Zero-waste chest and waist structure fabric breadth intelligent prediction method based on maximization of discharge rate

Abstract

The invention relates to the field of intelligent clothing manufacturing and digital design, and particularly discloses a zero-waste chest and waist structure fabric breadth length intelligent prediction method based on maximization of a discharging rate. According to the method, a quantitative analysis model fusing cutting piece geometric area calculation, nesting gain and curved edge loss is constructed, a standardized input system containing style parameters, size data and fabric information is established, and an accurate fabric breadth length prediction result is automatically generated. According to the method, nesting benefits caused by different cutting piece numbers and efficiency loss caused by curved edge cutting pieces can be accurately quantified, accurate estimation of the discharging rate is achieved, and the defects that traditional artificial experience estimation is low in precision and poor in stability are effectively overcome. Practical verification shows that the average error of the predicted amplitude length is smaller than + / -2cm, the prediction error of the material arrangement rate is smaller than + / -0.5%, a scientific and reliable fabric consumption budgeting tool is provided for clothing enterprises, the material utilization rate is remarkably increased, and industrial production of zero-waste clothing is assisted.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of intelligent manufacturing and digital design of clothing, in particular to a zero-waste chest and waist structure fabric width intelligent prediction method based on maximum material utilization rate. BACKGROUND

[0002] In the industrial production process of clothing, material layout and cutting are the key link between design creativity and physical product. The core goal is to cut a complete set of clothing patterns with the smallest fabric consumption (i.e. the highest material utilization rate) on a given fabric width by optimizing the layout of the patterns. The efficiency of this process directly determines the material cost and material waste level of the product. For "zero-waste" clothing that pursues sustainable development, its design often adopts a unique chest and waist structure, with complex pattern shapes and more curved edges, and different from the pattern composition of traditional clothing, which makes its material layout more special and complex. The traditional material layout knowledge system relies on geometry, operations research and the long-term experience of craftsmen. The layout designer needs to consider various factors such as the geometric shape of the pattern, the texture direction of the fabric, the process of sewing, and the combination of sets, and repeatedly tries to layout within the limited width to seek an approximately optimal layout solution.

[0003] Currently, the prediction of fabric width mainly relies on two methods when making production plans and purchasing fabrics: one is to use experience analogy based on the average single consumption of similar styles in history; the other is to make a preliminary, small-scale paper layout or estimate by experience according to the style structure diagram. However, these existing methods have a significant defect: low prediction accuracy, poor stability and serious dependence on personal experience, which cannot quickly and accurately quantify the fabric consumption of "zero-waste" complex structure clothing before mass production. The experience analogy method ignores the specific differences in pattern shape, number of curved edges and nesting potential of different styles, while the manual estimation method is subject to the workload and state of the layout designer, resulting in large fluctuations and low repeatability. This defect directly leads to the dilemma faced by enterprises in actual production: if the budget is too conservative, production may be stalled due to insufficient fabric; if the budget is excessively conservative for safety, it will inevitably result in a large amount of fabric waste and capital occupation, which is contrary to the original intention of "zero-waste" design. SUMMARY

[0004] To solve the above technical problems, the present application provides a zero-waste chest and waist structure fabric width intelligent prediction method based on maximum material utilization rate, to solve the problem of low prediction accuracy and poor stability caused by relying on manual experience and rough estimation in the prior art, which cannot meet the precision requirements of material budgeting for zero-waste clothing production, resulting in low production efficiency and cost waste.

[0005] A method for intelligently predicting the fabric width of a zero-waste bust / waist structure based on maximizing material feed rate includes the following steps:

[0006] S1. Obtain the style parameters, size parameters, and fabric parameters of the target garment;

[0007] S2. Based on the modular design of the zero-waste bust and waist fitted structure, the garment pieces are classified and their areas are synthesized to obtain the area of ​​the main piece of a single garment.

[0008] S3. Based on the number of main pieces and the number of curved edge pieces, calculate the material feed rate gain brought by nested multiple pieces and the material feed rate loss brought by curved edge pieces, respectively.

