CN117265720A - Intelligent control system and method for ring spinning frame - Google Patents
Intelligent control system and method for ring spinning frame Download PDFInfo
- Publication number
- CN117265720A CN117265720A CN202311558538.XA CN202311558538A CN117265720A CN 117265720 A CN117265720 A CN 117265720A CN 202311558538 A CN202311558538 A CN 202311558538A CN 117265720 A CN117265720 A CN 117265720A
- Authority
- CN
- China
- Prior art keywords
- roving
- attribute
- data
- scanning
- attribute data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000007378 ring spinning Methods 0.000 title claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 25
- 230000007246 mechanism Effects 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 28
- 230000000875 corresponding effect Effects 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 22
- 238000012544 monitoring process Methods 0.000 claims description 14
- 230000001276 controlling effect Effects 0.000 claims description 6
- 238000009966 trimming Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000009987 spinning Methods 0.000 abstract description 16
- 230000003044 adaptive effect Effects 0.000 abstract description 3
- 239000004753 textile Substances 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract 1
- 244000025254 Cannabis sativa Species 0.000 description 16
- 235000012766 Cannabis sativa ssp. sativa var. sativa Nutrition 0.000 description 16
- 235000012765 Cannabis sativa ssp. sativa var. spontanea Nutrition 0.000 description 16
- 235000009120 camo Nutrition 0.000 description 16
- 235000005607 chanvre indien Nutrition 0.000 description 16
- 239000011487 hemp Substances 0.000 description 16
- 229920000742 Cotton Polymers 0.000 description 15
- 210000002268 wool Anatomy 0.000 description 14
- 238000004519 manufacturing process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000004804 winding Methods 0.000 description 7
- 240000008564 Boehmeria nivea Species 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 241000208202 Linaceae Species 0.000 description 4
- 235000004431 Linum usitatissimum Nutrition 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012356 Product development Methods 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012795 verification 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
-
- 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)
- Spinning Or Twisting Of Yarns (AREA)
Abstract
The invention provides an intelligent control system and method for a ring spinning frame, and belongs to the technical field of intelligent control of textile equipment. Aiming at the defect that the efficiency of manually adjusting the drafting parameters of the ring spinning frame is low when the roving is switched in spinning operation, the invention designs a scheme for automatically acquiring the properties of the roving through scanning equipment so as to obtain the corresponding drafting parameters by matching calculation, and does not need to manually adjust the drafting parameters. According to the scheme, on one hand, the automatic determination of the roving draft parameters is realized, and the workload of manually adjusting the draft parameters can be effectively reduced; on the other hand, the scheme of the invention can also use the attribute model to predict the attributes of the rovings which fail to match, thereby further improving the adaptive performance of automatic determination of the draft parameters.
Description
Technical Field
The invention relates to the technical field of intelligent control of textile equipment, in particular to an intelligent control system and method of a ring spinning frame.
Background
The ring spinning frame consists of spindle, ring and steel wire ring and consists of feeding, drafting, twisting and winding mechanism. The working tasks of the ring spinning frame include: 1) Drawing: drawing and thinning the roving into strands with required fineness; 2) Twisting: twisting the strands into a spun yarn with certain twist; 3) Winding: the spun yarn is wound into a certain package for storage, transportation and further processing.
The following related patents already exist:
related patent 1 (CN 108776463 a): an intelligent fancy yarn control system comprises an upper industrial personal computer, a lower computer PLC control module, a decoder, a digital signal processing module, a display module and a motor driving module; the upper industrial personal computer is connected with a plurality of lower computer PLC control modules through serial buses; the high-speed data port of the lower computer PLC control module is connected with the digital signal processing module and is used for controlling the rotating speed of each roller motor and sending data information to the digital signal processing module; the low-speed data port of the lower computer PLC control module is connected with the input end of the decoder and is used for gating each path of data signal processing module and setting each path of control data; the output end of the decoder is connected with the digital signal processing module; the digital processing module is connected with the motor driving module, and digital pulses output by the digital processing module control the motor driving module. The invention has the following beneficial effects: 1. the intelligent fancy yarn control system is mainly used for improving the existing spinning frame to produce fancy yarns in spinning, and realizes the cooperative work of multiple servo mechanisms through the intelligent fancy yarn control system. The invention adopts the SPI port to control the signal processing module to realize the cooperative work of the mechanisms such as the middle and rear rollers, the hollow spindle and the like in the lower computer, realizes the production of fancy yarn, solves the problems of low comprehensive performance and low processing precision of the existing domestic controller production equipment, and has the characteristics of higher processing precision, simpler and easier new product development, easier realization and the like. 2. The invention controls each roller through the AD9833 with the high-speed data output digital signal gate of the PLC control module, and is driven by the independent variable-frequency asynchronous motor, the stepping motor or the servo motor to regulate the speed, so that various fancy yarns can be produced, and the production level and the production efficiency of the fancy spinning machine imported abroad are basically achieved. 3. The invention does not require one machine to control by one computer, can greatly improve the automatic production level and the production efficiency of the compound fancy yarn, and has great application significance and popularization value for the production of the fancy yarn.
