Parameter processing method, parameter processor, electronic device, storage medium, and program

Abstract

To provide a parameter processing method, a parameter processor, an electronic device, a storage medium, and a program that reduce human costs and time costs and improve production quality and production efficiency of wound yarn packages.SOLUTION: The parameter processing method determines T full winding ratios of a winding package wound by a winding machine. A t (a positive integer of 1 or more)-th full winding ratio among the T (a positive integer of 1 or more) full winding ratios is obtained based on N first characteristic parameters collected at a t-th time, the parameters affecting the full winding ratio of the winding package wound by the winding machine. The method also determines a candidate characteristic parameter set when none of M (a positive integer of≤<M≤T) full winding ratios among the T full winding ratios meets a preset full winding ratio requirement. In the candidate characteristic parameters included in the set, a full winding ratio selected from the N first characteristic parameters corresponding to full winding ratios that do not meet the preset full winding ratio requirement does not meet the preset full winding ratio.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to the technical field of data processing, and in particular to a parameter processing method, a parameter processing device, an electronic device, a storage medium, and a program. [Background technology]

[0002] In the daily production process of a wound yarn package, after the winding of the wound yarn package is completed, an operator randomly checks the full winding rate of the wound yarn package, and if the result of the random check does not reach the expected target value, the operator needs to analyze and adjust the parameters that may cause the full winding rate to not reach the standard based on experience. However, this method relies relatively heavily on human experience, and the parameters that cause the full winding rate to not reach the standard during the production process cannot be quickly identified and adjusted in a timely manner, which affects production efficiency and production quality. Summary of the Invention [Problem to be solved by the invention]

[0003] The present disclosure provides a parameter processing method, a parameter processing apparatus, an electronic device, a storage medium, and a program to solve or alleviate one or more technical problems in the prior art. [Means for solving the problem]

[0004] In a first aspect, the present disclosure provides a parameter processing method, the method comprising: determining T full winding rates of a wound yarn package wound by a winding machine, where a t-th full winding rate among the T full winding rates is obtained based on N first characteristic parameters collected at a t-th time, a first characteristic parameter among the N first characteristic parameters is a characteristic parameter that can affect the full winding rate of the wound yarn package wound by the winding machine, T is a positive integer greater than or equal to 1, t is a positive integer greater than or equal to 1 and less than or equal to T, and N is a positive integer greater than or equal to 1; determining a candidate feature parameter set when it is determined that none of M full winding rates among the T full winding rates satisfy a preset full winding rate requirement, wherein the candidate feature parameters included in the candidate feature parameter set are feature parameters that cause the full winding rate to not satisfy the preset full winding rate requirement, selected from N first feature parameters corresponding to the full winding rates that do not satisfy the preset full winding rate requirement, and which cause the full winding rate to not satisfy the preset full winding rate requirement, and wherein M is a positive integer greater than or equal to 1 and less than or equal to T.

[0005] In a second aspect, the present disclosure provides a parameter processing apparatus, the apparatus comprising: a result prediction unit for determining T full winding rates of a wound yarn package wound by a winding machine, where a t-th full winding rate among the T full winding rates is obtained based on N first characteristic parameters collected at a t-th time, a first characteristic parameter among the N first characteristic parameters is a characteristic parameter that can affect the full winding rate of the wound yarn package wound by the winding machine, T is a positive integer greater than or equal to 1, t is a positive integer greater than or equal to 1 and less than or equal to T, and N is a positive integer greater than or equal to 1; and a parameter determination unit for determining a candidate feature parameter set when it is determined that none of M full winding rates among the T full winding rates satisfy a preset full winding rate requirement, wherein the candidate feature parameters included in the candidate feature parameter set are feature parameters that cause the full winding rate to not satisfy the preset full winding rate requirement, selected from N first feature parameters corresponding to the full winding rates that do not satisfy the preset full winding rate requirement, and which cause the full winding rate to not satisfy the preset full winding rate requirement, and M is a positive integer greater than or equal to 1 and less than or equal to T.

[0006] In a third aspect, the present disclosure provides an electronic device, the device comprising: At least one processor; a memory in communication with the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, cause the implementation of any one of the methods in the embodiments of the present disclosure.

[0007] In a fourth aspect, there is provided a non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to perform any one of the methods in the embodiments of the present disclosure.

[0008] In a fifth aspect, a program is provided, which, when executed by a processor, implements any one of the methods in the embodiments of the present disclosure.

[0009] The beneficial effects of the technical solutions provided by the present disclosure include at least the following:

[0010] According to an embodiment of the present disclosure, T full winding rates are determined during the production process, the standard achievement status of each full winding rate among the T full winding rates is determined, and when the standard achievement status does not meet the requirements, candidate feature parameters that will cause the full winding rate to not reach the standard can be determined in a timely manner. In this way, the situation in which the full winding rate of the wound yarn package may not reach the standard can be determined in a timely and efficient manner during the production process of the wound yarn package, and the parameters of the winding machine can be monitored and adjusted in real time during the production process, laying a foundation for enabling timely automatic adjustment to the winding machine thereafter.

[0011] It should be understood that the contents described herein are not intended to describe key points or important features of the embodiments of the present disclosure, nor are they used to limit the scope of the present disclosure. Other features of the present disclosure are facilitated by the following description. [Brief description of the drawings]

[0012] In the accompanying drawings, the same numbers represent the same or similar parts or elements throughout the several views unless otherwise stated. The accompanying drawings are not necessarily drawn to scale. It should be understood that the drawings depict only some embodiments provided by the present disclosure and should not be considered as limiting the scope of the present disclosure. [Figure 1] 1 is a schematic flowchart of a parameter processing method according to an embodiment of the present disclosure. [Diagram 2] 2 is a second schematic flowchart of a parameter processing method according to an embodiment of the present disclosure. [Diagram 3] 3 is a schematic flowchart of a parameter processing method according to an embodiment of the present disclosure. [Figure 4] 4 is a schematic flowchart of a parameter processing method according to an embodiment of the present disclosure. [Diagram 5] 1 is a schematic diagram showing a configuration of a parameter processing device according to an embodiment of the present disclosure. [Figure 6] FIG. 2 is a block diagram of an electronic device for implementing a parameter processing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] The present disclosure will now be described in more detail with reference to the accompanying drawings, in which like numbers represent functionally identical or similar elements, and in which various aspects of the embodiments are illustrated, and which, unless otherwise noted, are not necessarily drawn to scale.

