermore, considering that the yarn itself has a certain amount of electrostatic charge, when the yarn is moving, the charge will change due to contact and friction with the surrounding environment. Specifically, the charge distribution on the yarn surface will be affected by the speed of the yarn movement. When the yarn is stationary, the charge distribution on its surface is relatively stable; when the yarn moves, the charge distribution on the yarn surface will change due to factors such as the friction of the yarn. This change can be detected and converted into a change in the charge signal.

[0051] Utilizing this characteristic, the present disclosure provides a charge-based intelligent yarn detection method. Figure 2 is a flow chart of a charge-based intelligent yarn detection method according to an exemplary embodiment. Figure 2 As shown, the method includes:

[0052] Step 101, obtaining a time series of a yarn charge signal;

[0053] Step 102, performing signal processing on the time series of the yarn charge signal to obtain a processed time series of the yarn charge; and

[0054] Step 103: Determine the movement speed value of the yarn based on the time series of the charge amount of the yarn after the treatment.

[0055] In an embodiment of the present disclosure, in step 102, signal processing is performed on the time series of the yarn charge signal to obtain the time series of the processed yarn charge, including: performing a first-level differential amplification processing and a bandpass filtering amplification processing on each yarn charge signal in the time series of the yarn charge signal to obtain the time series of the processed yarn charge.

[0056] Among them, in order to intelligently realize the function of step 103 and reduce the error problem caused by manual calculation, the technical concept of the present invention is: to use a deep learning algorithm to analyze the potential time series correlation characteristics of the yarn motion state contained in the time series of the yarn charge after processing, and introduce prior information as a reasoning clue to comprehensively characterize the yarn movement speed, so as to estimate the yarn movement speed value by decoding regression.

[0057] In one embodiment of the present disclosure, based on the time series of the yarn charge after processing, the movement speed value of the yarn is determined, including: arranging the time series of the yarn charge after processing according to the time dimension to obtain the yarn charge time series input vector; performing local time series correlation analysis on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge; using an inferencer based on prior information on the sequence of local time series implicit feature vectors of the yarn charge to obtain an implicit characterization feature vector of the yarn movement speed; and determining the movement speed value of the yarn based on the implicit characterization feature vector of the yarn movement speed.

[0058] Based on this, in the technical solution of the present disclosure, the specific process of determining the movement speed value of the yarn based on the time series of the yarn charge after the treatment includes: first, arranging the time series of the yarn charge after the treatment according to the time dimension to obtain the yarn charge time series input vector. In this way, the discretely distributed yarn charge data is converted into a structured vector representation according to the time dimension, which can integrate the time information into it and facilitate the further processing and analysis of the subsequent model.

[0059] In one embodiment of the present disclosure, a local time series correlation analysis is performed on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge, including: performing data regularization on the yarn charge time series input vector to obtain a sequence of local time series input vectors of the yarn charge; and passing the sequence of local time series input vectors of the yarn charge through a yarn charge time series context encoder based on a bidirectional LSTM model to obtain a sequence of local time series implicit feature vectors of the yarn charge.

[0060] Then, the yarn charge time series input vector is segmented based on a predetermined time scale to obtain a sequence of yarn charge local time series input vectors. In this way, the longer vector data is segmented into a series of yarn charge local time series input vectors with smaller lengths by sequence segmentation, so that the subsequent model can pay more attention to the subtle changes and local time series correlation characteristics in the time series of the processed yarn charge in a finer granularity.

[0061] In one embodiment of the present disclosure, data regularization is performed on the yarn charge quantity time series input vector to obtain a sequence of local time series input vectors of the yarn charge quantity, including: sequence segmentation of the yarn charge quantity time series input vector based on a predetermined time scale to obtain a sequence of local time series input vectors of the yarn charge quantity.

[0062] Next, the sequence of the local time series input vector of the yarn charge is passed through the yarn charge time series context encoder based on the bidirectional LSTM model to obtain a sequence of the local time series implicit feature vector of the yarn charge. Among them, the bidirectional long short-term memory network (Bidirectional LSTM) is a deep learning model that combines the LSTM structure in both the forward and reverse directions, and can better capture the time series information and long-term dependencies in the sequence data. In the bidirectional LSTM, the output of each time step is jointly determined by the hidden states of the forward LSTM and the reverse LSTM, so that the past and future information can be comprehensively considered. In other words, the bidirectional LSTM can simultaneously consider the information before and after the current moment, which is conducive to capturing the context information of the current local time series input vector of the yarn charge, so that the model can more comprehensively understand the time series correlation change characteristics of the yarn charge.

[0063] Further, the sequence of the implicit characteristic vector of the local time series of the yarn charge is based on the reasoner of the prior information to obtain the implicit characteristic vector of the yarn movement speed. Here, the sequence of the implicit characteristic vector of the local time series of the yarn charge is passed through the reasoner based on the prior information to use the prior information as a guide to better predict the sequence of the implicit characteristic vector of the local time series of the yarn charge. In the embodiment of the present disclosure, the reasoner based on the prior information increases the diversity of the model search space and the possibility of jumping out of the local extreme value through the Gaussian difference mutation strategy. Different from the traditional difference mutation strategy using the uniform distribution function, since the uniform distribution function is equally likely in the interval of the same length interval, sometimes it is impossible to generate a large disturbance near the mutation data, so it may not be possible to jump out of the local extreme value. However, the peak value of the Gaussian distribution function is small at the origin, and the distribution at both ends is relatively long. That is to say, the Gaussian difference mutation strategy generates disturbances through the Gaussian distribution function, so that a larger disturbance is generated near the current data, which helps to better explore the search space and avoid falling into the local optimal solution. In this way, the prior information-based reasoner combined with the Gaussian difference mutation strategy can use the prior information to guide and comprehensively infer the temporal correlation change characteristic distribution of the historical yarn charge quantity, thereby performing a predictive characterization of the yarn movement speed based on the search space randomization enhancement.

[0064] In one embodiment of the present disclosure, the sequence of the local temporal implicit feature vectors of the yarn charge is processed based on a priori information inference to obtain the implicit characterization feature vector of the yarn movement speed, including: processing the sequence of the local temporal implicit feature vectors of the yarn charge with the following inference formula to obtain the implicit characterization feature vector of the yarn movement speed; wherein the inference formula is: ;in, and are the first weight coefficient and the second weight coefficient respectively, and are the first random coefficient and the second random coefficient randomly sampled from the standard normal distribution, is the mean eigenvector of the sequence of the local temporal implicit eigenvectors of the yarn charge, is the number of the sequence of the local temporal implicit feature vectors of the yarn charge The local time series implicit eigenvector of the yarn charge, is the number of sequences of implicit characteristic vectors of the local time series of the yarn charge, is a local time series implicit feature vector of the yarn charge randomly selected from the sequence of the local time series implicit feature vectors of the yarn charge, is the implicit characteristic vector representing the yarn movement speed.

[0065] Furthermore, in one embodiment of the present disclosure, the movement speed value of the yarn is determined based on the implicit characterization feature vector of the yarn movement speed, including: performing characteristic distribution correction on the implicit characterization feature vector of the yarn movement speed to obtain the corrected implicit characterization feature vector of the yarn movement speed; and passing the corrected implicit characterization feature vector of the yarn movement speed through a decoder-based motion speed estimator to obtain the movement speed value of the yarn.

[0066] In the above technical scheme, the sequence of local time series implicit feature vectors of the yarn charge expresses the time series distribution characteristics of the short-range and long-range bidirectional correlation between local time domains of the yarn charge in the local time domain determined by time series segmentation in the global time domain. After the sequence of local time series implicit feature vectors of the yarn charge is based on the reasoner of prior information, the implicit characterization feature vector of the yarn movement speed obtained will also deviate from the sequence of local time series implicit feature vectors of the yarn charge due to the introduction of prior information reasoning to obtain the local-global time domain multi-dimensional time series correlation feature representation. Therefore, it is expected to strengthen the implicit characterization feature vector of the yarn movement speed by fusing the implicit characterization feature vector of the yarn movement speed and the sequence of local time series implicit feature vectors of the yarn charge.

