Material consumption analysis method based on textile technology

Abstract

The invention discloses a material consumption analysis method based on a textile technology, and relates to the technical field of textile. The method comprises the following steps: reading a predetermined analysis dimension, and carrying out feature collection on a textile process to obtain textile process feature parameters; comparing the target process characteristic parameter with a first historical process characteristic parameter to obtain a first comparison result; when a first process similarity obtained by analyzing the first comparison result reaches a similarity limit value, extracting a first historical material consumption record; matching a first material use amount of a first material use type in the plurality of types of materials in the plurality of material use amounts, and generating a first material use amount time sequence; analyzing the first material consumption time sequence to obtain a first predicted material consumption; and generating a material consumption prediction result of the textile process based on a first corresponding relationship between the first predicted material amount and the first material type. The technical problem that the textile process material consumption is difficult to accurately predict in the prior art is solved, and the technical effect of improving the accuracy of textile process material consumption prediction is achieved.

Description

Technical Field

[0001] The invention relates to the field of textile technology, and in particular to a material consumption analysis method based on textile technology. Background Art

[0002] In the textile industry, material consumption analysis has always been a key factor affecting production efficiency, cost control and product quality. With the intensification of market competition and the diversification of consumer demand, textile companies are faced with the challenges of improving production efficiency, reducing production costs and ensuring product quality. However, due to the complexity and variability of textile processes, the types, amounts and proportions of raw materials used in the production process of different textiles are different, which brings great difficulties to material consumption analysis. Traditional material consumption analysis methods often rely on empirical estimates and simple data statistics, which are difficult to accurately reflect the material consumption of textile processes, and cannot effectively predict future material consumption. This leads to problems in inventory management for enterprises, such as inventory backlogs or shortages, which in turn affects the execution of production plans and the guarantee of delivery dates. Summary of the invention

[0003] The embodiment of the present application provides a material consumption analysis method based on textile technology, which solves the technical problem in the prior art that it is difficult to accurately predict the material consumption of textile technology.

[0004] In view of the above problems, an embodiment of the present application provides a material consumption analysis method based on textile technology.

[0005] The present application embodiment provides a material consumption analysis method based on a textile process, the method comprising: Read a predetermined analysis dimension, and collect characteristics of a textile process based on the predetermined analysis dimension to obtain textile process characteristic parameters; compare the target process characteristic parameters in the textile process characteristic parameters with the first historical process characteristic parameters in the first historical textile record to obtain a first comparison result, wherein the first historical textile record represents any historical textile record of the same type of textile of the textile process; when the first process similarity obtained by analyzing the first comparison result reaches a similarity limit, extract the first historical material consumption record in the first historical textile record, wherein the first historical material consumption record includes multiple material quantities of multiple material categories; match the first material quantity of a first material category among the multiple material categories among the multiple material quantities, and generate a first material quantity time series in combination with a predetermined unit period; call a consumption integrated prediction model to analyze the first material quantity time series to obtain a first predicted material quantity, wherein the first predicted material quantity refers to the predicted value of the first material category consumed by the textile process at the first time; based on the first corresponding relationship between the first predicted material quantity and the first material category, generate a material consumption prediction result for the textile process.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, a predetermined analysis dimension is read, and characteristics of the textile process are collected based on the predetermined analysis dimension to obtain textile process characteristic parameters. Then, the target process characteristic parameters in the textile process characteristic parameters are compared with the first historical process characteristic parameters in the first historical textile record to obtain a first comparison result, and the first historical textile record represents any historical textile record of the same type of textile of the textile process. When the first process similarity obtained by analyzing the first comparison result reaches the similarity limit, the first historical material consumption record in the first historical textile record is extracted, and the first historical material consumption record includes multiple material quantities of multiple types of materials. Then, the first material quantity of the first material class in the multiple types of materials is matched among the multiple material quantities, and the first material quantity time series is generated in combination with the predetermined unit period. The first material quantity time series is analyzed by calling the consumption integrated prediction model to obtain the first predicted material quantity, and the first predicted material quantity refers to the predicted value of the textile process consuming the first material class at the first time. Finally, based on the first corresponding relationship between the first predicted material quantity and the first material class, the material consumption prediction result of the textile process is generated. The invention solves the technical problem that it is difficult to accurately predict the consumption of textile process materials in the prior art, and achieves the technical effect of improving the accuracy of the prediction of the consumption of textile process materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A schematic diagram of a material consumption analysis method based on a textile process provided in an embodiment of the present application; Figure 2 A schematic flow chart of obtaining the first process similarity in the material consumption analysis method based on textile process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The embodiment of the present application solves the technical problem in the prior art that it is difficult to accurately predict the material consumption of the textile process by providing a material consumption analysis method based on the textile process.