[0009] S4. Combining the target feed rate, the feed rate gain, and the feed rate loss, calculate the predicted fabric width required to achieve the target feed rate.

[0010] Preferably, the feed rate gain increases with the increase of the number of feed sheets, but its marginal gain decreases.

[0011] Preferably, the material feed rate loss is positively correlated with the number of curved edge pieces. When the number of curved edge pieces exceeds a preset benchmark value, loss begins to occur.

[0012] Preferably, when calculating the predicted fabric width, a fabric layout correction term based on the production set quantity and size combination type is also introduced.

[0013] Preferably, the modular design includes at least a yoke, a seven-piece bust and waist structure, a skirt, and decorative supplementary modules, and the area of ​​the main piece is composed of the cut pieces area of ​​each module.

[0014] Preferably, the method is applicable to various garment styles produced using a unified grading rule under a zero-waste chest and waist fitted core structure.

[0015] A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method as described above.

[0016] A fabric width intelligent prediction system includes a memory and a processor. The memory stores a computer program, and the processor executes the program to implement the method described above.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] By transforming complex fabric shapes, layout rules, and material properties into calculable mathematical relationships, i.e., by inputting style parameters and production plans, high-precision length prediction values ​​can be automatically output. This enables companies to obtain scientific and reliable data support when purchasing fabrics and developing cutting plans, thus avoiding material waste or production interruptions caused by inaccurate budgets from the source, and laying a solid technical foundation for achieving the goal of "zero waste" production.

[0019] By introducing a nested gain function driven by the number of cut pieces and a layout loss function driven by the number of curved cut pieces, the model can accurately capture the core dynamic factors affecting layout efficiency. The nested gain function simulates the material saving effect brought about by the nested arrangement of multiple cut pieces, while the curved loss function quantifies the unavoidable efficiency loss when dealing with complex curved cut pieces. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating the method of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] like Figure 1 As shown:

[0023] Example 1: A method for intelligent prediction of fabric width of zero-waste bust and waist structure based on maximizing material feed rate, comprising the following steps:

[0024] Parameter input and area synthesis: Obtain garment style parameters (such as style code, total number of cut pieces) Number of curved edge pieces Size parameters (chest circumference) ,waistline ) and fabric parameters (width) Target discharge rate Planned production quantity Based on a modular design with a zero-waste bust and waist fitted structure, the fabric pieces are categorized into modules such as the bust yoke, the seven-piece bust and waist structure, the skirt, and decorative patches, and then combined to form the total area of ​​a single garment's main piece. .

[0025] Discharge rate efficiency correction: The target discharge rate is adjusted to reflect the complex factors in actual discharge. The corrected expected discharge rate is... Calculated using the following model:

[0026]

[0027] in:

[0028] Based on the number of production sets The material layout correction item for size combination type (same size or mixed size).

[0029] It is a nested gain function, representing the improvement in material layout efficiency brought about by the nested arrangement of multiple fabric pieces. This gain increases with the number of fabric pieces. It increases with the increase of [something], but the marginal gain decreases, and its specific form is as follows:

[0030]

[0031] In the formula, and These are the model parameters determined by fitting historical data. The baseline number of clips to start generating nested gain.

[0032] This is the edge loss function, which characterizes the loss in material layout efficiency caused by the presence of curved edges in the cut pieces. This loss is related to the number of curved edge cut pieces. Positive correlation, specifically in the form of:

[0033]

[0034] In the formula, These are the model parameters determined by fitting historical data. The baseline number of curved edge pieces used to begin inducing curved edge loss. Indicates taking The larger of 0.

[0035] Fabric width prediction calculation: Substitute the composite area and the corrected cut-out ratio into the fabric width calculation formula to obtain the minimum fabric width prediction value required to achieve the target cut-out ratio. :

[0036]

[0037] This forecast can be directly used to guide the optimization of fabric procurement, cutting, and layout schemes.

[0038] Application Example 1: This application example uses a specific garment—a strapless maxi dress (CY2)—to demonstrate the specific application process of the method of the present invention.