Related patent 2 (CN 107614407 a): in a yarn winding system including a spinning frame forming a yarn supplying bobbin and an automatic winder winding yarn from the yarn supplying bobbin to form a package, the spinning frame includes a first control device for controlling an operation of the spinning frame, the automatic winder includes a second control device for controlling the operation of the automatic winder, and a first interface section of the first control device is capable of performing display or operation related to a function of the second device under the control of the second control device. Provided are a yarn winding system, an automatic winder, a spinning frame, and a yarn winding method, which can suppress a reduction in operating efficiency and can suppress an increase in cost.
The prior patent focuses much on the follow-up working procedures of yarn control, yarn winding and the like, but lacks optimization of the drafting working procedure. Specifically, the ring spinning frame includes cotton spinning, wool spinning, silk spinning, hemp spinning and the like, hemp spinning (ramie and flax) includes long hemp spinning and short hemp spinning, so that the class of the roving targeted by the drafting operation includes cotton yarn, wool yarn, hemp yarn and the like, and the drafting indexes of the roving in different classes have large differences, so that when the different spinning operations are switched, an operator is required to adjust the drafting parameters of the ring spinning frame, otherwise, the condition that the roving is broken by drafting easily occurs. Obviously, the efficiency of the manual switching mode is too low to meet the actual production needs.
Disclosure of Invention
The invention provides an intelligent control method, an intelligent control system, electronic equipment and a computer storage medium for a ring spinning frame, which are used for solving the technical problems.
The first aspect of the invention provides an intelligent control method of a ring spinning frame, which comprises the following method steps:
scanning the roving, and obtaining first attribute data of the roving according to the scanning data;
matching and calculating the first attribute data with a roving attribute database to obtain a first drafting parameter; the first drafting parameters are used for drafting the roving to a first fineness;
when no first attribute data is obtained according to the scanning data, extracting appearance characteristic data of the roving according to the scanning data, inputting the appearance characteristic data into an attribute prediction model, and predicting to obtain second attribute data of the roving;
matching and calculating the second attribute data with the roving attribute database to obtain a second drafting parameter; the second drafting parameter is used for drafting the roving to a second fineness;
and controlling a drawing mechanism to draw the roving to the first fineness or the second fineness according to the first drawing parameter or the second drawing parameter.
In some embodiments, scanning the roving includes:
the short-range scanning equipment performs wireless scanning on the appointed area to obtain scanning data of the roving positioned in the appointed area;
when the monitoring camera equipment detects that the roving exists in the appointed area, the image data of the appointed area are shot, the appearance characteristics of the roving are analyzed, and scanning data are obtained.
In some embodiments, prior to scanning the roving, further comprising:
the monitoring camera equipment is used for monitoring the roving in the appointed area, and if the existence of the roving is monitored and the existence duration reaches the appointed duration, a trigger signal is generated and sent to the short-range scanning equipment;
the triggering signal is used for triggering the short-range scanning equipment to wirelessly scan the designated area.
In some embodiments, matching the first attribute data with a roving attribute database to obtain a first draft parameter includes:
matching and calculating the first attribute data with each pre-stored attribute data in the roving attribute database according to attribute codes, and hitting a first target pre-stored attribute data; wherein, the attribute codes of the first target pre-stored attribute data and the first attribute data are completely the same;
and determining a first associated draft parameter according to the first target pre-stored attribute data and the corresponding associated index, and taking the first associated draft parameter as the first draft parameter.
In some embodiments, inputting the appearance feature data into an attribute prediction model, predicting second attribute data of the roving, comprising:
inputting the appearance characteristic data into an attribute prediction model, wherein the attribute prediction model outputs a plurality of predicted attribute data and corresponding confidence values;
performing pre-matching calculation on the appearance characteristic data and at least one part of attribute parameters of each pre-stored attribute data in the roving attribute database to obtain the matching hit number of the roving major class;
determining roving major categories to which each piece of predicted attribute data belongs through similarity calculation, and associating the matching hit number with the corresponding predicted attribute data;
determining a fine tuning coefficient according to the number of the matching hits, and adjusting the confidence value by using the fine tuning coefficient;
and screening each piece of predicted attribute data according to the adjusted confidence value, and taking the screened predicted attribute data as second attribute data of the roving.
In some embodiments, performing a pre-match calculation on the appearance feature data and at least a portion of attribute parameters of each pre-stored attribute data in the roving attribute database to obtain a number of match hits for a roving class, including:
the method comprises the steps of (1) carrying out random combination from one to all of each pre-stored feature of pre-stored appearance feature data of each roving subclass to obtain a pre-stored feature set;
performing matching calculation on the appearance characteristic data and each element in a pre-stored characteristic set, and determining successful matching as hit;
and counting according to hit results of the roving subclasses to obtain the matched hit number of the roving subclasses.