[0067] In addition, considering the difference in the distribution structure of the time-related characteristics of the implicit characterization feature vector of the yarn movement speed brought about by prior information reasoning relative to the sequence of the local time series implicit feature vector of the yarn charge, it is expected to improve the fusion effect of the sequence of the implicit characterization feature vector of the yarn movement speed and the local time series implicit feature vector of the yarn charge.

[0068] Therefore, the inventors of the present disclosure perform a fusion correction on the sequence of the implicit characteristic vector of the yarn motion speed and the implicit characteristic vector of the local time series of the yarn charge, which is expressed as: the implicit characteristic vector of the yarn motion speed and the sequence of the implicit characteristic vector of the local time series of the yarn charge are fused and corrected by the following optimization formula to obtain the corrected implicit characteristic vector of the yarn motion speed; wherein the optimization formula is: ;in, is the implicit characteristic vector representing the yarn motion speed, is the cascaded feature vector of the local temporal implicit feature vectors of the yarn charge, , Eigenvector and Have the same length , and is a scale hyperparameter, and is the distance difference hyperparameter, is the transposed vector of the cascaded feature vector of the local temporal implicit feature vector of the yarn charge, is the eigenvalue of the eigenvector implicitly representing the yarn motion speed, is the eigenvalue of the cascaded eigenvector of the local temporal implicit eigenvector of the yarn charge, is the eigenvalue of the implicit characteristic vector of the yarn motion speed after correction, Represents vector multiplication.

[0069] Here, in order to solve the problem of difficulty in reconstructing the interaction of manifold network structure caused by the manifold distribution distance between the implicit characteristic vector of yarn motion speed and the sequence of implicit characteristic vector of yarn charge in local time series in feature fusion scenario, the low-order mesoscale Hilbert space primitive structure is used to effectively approximate the network substructure in the complex manifold network structure, so as to construct the low-order mesoscale submanifold interaction behavior based on distance representation, so as to understand the abnormal submanifold interaction in the network at the network interaction level and improve the feature fusion effect of the sequence of implicit characteristic vector of yarn motion speed and the sequence of implicit characteristic vector of yarn charge in local time series. In this way, The optimized implicit characteristic vector representing the movement speed of the yarn is decoded by a decoder, so that the accuracy of the obtained movement speed value of the yarn can be improved by improving the expression effect of the implicit characteristic vector representing the movement speed of the yarn.

[0070] Then, the corrected yarn motion speed implicit characterization feature vector is passed through a decoder-based motion speed estimator to obtain the motion speed value of the yarn.

[0071] In one embodiment of the present disclosure, the corrected implicit characterization feature vector of the yarn movement speed is passed through a decoder-based motion speed estimator to obtain the motion speed value of the yarn, which is used to: use the decoder-based motion speed estimator to decode and regress the corrected implicit characterization feature vector of the yarn movement speed using the following decoding formula to obtain the motion speed value of the yarn; wherein the decoding formula is: ;in, represents the implicit characteristic vector of the corrected yarn speed, represents the moving speed value of the yarn, represents the weight matrix, represents the bias vector, Represents matrix multiplication.

[0072] In summary, the above scheme is adopted to use a deep learning algorithm to analyze the potential temporal correlation characteristics of the yarn motion state contained in the time series of the yarn charge after the treatment, and introduce prior information as a reasoning clue to comprehensively characterize the yarn movement speed, so as to estimate the yarn movement speed value by decoding regression.

[0073] Figure 3 FIG. 1 is a block diagram of a charge-based intelligent yarn detection system according to an exemplary embodiment. Figure 3 As shown, the system 200 includes:

[0074] The yarn charge signal acquisition module 201 is used to acquire the time series of the yarn charge signal;

[0075] A signal processing module 202, configured to perform signal processing on the time series of the yarn charge signal to obtain a time series of the processed yarn charge; and

[0076] The yarn movement speed value determination module 203 is used to determine the yarn movement speed value based on the time series of the yarn charge after the processing.

[0077] Reference below Figure 4 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0078] like Figure 4 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0079] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0080] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0081] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0082] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0083] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0084] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0085] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0086] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".

[0087] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0088] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0089] According to one or more embodiments of the present disclosure, Example 1 provides a charge-based yarn intelligent detection method, the method comprising:

[0090] Obtaining the time series of yarn charge signal;

[0091] Performing signal processing on the time series of the yarn charge signal to obtain a time series of the processed yarn charge; and

[0092] Based on the time series of the charge amount of the yarn after the treatment, the moving speed value of the yarn is determined.

[0093] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, performing signal processing on the time series of the yarn charge signal to obtain the time series of the processed yarn charge, including:

[0094] Each yarn charge signal in the time series of the yarn charge signal is subjected to a first-order differential amplification process and a band-pass filter amplification process to obtain the time series of the yarn charge after the process.

[0095] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 2, and determines the movement speed value of the yarn based on the time series of the charge amount of the yarn after the treatment, including:

[0096] Arranging the time series of the yarn charge after the treatment according to the time dimension to obtain a yarn charge time series input vector;

[0097] Performing local time series correlation analysis on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge;

[0098] The sequence of the local temporal implicit feature vectors of the yarn charge is based on the inference of the prior information to obtain the implicit representation feature vector of the yarn motion speed; and

[0099] The moving speed value of the yarn is determined based on the implicit characteristic vector representing the moving speed of the yarn.

[0100] According to one or more embodiments of the present disclosure, Example 4 provides the method of Example 3, performing local time series correlation analysis on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge, including:

[0101] Performing data regularization on the yarn charge time series input vector to obtain a sequence of yarn charge local time series input vectors; and

[0102] The sequence of the local time series input vectors of the yarn charge is passed through a yarn charge time series context encoder based on a bidirectional LSTM model to obtain a sequence of the local time series implicit feature vectors of the yarn charge.

[0103] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 4, performing data regularization on the yarn charge time series input vector to obtain a sequence of yarn charge local time series input vectors, including:

[0104] The yarn charge quantity time series input vector is sequentially segmented based on a predetermined time scale to obtain a sequence of the yarn charge quantity local time series input vectors.

[0105] According to one or more embodiments of the present disclosure, Example 6 provides the method of Example 5, wherein the sequence of the local temporal implicit feature vectors of the yarn charge is based on an inferencer of prior information to obtain an implicit representation feature vector of the yarn motion speed, including:

[0106] The sequence of the local temporal implicit characteristic vectors of the yarn charge is processed by the following inference formula to obtain the implicit characteristic vector representing the yarn motion speed; wherein the inference formula is: ;in, and are the first weight coefficient and the second weight coefficient respectively, and are the first random coefficient and the second random coefficient randomly sampled from the standard normal distribution, is the mean eigenvector of the sequence of the local temporal implicit eigenvectors of the yarn charge, is the number of the sequence of the local temporal implicit feature vectors of the yarn charge The local time series implicit eigenvector of the yarn charge, is the number of sequences of implicit characteristic vectors of the local time series of the yarn charge, is a local time series implicit feature vector of the yarn charge randomly selected from the sequence of the local time series implicit feature vectors of the yarn charge, is the implicit characteristic vector representing the yarn movement speed.

[0107] According to one or more embodiments of the present disclosure, Example 7 provides the method of Example 6, which determines the movement speed value of the yarn based on the implicit characterization feature vector of the yarn movement speed, including:

[0108] Performing characteristic distribution correction on the implicit characteristic vector representing the yarn movement speed to obtain a corrected implicit characteristic vector representing the yarn movement speed; and

[0109] The corrected yarn motion speed implicit characterization feature vector is passed through a motion speed estimator based on a decoder to obtain the motion speed value of the yarn.

[0110] According to one or more embodiments of the present disclosure, Example 8 provides the method of Example 7, wherein the corrected implicit characterization feature vector of the yarn motion speed is passed through a decoder-based motion speed estimator to obtain the motion speed value of the yarn, and is used to: use the decoder-based motion speed estimator to decode and regress the corrected implicit characterization feature vector of the yarn motion speed using the following decoding formula to obtain the motion speed value of the yarn;

[0111] Wherein, the decoding formula is: ;in, represents the implicit characteristic vector of the corrected yarn speed, represents the moving speed value of the yarn, represents the weight matrix, represents the bias vector, Represents matrix multiplication.

[0112] According to one or more embodiments of the present disclosure, Example 9 provides a charge-based yarn intelligent detection system, the system comprising:

[0113] A yarn charge signal acquisition module is used to acquire the time series of the yarn charge signal;

[0114] A signal processing module, used for performing signal processing on the time series of the yarn charge signal to obtain a time series of the processed yarn charge; and

[0115] The yarn movement speed value determination module is used to determine the yarn movement speed value based on the time series of the yarn charge amount after the treatment.

[0116] According to one or more embodiments of the present disclosure, Example 10 provides the system of Example 9, wherein the signal processing module is configured to:

[0117] Each yarn charge signal in the time series of the yarn charge signal is subjected to a first-order differential amplification process and a band-pass filter amplification process to obtain the time series of the yarn charge after the process.

[0118] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0119] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0120] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A charge-based intelligent yarn detection method, characterized in that: include: Obtaining the time series of yarn charge signal; Performing signal processing on the time series of the yarn charge signal to obtain a time series of the processed yarn charge; as well as Determining the movement speed value of the yarn based on the time series of the charge amount of the yarn after the treatment; Wherein, determining the movement speed value of the yarn based on the time series of the charge amount of the yarn after the treatment includes: Arranging the time series of the yarn charge after the treatment according to the time dimension to obtain a yarn charge time series input vector; Performing local time series correlation analysis on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge; The sequence of the local temporal implicit feature vectors of the yarn charge is based on the inference of the prior information to obtain the implicit representation feature vector of the yarn movement speed; and Determining the value of the yarn's moving speed based on the yarn's moving speed implicit characterization feature vector; The sequence of the local temporal implicit feature vectors of the yarn charge is based on the inference of prior information to obtain the implicit representation feature vector of the yarn movement speed, including: The sequence of the local temporal implicit characteristic vectors of the yarn charge is processed by the following inference formula to obtain the implicit characteristic vector representing the yarn motion speed; wherein the inference formula is: ;in, and are the first weight coefficient and the second weight coefficient respectively, and are the first random coefficient and the second random coefficient randomly sampled from the standard normal distribution, is the mean eigenvector of the sequence of the local temporal implicit eigenvectors of the yarn charge, is the number of the sequence of the local temporal implicit feature vectors of the yarn charge The local time series implicit eigenvector of the yarn charge, is the number of sequences of implicit characteristic vectors of the local time series of the yarn charge, is a local time series implicit feature vector of the yarn charge randomly selected from the sequence of the local time series implicit feature vectors of the yarn charge, is an implicit characteristic vector representing the yarn movement speed; Wherein, determining the movement speed value of the yarn based on the implicit characterization feature vector of the yarn movement speed includes: Performing characteristic distribution correction on the implicit characterization feature vector of the yarn movement speed to obtain a corrected implicit characterization feature vector of the yarn movement speed; and Passing the corrected implicit characteristic vector of the yarn motion speed through a decoder-based motion speed estimator to obtain a motion speed value of the yarn; The corrected implicit characterization feature vector of the yarn movement speed is passed through a decoder-based motion speed estimator to obtain the motion speed value of the yarn, which is used to: use the decoder-based motion speed estimator to decode and regress the corrected implicit characterization feature vector of the yarn movement speed using the following decoding formula to obtain the motion speed value of the yarn; ;in, represents the implicit characteristic vector of the corrected yarn speed, represents the moving speed value of the yarn, represents the weight matrix, represents the bias vector, Represents matrix multiplication.

2. The charge-based intelligent yarn detection method according to claim 1 is characterized in that: The method of performing signal processing on the time series of the yarn charge signal to obtain a time series of the processed yarn charge signal comprises: Each yarn charge signal in the time series of the yarn charge signal is subjected to a first-order differential amplification process and a band-pass filter amplification process to obtain the time series of the yarn charge after the process.

3. The charge-based intelligent yarn detection method according to claim 2 is characterized in that: Performing local time series correlation analysis on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge, including: Performing data regularization on the yarn charge time series input vector to obtain a sequence of yarn charge local time series input vectors; and The sequence of the local time series input vectors of the yarn charge is passed through a yarn charge time series context encoder based on a bidirectional LSTM model to obtain a sequence of the local time series implicit feature vectors of the yarn charge.

4. The charge-based intelligent yarn detection method according to claim 3 is characterized in that: The yarn charge time series input vector is subjected to data regularization to obtain a sequence of yarn charge local time series input vectors, including: The yarn charge quantity time series input vector is sequentially segmented based on a predetermined time scale to obtain a sequence of the yarn charge quantity local time series input vectors.

5. A charge-based yarn intelligent detection system, characterized in that: include: A yarn charge signal acquisition module is used to acquire the time series of the yarn charge signal; A signal processing module, used for performing signal processing on the time series of the yarn charge signal to obtain a time series of the processed yarn charge; as well as A yarn movement speed value determination module, used to determine the yarn movement speed value based on the time series of the yarn charge after the treatment; Wherein, determining the movement speed value of the yarn based on the time series of the charge amount of the yarn after the treatment includes: Arranging the time series of the yarn charge after the treatment according to the time dimension to obtain a yarn charge time series input vector; Performing local time series correlation analysis on the yarn charge time series input vector to obtain a sequence of local time series implicit feature vectors of the yarn charge; The sequence of the local temporal implicit feature vectors of the yarn charge is based on the inference of the prior information to obtain the implicit representation feature vector of the yarn motion speed; and Determining the value of the yarn's moving speed based on the yarn's moving speed implicit characterization feature vector; The sequence of the implicit characteristic vectors of the local time series of the yarn charge is based on the inference of the prior information to obtain the implicit characteristic vector of the yarn movement speed, including: The sequence of the local temporal implicit characteristic vectors of the yarn charge is processed by the following inference formula to obtain the implicit characteristic vector representing the yarn motion speed; wherein the inference formula is: ;in, and are the first weight coefficient and the second weight coefficient respectively, and are the first random coefficient and the second random coefficient randomly sampled from the standard normal distribution, is the mean eigenvector of the sequence of the local temporal implicit eigenvectors of the yarn charge, is the number of the sequence of the local temporal implicit feature vectors of the yarn charge The local time series implicit eigenvector of the yarn charge, is the number of sequences of implicit characteristic vectors of the local time series of the yarn charge, is a local time series implicit feature vector of the yarn charge randomly selected from the sequence of the local time series implicit feature vectors of the yarn charge, is an implicit characteristic vector representing the yarn movement speed; Wherein, determining the movement speed value of the yarn based on the implicit characterization feature vector of the yarn movement speed includes: Performing characteristic distribution correction on the implicit characteristic vector representing the yarn movement speed to obtain a corrected implicit characteristic vector representing the yarn movement speed; and Passing the corrected implicit characteristic vector of the yarn motion speed through a motion speed estimator based on a decoder to obtain a motion speed value of the yarn; The corrected implicit characteristic vector of the yarn movement speed is passed through a decoder-based motion speed estimator to obtain the motion speed value of the yarn, which is used to: use the decoder-based motion speed estimator to decode and regress the corrected implicit characteristic vector of the yarn movement speed using the following decoding formula to obtain the motion speed value of the yarn; Among them, the decoding formula is: ;in, represents the implicit characteristic vector of the corrected yarn speed, represents the moving speed value of the yarn, represents the weight matrix, represents the bias vector, Represents matrix multiplication.

6. The charge-based yarn intelligent detection system according to claim 5, characterized in that: The signal processing module is used for: Each yarn charge signal in the time series of the yarn charge signal is subjected to a first-order differential amplification process and a band-pass filter amplification process to obtain the time series of the yarn charge after the process.