[0039] S1: Parameter Input and Initialization

[0040] First, retrieve the parameters of the target style "CY2" from the pre-stored clothing style library and input the production plan:

[0041] Style parameters:

[0042] Number of CEO films ;

[0043] Number of curved edge pieces ;

[0044] Size parameters: This production is size M, chest circumference ,waistline .

[0045] Fabric and production parameters:

[0046] Fabric width ;

[0047] Target discharge rate (i.e., 95%)

[0048] Planned production quantity ;

[0049] Size combination type: Same size (i.e., all 3 sets are size M);

[0050] At the same time, the system calls the model parameters that have been pre-fitted using historical data:

[0051] Nested gain parameters: ;

[0052] Curved edge loss parameters: ;

[0053] Standard number of cut pieces: ;

[0054] Baseline number of curved edge cut pieces: ;

[0055] S2: Calculation of area for a single set of president's films

[0056] The system is based on the modular structure of the CY2 style (top yoke, seven-piece bust and waist structure, skirt, etc.), combined with the size M ( Using a pre-stored geometric area model, the area of ​​the executive piece for a single garment is calculated and synthesized.

[0057]

[0058] (This value is derived from actual data of CY2 and is one of the core inputs for model calculation.)

[0059] S3: Discharge Rate Efficiency Correction Calculation

[0060] The system calculates the corrected expected discharge rate based on the parameters in S1.

[0061] Calculate nested gain:

[0062]

[0063] Due to the number of pieces Less than the benchmark value Nested gain is a small positive value.

[0064] Calculate the curved edge loss:

[0065]

[0066] The number of curved edge pieces is equal to the baseline value, so the waste is zero.

[0067] Determine the number of sets and correct mixed numbers:

[0068] According to the pre-stored rule table, for The "same number" layout of the set was checked and correction items were found. .

[0069] Calculate the expected discharge rate:

[0070]

[0071] That is, the expected discharge rate is 97.16%.

[0072] S4: Fabric Length Prediction Calculation

[0073] Substituting the above results into the amplitude prediction formula:

[0074]

[0075] The system output prediction result is: the required fabric length is approximately 374.5 cm.

[0076] S5: Results Verification and Effects

[0077] Based on actual production data, the actual width used for the CY2 style, under the same size conditions, is... .

[0078] Amplitude prediction error: The error rate is only -0.65%.

[0079] Discharge rate prediction result: In this application example, the predicted discharge rate is 97.16%, while the actual discharge rate is 96.3%, and the predicted value is highly consistent with the actual value.

[0080] Conclusion: This method can accurately predict the required fabric width for production based on the structural parameters of clothing through a quantitative model. The prediction error is small, which fully meets the accuracy requirements for material budgeting and cost control in industrial production, and provides a reliable technical tool for achieving "zero waste" production.

[0081] Application Example 2: This application example takes the "mixed sizes" production of the flower bud dress (CY3) as an example to further demonstrate the application process of the method of the present invention under different parameter conditions.

[0082] S1: Parameter Input and Initialization

[0083] Call the parameters for the target style "CY3" and enter the mixed-number production plan:

[0084] Style parameters:

[0085] Number of CEO films ;

[0086] Number of curved edge pieces ;

[0087] Size parameters: This production is a mixed size (one set each of S, M, and L sizes). Sizes are calculated using the corresponding average chest and waist measurements, or calculated separately and then summed. For simplicity, the area composite result is used here.

[0088] Fabric and production parameters:

[0089] Fabric width ;

[0090] Target discharge rate (i.e., 95%)

[0091] Planned production quantity ;

[0092] Size combination type: Mixed sizes (S+M+L);

[0093] At the same time, the system calls the model parameters that have been pre-fitted using historical data:

[0094] Nested gain parameters: ;

[0095] Curved edge loss parameters: ;

[0096] Standard number of cut pieces: ;

[0097] Baseline number of curved edge cut pieces: ;

[0098] S2: Calculation of area for a single set of president's films

[0099] The system calculates and synthesizes the geometric area based on the modular structure of the CY3 style. Since it uses mixed-size layouts, the area of ​​a single set is taken as the average of all sizes, or the equivalent area corresponding to the mixed-size layout is directly used. Based on model calculations and data calibration:

[0100]

[0101] S3: Discharge Rate Efficiency Correction Calculation

[0102] Calculate nested gain:

[0103]

[0104] Number of pieces Slightly larger than the baseline value This results in a positive nesting gain.

[0105] Calculate the curved edge loss:

[0106]

[0107] Number of curved edge pieces Less than the benchmark value By definition, the loss on curved edges is zero.

[0108] Determine the number of sets and correct mixed numbers:

[0109] for When using mixed-number layouts, the layout rate is usually slightly lower than that of layouts with the same number, according to pre-stored rules. A correction item is set. .

[0110] Calculate the expected discharge rate:

[0111]

[0112]

[0113] That is, the expected discharge rate is 94.37%.

[0114] S4: Fabric Length Prediction Calculation

[0115] Substituting the above results into the amplitude prediction formula:

[0116]

[0117] The system output prediction result is: the required fabric length is approximately 292.1 cm.

[0118] S5: Results Verification and Effects

[0119] According to verification data, the actual width of the CY3 style used in mixed-size cases is... Actual discharge rate .

[0120] Length prediction error: In this application example, the predicted value is 292.1cm, which differs from the actual value of 283.73cm by +8.37cm. It should be noted that this error is slightly larger than that in application example one, reflecting the significant impact of the randomness and complexity of size combinations in mixed-size layout on the layout rate, and also indicating that the model has room for further optimization in extreme cases.

[0121] Material layout rate prediction analysis: In this application example, the predicted material layout rate was 94.37%, while the actual rate reached 97.2%. This indicates that in actual mixed-number material layout, the nesting effect exceeded the basic expectations of the model through the optimization operation of the material layout engineer. This difference can be used for subsequent iterative optimization of model parameters.

[0122] Conclusion: This application example demonstrates the application of the method of the present invention in a more complex "mixed-number" production scenario. Although the prediction accuracy fluctuates compared to "same-number" production, the model still provides a reasonable amplitude estimate and successfully predicts that the efficiency of mixed-number material layout will be lower than that of same-number material layout. This proves that the method of the present invention has strong robustness and wide applicability, and can provide a scientific decision-making basis for different types of production plans.

[0123] The embodiments of the present invention are given for the purposes of illustration and description. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Any changes, modifications, substitutions and variations made by those skilled in the art to the above embodiments within the scope of the present invention should be included within the protection scope of the present invention.

Claims

1. A zero-waste chest and lumbar structural fabric web length intelligent prediction method based on maximum discharge rate, characterized by, The method comprises the following steps: S1, obtaining style parameters, size parameters and fabric parameters of a target garment; S2, based on the modular design of the zero-waste chest and waist combined structure, classifying and area synthesizing the garment patterns to obtain the total pattern area of a single garment; S3, calculating the nesting gain of multiple patterns and the nesting loss of curved patterns according to the total pattern number and the curved pattern number; S4, synthesizing the target nesting rate, the nesting gain and the nesting loss to calculate the fabric width prediction value required to achieve the target nesting rate.

2. The method of claim 1, wherein, The nesting gain increases with the increase of the total pattern number, but the marginal gain decreases.

3. The method of claim 1, wherein, The nesting loss is positively correlated with the number of curved patterns, and starts to produce loss when the number of curved patterns exceeds a preset reference value.

4. The method of claim 1, wherein, When calculating the fabric width prediction value, a nesting rate correction term based on the production set number and size combination type is introduced.

5. The method of claim 1, wherein, The modular design at least includes a chest and back panel, a seven-piece chest and waist structure, a lower skirt and a decoration and supplementary module, and the total pattern area is synthesized by the pattern area of each module.

6. The method of claim 1, wherein, The method is suitable for various garment styles produced by using a unified cutting rule under the zero-waste chest and waist combined core structure.

7. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of claims 1 to 6.

8. A fabric width intelligent prediction system comprising a memory and a processor, the memory storing a computer program, and the processor implementing the method of any one of claims 1 to 6 when executing the program.

Images