In some embodiments, determining the trim coefficients from the number of match hits comprises:
the trim coefficient is positively correlated with the number of match hits.
The second aspect of the invention provides an intelligent control system of a ring spinning frame, which comprises a scanning mechanism, a processing mechanism and a drafting mechanism; the processing mechanism is connected with the scanning mechanism and the drafting mechanism; wherein,
the scanning mechanism is used for scanning the roving and transmitting scanning data to the processing mechanism;
the processing mechanism is used for calling executable computer program codes to process the scanning data so as to execute any one of the methods to obtain draft parameters and transmit the draft parameters to the draft mechanism;
and the drafting mechanism is used for stretching the roving to the specified fineness according to the drafting parameters.
A third aspect of the present invention provides an electronic device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, the processor executing the computer program to implement a method as described in any one of the preceding claims.
A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, characterized in that: the computer program being executed by a processor to implement a method as described in any of the preceding.
A fifth aspect of the invention provides a computer program product which, when run on an electronic device, causes the electronic device to execute to carry out the method as claimed in any preceding claim.
The invention has the beneficial effects that:
compared with the traditional mode of manually adjusting the draft parameters, the invention can scan the roving through the scanning equipment, further can analyze and determine the first attribute data of the roving, and the association relation between various types of the roving and the corresponding draft parameters is stored in the roving attribute database, so that the first draft parameters of the current roving can be determined through matching calculation. In addition, for certain new types of rovings or rovings the attribute data of which cannot be directly and uniquely determined through scanning data, the invention further uses an attribute prediction model to carry out intelligent analysis on the appearance characteristic data, so as to predict and obtain the most probable attribute data, namely second attribute data, and then calculates a second drafting parameter associated with the second attribute data according to the matching of the second attribute data. Therefore, the scheme of the invention realizes the automatic determination of the roving draft parameters on one hand, and can effectively reduce the workload of manually adjusting the draft parameters; on the other hand, the scheme of the invention can also use the attribute model to predict the attributes of the rovings which fail to match, thereby further improving the adaptive performance of automatic determination of the draft parameters.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an intelligent control method of a ring spinning frame according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of an intelligent control system of a ring spinning frame according to an embodiment of the present invention.
Detailed Description
Other advantages and advantages of the present application will become apparent to those skilled in the art from the following description of specific embodiments, which is to be read in light of the present disclosure, wherein the present embodiments are described in some, but not all, of the several embodiments. 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.
In addition, the technical features described below in the different embodiments of the present application may be combined with each other as long as they do not collide with each other.
As shown in fig. 1, the embodiment of the invention discloses an intelligent control method of a ring spinning frame, which comprises the following steps:
scanning the roving, and obtaining first attribute data of the roving according to the scanning data;
matching and calculating the first attribute data with a roving attribute database to obtain a first drafting parameter; the first drafting parameters are used for drafting the roving to a first fineness;
when no first attribute data is obtained according to the scanning data, extracting appearance characteristic data of the roving according to the scanning data, inputting the appearance characteristic data into an attribute prediction model, and predicting to obtain second attribute data of the roving;
matching and calculating the second attribute data with the roving attribute database to obtain a second drafting parameter; the second drafting parameter is used for drafting the roving to a second fineness;
and controlling a drawing mechanism to draw the roving to the first fineness or the second fineness according to the first drawing parameter or the second drawing parameter.
Compared with the traditional mode of manually adjusting the draft parameters, the invention can scan the roving through the scanning equipment, further can analyze and determine the first attribute data of the roving, and the association relation between various types of the roving and the corresponding draft parameters is stored in the roving attribute database, so that the first draft parameters of the current roving can be determined through matching calculation. In addition, for certain new types of rovings or rovings the attribute data of which cannot be directly and uniquely determined through scanning data, the invention further uses an attribute prediction model to carry out intelligent analysis on the appearance characteristic data, so as to predict and obtain the most probable attribute data, namely second attribute data, and then calculates a second drafting parameter associated with the second attribute data according to the matching of the second attribute data. Therefore, the scheme of the invention realizes the automatic determination of the roving draft parameters on one hand, and can effectively reduce the workload of manually adjusting the draft parameters; on the other hand, the scheme of the invention can also use the attribute model to predict the attributes of the rovings which fail to match, thereby further improving the adaptive performance of automatic determination of the draft parameters.
In some embodiments, scanning the roving includes:
the short-range scanning equipment performs wireless scanning on the appointed area to obtain scanning data of the roving positioned in the appointed area;
when the monitoring camera equipment detects that the roving exists in the appointed area, the image data of the appointed area are shot, the appearance characteristics of the roving are analyzed, and scanning data are obtained.
