A method and system for monitoring and warning the operating state of a PP yarn spinning machine

Abstract

The present application provides an operating status monitoring and early warning method and system for a PP line spinning machine, which relates to the technical field of spinning machine monitoring. The method includes: obtaining fault record data of the same family, performing classification and identification, and obtaining multiple component fault records corresponding to multiple components; performing fault sensing feature identification and obtaining a first fault sensing feature; performing real-time sensing monitoring, obtaining a first monitoring parameter set, and obtaining a first component risk index; obtaining multiple output image data sets; extracting the first output image data set of the first operating output node, performing output quality identification, and obtaining a first output quality index; and generating a first status early warning information. The present application mainly solves the problem that the monitoring means are too single and lack automation, resulting in low efficiency and inaccurate monitoring results. It is impossible to fully cover all operating states of the equipment and it is impossible to monitor the operating state of the PP line spinning machine in real time. The monitoring efficiency and accuracy are improved.

Description

Technical Field

[0001] This application relates to the technical field of spinning machine monitoring, and particularly to a method and system for monitoring and warning the operating status of a PP line spinning machine. Background Art

[0002] With the rapid development of the textile industry, as an important piece of equipment in the textile industry, the operating status of a PP line spinning machine has an important impact on production efficiency and product quality. However, traditional monitoring methods for PP line spinning machines usually rely on manual inspections and empirical judgments, which have problems such as low efficiency, low accuracy, and easy missed inspections. To solve these problems and improve monitoring efficiency and accuracy, a method for monitoring and warning the operating status of a PP line spinning machine is proposed.

[0003] However, in the process of implementing the inventive technical solutions in the embodiments of this application, it is found that the above technologies at least have the following technical problems:

[0004] The monitoring means are too single and lack automation, resulting in low efficiency and inaccurate monitoring results. It cannot comprehensively cover all operating states of the equipment and cannot monitor the operating status of the PP line spinning machine in real time. Summary of the Invention

[0005] This application mainly solves the problems that the monitoring means are too single and lack automation, resulting in low efficiency and inaccurate monitoring results. It cannot comprehensively cover all operating states of the equipment and cannot monitor the operating status of the PP line spinning machine in real time.

[0006] In view of the above problems, the present application provides an operating status monitoring and early warning method and system for a PP line spinning machine. In the first aspect, the present application provides an operating status monitoring and early warning method for a PP line spinning machine, the method comprising: obtaining the same family fault record data of a first PP line spinning machine, classifying and identifying the same family fault record data based on the faulty components, and obtaining multiple component fault records corresponding to multiple components; extracting the first component and the first component fault record based on the multiple component fault records, and identifying the fault sensing feature of the first component fault record to obtain the first fault sensing feature; performing real-time sensing monitoring on the first component based on the first fault sensing feature to obtain a first monitoring parameter set, and based on the The first monitoring parameter set is used to identify fault risks and obtain a first component risk index; multiple operation output nodes of the first PP line spinning machine are obtained, and output images are collected based on the multiple operation output nodes to obtain multiple output image data sets; based on the multiple output image data sets, a first output image data set of the first operation output node is extracted, and the output quality is identified with the first output image data set to obtain a first output quality index; if the first component risk index is greater than or equal to a predetermined fault risk and / or the first output quality index is less than or equal to a predetermined output quality index, a first status warning information is generated, and the first status warning information is a first component warning information and / or a first output node warning information.

[0007] In the second aspect, the present application provides an operating status monitoring and early warning system for a PP line spinning machine, the system comprising: a fault record acquisition module, the fault record acquisition module is used to obtain the same family fault record data of a first PP line spinning machine, classify and identify the same family fault record data based on the faulty components, and obtain multiple component fault records corresponding to multiple components; a first fault sensing feature acquisition module, the first fault sensing feature acquisition module extracts the first component and the first component fault record based on the multiple component fault records, and identifies the fault sensing feature of the first component fault record to obtain the first fault sensing feature; a first component risk index acquisition module, the first component risk index acquisition module performs real-time sensing monitoring on the first component based on the first fault sensing feature to obtain a first monitoring parameter set, and performs fault risk identification based on the first monitoring parameter set to obtain A first component risk indicator; an image data set acquisition module, the image data set acquisition module is used to acquire multiple operation output nodes of the first PP line spinning machine, collect output images based on the multiple operation output nodes, and obtain multiple output image data sets; a first output quality indicator acquisition module, the first output quality indicator acquisition module is based on the multiple output image data sets, extracts the first output image data set of the first operation output node, performs output quality identification with the first output image data set, and obtains the first output quality indicator; a first status warning information generation module, the first status warning information generation module generates a first status warning information if the first component risk indicator is greater than or equal to a predetermined fault risk and / or the first output quality indicator is less than or equal to a predetermined output quality indicator, the first status warning information being the first component warning information and / or the first output node warning information.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The present application provides an operating status monitoring and early warning method and system for a PP line spinning machine, which relates to the technical field of spinning machine monitoring. The method includes: obtaining fault record data of the same family, performing classification and identification, and obtaining multiple component fault records corresponding to multiple components; performing fault sensing feature identification and obtaining a first fault sensing feature; performing real-time sensing monitoring, obtaining a first monitoring parameter set, and obtaining a first component risk index; obtaining multiple output image data sets; extracting the first output image data set of the first operation output node, performing output quality identification, and obtaining a first output quality index; and generating first status early warning information.

[0010] This application primarily addresses the issues of overly simplistic monitoring methods and a lack of automation, which lead to low efficiency and inaccurate monitoring results. This also prevents comprehensive coverage of all equipment operating conditions and the inability to monitor the operating status of PP yarn spinning machines in real time. This improves monitoring efficiency and accuracy.

[0011] The above description is only an overview of the technical solution of the present application. In order to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically given below. Description of the Drawings

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0013] Figure 1 It is a schematic flow chart of a method for monitoring and warning the operating status of a PP yarn spinning machine provided by an embodiment of the present application;

[0014] Figure 2 It is a schematic flow chart of a method for obtaining the first fault sensing feature in a method for monitoring and warning the operating status of a PP yarn spinning machine provided by an embodiment of the present application;

[0015] Figure 3 It is a schematic flow chart of a method for optimizing control of the first component in a method for monitoring and warning the operating status of a PP yarn spinning machine provided by an embodiment of the present application;

[0016] Figure 4 It is a schematic structural diagram of a system for monitoring and warning the operating status of a PP yarn spinning machine provided by an embodiment of the present application.

[0017] Description of the reference numerals: Fault record acquisition module 10, First fault sensing feature acquisition module 20, First component risk index acquisition module 30, Image data set acquisition module 40, First output quality index acquisition module 50, First status warning information generation module 60. Detailed Embodiments

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0019] This application mainly solves the problems that the monitoring means are too single and lack automation, resulting in low efficiency and inaccurate monitoring results. It cannot comprehensively cover all operating states of the equipment and cannot monitor the operating state of the PP line spinning machine in real time. The monitoring efficiency and accuracy are improved.

[0020] To better understand the above technical solution, the above solution will be introduced in detail below in combination with the accompanying drawings of the specification and specific implementation manners.

[0021] Example 1: As Figure 1 shown, a method for monitoring and warning the operating state of a PP line spinning machine, the method includes:

[0022] Obtain the homologous fault record data of the first PP line spinning machine, classify and identify the homologous fault record data based on the faulty components, and obtain multiple component fault records corresponding to multiple components;

[0023] Specifically, first, collect the homologous fault record data of the first PP line spinning machine. It includes information such as fault time, fault location, fault type, etc. Then clean the collected data to remove duplicate, invalid or incorrect data. Classify and identify the homologous fault record data based on the faulty components. For example, the fault records can be classified according to different components (such as motors, drive systems, sensors, etc.). Extract component fault records: For each component, extract its corresponding homologous fault record data. These data will include information such as the fault time, fault type, and fault location of the component. Multiple component fault records corresponding to multiple components of the first PP line spinning machine can be obtained. It can be used for further analysis and fault prediction to help improve the reliability and production efficiency of the equipment.

[0024] Extract the first component and the first component fault record based on the multiple component fault records, and identify the fault sensing characteristics of the first component fault record to obtain the first fault sensing characteristics;

[0025] Specifically, after extracting the first component and the first component failure record based on the multiple component failure records, the failure sensing characteristics of the first component failure record can be identified to obtain the first failure sensing characteristics. The first component to be analyzed is selected from multiple components, which can be determined from historical failure records or other relevant factors. The failure records related to the first component are extracted from the multiple component failure records, including detailed information such as the time, type, and location of the failure. For the first component failure record, by identifying relevant sensor signals or data, the sensing characteristics related to the failure are extracted. These sensing characteristics can be signal amplitude, frequency, waveform, etc., or other sensor data related to the failure. From the identified failure sensing characteristics, the unique and representative first failure sensing characteristics of the first component are extracted. These characteristics can be used for subsequent failure diagnosis and warning. The first component and the first component failure record can be extracted based on the multiple component failure records, and the failure sensing characteristics of the first component failure record can be identified to obtain the first failure sensing characteristics. These characteristics can be used for further analysis and prediction to improve the reliability and production efficiency of the equipment.

[0026] Based on the first failure sensing characteristics, real-time sensing monitoring is performed on the first component to obtain a first monitoring parameter set, and based on the first monitoring parameter set, failure risk identification is performed to obtain a first component risk indicator;

[0027] Specifically, based on the first failure sensing characteristics, real-time sensing monitoring is performed on the first component, and a first monitoring parameter set can be obtained. These parameter sets reflect the operating state and health status of the first component. Next, based on the first monitoring parameter set, failure risk identification is performed to obtain a first component risk indicator. This risk indicator can be one or more and is used to evaluate the failure risk of the first component. The failure risk includes parameter abnormality, parameter stability, and historical data comparison. According to the change trend and abnormal values of the monitoring parameters, it is judged whether the first component has a failure risk. For example, if the signal amplitude of a certain sensor continuously decreases or exceeds the normal range, it may mean that the component has a failure risk. Parameter stability: Analyze the stability of the monitoring parameters. By comparing the change rate and fluctuation range of the parameters, it is judged whether the operating state of the first component is stable. If the parameters fluctuate greatly or the change rate is high, it may mean that the component has a potential failure risk. Historical data comparison: Compare the current monitoring parameters with historical data to observe whether there are abnormal changes or trends. By comparing historical data, potential failure signs or trends can be found, thereby identifying the failure risk of the component.

[0028] Obtain multiple operation output nodes of the first PP line spinning machine, and based on the multiple operation output nodes, collect output images to obtain multiple output image data sets;

[0029] Specifically, obtain multiple operation output nodes of the first PP-line spinning machine, collect output images based on the multiple operation output nodes, and obtain multiple output image datasets. First, determine the multiple operation output nodes of the first PP-line spinning machine. These nodes are different parts or components of the device, such as spinning heads, winding devices, transmission systems, etc. Install image acquisition devices, such as cameras or sensors, on each operation output node. These devices will be used to collect the output images of the node in real time. Through the image acquisition devices, collect the output images of each operation output node in real time. These images include information on various aspects such as the operating state of the device, the form of the product, and the material flow. Store the collected output image data to form an output image dataset. This dataset will contain the image data of multiple operation output nodes and be used for subsequent analysis and processing. It is possible to obtain the output image datasets of multiple operation output nodes of the first PP-line spinning machine. These datasets can be used for further analysis and diagnosis to help improve the operating efficiency of the device, product quality, and production stability.

[0030] Based on the multiple output image datasets, extract the first output image dataset of the first operation output node, and perform output quality identification on the first output image dataset to obtain the first output quality indicator;

[0031] Specifically, based on the multiple output image datasets, extract the first output image dataset of the first operation output node, and perform output quality identification on the first output image dataset to obtain the first output quality indicator. From the multiple output image datasets, extract the first output image dataset related to the first operation output node. This dataset should contain the image data of the node under normal and abnormal conditions. Perform preprocessing on the first output image dataset, such as denoising and enhancement operations, to improve the quality and recognition accuracy of the image. Extract the features related to the output quality from the preprocessed image. These features can include color, texture, shape, etc., and are used to represent the appearance and structure of the output product. Use the extracted features to train a classifier for identifying the quality of the output. The classifier can be a supervised learning model, such as a support vector machine (SVM), neural network, etc. Apply the trained classifier to the first output image dataset to perform output quality identification on each image. According to the output results of the classifier, the output quality indicators of each image can be obtained. Based on the recognition results, evaluate the first output quality indicator of the first operation output node. This indicator can be one or more and is used to represent the output quality level of the node. It is possible to extract the first output image dataset of the first operation output node based on the multiple output image datasets and perform output quality identification to obtain the first output quality indicator. These indicators can be used to guide the adjustment and optimization of the device to improve product quality and production efficiency.

[0032] If the risk index of the first component is greater than or equal to the predetermined failure risk and / or the first output quality index is less than or equal to the predetermined output quality index, a first status warning message is generated, and the first status warning message is a first component warning message and / or a first output node warning message.

[0033] Specifically, if the risk index of the first component is greater than or equal to the predetermined failure risk and / or the first output quality index is less than or equal to the predetermined output quality index, a first status warning message is generated, and the first status warning message is a first component warning message and / or a first output node warning message. When the risk index of the first component is greater than or equal to the predetermined failure risk, a first component warning message can be generated. This warning message can include information such as the type of component failure, the location of the failure, and the time of the failure, to remind the operator to take timely measures for repair and replacement. Similarly, when the quality index of the first output is less than or equal to the predetermined output quality index, a first output node warning message can be generated. This warning message can include information such as abnormal conditions of the output node and product quality problems, to remind the operator to adjust the equipment parameters or replace relevant components in a timely manner to ensure product quality and production efficiency. The first status warning message can be a first component warning message and / or a first output node warning message, and these warning messages can be used to guide the maintenance and repair work of the equipment, detect potential failures in a timely manner and take corresponding measures to ensure the normal operation of the equipment and production efficiency.

[0034] Furthermore, as Figure 2 shown, for the method of the present application, the identification of the fault sensing characteristics of the first component fault record to obtain the first fault sensing characteristic includes:

[0035] Extracting sensing data based on the first component fault record to obtain a plurality of sensing factors and a plurality of sensing parameter sets;

[0036] Performing fault correlation analysis based on the plurality of sensing parameter sets to obtain a plurality of fault correlation coefficients;

[0037] Obtaining a plurality of target sensing factors with fault correlation coefficients greater than the predetermined correlation coefficient;

[0038] Performing time series combination of the plurality of sensing parameter sets according to the plurality of target sensing factors to obtain a plurality of factor parameter combinations at multiple time nodes;

[0039] Performing commonality identification and screening of sensing factors based on the plurality of factor parameter combinations to obtain the first fault sensing characteristic.

[0040] Specifically, based on the first component failure record, the sensing data is extracted to obtain multiple sensing factors and multiple sets of sensing parameters. By analyzing the failure record of the first component, the sensing data related to the failure can be extracted. These data include multiple sensing factors and multiple sets of sensing parameters. The sensing factors can reflect the working state, performance parameters, etc. of the component, while the set of sensing parameters contains the specific values and change conditions of these factors. By performing correlation analysis on multiple sets of sensing parameters, the correlation degree between each parameter and the failure can be determined. This correlation degree can be measured by the failure correlation coefficient. The larger the correlation coefficient, the higher the correlation degree of the parameter with the failure. According to the results of the correlation analysis, select those sensing factors whose failure correlation coefficients are greater than the predetermined correlation coefficient as the target sensing factors. These target sensing factors are the factors most relevant to the failure and most capable of reflecting the failure characteristics. Combining the target sensing factors with the corresponding sets of sensing parameters in time series can obtain multiple factor-parameter combinations at multiple time nodes. These combinations reflect the state and performance changes of the component at different time points. By performing commonality identification and screening on multiple factor-parameter combinations, the first failure sensing feature most relevant to the failure and most representative can be extracted. These features can be used for subsequent failure diagnosis and warning, improving the reliability of the equipment and production efficiency. By extracting sensing data, performing correlation analysis, selecting target sensing factors, time series combination, and commonality identification and screening, etc., the first failure sensing feature of the first component can be obtained.

[0041] Furthermore, in the method of the present application, the commonality identification and screening of the sensing factors based on the multiple factor-parameter combinations to obtain the first failure sensing feature includes:

[0042] Mark abnormal factors for the multiple factor-parameter combinations to obtain multiple sets of marked factors;

[0043] Perform repeated marking combinations for multiple time nodes with the multiple sets of marked factors, and clean the repeated factors for the repeated marking combinations to obtain the first failure sensing feature.

[0044] Specifically, by marking abnormal factors through combinations of multiple factor parameters, those factors that are significantly abnormal compared to the normal state can be identified. These sets of abnormal factors constitute multiple sets of marked factors. By performing repeated marking combinations at multiple time nodes with the multiple sets of marked factors, that is, combining the multiple sets of marked factors at different time nodes, repeated marking combinations at multiple time nodes can be obtained. These combinations reflect the abnormal states and change trends of the component at different time points. By cleaning the repeated factors in the repeated marking combinations, the first fault sensing feature is obtained. By cleaning the repeated factors in the repeated marking combinations, redundant and repeated information can be removed, and a more concise and accurate first fault sensing feature can be obtained. These features reflect the main abnormal states and change trends of the component, and are of great significance for fault diagnosis and early warning.

[0045] Furthermore, in the method of the present application, for the fault risk identification based on the first monitoring parameter set to obtain the first component risk index, it includes:

[0046] Obtain the factory-calibrated sensing feature of the first component;

[0047] Collect the maintenance records and usage duration of the first component, and perform variation prediction of the sensing feature based on the maintenance records and the usage duration;

[0048] Compensate and correct the factory-calibrated sensing feature with the variation prediction result, and perform fault risk identification on the first monitoring parameter set with the corrected calibrated sensing feature to obtain the first component risk index.

[0049] Specifically, the factory-calibrated sensing feature refers to the sensing feature obtained after strict calibration and testing during the manufacturing process of the first component. These features reflect the normal performance and parameter range of the component. By collecting the maintenance records and usage duration of the first component, the usage situation and maintenance history of the component can be understood. This information can be used to analyze the variation of the sensing feature and predict its possible future change trend. According to the variation prediction result, the factory-calibrated sensing feature can be compensated and corrected. The corrected sensing feature is closer to the actual usage situation, improving the accuracy of fault diagnosis and monitoring. By comparing and analyzing the corrected calibrated sensing feature with the first monitoring parameter set, the fault risk of the component can be identified. According to the identification result, the risk index of the first component can be obtained, providing a reference basis for the maintenance and repair of the equipment. By obtaining the factory-calibrated sensing feature, collecting the maintenance records and usage duration, performing variation prediction of the sensing feature, compensating and correcting the calibrated sensing feature, and performing fault risk identification and other steps, the risk index of the first component can be obtained.

[0050] Furthermore, for the method of the present application, when output quality recognition is performed on the first output image dataset to obtain a first output quality indicator, it further includes:

[0051] Obtain the required output features of the first job output node, mine output defect features based on the required output features, and form an output defect convolution feature library;

[0052] Use the defect convolution feature library to perform a traversal comparison of the image features of the first output image dataset, and obtain the first output quality indicator based on the comparison result.

[0053] Specifically, obtain the required output features of the first job output node, mine output defect features based on the required output features, and form an output defect convolution feature library; obtain the required output features of the first job output node. These features are the expectations and requirements of users for products or services, reflecting market demand and customer needs. Then, mine output defect features based on the required output features. These defect features may include problems in aspects such as product appearance, structure, and performance, directly affecting product quality and user experience. Next, form an output defect convolution feature library. A convolutional neural network (CNN) is an image processing tool that can be used to extract features in images. By training a CNN model to enable it to identify and classify output defect features, an output defect convolution feature library can be constructed. Use the defect convolution feature library to perform a traversal comparison of the image features of the first output image dataset. For each image, input it into the CNN model, extract its features, and compare them with the features in the output defect convolution feature library. Obtain the first output quality indicator based on the comparison result. According to the comparison result, the output quality indicator of the first output image dataset can be evaluated. If the features of a certain image are highly similar to the features in the output defect convolution feature library, it can be considered that the image has defects or quality problems. By statistically analyzing these comparison results, the first output quality indicator can be obtained, which is used to evaluate product quality and production efficiency. By performing steps such as obtaining required output features, mining output defect features, forming a defect convolution feature library, performing a traversal comparison of image features, and obtaining the first output quality indicator, the evaluation and monitoring of product quality can be achieved.

[0054] Furthermore, the method of the present application further includes:

[0055] If the first status warning information includes the first component warning information, generate a first maintenance instruction to perform maintenance on the first component;

[0056] Perform state monitoring and early warning update after maintenance under a predetermined time window. If the first component update early warning information is received and the first component update early warning information is the first output node early warning information, identify the node output control components for the multiple components and the first operation output node to obtain the first control component;

[0057] Control and optimize the control parameters of the first control component based on the first output node early warning information.

[0058] Specifically, if the first status early warning information includes the first component early warning information, generate a first maintenance instruction to perform maintenance on the first component; when the first status early warning information includes the first component early warning information, it indicates that there is a fault or abnormality in the first component. At this time, a first maintenance instruction can be generated to perform maintenance on the first component. The content of the maintenance may include replacing faulty components, adjusting equipment parameters, cleaning and lubricating, etc. Perform state monitoring and early warning update after maintenance under a predetermined time window. After the maintenance is completed, it is necessary to perform state monitoring and early warning update within a predetermined time window. This can ensure that the equipment returns to the normal operating state and detect whether there are other potential faults or abnormalities. If the first component update early warning information is received and the first component update early warning information is the first output node early warning information, identify the node output control components for the multiple components and the first operation output node to obtain the first control component; If the update early warning information of the first component is received and the warning information is associated with the early warning information of the first output node, then it is necessary to identify the node output control components for the multiple components and the first operation output node. Through identification, the first control component directly related to the first operation output node can be obtained. Control and optimize the control parameters of the first control component based on the first output node early warning information. According to the early warning information of the first output node, the control parameters of the first control component can be optimized. The optimization objectives may be to improve control accuracy, reduce errors, improve production efficiency, etc. By adjusting the control parameters, the first control component can better adapt to the requirements of the operation output node and improve the overall performance and stability of the equipment. Through steps such as generating maintenance instructions, performing state monitoring and early warning update after maintenance, identifying control components, and optimizing control parameters, a comprehensive fault diagnosis and repair of the equipment can be carried out to ensure the normal operation and production efficiency of the equipment.

[0059] Furthermore, as Figure 3 shown, for the method of the present application, the control and optimization of the control parameters of the first control component based on the first output node early warning information includes:

[0060] Based on the demand output characteristics of the first job output node, retrieve multiple groups of historical control parameter records, and the multiple groups of historical control parameter records have control sensitivity identifiers;

[0061] Conduct a control sensitivity test on the first control component to obtain the first test sensitivity;

[0062] Match and screen the multiple groups of historical control parameter records with the first test sensitivity to obtain multiple groups of optimized control parameters;

[0063] Remove discrete values from the multiple groups of optimized control parameters, and obtain target control parameters to optimize the control of the first component.

[0064] Specifically, based on the demand output characteristics of the first job output node, retrieve multiple groups of historical control parameter records, and the multiple groups of historical control parameter records have control sensitivity identifiers; based on the demand output characteristics of the first job output node, multiple groups of historical control parameter records can be retrieved. These historical records contain the control parameters of the device at different times and different states, and each group of records has a control sensitivity identifier. By conducting a control sensitivity test on the first control component, the response degree and change trend of the component to different control parameters can be evaluated. This test can provide the first test sensitivity, and using the first test sensitivity, multiple groups of historical control parameter records can be matched and screened. By comparing the similarity between the control sensitivity of each historical record and the first test sensitivity, the optimized control parameters that best match the current device state and requirements can be screened out. To ensure the stability and accuracy of control, it is necessary to remove discrete values from the multiple groups of optimized control parameters screened out. By removing extreme values or parameters with large discreteness, more robust and reliable target control parameters can be obtained. Finally, based on the obtained target control parameters, the first component is optimized for control. This optimization may include adjusting control parameters, updating algorithms, or changing operation modes, etc. By optimizing control, the performance, efficiency, and stability of the device can be further improved. By retrieving historical control parameter records, conducting control sensitivity tests, matching and screening optimized control parameters, and implementing optimized control and other steps, the device can be comprehensively optimized and controlled to improve the performance and production efficiency of the device.

[0065] Embodiment 2: Based on the same inventive concept as the operation state monitoring and warning method of the PP line spinning machine in the foregoing Embodiment 1, as Figure 4 shown, the present application provides an operation state monitoring and warning system for a PP line spinning machine, and the system includes:

[0066] A fault record acquisition module 10 is configured to acquire fault record data of the same family of the first PP yarn spinning machine, classify and identify the fault record data of the same family based on the faulty components, and acquire multiple component fault records corresponding to the multiple components;

[0067] A first fault sensing feature acquisition module 20, which extracts a first component and a first component fault record based on the plurality of component fault records, and identifies a fault sensing feature of the first component fault record to acquire a first fault sensing feature;

[0068] A first component risk indicator acquisition module 30, which performs real-time sensing monitoring of the first component based on the first fault sensing feature to obtain a first monitoring parameter set, and performs fault risk identification based on the first monitoring parameter set to obtain a first component risk indicator;

[0069] An image data set acquisition module 40 is configured to acquire a plurality of operation output nodes of the first PP yarn spinning machine, and collect output images based on the plurality of operation output nodes to obtain a plurality of output image data sets;

[0070] A first output quality indicator acquisition module 50 is configured to extract a first output image dataset of a first job output node based on the multiple output image datasets, perform output quality identification using the first output image dataset, and obtain a first output quality indicator;

[0071] The first status warning information generation module 60 generates a first status warning information if the first component risk index is greater than or equal to the predetermined failure risk and / or the first output quality index is less than or equal to the predetermined output quality index. The first status warning information is the first component warning information and / or the first output node warning information.

[0072] Furthermore, the system also includes:

[0073] The multiple factor parameter combination acquisition module extracts sensor data based on the first component fault record to obtain multiple sensor factors and multiple sensor parameter sets; performs fault correlation analysis based on the multiple sensor parameter sets to obtain multiple fault correlation coefficients; obtains multiple target sensor factors whose fault correlation coefficients are greater than predetermined correlation coefficients; performs time series combination of the multiple sensor parameter sets according to the multiple target sensor factors to obtain multiple factor parameter combinations at multiple time nodes; performs common identification and screening of sensor factors based on the multiple factor parameter combinations to obtain the first fault sensing feature.

[0074] Furthermore, the system further includes:

[0075] A first fault sensing feature acquisition module, configured to perform abnormal factor marking on the multiple factor parameter combinations to obtain multiple marked factor sets; perform repeated marking combinations at multiple time nodes with the multiple marked factor sets, and clean the repeated factors in the repeated marking combinations to obtain the first fault sensing feature.

[0076] Furthermore, the system further includes:

[0077] A first component risk index acquisition module, configured to obtain the factory-calibrated sensing feature of the first component; collect the maintenance records and usage duration of the first component, perform variation prediction on the sensing feature based on the maintenance records and the usage duration; perform compensation and correction on the factory-calibrated sensing feature with the variation prediction result, and perform fault risk identification on the first monitoring parameter set with the corrected calibrated sensing feature to obtain the first component risk index.

[0078] Furthermore, the system further includes:

[0079] A first output quality index comparison module, configured to obtain the required output feature of the first operation output node, mine the output defect feature based on the required output feature, and form an output defect convolutional feature library; perform traversal comparison of the image features on the first output image dataset with the defect convolutional feature library, and obtain the first output quality index based on the comparison result.

[0080] Furthermore, the system further includes:

[0081] A control optimization module, if the first status warning information includes the first component warning information, generate a first maintenance instruction to perform maintenance on the first component; perform status monitoring warning update after maintenance within a predetermined time window, if receiving the first component update warning information and the first component update warning information is the first output node warning information, perform node output control component identification on the multiple components and the first operation output node to obtain a first control component; perform control optimization on the control parameters of the first control component based on the first output node warning information.

[0082] Furthermore, the system further includes:

[0083] The optimization control module retrieves multiple groups of historical control parameter records based on the demand output characteristics of the first job output node, and the multiple groups of historical control parameter records have control sensitivity identifiers; performs a control sensitivity test on the first control component to obtain a first test sensitivity; matches and filters the multiple groups of historical control parameter records with the first test sensitivity to obtain multiple groups of optimized control parameters; removes discrete values from the multiple groups of optimized control parameters to obtain target control parameters for optimizing the control of the first component.

[0084] Through the detailed description of the foregoing method for monitoring and warning the operating status of a PP yarn spinning machine in the specification, those skilled in the art can clearly understand the system for monitoring and warning the operating status of a PP yarn spinning machine in this embodiment. For the system disclosed in the embodiment, since it corresponds to the disclosed device in the embodiment, the description is relatively simple. For the relevant parts, reference may be made to the description in the method section.

[0085] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring and warning the operating status of a PP yarn spinning machine, characterized in that: The method comprises: Acquire same-family fault record data of the first PP yarn spinning machine, classify and identify the same-family fault record data based on faulty components, and acquire multiple component fault records corresponding to multiple components; extracting a first component and a first component fault record based on the plurality of component fault records, and identifying a fault sensing feature of the first component fault record to obtain a first fault sensing feature; Performing real-time sensing monitoring on the first component based on the first fault sensing feature to obtain a first monitoring parameter set, and performing fault risk identification based on the first monitoring parameter set to obtain a first component risk index; Acquire multiple operation output nodes of the first PP yarn spinning machine, and collect output images based on the multiple operation output nodes to obtain multiple output image data sets; extracting a first output image dataset of a first job output node based on the multiple output image datasets, performing output quality identification on the first output image dataset to obtain a first output quality indicator; If the first component risk indicator is greater than or equal to the predetermined failure risk and / or the first output quality indicator is less than or equal to the predetermined output quality indicator, first status warning information is generated, and the first status warning information is first component warning information and / or first output node warning information.

2. The method according to claim 1, wherein The identifying the fault sensing feature of the first component fault record to obtain the first fault sensing feature includes: Extracting sensor data based on the first component fault record to obtain a plurality of sensor factors and a plurality of sensor parameter sets; Performing fault correlation analysis based on the multiple sensor parameter sets to obtain multiple fault correlation coefficients; acquiring a plurality of target sensing factors having a fault correlation coefficient greater than a predetermined correlation coefficient; Performing time-series combination on the multiple sensor parameter sets according to the multiple target sensor factors to obtain multiple factor parameter combinations at multiple time nodes; Commonality identification and screening of sensing factors are performed based on the combination of the multiple factor parameters to obtain the first fault sensing feature.

3. The method according to claim 2, wherein The performing common identification and screening of sensing factors based on the combination of the multiple factor parameters to obtain the first fault sensing feature includes: Marking the multiple factor parameter combinations as abnormal factors to obtain multiple marked factor sets; Perform repeated marking combinations on multiple time nodes using the multiple marking factor sets, perform repeated factor cleaning on the repeated marking combinations, and obtain the first fault sensing feature.

4. The method according to claim 1, wherein The performing fault risk identification based on the first monitoring parameter set to obtain a first component risk index includes: obtaining a factory-calibrated sensor characteristic of the first component; collecting maintenance records and usage duration of the first component, and predicting variations in sensor characteristics based on the maintenance records and usage duration; The factory-calibrated sensor characteristics are compensated and corrected using the variation prediction result, and the fault risk of the first monitoring parameter set is identified using the corrected calibration sensor characteristics to obtain the first component risk index.

5. The method according to claim 1, wherein The performing output quality identification using the first output image data set to obtain a first output quality index further includes: Obtaining a required output feature of the first job output node, mining output defect features based on the required output feature, and establishing an output defect convolution feature library; Perform a traversal comparison of image features on the first output image dataset using a defect convolution feature library, and obtain the first output quality indicator based on the comparison result.

6. The method according to claim 1, wherein The method further comprises: If the first status warning information includes the first component warning information, generating a first maintenance instruction to perform maintenance on the first component; Performing a status monitoring warning update after maintenance within a predetermined time window, if first component update warning information is received, and the first component update warning information is the first output node warning information, performing node output control component identification on the multiple components and the first operation output node to obtain a first control component; Control parameters of the first control component are optimized based on the first output node warning information.

7. The method according to claim 6, wherein The controlling and optimizing the control parameters of the first control component based on the first output node warning information includes: Retrieving multiple sets of historical control parameter records based on the demand output characteristics of the first job output node, wherein the multiple sets of historical control parameter records have control sensitivity identifiers; performing a control sensitivity test on the first control component to obtain a first test sensitivity; Matching and screening the multiple sets of historical control parameter records using the first test sensitivity to obtain multiple sets of optimized control parameters; Discrete values are removed from the multiple groups of optimized control parameters to obtain target control parameters for optimizing control of the first component.

8. A PP yarn spinning machine operation status monitoring and early warning system, characterized in that: The system comprises: a fault record acquisition module, the fault record acquisition module being configured to acquire same-family fault record data of the first PP yarn spinning machine, classify and identify the same-family fault record data based on faulty components, and acquire multiple component fault records corresponding to multiple components; a first fault sensing feature acquisition module, wherein the first fault sensing feature acquisition module extracts a first component and a first component fault record based on the plurality of component fault records, and identifies a fault sensing feature of the first component fault record to acquire a first fault sensing feature; a first component risk indicator acquisition module, the first component risk indicator acquisition module performing real-time sensing monitoring of the first component based on the first fault sensing feature to obtain a first monitoring parameter set, and performing fault risk identification based on the first monitoring parameter set to obtain a first component risk indicator; an image data set acquisition module, the image data set acquisition module being configured to acquire a plurality of operation output nodes of the first PP yarn spinning machine, and to collect output images based on the plurality of operation output nodes to obtain a plurality of output image data sets; a first output quality indicator acquisition module, which extracts a first output image dataset of a first job output node based on the multiple output image datasets, performs output quality identification using the first output image dataset, and obtains a first output quality indicator; The first status warning information generation module generates a first status warning information if the first component risk index is greater than or equal to the predetermined failure risk and / or the first output quality index is less than or equal to the predetermined output quality index. The first status warning information is the first component warning information and / or the first output node warning information.

Images