[0014] Furthermore, in order to better explain the present disclosure, many specific details are described in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can be similarly implemented without specific details. In some embodiments, methods, means, components, circuits, etc. that are well known to those skilled in the art are not described in detail so as not to obscure the subject matter of the present disclosure.

[0015] In the daily production process of a wound yarn package, a winding machine for winding the wound yarn package may be affected by various factors (e.g., winding speed, speed of the first godet roller, oil content, intertwining pressure, air temperature, air pressure, etc.), and as a result, the full winding rate of the wound yarn package may not reach the expected target value. In the existing process, after the winding of the wound yarn package is completed, an operator performs a random inspection of the full winding rate of the wound yarn package. If the result of the random inspection does not reach the expected target value, the operator must analyze and adjust parameters that may cause the full winding rate to not reach the standard based on experience. However, this method relies relatively heavily on human experience and cannot quickly determine and timely adjust parameters that cause the full winding rate to not reach the standard in the production process, which affects production efficiency and production quality. Therefore, a method for quickly and timely determining parameters that cause the full winding rate to not reach the standard in the production process of a wound yarn package is needed, thereby improving production quality.

[0016] Based on this, the present disclosure proposes a parameter processing method to solve the above problems.

[0017] 1 is a schematic flow chart of a parameter processing method according to an embodiment of the present disclosure, optionally applied to electronic devices such as personal computers, servers, server clusters, and the like.

[0018] Furthermore, the method at least includes at least part of the following contents: As shown in FIG.

[0019] In step S101, a full winding rate of T wound yarn packages wound by a winding machine is determined.

[0020] Here, the t-th full winding rate among the T full winding rates is obtained based on N first characteristic parameters collected at the t-th time (for example, at the t-th time in the generation process), where T is a positive integer of 1 or more, and t is a positive integer of 1 to T.

[0021] It should be understood that the t-th full winding ratio is specifically the full winding ratio corresponding to the t-th time in the production process of the winding machine.

[0022] Furthermore, a first characteristic parameter among the N first characteristic parameters is a characteristic parameter that can affect the full winding rate of the wound yarn package wound by the winding machine, and N is a positive integer greater than or equal to 1.

[0023] It should be noted that the N first characteristic parameters include at least one of spinning process parameters such as, but are not limited to, oil concentration, oil pump rotation speed, oil content, air temperature, air humidity, air pressure, spinneret diameter, winding speed, speed of the first godet roller (GR1), temperature of the second godet roller (GR2), entanglement (including pre-entanglement and main entanglement) pressure, and overfeed rate.

[0024] In step S102, when it is determined that none of the M full winding rates among the T full winding rates meets a preset full winding rate requirement, a candidate feature parameter set is determined.

[0025] Here, the candidate feature parameters included in the candidate feature parameter set are feature parameters that cause the full winding rate to not satisfy the preset full winding rate requirement, selected from N first feature parameters corresponding to the full winding rate that does not satisfy the preset full winding rate requirement, and M is a positive integer greater than or equal to 1 and less than or equal to T.

[0026] In one example, the preset full winding rate requirement may specifically be that the full winding rate is equal to or greater than a preset full winding rate, and the preset full winding rate is an empirical value, and may be set according to actual needs, for example, the preset full winding rate may take a value of 95% or 98%, but the present disclosure is not limited thereto.

[0027] Furthermore, in one specific example, M is a positive integer greater than or equal to a preset threshold and less than or equal to T, where the preset threshold is a positive integer greater than or equal to 1 and less than or equal to T, and may be set according to actual needs, for example, by taking an intermediate value in the interval [1,T], but the present disclosure is not limited thereto.

[0028] Furthermore, in one example, the M full winding rates among the T full winding rates may be full winding rates corresponding to M consecutive times, or may be full winding rates corresponding to M non-consecutive times, but this disclosure is not limited thereto.

[0029] In one embodiment, when it is determined that all of the M full winding rates among the T full winding rates meet the preset full winding rate requirement, the current process is terminated. Furthermore, after the current process is terminated, after a specified time is reached, or after a specified command is received, the T full winding rates can be newly determined and newly processed according to the method described in the solution of the present disclosure, thus facilitating the monitoring of the full winding rate and the prompt and timely determination of the parameters that cause the full winding rate to not reach the standard, and laying the foundation for improving production quality.

[0030] In this way, according to the solution disclosed herein, it is possible to determine T full winding rates during the production process, determine the standard achievement status of each full winding rate among the T full winding rates, and further timely determine candidate feature parameters that will result in the full winding rate not achieving the standard when the standard achievement status does not meet the requirements. In this way, it is possible to timely and efficiently determine situations in which the full winding rate of a wound yarn package may not achieve the standard during the production process of a wound yarn package, laying a foundation for enabling timely automatic adjustments to subsequent winding machines.

[0031] Furthermore, compared with the method of relying on human experience to retroactively analyze the causes of non-compliance with standards, the solution disclosed herein does not need to rely on human experience, and at the same time, it is possible to monitor and even adjust the parameters of the winding machine in real time during the production process, so that the winding machine parameter monitoring or adjustment process is pre-empted, automated, and intelligentized, thus reducing a large amount of human and time costs, thereby improving production quality, and at the same time further improving the production efficiency of the wound yarn package.

[0032] 2 is a schematic flow chart of a parameter processing method according to an embodiment of the present invention. The present invention is optionally applied to electronic devices such as personal computers, servers, server clusters, etc. It should be understood that the relevant content of the method shown in FIG. 1 above can also be applied to this example, and detailed description of the relevant content will be omitted in this example.

[0033] Furthermore, the method at least includes at least part of the following contents: As shown in FIG.

[0034] In step S201, a winding prediction step is executed in response to a first detection command.

[0035] In one example, the first sensing command may be generated when a task command for producing a wound yarn package is received, for example, the first sensing command is generated during a process of producing a wound yarn package.

[0036] In step S202, when the preset time interval is reached, the next winding prediction step is performed up to T times to obtain the corresponding full winding rates of the winding machine at T different times.

[0037] Here, the t-th winding prediction step specifically includes the following steps.

[0038] In step S202-1, N first characteristic parameters of the winding machine at the t-th time are obtained.

[0039] In step S202-2, the t-th full winding rate of the wound yarn package wound by the winding machine is estimated based on the N first characteristic parameters at the t-th time.

[0040] Here, the first characteristic parameter among the N first characteristic parameters is a characteristic parameter that can affect the full winding rate of the wound yarn package wound by the winding machine, T is a positive integer greater than or equal to 1, t is a positive integer greater than or equal to 1 and less than or equal to T, and N is a positive integer greater than or equal to 1.

[0041] Furthermore, in one specific example, the tth full winding rate of the wound yarn package wound by the winding machine can be obtained as follows. Specifically, estimating and obtaining the tth full winding rate of the wound yarn package wound by the winding machine based on the N first characteristic parameters at the tth time described above (i.e., the above step S202-2) specifically includes the following steps.

[0042] The N first feature parameters at the t-th time are inputted into a target winding prediction model to obtain at least a first prediction result corresponding to the t-th time, which is outputted by a first branch of the target winding prediction model.

[0043] Here, the first branch of the target winding prediction model is used to predict the full winding rate of the wound yarn package wound by the winding machine, and the first prediction result corresponding to the t-th time includes a first value representing the predicted full winding rate of the wound yarn package wound by the winding machine. In this way, an efficient full winding rate prediction method is provided, which can quickly obtain full winding rates corresponding to different times, improve processing efficiency, and lay a foundation for determining whether subsequent adjustments to winding machine parameters are necessary.

[0044] Furthermore, in one specific example, when a first prediction result corresponding to the tth time is obtained in the tth winding prediction step and output by a first branch of the target winding prediction model, a second prediction result corresponding to the tth time is also obtained and output by a second branch of the target winding prediction model.

[0045] Here, the second branch of the target winding prediction model is used to predict the degree of influence of each of the N first characteristic parameters on the full winding rate at the input t-th time, and the second prediction result corresponding to the t-th time includes N second values, and the n-th element of the N second values ​​represents the degree of influence of the n-th first characteristic parameter of the N first characteristic parameters on the full winding rate at the input t-th time.

[0046] That is, after the N first feature parameters at the t-th time are input into the target winding prediction model, two partial results are output, the first partial result (i.e., the first prediction result) represents the full winding rate corresponding to the t-th time, and the second partial result (i.e., the second prediction result) represents the degree of influence that each of the first feature parameters input at the t-th time has on the full winding rate.

[0047] For example, taking five first feature parameters {x1, x2, x3, x4, x5} at a first time as an example, the five first feature parameters are input into a target winding prediction model to obtain a first prediction result corresponding to the first time output by a first branch of the target winding prediction model, and a second prediction result corresponding to the first time output by a second branch of the target winding prediction model, which can be written as, for example, {x1:a1, x2:a2, x3:a3, x4:a4, x5:a5}, where a1, a2, a3, a4, and a5 represent second values, specifically, the degree of influence of the corresponding first feature parameters at the first time on the full winding rate.

[0048] It should be understood that {x1:a1, x2:a2, x3:a3, x4:a4, x5:a5} in this example is just one example, and other expressions may be used in actual applications, and the present disclosure is not limited thereto.

[0049] Furthermore, the target winding prediction model may be a neural network model or an interpretable model, and the present disclosure is not limited thereto.

[0050] In step S203, it is determined whether any of the M full winding rates among the T full winding rates meets the preset full winding rate requirement, and if so, proceed to step S204, or if not, proceed to step S205.

[0051] Here, the full winding rate of M pieces can be determined by referring to the above example, so it will not be described here repeatedly.

[0052] In step S204, when it is determined that none of the M full winding rates among the T full winding rates meets a preset full winding rate requirement, a candidate feature parameter set is determined.

[0053] Here, the candidate feature parameters included in the candidate feature parameter set are feature parameters that cause the full winding rate to not satisfy the preset full winding rate requirement, selected from N first feature parameters corresponding to the full winding rate that does not satisfy the preset full winding rate requirement, and M is a positive integer greater than or equal to 1 and less than or equal to T.

[0054] In step S205, the process ends.

[0055] In this way, the solution of the present disclosure provides a specific example of obtaining T full winding rates, and further, after determining the T full winding rates, judge whether it is necessary to determine a candidate parameter feature set based on the standard achievement status of each full winding rate in the T full winding rates, thus effectively improving the parameter detection efficiency of the winding machine, making the parameter detection more automated and intelligent, laying a foundation for smooth automatic adjustment of the winding machine in the future, and also laying a foundation for improving the production quality and production efficiency of the wound yarn package.

[0056] 3 is a schematic flow diagram No. 3 of a parameter processing method according to an embodiment of the present disclosure. The present invention is optionally applied to electronic devices such as personal computers, servers, server clusters, etc. It should be understood that the relevant contents of the methods shown in the above Figures 1 and 2 can also be applied to this example, and detailed descriptions of the relevant contents will be omitted in this example.

[0057] In addition, the method of the present disclosure at least includes at least part of the following contents: As shown in FIG.

[0058] In step S301, a winding prediction step is executed in response to a first detection command.

[0059] In step S302, when a preset time interval is reached, perform the next winding prediction step up to T times to obtain the corresponding full winding rates of the winding machine at T different times.

[0060] In one example, the t-th winding prediction step includes the following steps:

[0061] In step S302-1, N first characteristic parameters of the winding machine at the t-th time are obtained.

[0062] In step S302-2, the N first feature parameters at the t-th time are input into a target winding prediction model to obtain a first prediction result corresponding to the t-th time that is output by a first branch of the target winding prediction model, and a second prediction result corresponding to the t-th time that is output by a second branch of the target winding prediction model.

[0063] It should be understood that the first prediction results corresponding to T different time instants and the second prediction results corresponding to T different time instants are obtained after performing T winding prediction steps.

[0064] Here, the first branch of the target winding prediction model is used to predict the full winding rate of the wound yarn package wound by the winding machine, and the first prediction result corresponding to the tth time includes a first value, and the first value represents the full winding rate of the wound yarn package wound by the winding machine obtained by prediction.

[0065] Furthermore, the second branch of the target winding prediction model is used to predict the degree of influence of each of the N first feature parameters on the full winding rate at the input t-th time, and the second prediction result corresponding to the t-th time includes N second values, and the n-th element of the N second values ​​represents the degree of influence of the n-th first feature parameter of the N first feature parameters on the full winding rate at the input t-th time.

[0066] In step S303, it is determined whether any of the M full winding rates among the T full winding rates meets the preset full winding rate requirement, and if so, proceed to step S304; otherwise, proceed to step S306.

[0067] Here, M is a positive integer not less than 1 and not more than T. The above example can be referred to for the M full winding ratio, so it will not be described here repeatedly.

[0068] In step S304, the process selects, from among the T second prediction results, second prediction results corresponding to M full winding rates that do not satisfy the preset full winding rate requirement, for a total of M second prediction results. The process proceeds to step S305.

[0069] Here, the T second prediction results are obtained after performing T winding prediction steps.

[0070] In step S305, a candidate feature parameter set is obtained based on the second prediction results corresponding to the M full winding ratios that do not satisfy the preset full winding ratio requirement.

[0071] In one specific example, the set of candidate feature parameters can be obtained using a method such as the following (e.g., method 1 or method 2), and specifically, obtaining a set of candidate feature parameters based on the second prediction results corresponding to M full winding rates that do not satisfy the above-described predetermined full winding rate requirement (i.e., the above step S305) includes:

[0072] In method 1, an initial set of M sets is obtained based on second prediction results corresponding to M full winding rates that do not satisfy a preset full winding rate requirement, and candidate feature parameters are selected from the initial set of M sets to obtain a candidate feature parameter set.

[0073] Here, the initial set of the M initial sets includes a first characteristic parameter whose second value is greater than a preset value among the second prediction results corresponding to the full winding rate not satisfying the preset full winding rate requirement, i.e., the initial set includes a main first characteristic parameter that causes the full winding rate not to satisfy the preset full winding rate requirement.

[0074] Furthermore, selecting candidate feature parameters from the initial set of M sets to obtain a candidate feature parameter set may specifically include: calculating the frequency of each element included in the initial set of M sets, and selecting a predetermined number of target elements whose frequency of the calculated frequency is relatively large as candidate feature parameters, where the predetermined number is a positive integer equal to or larger than 1 and smaller than N.

[0075] For example, in the case of the second prediction results corresponding to three full winding rate requirements that do not satisfy the preset full winding rate requirements, the second prediction results corresponding to the full winding rate requirements that do not satisfy the preset full winding rate requirements can be written as follows: second prediction result no. 1 is {x1: 0.7, x2: 0.4, x3: 0.55, x4: 0.1}, second prediction result no. 2 is {x1: 0.6, x2: 0.45, x3: 0.4, x4: 0.5}, and second prediction result no. 3 is {x1: 0.7, x2: 0.65, x3: 0.45, x4: 0.55}. In this case, the second value can be predicted from the second prediction result no. 1. From the second prediction result No. 2, first feature parameters x1, x3 (which can be denoted as initial set 1, {x1, x3}) whose second values ​​are greater than the preset numerical value of 0.5 are selected; from the second prediction result No. 2, first feature parameters x1, x4 (which can be denoted as initial set 2, {x1, x4}) whose second values ​​are greater than the preset numerical value of 0.5 are selected; and from the second prediction result No. 3, first feature parameters x1, x2, x4 (which can be denoted as initial set 3, {x1, x2, x4}) whose second values ​​are greater than the preset numerical value of 0.5 are selected, to obtain a total of three initial sets.

[0076] Furthermore, by calculating the number of times each element in the three initial sets appears, the number of times x1 appears is 3, the number of times x4 appears is 2, and the number of times x2 and x3 appear is 1. At this time, the top two elements with the largest statistics, x1 and x4, are extracted and used as candidate feature parameters.

[0077] In method 2, a feature parameter matrix with M rows and N columns is obtained based on the second prediction results corresponding to the M full winding rates that do not satisfy the preset full winding rate requirement, where each row in the feature parameter matrix corresponds to N second values, and the second values ​​of the same first feature parameter corresponding to different full winding rates are located in the same column, and a weighting process is performed on the columns in the feature parameter matrix to obtain a 1 row by N column vector, and the candidate feature parameter set is obtained based on the 1 row by N column vector, where the 1 row by N column represents the N third values.

[0078] For example, when the value of M is 3 (i.e., there are three full winding rates that do not meet the preset full winding rate requirement) and the value of N is 4 (there are a total of four first feature parameters collected at each time), the second prediction results corresponding to the full winding rates that do not meet the preset full winding rate requirement are respectively the second prediction result corresponding to the first full winding rate (which can be written as {a11, a12, a13, a14}), the second prediction result corresponding to the second full winding rate (which can be written as {a21, a22, a23, a24}), and the second prediction result corresponding to the third full winding rate (which can be written as {a21, a22, a23, a24}). is the second prediction result corresponding to the winding ratio No. 3 (which can be written as {a31, a32, a33, a34}), where a represents the second value, a·1 represents the influence of the first feature parameter x1 on the full winding ratio, a·2 represents the influence of the first feature parameter x2 on the full winding ratio, a·3 represents the influence of the first feature parameter x3 on the full winding ratio, and a·4 represents the influence of the first feature parameter x4 on the full winding ratio. In this case, the obtained 3-by-4 feature parameter matrix is ​​as follows:

[0079]

number

[0080] Furthermore, a weighting process is performed on the second values ​​of each column in the feature parameter matrix to obtain, for example, the following:

number

[0081] In this way, four third values ​​are obtained, which can be represented as a 1 row by 4 column vector and written, for example, as follows:

number

[0082] Furthermore, obtaining the candidate feature parameter set based on the 1 row by N column vector may specifically include selecting a predetermined number (e.g., N / 2) of first feature parameters having a relatively large third value from the 1 row by N column vector as candidate feature parameters, where the predetermined number is a positive integer greater than or equal to 1 and less than N.

[0083] In step S306, the process ends.

[0084] In this way, the solution disclosed herein provides a concrete example of feature prediction, which can efficiently determine the key parameters that lead to the full winding rate not reaching the standard, effectively improve the parameter detection efficiency of the winding machine, and lay the foundation for smooth automatic adjustment of the winding machine thereafter, as well as for improving the production quality and production efficiency of the wound yarn package.

[0085] 4 is a schematic flow chart No. 4 of a parameter processing method according to an embodiment of the present disclosure. The present invention is optionally applied to electronic devices such as personal computers, servers, server clusters, etc. It should be understood that the relevant contents of the methods shown in the above Figures 1, 2, and 3 can also be applied to this example, and detailed descriptions of the relevant contents will be omitted in this example.

[0086] Furthermore, the method at least includes at least part of the following contents: As shown in FIG.

[0087] In step S401, a full winding rate of T wound yarn packages wound by a winding machine is determined.

[0088] Here, the tth full winding rate among the T full winding rates is obtained based on N first characteristic parameters collected at the tth time, a first characteristic parameter among the N first characteristic parameters is a characteristic parameter that can affect the full winding rate of the wound yarn package wound by the winding machine, T is a positive integer greater than or equal to 1, t is a positive integer greater than or equal to 1 and less than or equal to T, and N is a positive integer greater than or equal to 1.

[0089] Here, the first characteristic parameter can be described in the above example, and will not be described again here.

[0090] In step S402, it is determined whether any of the M full winding rates among the T full winding rates meets a preset full winding rate requirement, and if so, proceed to step S403, whereas if not, proceed to step S409.

[0091] In step S403, when it is determined that none of the M full winding rates among the T full winding rates meets the preset full winding rate requirement, a candidate feature parameter set is determined. Then, the process proceeds to step S404.

[0092] Here, the candidate characteristic parameters included in the candidate characteristic parameter set are characteristic parameters that cause the full winding rate to not satisfy the preset full winding rate requirement, selected from N first characteristic parameters corresponding to the full winding rate that does not satisfy the preset full winding rate requirement, and M is a positive integer between 1 and T. Note that the M full winding rates and the preset full winding rate requirement can be referred to in the above example, and will not be described here repeatedly.

[0093] In step S404, simulation and adjustment are performed for each candidate feature parameter in the candidate feature parameter set, and the process proceeds to step S405.

[0094] The simulation and adjustment refers to a method of making numerical adjustments to candidate feature parameters in a candidate feature parameter set, predicting the full winding rate based on the adjusted feature parameters, thereby improving the full winding rate and adjusting the full winding rate to achieve a preset full winding rate requirement.

[0095] In step S405, a new full winding rate of the yarn package wound by the winding machine is newly estimated based on at least each candidate characteristic parameter after simulation and adjustment, and then the process proceeds to step S406.

[0096] For example, in one example, each candidate feature parameter after simulation and adjustment and other first feature parameters other than the candidate feature parameters that are collected at the collection time of the candidate feature parameter can be re-input into the target winding prediction model to predict the full winding rate.

[0097] In step S406, it is determined whether the new full winding ratio of the wound yarn package wound by the winding machine satisfies the preset full winding ratio requirement, and if so, proceed to step S407, whereas if not, return to step S404 and perform new simulation and adjustment for each candidate characteristic parameter in the candidate characteristic parameter set.

[0098] In step S407, if the new full winding ratio of the wound yarn package wound by the winding machine satisfies the preset full winding ratio requirement, a target adjustment method is obtained, and then the process proceeds to step S408.

[0099] In step S408, a first adjustment command is generated based on the target adjustment method.

[0100] Here, the first adjustment command is used for instructing to physically adjust each candidate characteristic parameter in the candidate characteristic parameter set of the winding machine according to the target adjustment method.

[0101] In step S409, the process ends.

[0102] In this way, the solution disclosed herein provides a concrete example of automated adjustment of winding machine parameters, which allows the winding machine parameters to be monitored and adjusted in real time during the production process, and the process of monitoring or adjusting the winding machine parameters can be pre-staged, automated and intelligentized, thereby reducing a large amount of human and time costs, improving production quality, and further improving the production efficiency of the wound yarn package.

[0103] To sum up, the solution of the present disclosure has several advantages over existing technologies, including:

[0104] First, the response is more timely. Compared with the solution that relies on human experience to retroactively analyze the causes of non-achievement of the standard, the solution disclosed herein can predict the full winding rate during the production process of the yarn package, so that once it is detected that the full winding rate does not reach the standard, the characteristic parameters that cause the full winding rate to not reach the standard can be quickly determined, and the response speed is fast; in addition, this method does not need to rely on human experience, and at the same time, the parameters of the winding machine can be monitored and further adjusted in real time during the production process.

[0105] Second, it is more automated. Compared with the post-facto solution, the solution disclosed herein can quickly determine the characteristic parameters that cause the full winding rate to fall short of the standard during the production process of a wound yarn package, and can promptly create parameter adjustment suggestions so that the full winding rate of the wound yarn package wound by the winding machine meets the production standard, which is more automated and intelligent, thereby reducing a large amount of human and time costs.

[0106] Third, the production efficiency and production quality are improved. Compared with the prior art, the solution of the present disclosure makes the winding machine parameter monitoring or adjustment process pre-staged, automated and intelligent, which can reduce a large amount of human and time costs, thus improving the production quality and further improving the production efficiency of the wound yarn package.

[0107] The solution of the present disclosure also provides a parameter processing device. As shown in FIG. 5, the device specifically includes:

[0108] a result prediction unit 501 for determining T full winding rates of a wound yarn package wound by a winding machine, where a t-th full winding rate among the T full winding rates is obtained based on N first characteristic parameters collected at a t-th time, a first characteristic parameter among the N first characteristic parameters is a characteristic parameter that can affect the full winding rate of the wound yarn package wound by the winding machine, T is a positive integer greater than or equal to 1, t is a positive integer greater than or equal to 1 and less than or equal to T, and N is a positive integer greater than or equal to 1;

[0109] and a parameter determination unit 502 for determining a candidate feature parameter set when it is determined that none of M full winding rates among the T full winding rates satisfy a preset full winding rate requirement, wherein the candidate feature parameters included in the candidate feature parameter set are feature parameters that cause the full winding rate to not satisfy the preset full winding rate requirement, selected from N first feature parameters corresponding to the full winding rates that do not satisfy the preset full winding rate requirement, and which cause the full winding rate to not satisfy the preset full winding rate requirement, where M is a positive integer greater than or equal to 1 and less than or equal to T.

[0110] In one embodiment of the solution of the present disclosure, the result prediction unit specifically comprises: Executing a winding prediction step in response to a first detection command; When a preset time interval is reached, performing a next winding prediction step up to T times to obtain corresponding full winding rates of the winding machine at T different times; Here, the t-th winding prediction step is Obtaining N first characteristic parameters of the winding machine at a t-th time; and estimating and obtaining the t-th full winding rate of the wound yarn package wound by the winding machine based on the N first characteristic parameters at the t-th time.

[0111] In one embodiment of the solution of the present disclosure, the result prediction unit specifically comprises: The N first characteristic parameters at the t-th time are inputted into a target winding prediction model to obtain at least a first prediction result corresponding to the t-th time outputted by a first branch of the target winding prediction model; Here, the first branch of the target winding prediction model is used to predict the full winding rate of the wound yarn package wound by the winding machine, and the first prediction result corresponding to the tth time includes a first value representing the full winding rate of the wound yarn package wound by the winding machine obtained by prediction.

[0112] In one embodiment of the solution of the present disclosure, the result prediction unit specifically comprises: In the t-th winding prediction step, when a first prediction result corresponding to the t-th time is outputted by a first branch of the target winding prediction model, the second prediction result corresponding to the t-th time is further used to obtain a second prediction result corresponding to the t-th time outputted by a second branch of the target winding prediction model; Here, the second branch of the target winding prediction model is used to predict the degree of influence of each of the N first characteristic parameters on the full winding rate at the input t-th time, and the second prediction result corresponding to the t-th time includes N second values, and the n-th element of the N second values ​​represents the degree of influence of the n-th first characteristic parameter of the N first characteristic parameters on the full winding rate at the input t-th time.

[0113] In one embodiment of the solution of the present disclosure, the parameter determining unit specifically comprises: Selecting second prediction results corresponding to M full winding rates that do not satisfy a preset full winding rate requirement from among the T second prediction results, where the T second prediction results are obtained after performing T winding prediction steps; and obtaining the candidate feature parameter set based on a second prediction result corresponding to the M full winding rates that do not satisfy a preset full winding rate requirement.

[0114] In one embodiment of the solution of the present disclosure, the parameter determining unit specifically comprises: Obtaining an initial set of M sets based on second prediction results corresponding to M full winding rates that do not satisfy a preset full winding rate requirement, wherein the initial set in the initial set of M sets includes a first characteristic parameter whose second value is greater than a preset value among the second prediction results corresponding to the full winding rates that do not satisfy the preset full winding rate requirement; selecting candidate feature parameters from the initial set of M pairs to obtain a candidate feature parameter set.

[0115] In one embodiment of the solution of the present disclosure, the parameter determining unit specifically comprises: According to the second prediction results corresponding to the M full winding rates that do not meet the preset full winding rate requirement, a feature parameter matrix having M rows by N columns is obtained, where each row in the feature parameter matrix corresponds to N second values, and the second values ​​of the same first feature parameter corresponding to different full winding rates are located in the same column; performing a weighting process on columns in the feature parameter matrix to obtain a 1 row by N column vector representing N third values; and obtaining the candidate feature parameter set based on the 1 row by N column vector.

[0116] In one embodiment of the solution of the present disclosure, the parameter processing device further comprises a parameter adjustment unit; The parameter adjustment unit is used for performing simulation and adjustment for each candidate feature parameter in the candidate feature parameter set; The result prediction unit is further used for obtaining a new estimated full winding rate of the yarn package wound by the winding machine based on at least each candidate characteristic parameter after simulation and adjustment; The parameter adjusting unit is further used for obtaining a target adjusting method when a new full winding ratio of the wound yarn package wound by the winding machine meets a preset full winding ratio requirement.

[0117] In one embodiment of the solution of the present disclosure, the parameter adjustment unit comprises: The method is further used to generate a first adjustment command based on the target adjustment method, and the first adjustment command is used to instruct physically adjusting each candidate characteristic parameter in the candidate characteristic parameter set of the winding machine in accordance with the target adjustment method.

[0118] In one embodiment of the solution of the present disclosure, the parameter adjustment unit is further used for performing a new simulation and adjustment for each candidate characteristic parameter in the candidate characteristic parameter set when a new full winding ratio of the wound yarn package wound by the winding machine does not satisfy a preset full winding ratio requirement; The result prediction unit is further used for determining a new full winding ratio after performing a new simulation and adjustment for each candidate feature parameter in the candidate feature parameter set, and judging whether the new full winding ratio satisfies a preset full winding ratio requirement.

[0119] The specific functions and exemplary descriptions of each module and sub-module of the apparatus in the embodiments of the present disclosure may refer to the relevant descriptions of the corresponding steps in the embodiments of the above method, and will not be repeated here.

[0120] FIG. 6 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 6, the electronic device includes a memory 610 and a processor 620, and the memory 610 stores a computer program executable by the processor 620. The number of the memory 610 and the processor 620 may be one or more. The memory 610 may store one or more computer programs, which, when executed by the electronic device, cause the electronic device to perform the method provided by the above method embodiment. The electronic device may further include: The communication interface 630 is used for communicating with an external device and performing data interaction and transmission.

[0121] When the memory 610, the processor 620, and the communication interface 630 are implemented independently, the memory 610, the processor 620, and the communication interface 630 are connected to each other via a bus and can communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be classified into an address bus, a data bus, a control bus, and the like. For ease of explanation, only one thick line is shown in FIG. 6, but this does not indicate only one bus or only one type of bus.

[0122] Optionally, in a specific implementation, when the memory 610, the processor 620, and the communication interface 630 are integrated on one chip, the memory 610, the processor 620, and the communication interface 630 can communicate with each other via an internal interface.

[0123] It should be understood that the processor may be a Central Processing Unit (CPU) or may be other general purpose processors, Digital Signal Processing (DSP), Application Specific Integrated Circuits (ASIC), Field Programmable Gate Arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware assemblies, etc. The general purpose processor may be a microprocessor or any conventional processor, etc. Additionally, the processor may be a processor supporting the Advanced RISC Machines (ARM) architecture.

[0124] Additionally, optionally, the memory may include read-only memory and random access memory, and may further include non-volatile random access memory. The memory may be either volatile or non-volatile memory, or may include both volatile and non-volatile memory. Here, non-volatile memory may include Read-Only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically EPROM (EEPROM), or flash memory. Volatile memory may include Random Access Memory (RAM), which acts as an external cache. By way of example and not limitation, many forms of RAM are available. For example, static random access memory (Static RAM, SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (Double Data Rate SDRAM, DDR SDRAM), enhanced SDRAM (Enhanced SDRAM, ESDRAM), synchlink DRAM (Synchlink DRAM, SLDRAM), and direct RAMBUS RAM (DR RAM).

[0125] The above-mentioned embodiments may be implemented in whole or in part in software, hardware, firmware, or any combination thereof. When implemented in software, the whole or in part may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, a process or function according to the embodiments of the present disclosure is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, Bluetooth, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device including a server, a data center, etc. integrated with one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a Digital Versatile Disc (DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)). Note that the computer-readable storage medium referred to in this disclosure may be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0126] Those skilled in the art can understand that all or part of the steps for realizing the above embodiments may be implemented by hardware, or may be implemented by instructing relevant hardware by a program, and the program may be stored in a computer-readable storage medium, and the storage medium may be a read-only memory, a magnetic disk, an optical disk, etc.

[0127] In the description of the embodiments of the present disclosure, the reference words "one embodiment", "several embodiments", "examples", "specific examples", or "several examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. And, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in any one or more embodiments or examples. Furthermore, a person skilled in the art may combine different embodiments or examples and features of different embodiments or examples described in the present disclosure to the extent that they are not mutually inconsistent.

[0128] In the description of the embodiments of the present disclosure, unless otherwise specified, " / " means "or", for example, A / B can mean either A or B. "And / or" in the present disclosure is merely for describing the related relationship of related objects, and indicates that three kinds of relationships may exist, for example, A and / or B can indicate the following three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0129] In the description of the embodiments of the present disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying a relative importance, nor should they be construed as implying a number of technical features shown. Thus, features defined as "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, "plurality" means two or more, unless otherwise specified.

[0130] The above are merely illustrative examples of the present disclosure, and are not intended to limit the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present disclosure should be included within the scope of protection of the present disclosure.

Claims

1. determining T full winding rates of a wound yarn package wound by a winding machine, where a t-th full winding rate among the T full winding rates is obtained based on N first characteristic parameters collected at a t-th time, a first characteristic parameter among the N first characteristic parameters is a characteristic parameter that can affect the full winding rate of the wound yarn package wound by the winding machine, T is a positive integer greater than or equal to 1, t is a positive integer greater than or equal to 1 and less than or equal to T, and N is a positive integer greater than or equal to 1; determining a candidate feature parameter set when it is determined that none of M full winding rates among the T full winding rates satisfy a preset full winding rate requirement, wherein the candidate feature parameters included in the candidate feature parameter set are feature parameters that cause the full winding rate to not satisfy the preset full winding rate requirement, selected from N first feature parameters corresponding to the full winding rates that do not satisfy the preset full winding rate requirement, and which cause the full winding rate to not satisfy the preset full winding rate requirement, and wherein M is a positive integer not less than 1 and not more than T. Parameter handling method.

2. Determining the full winding rate of T wound yarn packages wound by the winding machine includes: Executing a winding prediction step in response to the first detection command; When a preset time interval is reached, performing a next winding prediction step up to T times to obtain corresponding full winding rates of the winding machine at T different times; Here, the t-th winding prediction step is Obtaining N first characteristic parameters of the winding machine at a t-th time; and estimating and obtaining a t-th full winding rate of the wound yarn package wound by the winding machine based on the N first characteristic parameters at the t-th time. The parameter processing method according to claim 1 .

3. The step of estimating and obtaining the t-th full winding rate of the wound yarn package wound by the winding machine based on the N number of first characteristic parameters at the t-th time includes the steps of: inputting the N first characteristic parameters at the t-th time into a target winding prediction model to obtain at least a first prediction result corresponding to the t-th time output by a first branch of the target winding prediction model; Here, a first branch of the target winding prediction model is used to predict a full winding rate of the wound yarn package wound by the winding machine, and a first prediction result corresponding to the t-th time includes a first value representing a full winding rate of the wound yarn package wound by the winding machine obtained by prediction. The parameter processing method according to claim 2 .

4. The t-th winding prediction step includes: The method further includes, in the t-th winding prediction step, obtaining a second prediction result corresponding to the t-th time outputted by a second branch of the target winding prediction model when a first prediction result corresponding to the t-th time outputted by a first branch of the target winding prediction model is obtained, Here, the second branch of the target winding prediction model is used to predict the influence of each of the N first characteristic parameters on the full winding rate at the input t-th time, the second prediction result corresponding to the t-th time includes N second values, and an n-th element of the N second values ​​represents the influence of the n-th first characteristic parameter of the N first characteristic parameters on the full winding rate at the input t-th time. The parameter processing method according to claim 3.

5. Determining the candidate feature parameter sets comprises: Selecting second prediction results corresponding to M full winding rates that do not satisfy a preset full winding rate requirement from among the T second prediction results, where the T second prediction results are obtained after performing T winding prediction steps; Obtaining the candidate feature parameter set based on a second prediction result corresponding to M full winding rates that do not satisfy a preset full winding rate requirement.

5. The parameter processing method according to claim 4.

6. Obtaining the candidate feature parameter set based on a second prediction result corresponding to M full winding rates that do not satisfy the preset full winding rate requirement, Obtaining an initial set of M sets based on second prediction results corresponding to M full winding rates that do not satisfy a preset full winding rate requirement, wherein the initial set in the initial set of M sets includes a first characteristic parameter whose second value is greater than a preset value among the second prediction results corresponding to the full winding rates that do not satisfy the preset full winding rate requirement; selecting candidate feature parameters from the initial set of M to obtain a candidate feature parameter set; The parameter processing method according to claim 5.

7. Obtaining the candidate feature parameter set based on a second prediction result corresponding to M full winding rates that do not satisfy the preset full winding rate requirement, According to the second prediction results corresponding to the M full winding rates that do not satisfy the preset full winding rate requirement, a feature parameter matrix having M rows by N columns is obtained, where each row in the feature parameter matrix corresponds to N second values, and the second values ​​of the same first feature parameter corresponding to different full winding rates are located in the same column; performing a weighting process on columns in the feature parameter matrix to obtain a 1 row by N column vector representing N third values; and obtaining the candidate feature parameter set based on the 1 row by N column vector. The parameter processing method according to claim 5.

8. After determining the candidate feature parameter sets, the parameter processing method comprises: performing simulation and adjustment for each candidate feature parameter in the candidate feature parameter set; A new full winding rate of the yarn package wound by the winding machine is estimated based on at least each candidate characteristic parameter after the simulation and adjustment. When a new full winding ratio of the winding package wound by the winding machine satisfies a preset full winding ratio requirement, obtaining a target adjustment method. The parameter processing method according to claim 3.

9. The parameter processing method includes: generating first adjustment instructions based on the target adjustment method, the first adjustment instructions being used to instruct physically adjusting each candidate characteristic parameter in the candidate characteristic parameter set of the winding machine according to the target adjustment method; The parameter processing method according to claim 8.

10. The parameter processing method includes: and when a new full winding ratio of the wound yarn package wound by the winding machine does not satisfy a preset full winding ratio requirement, performing a new simulation and adjustment for each candidate characteristic parameter in the candidate characteristic parameter set to determine a new full winding ratio, and determining whether the new full winding ratio satisfies the preset full winding ratio requirement. The parameter processing method according to claim 8.

11. a result prediction unit for determining T full winding rates of a wound yarn package wound by a winding machine, where a t-th full winding rate among the T full winding rates is obtained based on N first characteristic parameters collected at a t-th time, a first characteristic parameter among the N first characteristic parameters is a characteristic parameter that can affect the full winding rate of the wound yarn package wound by the winding machine, T is a positive integer greater than or equal to 1, t is a positive integer greater than or equal to 1 and less than or equal to T, and N is a positive integer greater than or equal to 1; and a parameter determination unit for determining a candidate feature parameter set when it is determined that none of M full winding rates among the T full winding rates satisfy a preset full winding rate requirement, the candidate feature parameters included in the candidate feature parameter set are feature parameters that cause the full winding rate to not satisfy the preset full winding rate requirement, selected from N first feature parameters corresponding to the full winding rates that do not satisfy the preset full winding rate requirement, and the M is a positive integer not less than 1 and not more than T. Parameter processing device.

12. At least one processor; a memory in communication with the at least one processor; An electronic device, comprising: the memory storing instructions executable by the at least one processor, the instructions, when executed by the at least one processor, causing the at least one processor to perform a parameter processing method according to any one of claims 1 to 10.

13. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to carry out the parameter processing method of any one of claims 1 to 10.

14. A program for implementing the parameter processing method according to any one of claims 1 to 10 when executed by a processor in a computer.

Images