In this embodiment, the roving can be scanned by two types of scanning devices, one is a short-range scanning device, mainly adopts short-range communication technologies such as RFID, bluetooth, zigBee, wiFi and the like, and also needs a matched identification tag, and the identification tag can be arranged on the roving or stored in a terminal device in a tag code manner, so that the short-range scanning device can acquire information stored in the short-range scanning device through scanning. The other is to directly adopt a monitoring camera device, wherein the monitoring camera device can shoot paper labels (two-dimensional codes, bar codes and the like) matched with the roving, extract the content of the paper labels through an OCR technology and further determine the attribute data of the paper labels. Of course, both modes can be implemented simultaneously to improve the adaptability of the system.
In some embodiments, prior to scanning the roving, further comprising:
the monitoring camera equipment is used for monitoring the roving in the appointed area, and if the existence of the roving is monitored and the existence duration reaches the appointed duration, a trigger signal is generated and sent to the short-range scanning equipment;
the triggering signal is used for triggering the short-range scanning equipment to wirelessly scan the designated area.
In this embodiment, the roving may be mistakenly entered into the designated area, so as to avoid scanning and subsequent identification by the short-range scanning device.
According to the scheme, the short-range scanning equipment and the monitoring camera equipment are preferentially used for acquiring more accurate attribute data of the roving through scanning matched labels, after acquisition fails (such as identification of missing or damage of the labels), the monitoring camera equipment is called to extract appearance characteristic data in an image identification mode, and attribute data belonging to the monitoring camera equipment is predicted through an attribute prediction model.
In some embodiments, matching the first attribute data with a roving attribute database to obtain a first draft parameter includes:
matching and calculating the first attribute data with each pre-stored attribute data in the roving attribute database according to attribute codes, and hitting a first target pre-stored attribute data; wherein, the attribute codes of the first target pre-stored attribute data and the first attribute data are completely the same;
and determining a first associated draft parameter according to the first target pre-stored attribute data and the corresponding associated index, and taking the first associated draft parameter as the first draft parameter.
In this embodiment, since the accurate attribute code is obtained by scanning, when matching calculation is performed with the roving attribute database, only the pre-stored attribute data that the attribute code hits completely is needed to be locked, and then the first draft parameter that is adapted to the attribute code obtained by scanning, that is, the first attribute data, can be found according to the associated index.
It should be noted that, pre-stored attribute data of various types of rovings such as cotton yarn, wool yarn, hemp yarn and the like and corresponding associated drafting parameters thereof are pre-stored in the roving attribute database, and the large types of the cotton yarn, the wool yarn, the hemp yarn and the like can be further refined, for example, the cotton yarn is divided into subclasses of different grades A1-A3, the hemp yarn is divided into grades B1-B2 (the ramie yarn, the ramie short yarn, the flax long hemp yarn and the flax short yarn can be further divided into four grades according to the ramie long hemp yarn, the ramie short yarn and the flax short yarn), the wool yarn is divided into grades C1-C3, the rovings of different grades have different tensile properties, and the corresponding associated drafting parameters are also different. It should be noted that the specific classification and the level subdivision manner may be set according to practical situations, and the present invention is not limited thereto.
In addition, the manner of obtaining the second draft parameter according to the second attribute data matching calculation is the same as that described above, and will not be described here again.
In some embodiments, inputting the appearance feature data into an attribute prediction model, predicting second attribute data of the roving, comprising:
inputting the appearance characteristic data into an attribute prediction model, wherein the attribute prediction model outputs a plurality of predicted attribute data and corresponding confidence values;
performing pre-matching calculation on the appearance characteristic data and at least one part of attribute parameters of each pre-stored attribute data in the roving attribute database to obtain the matching hit number of the roving major class;
determining roving major categories to which each piece of predicted attribute data belongs through similarity calculation, and associating the matching hit number with the corresponding predicted attribute data;
determining a fine tuning coefficient according to the number of the matching hits, and adjusting the confidence value by using the fine tuning coefficient;
and screening each piece of predicted attribute data according to the adjusted confidence value, and taking the screened predicted attribute data as second attribute data of the roving.
In this embodiment, different types of rovings have differences in indexes such as color, texture, fiber size (length, thickness), bulk, and the like, so these parameters can be extracted as appearance characteristic data of the rovings by an image recognition technique.
After the appearance characteristic data of the roving is analyzed by the attribute prediction model, a plurality of prediction attribute data and corresponding confidence values, such as cotton yarn A1, can be determined through prediction processing, and the confidence is 75%; cotton yarn A3, 60% confidence; wool yarn C2, confidence 80%, etc. If the attribute prediction model outputs only one predicted attribute data and the confidence is high enough (e.g., over 95%), it indicates that the roving has pre-stored accurate pre-stored attribute data in the roving attribute database, in other words, it is a common roving type, which can be actually confirmed directly at this time. Of course, in order to ensure accuracy, in this case or all cases, the attribute prediction result may be output to the related operator to perform verification and confirmation, and then the subsequent matching calculation and execution of the draft parameters may be performed. The attribute prediction model in the invention is preferably built by using an AI algorithm.
However, for new types of rovings or rovings with particularly high class subdivision, especially for some mixed types of rovings or rovings with high impurity content, the attribute prediction model often cannot obtain unique and accurate predicted attribute data, and a plurality of predicted attribute data with high confidence are output, but cannot be uniquely determined when the confidence is relatively close to each other. At this time, the present invention performs a pre-matching calculation on the appearance characteristic data and at least a part of attribute parameters of each pre-stored attribute data in the roving attribute database, where the pre-stored attribute data in the database not only includes an attribute code but also includes description data of the attribute, and mainly relates to each appearance characteristic data (for example, a numerical range of a bulk degree), and the number of matching hits of each roving class can be determined by performing a pre-matching calculation on the collected appearance characteristic data and at least a part of attribute parameters (also related to appearance characteristics) of each pre-stored attribute data. And then, determining the rough yarn category to which the obtained predicted attribute data belongs through similarity calculation, and associating the corresponding matching hit number with the corresponding predicted attribute data. And finally, determining a trimming coefficient of each piece of predicted attribute data according to the number of the matching hits, and correcting the corresponding confidence coefficient by using the trimming coefficient, wherein the predicted attribute data with the highest confidence coefficient can be determined as the second attribute data of the current roving.
The above-described scheme of the present invention is actually a prediction combining both aspects. Specifically, the attribute prediction model is used for black box prediction, then the white box prediction is carried out by using the explicit pre-stored appearance characteristic data in the database, and the white box prediction result is used for correcting the black box prediction result, so that the advantages and disadvantages of the two can be fully utilized, and the black box prediction result is more reliable.
In some embodiments, performing a pre-match calculation on the appearance feature data and at least a portion of attribute parameters of each pre-stored attribute data in the roving attribute database to obtain a number of match hits for a roving class, including:
the method comprises the steps of (1) carrying out random combination from one to all of each pre-stored feature of pre-stored appearance feature data of each roving subclass to obtain a pre-stored feature set;
performing matching calculation on the appearance characteristic data and each element in a pre-stored characteristic set, and determining successful matching as hit;
and counting according to hit results of the roving subclasses to obtain the matched hit number of the roving subclasses.
In this embodiment, according to the specific item related to the appearance feature, the pre-stored features corresponding to the appearance item may be pre-stored for each roving subclass (for example, the foregoing A1-A3) in the database, and then the pre-stored features may be combined arbitrarily, including 1 combination, 2 combination …, and so on, to obtain a pre-stored feature set. And then carrying out matching calculation on the appearance characteristic data and each pre-stored characteristic in the pre-stored characteristic set, if the matching is successful (for example, the color accords with the fluffiness falls into the range of the fluffiness), counting and hitting once, and determining the matching hit number of each roving class (cotton yarn, wool yarn, hemp yarn and the like) through statistical analysis.
In some embodiments, determining the trim coefficients from the number of match hits comprises:
the trim coefficient is positively correlated with the number of match hits.
In the embodiment, the more the number of matching hits, the greater the probability that the roving belongs to the roving major class is, and the confidence value of the predicted attribute data predicted by the corresponding heightening attribute prediction model is shown; otherwise, the confidence value of the predicted attribute data predicted by the attribute prediction model is lowered.
The following are illustrated:
s1, inputting the detected appearance characteristic data D into an attribute prediction model, wherein the output result of the attribute prediction model is as follows: cotton yarn A1, 75% confidence; cotton yarn A3, 60% confidence; hemp yarn B1, confidence 74%; wool yarn C2, confidence 80%.
S2, storing a plurality of pre-stored attribute data A, B, C and A, B, C in a roving attribute database, wherein the pre-stored attribute data correspond to three roving categories of cotton yarns, hemp yarns and wool yarns respectively; each roving major class can be subdivided into various roving minor classes, specifically A1-A3, B1-B2, C1-C3.
Pre-storing pre-stored characteristics corresponding to the appearance items for each roving subclass in a database, wherein the pre-stored characteristics are used for representing each appearance characteristic E of the roving of the corresponding subclass. For example, the color E1 of the roving, the texture E2 of the roving, the numerical range E3 of the bulk, etc., then:
1) Cotton yarn
The prestored feature of subclass A1 is EA1 = [ a1_e1, a1_e2, a1_e3];
the prestored feature of subclass A1 is EA2 = [ a2_e1, a2_e2, a2_e3];
the prestored feature of subclass A3 is EA3 = [ a3_e1, a3_e2, a3_e3];
2) Hemp yarn
The prestored feature of subclass B1 is eps1= [ b1_e1, b1_e2, b1_e3];
the pre-stored feature of subclass B2 is epb2= [ b2_e1, b2_e2, b2_e3];
3) Wool yarn
The pre-stored feature of subclass C1 is EC1 = [ c1_e1, c1_e2, c1_e3];
the pre-stored feature of subclass C2 is ec2= [ c2_e1, c2_e2, c2_e3];
the pre-stored characteristic of subclass C3 is ec3= [ c3_e1, c3_e2, c3_e3].
