Automatic can change control system and method based on artificial intelligence

Abstract

The invention discloses an automatic can change control system and method based on artificial intelligence, belonging to the field of artificial intelligence technology, and comprises the following steps: collecting and storing operation records of production equipment; obtaining a first record set and a second record set; calculating the average time interval of can change at different production speeds, and the target tension in the can change process; establishing and training a neural network model, calculating the can change timing value, and starting to change cans; obtaining the real-time yarn tension and the real-time turning speed in the can change process, calculating the tension error value in the can change process, and adjusting the real-time turning speed in the can change process; the invention not only effectively avoids the problems of yarn breakage, looseness and equipment jamming caused by excessive or insufficient tension, thereby improving production efficiency and product quality, but also ensures the stability and safety of the can change process, and further improves the continuous operation capability of the production line and the service life of the equipment.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and specifically relates to an automatic barrel changing control system and method based on artificial intelligence. Background Art

[0002] With the development of mechatronics technology, the automation level of textile industry production has also been improved. Modern warping machines process more warps and produce faster, making yarn cones more frequent. Shortening the downtime for cone change is of great significance to improving production efficiency.

[0003] Although the existing automatic can change control system can switch the can change process from manual to automatic, reduce the labor intensity and shorten the can change time, it lacks the control of the turning speed during the can change process. When the turning device controls the can turning during the can change process, the turning speed is too fast, which will lead to excessive tension, or the turning speed is too slow, which will lead to too little tension, thus causing problems such as yarn breakage, yarn loosening, and equipment jamming. This not only affects the quality of the product, but also causes the production line to stop, reduces production efficiency, and shortens the service life of the equipment.

[0004] Therefore, people are in urgent need of an automatic barrel changing control system based on artificial intelligence to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide an automatic can change control system based on artificial intelligence to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] An automatic drum changing control method based on artificial intelligence, the method comprising the following steps:

[0008] S1. Set up a sensor device to collect and store the operation records of the production equipment; filter the operation records to obtain a first record set and a second record set;

[0009] S2. Calculate the average time interval for changing the drum at different production speeds through the first record set; calculate the target tension during the drum changing process through the second record set;

[0010] S3, establish a neural network model, combine the average time interval of drum changing at different production speeds, train the neural network model, calculate the drum changing preparation time; extract the operation records after the drum changing preparation time, calculate the drum changing timing value, and start the drum changing;

[0011] S4. Acquire the real-time yarn tension and the real-time turning speed during the bobbin changing process, calculate the tension error value during the bobbin changing process in combination with the target tension during the bobbin changing process, and adjust the real-time turning speed during the bobbin changing process.

[0012] According to the above technical solution, step S1 includes the following:

[0013] S1-1. A sensor device is installed on the production equipment. Each time the sensor device collects data, an operation record of the production equipment is generated and stored in a database. The operation record includes yarn tension, production speed, bobbin changing time and turning speed;

[0014] The tension of the yarn is measured in real time by a tension sensor installed in the yarn channel. The tension sensor is usually based on strain gauges, optical fiber sensing technology or electromagnetic force principles, etc. The production speed refers to the speed of the reel in the warping machine. The warping machine evenly winds the yarn onto the reel, and the reel speed is usually related to the production speed (the length of winding per minute); the barrel changing time refers to the opening time of the corresponding flipping device during the barrel changing process; the flipping speed refers to the speed of the flipping device when performing the flipping operation during the barrel changing process; if the operation record is in the barrel changing process, the barrel changing time corresponding to the operation record is the latest opening time of the flipping device, and the flipping speed corresponding to the operation record is the real-time flipping speed; if the operation record is not in the barrel changing process, the barrel changing time corresponding to the operation record is the opening time of the flipping device most recently to the current time, and the flipping speed corresponding to the operation record is the flipping speed at the most recent opening time of the flipping device;

[0015] S1-2. According to the production speed, all operation records with the same production speed are extracted, and the extracted operation records with the same production speed are marked, each operation record is associated with the corresponding production speed, and all marked operation records are counted to form a first record set;

[0016] S1-3. According to the size of the yarn tension, calculate the average value of the yarn tension corresponding to all the operation records, which is recorded as A; if the yarn tension corresponding to a certain operation record is less than or equal to (1+α)×A and the yarn tension corresponding to the operation record is greater than or equal to (1-α)×A, then filter out the operation record as an operation record in the second record set, wherein α represents the tension screening parameter; filter all the operation records to form the second record set.

[0017] According to the above technical solution, step S2 includes the following:

[0018] S2-1, filter out the operation records with the same production speed in the first record set to form a filtered record set; sort the operation records in the filtered record set from front to back according to the drum changing time, calculate the time intervals between the drum changing times corresponding to adjacent operation records after sorting, and calculate the average value and standard deviation of all time intervals;

[0019] The time interval between the drum changing moments corresponding to a group of adjacent operation records is recorded as B1; the average value of all time intervals is recorded as B2; the standard deviation of all time intervals is recorded as B3; if B1 satisfies B2-β×B3≤B1≤B2-β×B3, the time interval between the drum changing moments corresponding to the group of adjacent operation records is retained; if B1 does not satisfy B2-β×B3≤B1≤B2-β×B3, the time interval between the drum changing moments corresponding to the group of adjacent operation records is removed; wherein β represents a time screening parameter;

[0020] It is used to remove abnormal time intervals to improve accuracy, such as the time interval between the drum changing moments corresponding to adjacent operation records is zero, or there is a shutdown behavior between the drum changing moments corresponding to adjacent operation records, which makes the time interval between the drum changing moments corresponding to adjacent operation records very large, etc.

[0021] Calculate the average of the time intervals retained in the filtered record set as the average time interval for changing the drum at the corresponding production speed;

[0022] S2-2. Calculate the average value of the yarn tension corresponding to each running record in the second record set as the target tension in the bobbin changing process.

[0023] According to the above technical solution, step S3 includes the following:

[0024] S3-1, establish a neural network model, take different production speeds as input, take the average time interval of drum replacement at different production speeds as output, and train the neural network model;

[0025] The operation records are screened at the current moment to select the real-time operation records; the production speed corresponding to the real-time operation records are input into the trained neural network model; the average time interval of can change corresponding to the production speed output by the trained neural network model is added to the can change time corresponding to the real-time operation record, and the time obtained is used as the can change preparation time corresponding to the current moment;

[0026] S3-2, extract the operation record after the bobbin change preparation moment, and use the formula: C = γ1 × C1 + γ2 × C2 to calculate the bobbin change timing value corresponding to a certain operation record after the bobbin change preparation moment, wherein C represents the bobbin change timing value corresponding to a certain operation record after the bobbin change preparation moment, C1 represents the yarn tension corresponding to a certain operation record after the bobbin change preparation moment, C2 represents the production speed corresponding to a certain operation record after the bobbin change preparation moment, γ1 represents the weight parameter of the yarn tension, and γ2 represents the weight parameter of the production speed;

[0027] When the drum changing opportunity value corresponding to a certain operation record after the drum changing preparation time is greater than or equal to the first threshold, the drum changing is started and the drum changing time is recorded;

[0028] Starting to change the drum means that the corresponding turning device starts to turn over when the drum is changed.

[0029] According to the above technical solution, step S4 includes the following:

[0030] S4-1. Use the sensing device to obtain the real-time yarn tension and real-time turning speed during the bobbin changing process; the real-time yarn tension during the bobbin changing process is recorded as D; the target tension during the bobbin changing process is recorded as D target ;Use the formula; ΔD=DD target , calculate the tension error value during the can change process, where ΔD represents the tension error value during the can change process;

[0031] S4-1, the absolute value of the tension error during the barrel changing process is recorded as |ΔD|;

[0032] When |ΔD| is less than or equal to the second threshold, the real-time flipping speed during the drum changing process is maintained;

[0033] When |ΔD| is greater than the second threshold, the real-time flipping speed during the drum changing process is adjusted. The specific process of the adjustment is as follows:

[0034] Adjust the real-time flip speed during the drum change process to E after =E before ×(1-δ×ΔD), where E after Indicates the adjusted real-time flip speed, E before It indicates the real-time turning speed before adjustment, and δ indicates the adjustment parameter; it ensures that the tension during the can change process is kept within a reasonable range, thereby improving the stability and accuracy of can change, effectively avoiding problems such as yarn breakage, looseness, and equipment jamming caused by excessive or insufficient tension, thereby improving production efficiency and product quality.

[0035] An automatic can change control system based on artificial intelligence, the system comprises a collection and screening module, a calculation module, a can change judgment module and a can change control module;

[0036] The collection and screening module is used to collect the operation records of the production equipment in real time through the sensing equipment, including yarn tension, production speed, drum changing time and flipping speed, and store them in the database, and filter the data to form a first record set and a second record set; the calculation module is used to calculate the average time interval of drum changing under different production speeds through the first record set, and calculate the target tension in the drum changing process through the second record set; the drum changing judgment module is used to obtain the relationship between the production speed and the time interval of drum changing through the neural network model, and calculate the drum changing timing value through the operation record to judge the start of drum changing; the drum changing control module is used to monitor the real-time yarn tension and real-time flipping speed in the drum changing process, and adjust the flipping speed in real time by calculating the tension error value to realize drum changing control.

[0037] According to the above technical solution, the acquisition and screening module includes a data acquisition unit and a data screening unit;

[0038] The data acquisition unit is used to continuously monitor the production equipment through the sensor equipment, collect the operation data of the production equipment in real time, and store the operation data records in the database; the data screening unit is used to screen and classify the collected operation records, and screen out the data that meets the requirements through the production speed and yarn tension to form a first record set and a second record set.

[0039] According to the above technical solution, the calculation module includes a time calculation unit and a tension calculation unit;

[0040] The time calculation unit is used to calculate the time interval between the bobbin changing moments by analyzing the filtered first record set, to count and generate the average value and standard deviation, and to retain the time interval data that meets the conditions; the tension calculation unit is used to calculate the target tension in the bobbin changing process by analyzing the yarn tension in the filtered second record set for statistics and analysis.

[0041] According to the above technical solution, the cartridge change judgment module includes a training unit and a timing judgment unit;

[0042] The training unit is used to train the neural network model to learn the time interval relationship of barrel changing under different production speeds. After the training is completed, the corresponding barrel changing preparation time is output according to the real-time production speed; the timing judgment unit is used to calculate the barrel changing timing value through real-time data, judge the start timing of barrel changing and record the barrel changing time.

[0043] According to the above technical solution, the drum changing control module includes an error calculation unit and a speed adjustment unit;

[0044] The error calculation unit is used to calculate the real-time tension error during the can change process, and generate a tension error value by comparing the difference between the real-time tension and the target tension; the speed adjustment unit is used to adjust the flip speed during the can change process according to the calculated tension error value.

[0045] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0046] The present invention realizes intelligent control in the process of automatic drum changing through artificial intelligence technology, solves the problem of insufficient control of yarn tension and turnover speed in traditional drum changing systems, and dynamically adjusts the drum changing timing and turnover speed according to different production speeds by collecting and screening the operating data of the production equipment in real time, effectively avoiding problems such as yarn breakage, looseness and equipment jamming caused by excessive or insufficient tension, thereby improving production efficiency and product quality; at the same time, compared with traditional automatic drum changing control systems, the present invention optimizes the timing judgment of the drum changing process through a neural network model, and ensures that the tension in the drum changing process is maintained within the target value range through real-time monitoring and adjustment of the turnover speed, thereby reducing manual intervention and improving the automation and accuracy of the system; in addition, the present invention ensures the stability and safety of the drum changing process by accurately controlling the adjustment of the turnover speed, further improving the continuous operation capability of the production line and the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 It is a flow chart of an automatic can change control method based on artificial intelligence of the present invention;

[0049] Figure 2 It is a structural schematic diagram of an automatic barrel changing control system based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technical visitors in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1 , the present invention provides a technical solution:

[0052] An automatic drum changing control method based on artificial intelligence, the method comprising the following steps:

[0053] S1. Set up a sensor device to collect and store the operation records of the production equipment; filter the operation records to obtain a first record set and a second record set;

[0054] According to the above technical solution, step S1 includes the following:

[0055] S1-1. A sensor device is installed on the production equipment. Each time the sensor device collects data, an operation record of the production equipment is generated and stored in a database. The operation record includes yarn tension, production speed, bobbin changing time and turning speed;

[0056] The tension of the yarn is measured in real time by a tension sensor installed in the yarn channel. The tension sensor is usually based on strain gauges, optical fiber sensing technology or electromagnetic force principles, etc. The production speed refers to the speed of the reel in the warping machine. The warping machine evenly winds the yarn onto the reel, and the reel speed is usually related to the production speed (the length of winding per minute); the barrel changing time refers to the opening time of the corresponding flipping device during the barrel changing process; the flipping speed refers to the speed of the flipping device when performing the flipping operation during the barrel changing process; if the operation record is in the barrel changing process, the barrel changing time corresponding to the operation record is the latest opening time of the flipping device, and the flipping speed corresponding to the operation record is the real-time flipping speed; if the operation record is not in the barrel changing process, the barrel changing time corresponding to the operation record is the opening time of the flipping device most recently to the current time, and the flipping speed corresponding to the operation record is the flipping speed at the most recent opening time of the flipping device;

[0057] S1-2. According to the production speed, all operation records with the same production speed are extracted, and the extracted operation records with the same production speed are marked, each operation record is associated with the corresponding production speed, and all marked operation records are counted to form a first record set;

[0058] S1-3. According to the size of the yarn tension, calculate the average value of the yarn tension corresponding to all the operation records, which is recorded as A; if the yarn tension corresponding to a certain operation record is less than or equal to (1+α)×A and the yarn tension corresponding to the operation record is greater than or equal to (1-α)×A, then filter out the operation record as an operation record in the second record set, wherein α represents the tension screening parameter; filter all the operation records to form the second record set.

[0059] S2. Calculate the average time interval for changing the drum at different production speeds through the first record set; calculate the target tension during the drum changing process through the second record set;

[0060] According to the above technical solution, step S2 includes the following:

[0061] S2-1, filter out the operation records with the same production speed in the first record set to form a filtered record set; sort the operation records in the filtered record set from front to back according to the drum changing time, calculate the time intervals between the drum changing times corresponding to adjacent operation records after sorting, and calculate the average value and standard deviation of all time intervals;

[0062] The time interval between the drum changing moments corresponding to a group of adjacent operation records is recorded as B1; the average value of all time intervals is recorded as B2; the standard deviation of all time intervals is recorded as B3; if B1 satisfies B2-β×B3≤B1≤B2-β×B3, the time interval between the drum changing moments corresponding to the group of adjacent operation records is retained; if B1 does not satisfy B2-β×B3≤B1≤B2-β×B3, the time interval between the drum changing moments corresponding to the group of adjacent operation records is removed; wherein β represents a time screening parameter;

[0063] It is used to remove abnormal time intervals to improve accuracy, such as the time interval between the drum changing moments corresponding to adjacent operation records is zero, or there is a shutdown behavior between the drum changing moments corresponding to adjacent operation records, which makes the time interval between the drum changing moments corresponding to adjacent operation records very large, etc.

[0064] Calculate the average of the time intervals retained in the filtered record set as the average time interval for changing the drum at the corresponding production speed;

[0065] S2-2. Calculate the average value of the yarn tension corresponding to each running record in the second record set as the target tension in the bobbin changing process.

[0066] S3, establish a neural network model, combine the average time interval of drum changing at different production speeds, train the neural network model, calculate the drum changing preparation time; extract the operation records after the drum changing preparation time, calculate the drum changing timing value, and start the drum changing;

[0067] According to the above technical solution, step S3 includes the following:

[0068] S3-1, establish a neural network model, take different production speeds as input, take the average time interval of drum replacement at different production speeds as output, and train the neural network model;

[0069] The operation records are screened at the current moment to select the real-time operation records; the production speed corresponding to the real-time operation records are input into the trained neural network model; the average time interval of can change corresponding to the production speed output by the trained neural network model is added to the can change time corresponding to the real-time operation record, and the time obtained is used as the can change preparation time corresponding to the current moment;

[0070] S3-2, extract the operation record after the bobbin change preparation moment, and use the formula: C = γ1 × C1 + γ2 × C2 to calculate the bobbin change timing value corresponding to a certain operation record after the bobbin change preparation moment, wherein C represents the bobbin change timing value corresponding to a certain operation record after the bobbin change preparation moment, C1 represents the yarn tension corresponding to a certain operation record after the bobbin change preparation moment, C2 represents the production speed corresponding to a certain operation record after the bobbin change preparation moment, γ1 represents the weight parameter of the yarn tension, and γ2 represents the weight parameter of the production speed;

[0071] When the drum changing opportunity value corresponding to a certain operation record after the drum changing preparation time is greater than or equal to the first threshold, the drum changing is started and the drum changing time is recorded;

[0072] Starting to change the drum means that the corresponding turning device starts to turn over when the drum is changed.

[0073] S4, obtaining the real-time yarn tension and the real-time turning speed during the bobbin changing process, calculating the tension error value during the bobbin changing process in combination with the target tension during the bobbin changing process, and adjusting the real-time turning speed during the bobbin changing process;

[0074] According to the above technical solution, step S4 includes the following:

[0075] S4-1. Use the sensing device to obtain the real-time yarn tension and real-time turning speed during the bobbin changing process; the real-time yarn tension during the bobbin changing process is recorded as D; the target tension during the bobbin changing process is recorded as D target ;Use the formula; ΔD=DD target , calculate the tension error value during the can change process, where ΔD represents the tension error value during the can change process;

[0076] S4-1, the absolute value of the tension error during the barrel changing process is recorded as |ΔD|;

[0077] When |ΔD| is less than or equal to the second threshold, the real-time flipping speed during the drum changing process is maintained;

[0078] When |ΔD| is greater than the second threshold, the real-time flipping speed during the drum changing process is adjusted. The specific process of the adjustment is as follows:

[0079] Adjust the real-time flip speed during the drum change process to E after =E before ×(1-δ×ΔD), where E after Indicates the adjusted real-time flip speed, E before represents the real-time flip speed before adjustment, and δ represents the adjustment parameter;

[0080] For example:

[0081] In a certain production, the real-time yarn tension during the bobbin change process is D=55; the target tension during the bobbin change process is D target =50; the second threshold is 3; the adjustment parameter δ=0.02; the real-time flip speed is 200;

[0082] Use the formula; ΔD=DD target =5, calculate the tension error value during the barrel changing process; the absolute value of the tension error value during the barrel changing process |ΔD|=5;

[0083] When |ΔD|=5 is greater than the second threshold value of 3, the real-time flipping speed during the drum changing process is adjusted. The specific process of the adjustment is as follows:

[0084] Adjust the real-time flip speed during the drum change process to E after =E before ×(1-δ×ΔD)=200×

[0085] (1-0.02×5)=180, where E before is the real-time flip speed, that is, E before =200;

[0086] Ensure that the tension during the bobbin changing process remains within a reasonable range, thereby improving the stability and accuracy of the bobbin changing, effectively avoiding problems such as yarn breakage, looseness, and equipment jamming caused by excessive or insufficient tension, thereby improving production efficiency and product quality.

[0087] See also Figure 2 , an automatic can change control system based on artificial intelligence, the system includes a collection and screening module, a calculation module, a can change judgment module and a can change control module;

[0088] The collection and screening module is used to collect the operation records of the production equipment in real time through the sensing equipment, including yarn tension, production speed, drum changing time and flipping speed, and store them in the database, and filter the data to form a first record set and a second record set; the calculation module is used to calculate the average time interval of drum changing under different production speeds through the first record set, and calculate the target tension in the drum changing process through the second record set; the drum changing judgment module is used to obtain the relationship between the production speed and the time interval of drum changing through the neural network model, and calculate the drum changing timing value through the operation record to judge the start of drum changing; the drum changing control module is used to monitor the real-time yarn tension and real-time flipping speed in the drum changing process, and adjust the flipping speed in real time by calculating the tension error value to realize drum changing control.

[0089] According to the above technical solution, the acquisition and screening module includes a data acquisition unit and a data screening unit;

[0090] The data acquisition unit is used to continuously monitor the production equipment through the sensor equipment, collect the operation data of the production equipment in real time, and store the operation data records in the database; the data screening unit is used to screen and classify the collected operation records, and screen out the data that meets the requirements through the production speed and yarn tension to form a first record set and a second record set.

[0091] According to the above technical solution, the calculation module includes a time calculation unit and a tension calculation unit;

[0092] The time calculation unit is used to calculate the time interval between the bobbin changing moments by analyzing the filtered first record set, to count and generate the average value and standard deviation, and to retain the time interval data that meets the conditions; the tension calculation unit is used to calculate the target tension in the bobbin changing process by analyzing the yarn tension in the filtered second record set for statistics and analysis.

[0093] According to the above technical solution, the cartridge change judgment module includes a training unit and a timing judgment unit;

[0094] The training unit is used to train the neural network model to learn the time interval relationship of barrel changing under different production speeds. After the training is completed, the corresponding barrel changing preparation time is output according to the real-time production speed; the timing judgment unit is used to calculate the barrel changing timing value through real-time data, judge the start timing of barrel changing and record the barrel changing time.

[0095] According to the above technical solution, the drum changing control module includes an error calculation unit and a speed adjustment unit;

[0096] The error calculation unit is used to calculate the real-time tension error during the can change process, and generate a tension error value by comparing the difference between the real-time tension and the target tension; the speed adjustment unit is used to adjust the flip speed during the can change process according to the calculated tension error value.

[0097] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention is described in detail with reference to the aforementioned embodiments, for technical visitors in the field, it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An automatic can change control method based on artificial intelligence, characterized in that: The method comprises the following steps: S1. Set up a sensor device to collect and store the operation records of the production equipment; filter the operation records to obtain a first record set and a second record set; S2. Calculate the average time interval for changing the drum at different production speeds through the first record set; calculate the target tension during the drum changing process through the second record set; S3, establish a neural network model, combine the average time interval of drum changing at different production speeds, train the neural network model, calculate the drum changing preparation time; extract the operation records after the drum changing preparation time, calculate the drum changing timing value, and start the drum changing; S4. Acquire the real-time yarn tension and the real-time turning speed during the bobbin changing process, calculate the tension error value during the bobbin changing process in combination with the target tension during the bobbin changing process, and adjust the real-time turning speed during the bobbin changing process.

2. The method for automatic can change control based on artificial intelligence according to claim 1, characterized in that: The step S1 comprises the following: S1-1. A sensor device is installed on the production equipment. Each time the sensor device collects data, an operation record of the production equipment is generated and stored in a database. The operation record includes yarn tension, production speed, bobbin changing time and turning speed; S1-2. According to the production speed, all operation records with the same production speed are extracted, and the extracted operation records with the same production speed are marked, each operation record is associated with the corresponding production speed, and all marked operation records are counted to form a first record set; S1-3. According to the yarn tension, calculate the average value of the yarn tension corresponding to all running records, which is recorded as A; If the yarn tension corresponding to a certain operation record is less than or equal to (1+α)×A and the yarn tension corresponding to the operation record is greater than or equal to (1-α)×A, then the operation record is selected as an operation record in the second record set, wherein α represents a tension selection parameter; All running records are screened to form a second record set.

3. The method for automatic can change control based on artificial intelligence according to claim 2, characterized in that: The step S2 comprises the following: S2-1, filter out the operation records with the same production speed in the first record set to form a filtered record set; sort the operation records in the filtered record set from front to back according to the drum changing time, calculate the time intervals between the drum changing times corresponding to adjacent operation records after sorting, and calculate the average value and standard deviation of all time intervals; The time interval between the drum changing times corresponding to a group of adjacent operation records is recorded as B1; the average value of all time intervals is recorded as B2; the standard deviation of all time intervals is recorded as B3; If B1 satisfies B2-β×B3≤B1≤B2-β×B3, the time interval between the drum changing moments corresponding to the group of adjacent operation records is retained; If B1 does not satisfy B2-β×B3≤B1≤B2-β×B3, then the time intervals between the drum changing times corresponding to the group of adjacent operation records are removed; wherein β represents the time screening parameter; Calculate the average of the time intervals retained in the filtered record set as the average time interval for changing the drum at the corresponding production speed; S2-2. Calculate the average value of the yarn tension corresponding to each running record in the second record set as the target tension in the bobbin changing process.

4. The method for automatic can change control based on artificial intelligence according to claim 3, characterized in that: The step S3 includes the following: S3-1, establish a neural network model, take different production speeds as input, take the average time interval of drum replacement at different production speeds as output, and train the neural network model; The operation records are screened at the current moment to select the real-time operation records; the production speed corresponding to the real-time operation records are input into the trained neural network model; the average time interval of can change corresponding to the production speed output by the trained neural network model is added to the can change time corresponding to the real-time operation record, and the time obtained is used as the can change preparation time corresponding to the current moment; S3-2, extract the operation record after the bobbin change preparation moment, and use the formula: C = γ1 × C1 + γ2 × C2 to calculate the bobbin change timing value corresponding to a certain operation record after the bobbin change preparation moment, wherein C represents the bobbin change timing value corresponding to a certain operation record after the bobbin change preparation moment, C1 represents the yarn tension corresponding to a certain operation record after the bobbin change preparation moment, C2 represents the production speed corresponding to a certain operation record after the bobbin change preparation moment, γ1 represents the weight parameter of the yarn tension, and γ2 represents the weight parameter of the production speed; When the drum changing opportunity value corresponding to a certain operation record after the drum changing preparation time is greater than or equal to the first threshold, the drum changing is started and the drum changing time is recorded.

5. The method for automatic can change control based on artificial intelligence according to claim 4, characterized in that: The step S4 comprises the following: S4-1. Using a sensing device, obtain the real-time yarn tension and real-time turning speed during the bobbin changing process; the real-time yarn tension during the bobbin changing process is recorded as D; The target tension during the drum change process is recorded as D target ; Use formula; ΔD=DD target , calculate the tension error value during the can change process, where ΔD represents the tension error value during the can change process; S4-1, the absolute value of the tension error during the barrel changing process is recorded as |ΔD|; When |ΔD| is less than or equal to the second threshold, the real-time flipping speed during the drum changing process is maintained; When |ΔD| is greater than the second threshold, the real-time flipping speed during the drum changing process is adjusted. The specific process of the adjustment is as follows: Adjust the real-time flip speed during the drum change process to E after =E before ×(1-δ×ΔD), where E after Indicates the adjusted real-time flip speed, E before It indicates the real-time flip speed before adjustment, and δ indicates the adjustment parameter.

6. An automatic can change control system based on artificial intelligence, used to implement an automatic can change control method based on artificial intelligence as claimed in any one of claims 1 to 5, characterized in that: The system includes a collection and screening module, a calculation module, a can change judgment module and a can change control module; The collection and screening module is used to collect the operation records of the production equipment in real time through the sensor equipment, including yarn tension, production speed, can change time and turnover speed, and store them in the database, and screen the data to form a first record set and a second record set; the calculation module is used to calculate the average time interval of can change under different production speeds through the first record set, and calculate the target tension in the can change process through the second record set; the can change judgment module is used to obtain the relationship between the production speed and the can change time interval through the neural network model, and calculate the can change timing value through the operation record to judge the start of can change; The bobbin changing control module is used to monitor the real-time yarn tension and the real-time turning speed during the bobbin changing process, and to adjust the turning speed in real time by calculating the tension error value to realize bobbin changing control.

7. The automatic can change control system based on artificial intelligence according to claim 6, characterized in that: The acquisition and screening module includes a data acquisition unit and a data screening unit; The data acquisition unit is used to continuously monitor the production equipment through the sensor equipment, collect the operation data of the production equipment in real time, and store the operation data records in the database; The data screening unit is used to screen and classify the collected operation records, and screen out data that meets the requirements according to the production speed and yarn tension to form a first record set and a second record set.

8. The automatic can change control system based on artificial intelligence according to claim 6, characterized in that: The calculation module includes a time calculation unit and a tension calculation unit; The time calculation unit is used to calculate the time interval between the drum changing moments by analyzing the filtered first record set, to count and generate the average value and standard deviation, and to retain the time interval data that meets the conditions; The tension calculation unit is used to calculate the target tension in the bobbin changing process by analyzing and performing statistics on the yarn tension in the filtered second record set.

9. The automatic can change control system based on artificial intelligence according to claim 6, characterized in that: The tube change judgment module includes a training unit and a timing judgment unit; The training unit is used to train the neural network model to learn the time interval relationship of barrel changing under different production speeds. After the training is completed, the corresponding barrel changing preparation time is output according to the real-time production speed; the timing judgment unit is used to calculate the barrel changing timing value through real-time data, judge the start timing of barrel changing and record the barrel changing time.

10. The automatic can change control system based on artificial intelligence according to claim 6, characterized in that: The drum changing control module includes an error calculation unit and a speed adjustment unit; The error calculation unit is used to calculate the real-time tension error during the drum changing process, and to generate a tension error value by comparing the difference between the real-time tension and the target tension; The speed adjustment unit is used to adjust the turning speed during the can changing process according to the calculated tension error value.

Images