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0011] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices. Embodiment 1

[0012] like Figure 1 As shown, the embodiment of the present application provides a material consumption analysis method based on a textile process, wherein the method includes: The predetermined analysis dimension is read, and characteristics of the textile process are collected based on the predetermined analysis dimension to obtain characteristic parameters of the textile process.

[0013] In the material consumption analysis of textile technology, it is necessary to read the predetermined analysis dimensions, which include material dimension and process dimension. The material dimension includes the raw material type, fiber composition, yarn specifications of textiles, etc., and the process dimension includes textile process steps, machine type, process parameters (such as tension, speed, temperature, etc.). Collect characteristics of textile technology according to the predetermined analysis dimensions, that is, collect the raw material types of textiles according to the material dimension, such as cotton, linen, silk, synthetic fibers, etc., determine the fiber composition and its proportion, and the specifications of yarns, such as count, twist, etc.; obtain the process of textile technology according to the process dimension, the type of machine used, such as looms, knitting machines, etc., and collect process parameters, such as the tension and speed of looms, the number of needles and needle length of knitting machines, and then obtain the characteristic parameters of textile technology.

[0014] The target process characteristic parameters in the textile process characteristic parameters are compared with the first historical process characteristic parameters in the first historical textile record to obtain a first comparison result, wherein the first historical textile record represents any historical textile record of the same type of textile of the textile process.

[0015] From the collected textile process characteristic parameters, select the target process characteristic parameters closely related to the target analysis, including machine model, process steps, key process parameters (such as tension, speed, temperature, etc.) and material type, etc. The first historical textile record refers to any historical textile record of the same type as the current textile process, that is, the material and textile type are the same, such as knitting cotton wool. From the first historical textile record, extract the historical process characteristic parameters corresponding to the current target process characteristic parameters, namely the first historical process characteristic parameters. Compare the current target process characteristic parameters with the extracted first historical process characteristic parameters, such as directly comparing parameter values, calculating parameter difference rates or performing similarity measurement, to obtain a first comparison result.

[0016] When the first process similarity obtained by analyzing the first comparison result reaches the similarity limit, the first historical material consumption record in the first historical textile record is extracted, and the first historical material consumption record includes multiple material quantities of multiple types of materials.

[0017] After comparative analysis, if the first process similarity (i.e., the degree of similarity between the target textile process and the first historical textile record) reaches the preset similarity limit, it means that the two have a high degree of similarity in process. According to the comparison result, the first historical textile record similar to the current textile process is located, and from the first historical textile record, the material consumption data corresponding to the first historical textile record is extracted, i.e., the first historical material consumption record. The first historical material consumption record contains multiple material quantities of multiple types of materials used in the historical textile process.

[0018] Furthermore, if Figure 2 As shown, obtaining the first process similarity includes: Read a predetermined process label scheme; perform label processing on the target process characteristic parameters and the first historical process characteristic parameters in turn according to the predetermined process label scheme to obtain a target process label and a first historical process label, respectively; compare and analyze the target process label and the first historical process label to obtain the first comparison result; obtain the first process similarity of the first comparison result based on the principle of Tanimoto similarity coefficient algorithm.

[0019] Preferably, a predetermined process label scheme is read, and the predetermined process label scheme defines the conversion of process characteristic parameters into comparable labels. According to the predetermined process label scheme, the target process characteristic parameters (i.e., the characteristic parameters of the current textile process) are labeled, including data cleaning, standardization, classification, and label assignment, etc., to ensure that each characteristic parameter is correctly converted into a corresponding label, and the processed label is called the target process label. Similarly, according to the predetermined process label scheme, the process characteristic parameters in the first historical textile record are labeled, and these historical parameters will obtain the first historical process label after processing. The target process label and the first historical process label are compared and analyzed. Since the label has been standardized, the label value can be directly compared or the similarity calculation can be performed to find the similarity and difference between the current process and the historical process. Based on the principle of the Tanimoto similarity coefficient algorithm, the similarity between the target process label and the first historical process label is calculated. In the process characteristic parameter comparison, the label can be regarded as an element in a set, and the Tanimoto similarity coefficient, i.e., the first process similarity, is obtained by calculating the intersection and union size of the labels.

[0020] Furthermore, it also includes: Extract target material characteristic parameters from the textile process characteristic parameters; perform weighted analysis on the target material characteristic parameters to obtain a target material quality index; use the target material quality index as a similarity adjustment coefficient to perform weighted calculation adjustment on the first process similarity to obtain a first process similarity adjustment result.

[0021] In the comparative analysis of textile processes, the process similarity is further adjusted by extracting the characteristic parameters of the target materials and calculating the target material quality index. Specifically, from the characteristic parameters of the textile process, the characteristic parameters of the target materials related to the material characteristics are screened out, including fiber type, fiber component ratio, yarn count, yarn twist, etc.; according to the importance of each target material characteristic parameter to the quality of the textile process, different weights are assigned in combination with expert experience, historical data or the degree of influence in actual production; each target material characteristic parameter is quantitatively scored, or normalized using existing standard values, and then the score of each parameter is multiplied by its corresponding weight to obtain a weighted material quality score, and all weighted material quality scores are summed to obtain the target material quality index, which reflects the comprehensive performance of the current textile process in terms of material quality; the target material quality index is used as a similarity adjustment coefficient to perform weighted calculation adjustment on the first process similarity, such as multiplying the first process similarity with the target material quality index to obtain the first process similarity adjustment result, or performing linear interpolation between the original similarity and the target material quality index to obtain the adjusted similarity. The first process similarity adjustment result not only considers the similarity of process parameters, but also considers the influence of material properties on process similarity, and is therefore more comprehensive and accurate.

[0022] Furthermore, the target material characteristic parameters include fiber lengths and fiber proportions of multiple fiber material types.

[0023] The target material characteristic parameters include the fiber length and fiber proportion of multiple fiber material types. Among them, fiber length is an important physical property of fiber, which directly affects the processing performance, yarn quality and fabric style of the fiber. Different fiber materials have different lengths. For example, the length of cotton fiber is generally between 25 and 35 mm, while the length of wool fiber may be longer. Generally speaking, the longer the length, the less textile waste. Fiber proportion refers to the proportion of different fiber materials in textile materials. This proportion determines the overall performance and use of the material. The higher the fiber proportion of fiber types with good weaving performance and long length, the less corresponding textile waste.

[0024] The first material quantity of the first material category among the multiple material categories is matched among the multiple material quantities, and a first material quantity timing sequence is generated in combination with a predetermined unit period.

[0025] From multiple material quantities, filter out the material quantities corresponding to the first material category, i.e., the first material quantities, and sort the first material quantities in chronological order to ensure that each data point corresponds to a clear timestamp. According to the predetermined unit period, divide the data points of the first material quantity into different time periods. For example, if the predetermined unit period is weekly, then it is necessary to group the first material quantity data by week, and then generate the first material quantity time series, which reflects the changing trend of the material quantity over time.

[0026] The consumption integrated prediction model is called to analyze the first material quantity time series to obtain a first predicted material quantity, where the first predicted material quantity refers to the predicted value of the first material type consumed by the textile process at the first time.

[0027] The first material quantity time series is analyzed by calling the consumption integrated prediction model to obtain the first predicted material quantity, which refers to the predicted value of the first material category consumed by the textile process at the first time. Specifically, according to the historical material data, the machine learning model is trained, and the consumption integrated prediction model is obtained after the training is completed; the first material quantity time series is input into the consumption integrated prediction model, and the consumption integrated prediction model will predict the first material quantity at a given time (the first time), and output the first predicted material quantity, which refers to the amount of the first material category that the textile process is expected to consume at the first time.

[0028] Further, including: Obtain a first prediction layer in the consumption integrated prediction model, and store a first fitting polynomial of the first material usage time series into the first prediction layer; input the first time into the first prediction layer to obtain a first prediction value; obtain a second prediction layer in the consumption integrated prediction model; input a first time series feature set of the first material usage time series collected based on predetermined multi-domain features into the second prediction layer to obtain a second prediction value; record the average of the first prediction value and the second prediction value as the first predicted material usage.

[0029] A first prediction layer is extracted from the consumption integrated prediction model. The first prediction layer is a polynomial fitting model based on historical data, which is used to capture the basic trend in the first material usage time series. The first fitting polynomial (i.e., polynomial coefficient) of the first material usage time series is stored in the first prediction layer. The first fitting polynomial can be fitted by a time series analysis method (such as the least squares method). The first time (i.e., the time point to be predicted) is input into the first prediction layer. The first time is polynomially calculated using the stored first fitting polynomial to obtain a first prediction value. A second prediction layer is obtained from the consumption integrated prediction model. The second prediction layer is constructed based on a machine learning or deep learning algorithm to capture complex patterns and influencing factors other than the basic trend in the first material usage time series. Based on predetermined multi-domain features, feature data related to the first material usage time series are collected and constructed into a first time series feature set. The first time series feature set can fully reflect various factors affecting the first material usage time series. The first time series feature set is input into the second prediction layer. The second prediction layer will use these feature data, combined with its internal machine learning or deep learning algorithm, to perform complex pattern recognition and prediction, thereby obtaining a second prediction value. The average of the first predicted value and the second predicted value is taken as the final first predicted material quantity. This average combines the first predicted value based on historical data trends and the second predicted value based on multi-domain features, thereby improving the accuracy and robustness of the prediction results.

[0030] Further, including: Draw a first material amount scatter plot of the first material amount time series; obtain a first material amount spline curve of the first material amount scatter plot based on the principle of random sampling consistency; perform polynomial fitting regression analysis on the first material amount spline curve to obtain the first fitting polynomial.

[0031] Preferably, the first material quantity time series includes a timestamp and a corresponding material quantity value, and a data visualization tool (such as Excel, Python's matplotlib library, etc.) is used to draw a first material quantity scatter plot of the first material quantity time series; random sampling consistency is an iterative method for estimating parameters of a mathematical model from a data set containing outliers, and a first material quantity spline curve is extracted from the first material quantity scatter plot based on the principle of random sampling consistency. Specifically, a portion of data points are randomly selected from the first material quantity scatter plot as support points of the initial spline curve, and a spline curve is fitted using these support points. The distances from all data points to the fitted curve are calculated, and the number of points whose distances are less than the error threshold is counted. If the termination condition is met (such as reaching the maximum number of iterations or finding enough inliers), the iteration is stopped, and the spline curve with the largest number of inliers or the smallest average error is selected from all iterations as the final result. A polynomial fitting regression analysis is performed on the first material quantity spline curve. The appropriate polynomial order is selected according to the complexity and requirements of the data. The data points on the spline curve are fitted to a polynomial function using the least squares method. The sum of squares of the residuals between the fitting polynomial and the data points is calculated to evaluate the fitting effect. The final polynomial function is the first fitting polynomial, which describes the trend and change pattern of the first material quantity time series.

[0032] Furthermore, the predetermined multi-domain features include predetermined time domain features, predetermined frequency domain features and predetermined component features, and the predetermined component features refer to features of the optimal material quantity component.

[0033] The predetermined multi-domain features include predetermined time domain features, predetermined frequency domain features, and predetermined component features. The predetermined time domain features describe the law of data changes over time. In material consumption forecasting, the predetermined time domain features may include time series data of historical material consumption, such as daily consumption, weekly consumption, monthly consumption, etc. By analyzing these time series data, the seasonal, cyclical or trend changes in material consumption can be captured. The predetermined frequency domain features describe the characteristics of the data in the frequency domain. For periodic or periodically changing material consumption data, frequency domain analysis can provide information about different frequency components. The predetermined frequency domain features may include the results of spectrum analysis, such as spectrum diagrams, power spectrum density, etc. These features help to identify the dominant frequency components in the material consumption data. The predetermined component characteristics refer to the characteristics of the optimal material quantity components. In the textile process, the optimal material quantity components may refer to the minimum material quantity required under the premise of meeting product quality and production efficiency. The predetermined component characteristics may include various parameters related to the optimal material quantity, such as the optimal material quantity ratio, the optimal material quantity distribution pattern, the optimal material quantity adjustment factor, etc. These characteristics can be determined through historical data analysis and expert knowledge, and are used to guide the adjustment and optimization of the material quantity in the production process. In short, the predetermined time domain characteristics and the predetermined frequency domain characteristics describe the characteristics of the data in the time and frequency domains, respectively, which help to capture the changing trend and periodic changes of the material quantity; the predetermined component characteristics specifically refer to the characteristics related to the optimal material quantity components, which are of great significance for guiding the adjustment and optimization of the material quantity in the production process.

[0034] Further, including: The first material quantity time series is subjected to modal decomposition processing by a multi-domain analyzer to obtain a plurality of material quantity components; multi-dimensional component features of the first material quantity component among the plurality of material quantity components are collected to obtain a first material quantity component feature set; when the deviation between the first material quantity component feature set and the material quantity feature of the first material quantity time series reaches a deviation limit, the first material quantity component is recorded as the optimal material quantity component.

[0035] By performing modal decomposition processing on the first material quantity time series through a multi-domain analyzer, different material quantity change patterns can be identified, and then multiple material quantity components can be obtained. Specifically, according to the characteristics of the data, a suitable modal decomposition method is selected, such as empirical mode decomposition (EMD), variational mode decomposition (VMD) or Fourier decomposition, etc., and the selected decomposition method is applied to decompose the first material quantity time series to obtain multiple material quantity components. Multi-dimensional component features are collected for the first material quantity component among the multiple material quantity components obtained by decomposition, including time domain features, frequency domain features or other statistical features, which can describe different aspects of the first material quantity component. Specifically, appropriate features are selected according to actual needs and data characteristics. For example, time domain features may include mean, variance, maximum value, minimum value, etc.; frequency domain features may include spectrum distribution, main frequency, etc., and the selected features are extracted from the first material quantity component to form a feature set of the first material quantity component. Compare the deviation between the first material quantity component feature set and the material quantity feature of the first material quantity time series to determine whether the deviation limit is reached, and if the deviation reaches or exceeds the limit, record the first material quantity component as the optimal material quantity component. Specifically, calculate the deviation between the first material quantity component feature set and the material quantity feature of the first material quantity time series, and compare the calculated deviation with the preset deviation limit, wherein the deviation limit can be set according to actual needs and data characteristics, and if the deviation reaches or exceeds the limit, record the first material quantity component as the optimal material quantity component.

[0036] Based on the first corresponding relationship between the first predicted material quantity and the first material category, a material consumption prediction result of the textile process is generated.

[0037] Based on the first corresponding relationship between the first predicted material quantity and the first material class, the predicted material quantity of each first material class is calculated, and then the material consumption prediction result of the textile process is generated.

[0038] In summary, the embodiments of the present application have at least the following technical effects: First, a predetermined analysis dimension is read, and characteristics of the textile process are collected based on the predetermined analysis dimension to obtain textile process characteristic parameters. Then, the target process characteristic parameters in the textile process characteristic parameters are compared with the first historical process characteristic parameters in the first historical textile record to obtain a first comparison result, and the first historical textile record represents any historical textile record of the same type of textile of the textile process. When the first process similarity obtained by analyzing the first comparison result reaches the similarity limit, the first historical material consumption record in the first historical textile record is extracted, and the first historical material consumption record includes multiple material quantities of multiple types of materials. Then, the first material quantity of the first material class in the multiple types of materials is matched among the multiple material quantities, and the first material quantity time series is generated in combination with the predetermined unit period. The first material quantity time series is analyzed by calling the consumption integrated prediction model to obtain the first predicted material quantity, and the first predicted material quantity refers to the predicted value of the textile process consuming the first material class at the first time. Finally, based on the first corresponding relationship between the first predicted material quantity and the first material class, the material consumption prediction result of the textile process is generated. The invention solves the technical problem that it is difficult to accurately predict the consumption of textile process materials in the prior art, and achieves the technical effect of improving the accuracy of the prediction of the consumption of textile process materials.

[0039] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0040] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0041] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A material consumption analysis method based on textile technology, characterized in that: The method comprises: Reading a predetermined analysis dimension, and collecting characteristics of the textile process based on the predetermined analysis dimension to obtain characteristic parameters of the textile process; Comparing the target process characteristic parameter in the textile process characteristic parameter with the first historical process characteristic parameter in the first historical textile record to obtain a first comparison result, wherein the first historical textile record represents any historical textile record of the same type of textile of the textile process; When the first process similarity obtained by analyzing the first comparison result reaches a similarity limit, extracting a first historical material consumption record in the first historical textile record, wherein the first historical material consumption record includes a plurality of material amounts of a plurality of types of materials; Matching a first material quantity of a first material category among the multiple material categories among the multiple material quantities, and generating a first material quantity time sequence in combination with a predetermined unit period; Calling the consumption integrated prediction model to analyze the first material quantity time series to obtain a first predicted material quantity, where the first predicted material quantity refers to a predicted value of the first material type consumed by the textile process at a first time; Based on the first corresponding relationship between the first predicted material quantity and the first material category, a material consumption prediction result of the textile process is generated.

2. The material consumption analysis method based on textile technology according to claim 1 is characterized in that: include: Read the predetermined process label solution; According to the predetermined process labeling scheme, labeling is performed on the target process characteristic parameters and the first historical process characteristic parameters in sequence to obtain a target process label and a first historical process label respectively; Comparing and analyzing the target process label and the first historical process label to obtain the first comparison result; The first process similarity of the first comparison result is obtained based on the Tanimoto similarity coefficient algorithm principle.

3. The material consumption analysis method based on textile technology according to claim 1 is characterized in that: include: Extracting target material characteristic parameters from the textile process characteristic parameters; Weighted analysis of the target material characteristic parameters to obtain a target material quality index; The target material quality index is used as a similarity adjustment coefficient to perform weighted calculation and adjustment on the first process similarity to obtain a first process similarity adjustment result.

4. The material consumption analysis method based on textile technology according to claim 3 is characterized in that: The target material characteristic parameters include fiber lengths and fiber proportions of multiple fiber material types.

5. The material consumption analysis method based on textile technology according to claim 1 is characterized in that: include: Acquire a first prediction layer in the consumption integrated prediction model, and store a first fitting polynomial of the first material usage time series in the first prediction layer; Inputting the first time into the first prediction layer to obtain a first prediction value; Obtaining a second prediction layer in the consumption integrated prediction model; Inputting the first time series feature set of the first material usage time series collected based on the predetermined multi-domain features into the second prediction layer to obtain a second prediction value; The average of the first predicted value and the second predicted value is recorded as the first predicted material quantity.

6. The material consumption analysis method based on textile technology according to claim 5 is characterized in that: include: Draw a scatter plot of the first material amount of the first material amount time series; Obtaining a first material amount spline curve of the first material amount scatter diagram based on the principle of random sampling consistency; Performing polynomial fitting regression analysis on the first material amount spline curve to obtain the first fitting polynomial.

7. The material consumption analysis method based on textile technology according to claim 5 is characterized in that: The predetermined multi-domain features include predetermined time domain features, predetermined frequency domain features and predetermined component features, and the predetermined component features refer to features of the optimal material quantity component.

8. The material consumption analysis method based on textile technology according to claim 7 is characterized in that: include: Performing modal decomposition processing on the first material amount time series by a multi-domain analyzer to obtain a plurality of material amount components; Collect multi-dimensional component features of a first material quantity component among the multiple material quantity components to obtain a first material quantity component feature set; When the deviation between the first material quantity component feature set and the material quantity feature of the first material quantity time series reaches a deviation limit, the first material quantity component is recorded as the optimal material quantity component.

Images