Correspondingly, the appearance characteristic data D obtained by the detection also comprises corresponding characteristics, namely [ D1, D2, D3]. Since image acquisition is affected by a number of factors, some items in D may be empty.
And (3) carrying out random combination from one to all on all pre-stored characteristics (E1-E3) of pre-stored appearance characteristic data E of each roving subclass in the database to obtain a pre-stored characteristic set { EA, EB, EC }. Wherein, EA= { [ A1_E1], [ A1_E2], [ A1_E3], [ A1_E1, A1_E2], [ A1_E2, A1_E3], [ A1_E1, A1_E2, A1_E3] }, EB, EC are similar to EA, and are the arrangement combination of each element in the pre-stored feature. And (3) carrying out matching calculation on the calculated appearance characteristic data D and each element of EA, EB and EC one by one, and counting and hitting once when the matching is successful (for example, the color accords and the fluffiness falls into the fluffiness range). Finally, the matching hit numbers of EA, EB and EC (i.e. roving class) can be counted, for example, 1, 3 and 5 respectively.
S3, the predicted attribute data output by the attribute prediction model can be expressed as an attribute matrix, the appearance characteristic data of each roving prestored in the database can be expressed as an attribute matrix, and the similarity value of each predicted attribute data and each roving class can be calculated by adopting the existing similarity calculation formulas such as European examples and the Pearson correlation coefficient method, for example, the similarity values of the predicted attribute data 1 and the roving classes A (representing cotton yarn), B (representing hemp yarn) and C (representing wool yarn) are respectively 40%, 45% and 86%, and the predicted attribute data 1 is judged to belong to the wool yarn, so that the matching hit number 5 of the wool yarn, namely EC, can be associated with the predicted attribute data 1.
S4, a functional relationship between the number of matching hits and the trimming coefficient is pre-established, for example, trimming coefficient=number of matching hits 0.1+0.3. Then, the fine adjustment coefficient of the predicted attribute data 1 (corresponding to the cotton A1, confidence 75%) is=5×0.1+0.3=0.8. According to the above method, the number of matching hits of the predicted attribute data 2 (corresponding to the cotton yarn A3 and the confidence coefficient of 60%) is 2, the number of matching hits of the predicted attribute data 3 (corresponding to the hemp yarn B1 and the confidence coefficient of 74%) is 3, the number of matching hits of the predicted attribute data 4 (corresponding to the wool yarn C2 and the confidence coefficient of 80%) is 3, and the corresponding trimming coefficients of 0.5, 0.6 and 0.6 are calculated based on the above formula respectively. Then, the new confidence coefficients of the predicted attribute data 1 to 4 are calculated to be 0.6, 0.3, 0.444, and 0.48, respectively, according to the new confidence=confidence×fine adjustment coefficient.
S5, the new confidence coefficient is 0.6 maximum, so that the predicted attribute data 1 is determined to be the true attribute of the roving to be identified at this time.
As shown in fig. 2, the embodiment of the invention also discloses an intelligent control system of the ring spinning frame, which comprises a scanning mechanism, a processing mechanism and a drafting mechanism; the processing mechanism is connected with the scanning mechanism and the drafting mechanism; wherein,
the scanning mechanism is used for scanning the roving and transmitting scanning data to the processing mechanism;
the processing mechanism is used for calling executable computer program codes to process the scanning data so as to execute any one of the methods to obtain draft parameters and transmit the draft parameters to the draft mechanism;
and the drafting mechanism is used for stretching the roving to the specified fineness according to the drafting parameters.
The embodiment of the invention also discloses an electronic device, which comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized by: the processor executes the computer program to implement the method as described in the previous embodiments.
The embodiment of the invention also discloses a computer readable storage medium, which stores a computer program and is characterized in that: the computer program is executed by a processor to implement the method as described in the previous embodiments.
The embodiment of the invention also discloses a computer program product which, when run on an electronic device, causes the electronic device to execute to implement the method as described in the previous embodiment.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention.
Claims (9)
1. An intelligent control method of a ring spinning frame is characterized in that: the method comprises the following steps:
scanning the roving, and obtaining first attribute data of the roving according to the scanning data;
matching and calculating the first attribute data with a roving attribute database to obtain a first drafting parameter; the first drafting parameters are used for drafting the roving to a first fineness;
when no first attribute data is obtained according to the scanning data, extracting appearance characteristic data of the roving according to the scanning data, inputting the appearance characteristic data into an attribute prediction model, and predicting to obtain second attribute data of the roving;
matching and calculating the second attribute data with the roving attribute database to obtain a second drafting parameter; the second drafting parameter is used for drafting the roving to a second fineness;
controlling a drawing mechanism to draw the roving to the first fineness or the second fineness according to the first drawing parameter or the second drawing parameter;
inputting the appearance characteristic data into an attribute prediction model, predicting to obtain second attribute data of the roving, wherein the method comprises the following steps:
inputting the appearance characteristic data into an attribute prediction model, wherein the attribute prediction model outputs a plurality of predicted attribute data and corresponding confidence values;
performing pre-matching calculation on the appearance characteristic data and at least one part of attribute parameters of each pre-stored attribute data in the roving attribute database to obtain the matching hit number of the roving major class;
determining roving major categories to which each piece of predicted attribute data belongs through similarity calculation, and associating the matching hit number with the corresponding predicted attribute data;
determining a fine tuning coefficient according to the number of the matching hits, and adjusting the confidence value by using the fine tuning coefficient;
and screening each piece of predicted attribute data according to the adjusted confidence value, and taking the screened predicted attribute data as second attribute data of the roving.
2. The intelligent control method of the ring spinning frame according to claim 1, wherein the intelligent control method comprises the following steps: scanning the roving, comprising:
the short-range scanning equipment performs wireless scanning on the appointed area to obtain scanning data of the roving positioned in the appointed area;
when the monitoring camera equipment detects that the roving exists in the appointed area, the image data of the appointed area are shot, the appearance characteristics of the roving are analyzed, and scanning data are obtained.
3. The intelligent control method of the ring spinning frame according to claim 2, wherein the intelligent control method comprises the following steps: before scanning the roving, further comprising:
the monitoring camera equipment is used for monitoring the roving in the appointed area, and if the existence of the roving is monitored and the existence duration reaches the appointed duration, a trigger signal is generated and sent to the short-range scanning equipment;
the triggering signal is used for triggering the short-range scanning equipment to wirelessly scan the designated area.
4. A method for intelligent control of a ring spinning frame according to claim 3, wherein: matching calculation is carried out on the first attribute data and the roving attribute database to obtain a first drafting parameter, and the method comprises the following steps:
matching and calculating the first attribute data with each pre-stored attribute data in the roving attribute database according to attribute codes, and hitting a first target pre-stored attribute data; wherein, the attribute codes of the first target pre-stored attribute data and the first attribute data are completely the same;
and determining a first associated draft parameter according to the first target pre-stored attribute data and the corresponding associated index, and taking the first associated draft parameter as the first draft parameter.
5. The intelligent control method for the ring spinning frame according to claim 4, wherein the intelligent control method comprises the following steps: performing pre-matching calculation on the appearance characteristic data and at least one part of attribute parameters of each pre-stored attribute data in the roving attribute database to obtain the matching hit number of the roving major class, wherein the method comprises the following steps:
the method comprises the steps of (1) carrying out random combination from one to all of each pre-stored feature of pre-stored appearance feature data of each roving subclass to obtain a pre-stored feature set;
performing matching calculation on the appearance characteristic data and each element in a pre-stored characteristic set, and determining successful matching as hit;
and counting according to hit results of the roving subclasses to obtain the matched hit number of the roving subclasses.
6. The intelligent control method for the ring spinning frame according to claim 5, wherein the intelligent control method comprises the following steps: determining a trimming coefficient according to the number of matching hits, including:
the trim coefficient is positively correlated with the number of match hits.
7. An intelligent control system of a ring spinning frame comprises a scanning mechanism, a processing mechanism and a drafting mechanism; the processing mechanism is connected with the scanning mechanism and the drafting mechanism; wherein,
the scanning mechanism is used for scanning the roving and transmitting scanning data to the processing mechanism;
the method is characterized in that: the processing mechanism is used for calling executable computer program codes to process the scanning data so as to execute the method as claimed in any one of claims 1-6, obtain draft parameters and transmit the draft parameters to the draft mechanism;
and the drafting mechanism is used for stretching the roving to the specified fineness according to the drafting parameters.
8. An electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized by: the processor executes the computer program to implement the method of any of claims 1-6.
9. A computer-readable storage medium storing a computer program, characterized in that: the computer program being executable by a processor to implement the method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311558538.XA CN117265720B (en) | 2023-11-22 | 2023-11-22 | Intelligent control system and method for ring spinning frame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311558538.XA CN117265720B (en) | 2023-11-22 | 2023-11-22 | Intelligent control system and method for ring spinning frame |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117265720A true CN117265720A (en) | 2023-12-22 |
| CN117265720B CN117265720B (en) | 2024-02-09 |
Family
ID=89208490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311558538.XA Active CN117265720B (en) | 2023-11-22 | 2023-11-22 | Intelligent control system and method for ring spinning frame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117265720B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101348957A (en) * | 2007-07-16 | 2009-01-21 | 里特机械公司 | Method for operating a spinning frame |
| CN105350119A (en) * | 2015-12-18 | 2016-02-24 | 哈尔滨麻袋袜业有限公司 | Synchronized linkage control system and control method for linen wet spinning frame |
| CN107974737A (en) * | 2017-12-13 | 2018-05-01 | 湖南文理学院 | A kind of ring spinning drawing-off pressurization intelligent selection system and method for optimizing |
| CN108315841A (en) * | 2018-04-04 | 2018-07-24 | 江南大学 | A kind of RING SPINNING Numerical control system and its control method |
| CN111679634A (en) * | 2020-01-20 | 2020-09-18 | 武汉裕大华纺织有限公司 | Intelligent roving management system |
| CN111691028A (en) * | 2019-03-13 | 2020-09-22 | 卡维塔·钱德兰 | Take monitored control system's fly frame |
| CN115874321A (en) * | 2023-01-29 | 2023-03-31 | 江苏卓鹏智能机电有限公司 | Self-adaptive management method and system for improving yarn quality |
| CN116051607A (en) * | 2023-03-17 | 2023-05-02 | 浙江中烟工业有限责任公司 | Personnel track tracking method for tobacco shred overhead warehouse |
-
2023
- 2023-11-22 CN CN202311558538.XA patent/CN117265720B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101348957A (en) * | 2007-07-16 | 2009-01-21 | 里特机械公司 | Method for operating a spinning frame |
| CN105350119A (en) * | 2015-12-18 | 2016-02-24 | 哈尔滨麻袋袜业有限公司 | Synchronized linkage control system and control method for linen wet spinning frame |
| CN107974737A (en) * | 2017-12-13 | 2018-05-01 | 湖南文理学院 | A kind of ring spinning drawing-off pressurization intelligent selection system and method for optimizing |
| CN108315841A (en) * | 2018-04-04 | 2018-07-24 | 江南大学 | A kind of RING SPINNING Numerical control system and its control method |
| CN111691028A (en) * | 2019-03-13 | 2020-09-22 | 卡维塔·钱德兰 | Take monitored control system's fly frame |
| CN111679634A (en) * | 2020-01-20 | 2020-09-18 | 武汉裕大华纺织有限公司 | Intelligent roving management system |
| CN115874321A (en) * | 2023-01-29 | 2023-03-31 | 江苏卓鹏智能机电有限公司 | Self-adaptive management method and system for improving yarn quality |
| CN116051607A (en) * | 2023-03-17 | 2023-05-02 | 浙江中烟工业有限责任公司 | Personnel track tracking method for tobacco shred overhead warehouse |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117265720B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110427004B (en) | Intelligent management system for intelligent spinning workshop | |
| Hossen et al. | An application of Pareto analysis and cause-and-effect diagram (CED) to examine stoppage losses: a textile case from Bangladesh | |
| EP3654114A1 (en) | Parameter manager, central device and method of adapting operational parameters in a textile machine | |
| CN105678558A (en) | Tracing system and tracing method for quality of spun yarns | |
| US11643757B2 (en) | Optimization of the operation of a spinning machine | |
| CN107656508B (en) | Sewing machine station information acquisition and transmission system | |
| CN110997537B (en) | Method and device for texturing synthetic threads | |
| CN112114566A (en) | Method for optimizing and adjusting operating parameters of an industrial machine and related system | |
| CN117265720B (en) | Intelligent control system and method for ring spinning frame | |
| CN115328062B (en) | Intelligent control system for spunlace production line | |
| Alam et al. | Assessing the impact of speed change on energy consumption and productivity: Investigating ring frame process parameters | |
| CN111679634A (en) | Intelligent roving management system | |
| EP4170076A1 (en) | An electronic device for adjusting operational parameters of a winding machine of a spinning mill and a method for adjusting the same | |
| WO2023165979A1 (en) | Method and data-based assistance system for an optimal adjustment of a textile machine | |
| CN211199551U (en) | Two-for-one twister control system suitable for core-spun yarn production | |
| CN112926938A (en) | Dual spinning process recommendation system based on case reasoning | |
| CN109146877A (en) | A kind of intelligent classification winder method and its realization device based on coil grade | |
| CN102575388B (en) | Method for optimizing a textile production process | |
| CN108977951B (en) | Automatic design method of process suitable for various spinning equipment and any processing flow | |
| EP4163242A1 (en) | An electronic device for locating a functional disorder at a spinning and winding section of a spinning mill and a method for locating the same | |
| CN205617133U (en) | Prediction unit is rateed to yarn unevenness | |
| CN205501515U (en) | S+Z false twister | |
| CN115787213B (en) | Intelligent repairing method and system for broken thread of empty needle of sewing machine | |
| CN110308896B (en) | Development method for dynamic arrangement of shipment process in self-service vending machine | |
| CN117055508A (en) | Intelligent control system and method for twisting production |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |