CN117512835A - Method and system for monitoring and early warning of operation state of PP (Polypropylene) yarn spinning machine - Google Patents
Method and system for monitoring and early warning of operation state of PP (Polypropylene) yarn spinning machine Download PDFInfo
- Publication number
- CN117512835A CN117512835A CN202311797999.2A CN202311797999A CN117512835A CN 117512835 A CN117512835 A CN 117512835A CN 202311797999 A CN202311797999 A CN 202311797999A CN 117512835 A CN117512835 A CN 117512835A
- Authority
- CN
- China
- Prior art keywords
- fault
- component
- output
- sensing
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 76
- 238000009987 spinning Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000004743 Polypropylene Substances 0.000 title abstract description 43
- -1 Polypropylene Polymers 0.000 title abstract description 5
- 229920001155 polypropylene Polymers 0.000 title abstract description 5
- 230000007547 defect Effects 0.000 claims description 22
- 238000012423 maintenance Methods 0.000 claims description 20
- 230000035945 sensitivity Effects 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 238000012098 association analyses Methods 0.000 claims description 3
- 238000005406 washing Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 description 13
- 238000003745 diagnosis Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 239000004753 textile Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- D—TEXTILES; PAPER
- D01—NATURAL OR MAN-MADE THREADS OR FIBRES; SPINNING
- D01H—SPINNING OR TWISTING
- D01H13/00—Other common constructional features, details or accessories
- D01H13/32—Counting, measuring, recording or registering devices
-
- D—TEXTILES; PAPER
- D01—NATURAL OR MAN-MADE THREADS OR FIBRES; SPINNING
- D01H—SPINNING OR TWISTING
- D01H13/00—Other common constructional features, details or accessories
- D01H13/14—Warning or safety devices, e.g. automatic fault detectors, stop motions ; Monitoring the entanglement of slivers in drafting arrangements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Textile Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application provides a method and a system for monitoring and early warning of an operation state of a PP (Polypropylene) yarn spinning machine, and relates to the technical field of spinning machine monitoring, wherein the method comprises the following steps: acquiring the data of the same family fault records, classifying and identifying the data, and acquiring a plurality of component fault records corresponding to a plurality of components; identifying fault sensing characteristics and acquiring first fault sensing characteristics; performing real-time sensing monitoring to obtain a first monitoring parameter set and a first component risk index; obtaining a plurality of output image datasets; extracting a first output image data set of a first operation output node, and carrying out output quality identification to obtain a first output quality index; and generating first state early warning information. The method mainly solves the problems that the monitoring means is too single, automation is lacked, the efficiency is low, and the monitoring result is inaccurate. All the running states of the equipment cannot be covered comprehensively, and the operation state of the PP line spinning machine cannot be monitored in real time. The monitoring efficiency and the accuracy are improved.
Description
Technical Field
The application relates to the technical field of spinning machine monitoring, in particular to a method and a system for monitoring and early warning of an operation state of a PP (Polypropylene) yarn spinning machine.
Background
With the rapid development of the textile industry, PP yarn spinning machines are one of important devices in the textile industry, and the running state thereof has an important influence on the production efficiency and the product quality. However, the conventional monitoring method of the PP line spinning machine generally depends on manual inspection and experience judgment, and has the problems of low efficiency, low precision, easy omission and the like. In order to solve the problems and improve the monitoring efficiency and the accuracy, a method for monitoring and early warning the operation state of the PP line spinning machine is provided.
However, in the process of implementing the technical scheme of the invention in the embodiment of the application, the above technology is found to have at least the following technical problems:
the monitoring means is too single, lack of automation, and results in low efficiency and inaccurate monitoring results. All the running states of the equipment cannot be covered comprehensively, and the operation state of the PP line spinning machine cannot be monitored in real time.
Disclosure of Invention
The method mainly solves the problems that the monitoring means is too single, automation is lacked, the efficiency is low, and the monitoring result is inaccurate. All the running states of the equipment cannot be covered comprehensively, and the operation state of the PP line spinning machine cannot be monitored in real time.
In view of the foregoing, the present application provides a method and a system for monitoring and early warning of an operation state of a PP line spinning machine, and in a first aspect, the present application provides a method for monitoring and early warning of an operation state of a PP line spinning machine, where the method includes: the method comprises the steps of 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 fault components, and obtaining a plurality of component fault records corresponding to a plurality of components; extracting a first component and a first component fault record based on the plurality of component fault records, and identifying fault sensing characteristics of the first component fault record to obtain first fault sensing characteristics; performing real-time sensing monitoring on the first component based on the first fault sensing characteristic 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; acquiring a plurality of operation output nodes of the first PP linear spinning machine, and acquiring output images based on the plurality of operation output nodes to acquire a plurality of output image data sets; extracting a first output image data set of a first operation output node based on the plurality of output image data sets, and carrying out output quality identification by using the first output image data set to obtain a first output quality index; and if the first component risk index is greater than or equal to a preset fault risk and/or the first output quality index is less than or equal to a preset output quality index, generating first state early warning information, wherein the first state early warning information is first component early warning information and/or first output node early warning information.
In a second aspect, the present application provides a system for monitoring and early warning of an operation state of a PP line spinning machine, the system comprising: the fault record acquisition module is used for acquiring the same family fault record data of the first PP line spinning machine, classifying and identifying the same family fault record data based on the fault components, and acquiring a plurality of component fault records corresponding to the components; the first fault sensing characteristic acquisition module is used for extracting a first component and a first component fault record based on the plurality of component fault records, identifying fault sensing characteristics of the first component fault record and acquiring first fault sensing characteristics; the first component risk index acquisition module is used for carrying out real-time sensing monitoring on the first component based on the first fault sensing characteristics to obtain a first monitoring parameter set, and carrying out fault risk identification based on the first monitoring parameter set to obtain a first component risk index; the image data set acquisition module is used for acquiring a plurality of operation output nodes of the first PP line spinning machine, acquiring output images based on the plurality of operation output nodes and acquiring a plurality of output image data sets; the first output quality index acquisition module is used for extracting a first output image data set of a first operation output node based on the plurality of output image data sets, and carrying out output quality identification by using the first output image data set to obtain a first output quality index; the first state early warning information generation module generates first state early warning information if the first component risk index is greater than or equal to a preset fault risk and/or the first output quality index is less than or equal to a preset output quality index, wherein the first state early warning information is first component early warning information and/or first output node early warning information.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the application provides a method and a system for monitoring and early warning of an operation state of a PP (Polypropylene) yarn spinning machine, and relates to the technical field of spinning machine monitoring, wherein the method comprises the following steps: acquiring the data of the same family fault records, classifying and identifying the data, and acquiring a plurality of component fault records corresponding to a plurality of components; identifying fault sensing characteristics and acquiring first fault sensing characteristics; performing real-time sensing monitoring to obtain a first monitoring parameter set and a first component risk index; obtaining a plurality of output image datasets; extracting a first output image data set of a first operation output node, and carrying out output quality identification to obtain a first output quality index; and generating first state early warning information.
The method mainly solves the problems that the monitoring means is too single, automation is lacked, the efficiency is low, and the monitoring result is inaccurate. All the running states of the equipment cannot be covered comprehensively, and the operation state of the PP line spinning machine cannot be monitored in real time. The monitoring efficiency and the accuracy are improved.
The foregoing description is merely an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
For a clearer description of the technical solutions of the present application or of the prior art, the drawings used in the description of the embodiments or of the prior art will be briefly described below, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained, without inventive effort, by a person skilled in the art from the drawings provided.
Fig. 1 is a schematic flow chart of a method for monitoring and early warning of an operation state of a PP line spinning machine according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for obtaining a first fault sensing feature in a method for monitoring and early warning an operation state of a PP line spinning machine according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a method for performing optimization control on a first component in a method for monitoring and early warning an operation state of a PP line spinning machine according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an operation state monitoring and early warning system of a PP line spinning machine according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a fault record acquisition module 10, a first fault sensing characteristic acquisition module 20, a first component risk index acquisition module 30, an image dataset acquisition module 40, a first output quality index acquisition module 50 and a first state early warning information generation module 60.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The method mainly solves the problems that the monitoring means is too single, automation is lacked, the efficiency is low, and the monitoring result is inaccurate. All the running states of the equipment cannot be covered comprehensively, and the operation state of the PP line spinning machine cannot be monitored in real time. The monitoring efficiency and the accuracy are improved.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
Embodiment one: as shown in FIG. 1, the method for monitoring and early warning the operation state of the PP line spinning machine comprises the following steps:
the method comprises the steps of 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 fault components, and obtaining a plurality of component fault records corresponding to a plurality of components;
Specifically, first, the family fault record data of the first PP line spinning machine is collected. Including information on time of failure, location of failure, type of failure, etc. The collected data is then purged to remove duplicate, invalid or erroneous data. And classifying and identifying the same family fault record data according to the fault components. For example, fault records may be categorized by different components (e.g., motor, drive train, sensor, etc.). Extracting part fault records: for each component, its corresponding peer fault record data is extracted. Such data will include information about the time of failure, type of failure, location of failure, etc. of the component. A plurality of component fault records corresponding to the plurality of components of the first PP line spinning machine may be obtained. Can be used for further analysis and fault prediction to help improve the reliability and production efficiency of the apparatus.
Extracting a first component and a first component fault record based on the plurality of component fault records, and identifying fault sensing characteristics of the first component fault record to obtain first fault sensing characteristics;
specifically, based on the plurality of component fault records, after the first component and the first component fault record are extracted, the fault sensing feature of the first component fault record may be identified to obtain a first fault sensing feature. The first component to be analyzed is selected from the plurality of components, which may be determined from a historical fault record or other relevant factors. A fault record associated with the first component is extracted from the plurality of component fault records. Including details of the time, type, location, etc. of the failure. For a first component fault record, a fault-related sensing feature is extracted by identifying the associated sensor signal or data. These sensing characteristics may be signal amplitude, frequency, waveform, etc., as well as other fault-related sensor data. From the identified fault-sensing characteristics, a first fault-sensing characteristic specific to the first component is extracted. These features can be used for subsequent fault diagnosis and early warning. The first component and the first component fault record may be extracted based on the plurality of component fault records, and the first component fault record may be identified for fault sensing characteristics to obtain first fault sensing characteristics. These features can be used for further analysis and prediction to improve the reliability and production efficiency of the device.
Performing real-time sensing monitoring on the first component based on the first fault sensing characteristic 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;
specifically, the first component is subjected to real-time sensing monitoring based on the first fault sensing characteristic, so that a first monitoring parameter set can be obtained. These parameter sets reflect the operational status and health of the first component. Next, fault risk identification is performed based on the first set of monitored parameters, and a first component risk indicator may be obtained. This risk indicator may be one or more for assessing the risk of failure of the first component. The fault risk comprises parameter abnormality, parameter stability and historical data comparison, and whether the first component has the fault risk is judged according to the variation trend and abnormal value of the monitored parameter. For example, if the signal amplitude of a certain sensor continues to drop or go beyond normal range, it may mean that the component is at risk of failure. Parameter stability: and analyzing the stability of the monitoring parameters, and judging whether the operation state of the first component is stable or not by comparing the change rate and the fluctuation range of the parameters. If the parameter fluctuates more or the rate of change is higher, it may mean that there is a potential risk of failure of the component. Comparison of historical data: and comparing the current monitoring parameters with the historical data, and observing whether abnormal changes or trends exist. By comparing the historical data, potential fault signs or trends can be found, thereby identifying the risk of failure of the component.
Acquiring a plurality of operation output nodes of the first PP linear spinning machine, and acquiring output images based on the plurality of operation output nodes to acquire a plurality of output image data sets;
specifically, a plurality of operation output nodes of the first PP line spinning machine are acquired, output images are acquired based on the plurality of operation output nodes, a plurality of output image data sets are obtained, and first, the plurality of operation output nodes of the first PP line spinning machine are determined. These nodes are the different parts or components of the apparatus, such as the yarn ends, winding devices, drive trains, etc. An image acquisition device, such as a camera or sensor, is mounted on each job output node. These devices will be used to acquire the output image of the node in real time. And acquiring the output image of each job output node in real time through an image acquisition device. These images include information on the operational status of the device, product morphology, material flow, etc. The acquired output image data is stored to form an output image dataset. This dataset will contain image data for a plurality of job output nodes for subsequent analysis and processing. An output image dataset of a plurality of job output nodes of the first PP line spinner may be acquired. These data sets can be used for further analysis and diagnosis to help improve the operating efficiency, product quality and production stability of the plant.
Extracting a first output image data set of a first operation output node based on the plurality of output image data sets, and carrying out output quality identification by using the first output image data set to obtain a first output quality index;
specifically, a first output image dataset of a first job output node is extracted based on the plurality of output image datasets, output quality identification is performed with the first output image dataset, a first output quality index is obtained, and a first output image dataset related to the first job output node is extracted from the plurality of output image datasets. This dataset should contain the image data of the node in both normal and abnormal situations. The first output image dataset is pre-processed, such as denoising, enhancement, etc., to improve image quality and recognition accuracy. Features related to output quality are extracted from the preprocessed image. These features may include color, texture, shape, etc. to represent the appearance and structure of the output product. A classifier is trained using the extracted features to identify the quality of the output. The classifier may be a supervised learning model, such as a Support Vector Machine (SVM), neural network, or the like. And applying the trained classifier to the first output image data set, and carrying out output quality identification on each image. According to the output result of the classifier, the output quality index of each image can be obtained. And evaluating a first output quality index of the first job output node according to the identification result. This index may be one or more to indicate the output quality level of the node. The first output image dataset of the first job output node may be extracted based on the plurality of output image datasets and output quality identification may be performed to obtain a first output quality indicator. These indices can be used to guide the adjustment and optimization of the equipment, improving the quality and production efficiency of the product.
And if the first component risk index is greater than or equal to a preset fault risk and/or the first output quality index is less than or equal to a preset output quality index, generating first state early warning information, wherein the first state early warning information is first component early warning information and/or first output node early warning information.
Specifically, 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, first state early warning information is generated, wherein the first state early warning information is first component early warning information and/or first output node early warning information. When the risk index of the first component is greater than or equal to the predetermined fault risk, first component early warning information can be generated. The early warning information can comprise information such as fault type, fault position, fault time and the like of the component so as to remind an operator of taking measures in time for maintenance and replacement. Likewise, when the quality index of the first output is equal to or less than the predetermined output quality index, first output node warning information may be generated. The early warning information can comprise information such as abnormal conditions of the output node, product quality problems and the like so as to remind operators of timely adjusting equipment parameters or replacing related parts, so that the quality and the production efficiency of products are ensured. The first state early warning information can be first component early warning information and/or first output node early warning information, and the early warning information can be used for guiding maintenance and repair work of equipment, timely finding potential faults and taking corresponding measures to ensure normal operation and production efficiency of the equipment.
Further, as shown in fig. 2, in the method of the present application, the identifying the fault sensing feature of the first component fault record, and obtaining the first fault sensing feature includes:
extracting sensing data based on the first component fault record to obtain a plurality of sensing factors and a plurality of sensing parameter sets;
performing fault association analysis based on the plurality of sensing parameter sets to obtain a plurality of fault association coefficients;
acquiring a plurality of target sensing factors with fault association coefficients larger than a preset association coefficient;
performing time sequence combination on the sensing parameter sets according to the target sensing factors to obtain factor parameter combinations under the time nodes;
and carrying out commonality identification screening on the sensing factors based on the plurality of factor parameter combinations to obtain the first fault sensing characteristics.
Specifically, extracting sensing data based on the first component fault record to obtain a plurality of sensing factors and a plurality of sensing parameter sets; by analyzing the fault record of the first component, sensor data related to the fault can be extracted. The data includes a plurality of sensing factors and a plurality of sets of sensing parameters. The sensing factors can reflect the working state, performance parameters and the like of the component, and the sensing parameter set comprises specific values and changing conditions of the factors. By performing correlation analysis on a plurality of sensing parameter sets, the degree of correlation between each parameter and the fault can be determined. The degree of this association can be measured by a fault association coefficient, the greater the association coefficient, the higher the degree of association of the parameter with the fault. And selecting the sensing factors with the fault correlation coefficients larger than the preset correlation coefficient as target sensing factors according to the result of the correlation analysis. These target sensing factors are the factors most relevant to the fault and most reflective of the fault characteristics. And performing time sequence combination on the target sensing factors and the corresponding sensing parameter sets to obtain a plurality of factor parameter combinations under a plurality of time nodes. These combinations reflect the state and performance changes of the component at different points in time. By commonality identifying and screening the plurality of factor parameter combinations, the most relevant and representative first fault-sensing feature of the fault can be extracted. These features can be used for subsequent fault diagnosis and early warning, improving the reliability and production efficiency of the equipment. The first fault-sensing feature of the first component may be obtained by extracting the sensing data, performing a correlation analysis, selecting a target sensing factor, timing combination, commonality identification screening, and the like.
Further, in the method of the present application, the performing a commonality identifying and screening of sensing factors based on the plurality of factor parameter combinations, to obtain the first fault sensing feature includes:
carrying out abnormal factor marking on the multiple factor parameter combinations to obtain multiple marking factor sets;
and carrying out repeated mark combination of a plurality of time nodes by using the plurality of mark factor sets, and washing the repeated mark combination by using the repeated factors to obtain the first fault sensing characteristic.
Specifically, by labeling a plurality of factor parameter combinations for abnormal factors, those factors having significant abnormalities compared to normal conditions can be identified. These sets of anomaly factors constitute a plurality of sets of marker factors. And carrying out repeated marking combination of a plurality of time nodes by using the plurality of marking factor sets, and combining the plurality of marking factor sets on different time nodes to obtain the repeated marking combination of the plurality of time nodes. These combinations reflect abnormal states and trends of the components at different points in time. And cleaning the repeated mark combination by a repeated factor to obtain the first fault sensing characteristic, and removing redundant and repeated information by cleaning the repeated factor in the repeated mark combination to obtain the more concise and accurate first fault sensing characteristic. These features reflect the main abnormal state and the change trend of the component, and have important significance for fault diagnosis and early warning.
Further, in the method of the present application, the performing fault risk identification based on the first monitoring parameter set, to obtain a first component risk indicator, includes:
acquiring factory calibration sensing characteristics of the first component;
acquiring maintenance records and service time lengths of the first component, and predicting variation of sensing characteristics according to the maintenance records and the service time lengths;
and compensating and correcting the factory calibration sensing characteristic according to the variation prediction result, and carrying out fault risk identification on the first monitoring parameter set according to the corrected calibration sensing characteristic to obtain the first component risk index.
Specifically, the factory calibration sensing characteristic refers to a sensing characteristic obtained after the first component is subjected to strict calibration and testing in the manufacturing process. These features reflect the normal performance and parameter ranges of the component, and by collecting the service record and the service time of the first component, the service condition and service history of the component can be known. The information can be used for analyzing the variation condition of the sensing characteristics and predicting the possible future variation trend of the sensing characteristics. And compensating and correcting the factory calibration sensing characteristics according to the variation prediction result. The corrected sensing characteristics are closer to the actual use condition, and the accuracy of fault diagnosis and monitoring is improved. And comparing and analyzing the corrected calibration sensing characteristics with the first monitoring parameter set, so that the fault risk of the component can be identified. According to the identification result, the risk index of the first component can be obtained, and a reference basis is provided for maintenance and repair of equipment. The risk index of the first component can be obtained by the steps of obtaining factory calibration sensing characteristics, collecting maintenance records and using time, carrying out variation prediction of the sensing characteristics, compensating and correcting the calibration sensing characteristics, identifying fault risks and the like.
Further, in the method of the present application, the performing output quality recognition with the first output image dataset to obtain a first output quality index further includes:
acquiring a demand output characteristic of the first operation output node, excavating an output defect characteristic based on the demand output characteristic, and constructing an output defect convolution characteristic library;
and performing traversal comparison of image features on the first output image data set by using a defect convolution feature library, and acquiring the first output quality index based on a comparison result.
Specifically, acquiring a demand output characteristic of the first operation output node, excavating an output defect characteristic based on the demand output characteristic, and constructing an output defect convolution characteristic library; the demand output characteristics of the first job output node are obtained. These features are user expectations and demands for products or services reflecting market demands and customer demands. Then, the output defect feature is mined based on the demand output feature. These defective features may include problems with product appearance, structure, performance, etc., directly affecting product quality and user experience. Next, an output defect convolution feature library is constructed. Convolutional Neural Networks (CNNs) are an image processing tool that can be used to extract features from images. By training a CNN model, the CNN model can identify and classify the output defect characteristics, so that a defect convolution characteristic library is constructed. And performing traversal comparison of image features on the first output image data set by using the defect convolution feature library, and performing traversal comparison on the first output image data set by using the defect convolution feature library. For each image, it is input into the CNN model, its features are extracted and compared with features in the defect convolution feature library. And acquiring the first output quality index based on the comparison result, and evaluating the output quality index of the first output image data set according to the comparison result. If the feature of an image has high similarity with the features in the defect convolution feature library, the image can be considered to have defects or quality problems. Through statistics and analysis of the comparison results, a first output quality index can be obtained and used for evaluating the quality and production efficiency of the product. The evaluation and monitoring of the product quality can be realized by the steps of obtaining the required output characteristics, excavating the output defect characteristics, constructing a defect convolution characteristic library, performing traversal comparison of the image characteristics, obtaining the first output quality index and the like.
Further, the method of the present application further comprises:
if the first state early warning information comprises the first component early warning information, generating a first overhaul instruction, and carrying out overhaul maintenance on the first component;
performing state monitoring and early warning updating after maintenance under a preset time window, if first component updating early warning information is received and is the first output node early warning information, performing node output control component identification on the components and the first operation output node to obtain a first control component;
and performing control optimization on the control parameters of the first control component based on the first output node early warning information.
Specifically, if the first state early warning information comprises the first component early warning information, a first overhaul instruction is generated, and overhaul and maintenance are carried out on the first component; when the first state early warning information contains the first component early warning information, the first component is indicated to have a fault or abnormal condition. At this time, a first inspection instruction may be generated to inspect and maintain the first component. The content of the service may include replacement of faulty components, adjustment of equipment parameters, cleaning and lubrication, etc. And after the maintenance is completed, the state monitoring and early warning updating is required to be performed within the preset time window. This ensures that the device resumes normal operation and detects if there are other potential faults or anomalies. If first component updating early warning information is received and is the first output node early warning information, node output control component identification is carried out on the plurality of components and the first operation output node, and a first control component is obtained; if updated warning information for the first component is received and the warning information is associated with warning information for the first output node, then node output control component identification needs to be performed for the plurality of components and the first job output node. By identification, a first control component directly associated with the first job output node may be obtained. The control parameters of the first control component are controlled and optimized based on the early warning information of the first output node, and the control parameters of the first control component can be optimized according to the early warning information of the first output node. The objectives of the optimization 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 the overall performance and stability of the equipment are improved. The equipment can be subjected to comprehensive fault diagnosis and maintenance by generating an overhaul instruction, carrying out the steps of state monitoring, early warning and updating after maintenance, identifying a control part, optimizing control parameters and the like, and the normal operation and the production efficiency of the equipment are ensured.
Further, as shown in fig. 3, in the method of the present application, the optimizing control parameters of the first control unit based on the first output node early warning information includes:
based on the demand output characteristics of the first operation output node, a plurality of groups of history control parameter records are called, and the plurality of groups of history control parameter records are provided with control sensitivity marks;
performing control sensitivity test on the first control component to obtain a first test sensitivity;
matching and screening the plurality of groups of historical control parameter records by using the first test sensitivity to obtain a plurality of groups of optimized control parameters;
and performing discrete value removal on the plurality of groups of optimized control parameters, and obtaining target control parameters to perform optimized control on the first component.
Specifically, based on the demand output characteristics of the first job output node, a plurality of groups of history control parameter records are called, wherein the plurality of groups of history control parameter records are provided with control sensitivity marks; based on the demand output characteristics of the first job output node, multiple sets of history control parameter records may be retrieved. These histories contain control parameters of the device at different times and under different conditions, and each set of records has a control sensitivity identification. By performing a control sensitivity test on the first control component, the degree of response and the trend of the component to different control parameters can be evaluated. Such a test may provide a first test sensitivity with which multiple sets of historical control parameter records may be matched screened. By comparing the similarity of the control sensitivity of each set of history records to the first test sensitivity, the optimal control parameters that best match the current equipment status and requirements can be screened out. In order to ensure the stability and accuracy of control, discrete value removal is required for the screened multiple groups of optimized control parameters. By removing extreme values or discrete larger parameters, more robust and reliable target control parameters may be obtained. And finally, optimally controlling the first component according to the acquired target control parameters. Such optimization may include adjusting control parameters, updating algorithms, or changing modes of operation, etc. By optimizing the control, the performance, efficiency and stability of the device can be further improved. The method can comprehensively optimize and control the equipment and improve the performance and production efficiency of the equipment by the steps of calling the history control parameter record, performing control sensitivity test, matching, screening and optimizing the control parameter, implementing optimizing control and the like.
Embodiment two: based on the same inventive concept as the operation state monitoring and early warning method of the PP line spinning machine in the foregoing embodiment, as shown in fig. 4, the present application provides an operation state monitoring and early warning system of the PP line spinning machine, where the system includes:
the fault record acquisition module 10 is used for acquiring the same family fault record data of the first PP line spinning machine, classifying and identifying the same family fault record data based on the fault components, and acquiring a plurality of component fault records corresponding to the components;
the first fault sensing feature acquisition module 20 extracts a first component and a first component fault record based on the component fault records, and identifies fault sensing features of the first component fault record to acquire first fault sensing features;
the first component risk index obtaining module 30, wherein the first component risk index obtaining module 30 is configured to perform real-time sensing and monitoring on the first component based on the first fault sensing feature to obtain a first monitoring parameter set, and perform fault risk identification based on the first monitoring parameter set to obtain a first component risk index;
An image data set obtaining module 40, where the image data set obtaining module 40 is configured to obtain a plurality of operation output nodes of the first PP linear spinning machine, collect output images based on the plurality of operation output nodes, and obtain a plurality of output image data sets;
the first output quality index obtaining module 50, wherein the first output quality index obtaining module 50 extracts a first output image data set of a first job output node based on the plurality of output image data sets, and performs output quality identification with the first output image data set to obtain a first output quality index;
the first state early warning information generating module 60 generates first state early 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, where the first state early warning information is first component early warning information and/or first output node early warning information.
Further, the system further comprises:
the multiple factor parameter combination acquisition module is used for extracting sensing data based on the first component fault record to acquire multiple sensing factors and multiple sensing parameter sets; performing fault association analysis based on the plurality of sensing parameter sets to obtain a plurality of fault association coefficients; acquiring a plurality of target sensing factors with fault association coefficients larger than a preset association coefficient; performing time sequence combination on the sensing parameter sets according to the target sensing factors to obtain factor parameter combinations under the time nodes; and carrying out commonality identification screening on the sensing factors based on the plurality of factor parameter combinations to obtain the first fault sensing characteristics.
Further, the system further comprises:
the first fault sensing characteristic acquisition module is used for marking the abnormal factors of the multiple factor parameter combinations to obtain multiple marking factor sets; and carrying out repeated mark combination of a plurality of time nodes by using the plurality of mark factor sets, and washing the repeated mark combination by using the repeated factors to obtain the first fault sensing characteristic.
Further, the system further comprises:
the first component risk index acquisition module is used for acquiring factory calibration sensing characteristics of the first component; acquiring maintenance records and service time lengths of the first component, and predicting variation of sensing characteristics according to the maintenance records and the service time lengths; and compensating and correcting the factory calibration sensing characteristic according to the variation prediction result, and carrying out fault risk identification on the first monitoring parameter set according to the corrected calibration sensing characteristic to obtain the first component risk index.
Further, the system further comprises:
the first output quality index comparison module is used for acquiring the demand output characteristics of the first operation output node, excavating output defect characteristics based on the demand output characteristics and constructing an output defect convolution characteristic library; and performing traversal comparison of image features on the first output image data set by using a defect convolution feature library, and acquiring the first output quality index based on a comparison result.
Further, the system further comprises:
the control optimization module is used for generating a first overhaul instruction and carrying out overhaul maintenance on the first component if the first state early warning information comprises the first component early warning information; performing state monitoring and early warning updating after maintenance under a preset time window, if first component updating early warning information is received and is the first output node early warning information, performing node output control component identification on the components and the first operation output node to obtain a first control component; and performing control optimization on the control parameters of the first control component based on the first output node early warning information.
Further, the system further comprises:
the optimization control module is used for calling a plurality of groups of history control parameter records based on the demand output characteristics of the first operation output node, wherein the plurality of groups of history control parameter records are provided with control sensitivity marks; performing control sensitivity test on the first control component to obtain a first test sensitivity; matching and screening the plurality of groups of historical control parameter records by using the first test sensitivity to obtain a plurality of groups of optimized control parameters; and performing discrete value removal on the plurality of groups of optimized control parameters, and obtaining target control parameters to perform optimized control on the first component.
Through the foregoing detailed description of the operation state monitoring and early warning method of the PP line spinning machine, those skilled in the art can clearly understand that the operation state monitoring and early warning system of the PP line spinning machine in this embodiment, for the system disclosed in the embodiment, the description is relatively simple because it corresponds to the device disclosed in the embodiment, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The operation state monitoring and early warning method for the PP line spinning machine is characterized by comprising the following steps of:
the method comprises the steps of 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 fault components, and obtaining a plurality of component fault records corresponding to a plurality of components;
Extracting a first component and a first component fault record based on the plurality of component fault records, and identifying fault sensing characteristics of the first component fault record to obtain first fault sensing characteristics;
performing real-time sensing monitoring on the first component based on the first fault sensing characteristic 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;
acquiring a plurality of operation output nodes of the first PP linear spinning machine, and acquiring output images based on the plurality of operation output nodes to acquire a plurality of output image data sets;
extracting a first output image data set of a first operation output node based on the plurality of output image data sets, and carrying out output quality identification by using the first output image data set to obtain a first output quality index;
and if the first component risk index is greater than or equal to a preset fault risk and/or the first output quality index is less than or equal to a preset output quality index, generating first state early warning information, wherein the first state early warning information is first component early warning information and/or first output node early warning information.
2. The method of claim 1, wherein the identifying the fault-sensing feature of the first component fault record, obtaining the first fault-sensing feature, comprises:
extracting sensing data based on the first component fault record to obtain a plurality of sensing factors and a plurality of sensing parameter sets;
performing fault association analysis based on the plurality of sensing parameter sets to obtain a plurality of fault association coefficients;
acquiring a plurality of target sensing factors with fault association coefficients larger than a preset association coefficient;
performing time sequence combination on the sensing parameter sets according to the target sensing factors to obtain factor parameter combinations under the time nodes;
and carrying out commonality identification screening on the sensing factors based on the plurality of factor parameter combinations to obtain the first fault sensing characteristics.
3. The method of claim 2, wherein the performing a commonality identification screening of sensing factors based on the plurality of factor parameter combinations to obtain the first fault-sensing characteristic comprises:
carrying out abnormal factor marking on the multiple factor parameter combinations to obtain multiple marking factor sets;
and carrying out repeated mark combination of a plurality of time nodes by using the plurality of mark factor sets, and washing the repeated mark combination by using the repeated factors to obtain the first fault sensing characteristic.
4. The method of claim 1, wherein the performing fault risk identification based on the first set of monitored parameters to obtain a first component risk indicator comprises:
acquiring factory calibration sensing characteristics of the first component;
acquiring maintenance records and service time lengths of the first component, and predicting variation of sensing characteristics according to the maintenance records and the service time lengths;
and compensating and correcting the factory calibration sensing characteristic according to the variation prediction result, and carrying out fault risk identification on the first monitoring parameter set according to the corrected calibration sensing characteristic to obtain the first component risk index.
5. The method of claim 1, wherein said performing output quality identification with said first output image dataset to obtain a first output quality indicator, further comprises:
acquiring a demand output characteristic of the first operation output node, excavating an output defect characteristic based on the demand output characteristic, and constructing an output defect convolution characteristic library;
and performing traversal comparison of image features on the first output image data set by using a defect convolution feature library, and acquiring the first output quality index based on a comparison result.
6. The method of claim 1, wherein the method further comprises:
if the first state early warning information comprises the first component early warning information, generating a first overhaul instruction, and carrying out overhaul maintenance on the first component;
performing state monitoring and early warning updating after maintenance under a preset time window, if first component updating early warning information is received and is the first output node early warning information, performing node output control component identification on the components and the first operation output node to obtain a first control component;
and performing control optimization on the control parameters of the first control component based on the first output node early warning information.
7. The method of claim 6, wherein the controlling optimization of the control parameter of the first control component based on the first output node pre-warning information comprises:
based on the demand output characteristics of the first operation output node, a plurality of groups of history control parameter records are called, and the plurality of groups of history control parameter records are provided with control sensitivity marks;
performing control sensitivity test on the first control component to obtain a first test sensitivity;
Matching and screening the plurality of groups of historical control parameter records by using the first test sensitivity to obtain a plurality of groups of optimized control parameters;
and performing discrete value removal on the plurality of groups of optimized control parameters, and obtaining target control parameters to perform optimized control on the first component.
8. A system for monitoring and pre-warning the operation state of a PP line spinning machine, comprising:
the fault record acquisition module is used for acquiring the same family fault record data of the first PP line spinning machine, classifying and identifying the same family fault record data based on the fault components, and acquiring a plurality of component fault records corresponding to the components;
the first fault sensing characteristic acquisition module is used for extracting a first component and a first component fault record based on the plurality of component fault records, identifying fault sensing characteristics of the first component fault record and acquiring first fault sensing characteristics;
the first component risk index acquisition module is used for carrying out real-time sensing monitoring on the first component based on the first fault sensing characteristics to obtain a first monitoring parameter set, and carrying out fault risk identification based on the first monitoring parameter set to obtain a first component risk index;
The image data set acquisition module is used for acquiring a plurality of operation output nodes of the first PP line spinning machine, acquiring output images based on the plurality of operation output nodes and acquiring a plurality of output image data sets;
the first output quality index acquisition module is used for extracting a first output image data set of a first operation output node based on the plurality of output image data sets, and carrying out output quality identification by using the first output image data set to obtain a first output quality index;
the first state early warning information generation module generates first state early warning information if the first component risk index is greater than or equal to a preset fault risk and/or the first output quality index is less than or equal to a preset output quality index, wherein the first state early warning information is first component early warning information and/or first output node early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311797999.2A CN117512835A (en) | 2023-12-26 | 2023-12-26 | Method and system for monitoring and early warning of operation state of PP (Polypropylene) yarn spinning machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311797999.2A CN117512835A (en) | 2023-12-26 | 2023-12-26 | Method and system for monitoring and early warning of operation state of PP (Polypropylene) yarn spinning machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117512835A true CN117512835A (en) | 2024-02-06 |
Family
ID=89759059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311797999.2A Pending CN117512835A (en) | 2023-12-26 | 2023-12-26 | Method and system for monitoring and early warning of operation state of PP (Polypropylene) yarn spinning machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117512835A (en) |
-
2023
- 2023-12-26 CN CN202311797999.2A patent/CN117512835A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023071217A1 (en) | Multi-working-condition process industrial fault detection and diagnosis method based on deep transfer learning | |
| CN111222290B (en) | Multi-parameter feature fusion-based method for predicting residual service life of large-scale equipment | |
| KR102141391B1 (en) | Failure data management method based on cluster estimation | |
| US20070192063A1 (en) | Method of condition monitoring | |
| CN110515781B (en) | Complex system state monitoring and fault diagnosis method | |
| CN111665066B (en) | Equipment fault self-adaptive upper and lower early warning boundary generation method based on convolutional neural network | |
| CN116629627A (en) | Intelligent detection system of power transmission on-line monitoring device | |
| US12007745B2 (en) | Apparatus for predicting equipment damage | |
| CN109141625B (en) | Online state monitoring method for ball screw pair | |
| JP2021177380A (en) | Device and method for detecting defect in spinning mills and estimating one or more causes of defect | |
| CN117115169A (en) | Intelligent recognition method for abnormal deformation of surface of die-casting die of automobile part | |
| WO2020166236A1 (en) | Work efficiency evaluating method, work efficiency evaluating device, and program | |
| Becherer et al. | Intelligent choice of machine learning methods for predictive maintenance of intelligent machines | |
| CN117786373A (en) | Equipment operation diagnosis system based on big data corrugated paper processing | |
| CN117512835A (en) | Method and system for monitoring and early warning of operation state of PP (Polypropylene) yarn spinning machine | |
| CN117435908A (en) | Multi-fault feature extraction method for rotary machine | |
| CN117609716A (en) | Power equipment residual life remote prediction method and system based on state health information | |
| CN117382129A (en) | Injection molding machine data analysis system and electronic equipment | |
| CN112884212A (en) | Cigarette single gram weight deviation analysis and prediction method | |
| CN116755411A (en) | Industrial equipment data acquisition method and device | |
| CN116263734A (en) | Industrial robot state monitoring method, system and prompt terminal | |
| KR20220096794A (en) | Method and system for diagnosing defects in rotating machinery | |
| KR20220096793A (en) | Method and system for comprehensive diagnosis defects in rotating machinery | |
| KR102667861B1 (en) | heavy electrical equipment treatment apparatus using deep learning-based prediction model and method therefor | |
| US20220414555A1 (en) | Prediction system, information processing apparatus, and information processing program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |