Konjac mixed line production-oriented production line management method and system

Abstract

This invention discloses a production line management method and system for mixed-production konjac konjac lines, relating to the field of production process control technology. The method includes: when switching konjac production lines, collecting initial konjac production characteristics of the initial konjac product before the switch; based on the initial konjac production characteristics, performing a performance impact analysis of the mixing and stirring process within the konjac production line to obtain performance impact parameters; acquiring the switched konjac production characteristics of the konjac product after the switch, and optimizing the control and management parameters of the mixing and stirring process after the production line switch based on the performance impact parameters to obtain optimal control and management parameters. The control and management parameters are optimized based on weights assigned to the switched konjac production characteristics. This invention solves the technical problem in the prior art where mixed-production konjac lines affect the quality of konjac products.

Description

Technical Field

[0001] This invention relates to the field of production process control technology, specifically to a production line management method and system for mixed-line production of konjac. Background Technology

[0002] Konjac foods, as an important health food, are often produced using a mixed-line production method, where different types or formulas of konjac products are produced sequentially on the same production line to meet diverse demands. In existing technologies, konjac production lines rely primarily on fixed or empirical control parameters to adjust key processes such as mixing and stirring when switching between different products, for example, setting uniform temperature parameters. However, this extensive management approach has significant drawbacks: residual equipment conditions accumulated during the production of preceding products, such as the temperature inside the mixing tank, directly alter the performance of the mixing process. Existing technologies fail to effectively quantify these effects, leading to unreasonable control parameter settings after product switching. Specifically, the production characteristics of preceding products indirectly affect the quality of subsequent products through parameters such as equipment temperature, causing fluctuations in key indicators such as product moisture content and texture, thus reducing the quality and consistency of konjac products. Summary of the Invention

[0003] This application provides a production line management method and system for mixed-line production of konjac, which is used to address the technical problems that affect the quality of konjac products in the existing mixed-line production of konjac.

[0004] In view of the above problems, this application provides a production line management method and system for mixed production of konjac.

[0005] Firstly, this application provides a production line management method for mixed-line production of konjac, the method comprising:

[0006] When switching konjac production lines, the initial konjac production characteristics of the initial konjac product before the switch are collected.

[0007] Based on the initial konjac production characteristics, a performance impact analysis of the mixing and stirring process within the konjac production line was conducted to obtain performance impact parameters.

[0008] The switching characteristics of konjac production after production line switching are obtained. Based on the performance impact parameters, the control and management parameters of the mixing and stirring process after production line switching are optimized to obtain the optimal control and management parameters. The control and management parameters are optimized according to the weights configured based on the switching characteristics of konjac production.

[0009] The optimal control and management parameters are used to control and manage the konjac production line after it switches to a new production line.

[0010] Secondly, this application provides a production line management system for mixed-line production of konjac, including:

[0011] The feature acquisition module is used to collect the initial konjac production features of the initial konjac product before the production switch when switching konjac production lines.

[0012] The performance impact analysis module is used to perform performance impact analysis on the mixing and stirring process within the konjac production line based on the initial konjac production characteristics, and to obtain performance impact parameters.

[0013] The control parameter optimization module is used to acquire the switching konjac production characteristics after switching production and switching konjac products. Based on the performance impact parameters, the module optimizes the control management parameters of the mixing and stirring process after the production line switch to obtain the optimal control management parameters. The control management parameters are optimized by configuring weights according to the switching konjac production characteristics.

[0014] The production line control and management module is used to perform production line control and management after the konjac production line switches production, using the optimal control and management parameters.

[0015] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0016] This application proposes a production line management method and system for konjac mixed production lines. By collecting and analyzing the initial production characteristics before production line switchover and quantifying their impact on the mixing process, the optimal control and management parameters are dynamically optimized based on these impact parameters and the production characteristics of subsequent products. This significantly improves the quality control stability and production line operating efficiency of konjac mixed production lines after product switchover. Compared with traditional methods, the technical solution provided in this application significantly overcomes the blind spots caused by relying on fixed empirical parameters, achieving the technical effects of improving the quality of konjac mixed production lines, optimizing production resource allocation, and reducing overall management costs. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a production line management method for mixed-line production of konjac provided in an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the production line management system for mixed production of konjac provided in an embodiment of this application.

[0020] The components represented by each number in the attached diagram are explained below:

[0021] Feature acquisition module 100, performance impact analysis module 200, control parameter optimization module 300, and production line control management module 400. Detailed Implementation

[0022] This application provides a production line management method and system for mixed-line production of konjac, which is used to address the technical problems that affect the quality of konjac products in the existing mixed-line production of konjac.

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0024] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. 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 that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0025] Example 1, as Figure 1 As shown, this application provides a production line management method for mixed-line production of konjac, wherein the method includes:

[0026] S10: When switching konjac production lines, collect the initial konjac production characteristics of the initial konjac products produced before the switch.

[0027] In the actual operation of konjac mixed-production lines, when the production of one product is completed and preparations are made to switch to the next product, existing technologies often lack a systematic understanding of the preceding production status. Parameter adjustment decisions after production line switchover mostly rely on the operator's experience or fixed production plans, neglecting the potential impact of objective production characteristics left over from the preceding production process on subsequent processes.

[0028] Step S10 in the method provided in this application embodiment includes:

[0029] When switching konjac production lines, determine the initial konjac products to be produced before the switch and the konjac products to be produced after the switch.

[0030] The initial konjac production characteristics are collected before switching to production from the initial konjac product, wherein the initial konjac production characteristics include production volume.

[0031] In this embodiment of the application, when switching production on a konjac production line, the initial konjac product produced before the switch and the switch konjac product to be produced after the switch are determined. For example, the initial konjac product before the switch can be konjac slices, and the switch konjac product to be produced after the switch can be konjac noodles.

[0032] Collect the initial konjac production characteristics before switching to production. The initial konjac production characteristics include production volume, such as 5000 kg / day.

[0033] By collecting and recording the production characteristics of the initial konjac products before the production line switchover, a solid data foundation is laid for achieving precise production line management, enabling all subsequent analysis and optimization processes to be based on scientific decisions made using objective production data.

[0034] S20: Based on the initial konjac production characteristics, conduct a performance impact analysis of the mixing and stirring process within the konjac production line to obtain performance impact parameters.

[0035] After obtaining initial konjac production characteristic data, how to interpret this data and transform it into a substantial understanding of the performance of key processes in the production line is an urgent technical problem to be solved. The performance status of the mixing and stirring process, such as equipment temperature, is complexly influenced by the production characteristics of preceding products. It is necessary to quantify the residual impact of preceding production on the current state of the equipment in order to carry out subsequent optimization and adjustments.

[0036] Step S20 in the method provided in this application embodiment includes:

[0037] Obtain a performance impact predictor;

[0038] The performance impact predictor includes:

[0039] Based on historical production data from the konjac production line, a set of sample konjac product categories and a set of sample konjac production characteristics were collected.

[0040] The performance impact parameters of the mixing and stirring process in the konjac production line were collected under different konjac product categories and konjac production characteristics. The sample performance impact parameter set was obtained by labeling. Among them, each sample performance impact parameter includes at least the equipment temperature.

[0041] A network architecture for building a performance impact predictor based on machine learning;

[0042] Using the sample konjac product category set, sample konjac production characteristic set, and sample performance impact parameter set, the performance impact predictor is supervised and trained until it passes the test.

[0043] The initial konjac product and initial konjac production characteristics are input into the performance impact predictor, and the output is the performance impact parameters, wherein the performance impact parameters include at least the equipment temperature.

[0044] In this embodiment of the application, a sample konjac product category set and a sample konjac production characteristic set are collected based on the historical production data of the konjac production line. For example, the sample konjac product category is konjac chips, and the sample konjac production characteristic set is 5000 kg / day.

[0045] Performance-influencing parameters of the mixing and stirring process within a konjac production line were collected under different konjac product categories and production characteristics. These parameters were then labeled to obtain a set of performance-influencing parameters for each sample. Each sample's performance-influencing parameter included at least equipment temperature, which could be obtained through the equipment's temperature sensor. For example, for a sample konjac product category of konjac chips with a production capacity of 5000 kg / day, the performance-influencing parameter was 45℃.

[0046] Based on machine learning, a network architecture for a performance impact predictor is constructed. For example, a three-layer structure is adopted, where the input layer has two nodes to receive the konjac product category and konjac production characteristics, the hidden layer has 16 nodes and uses the ReLU activation function, and the output layer has one node and uses a linear activation function to output the performance impact parameters.

[0047] A performance impact predictor is trained and tested using a set of sample konjac product categories, a set of sample konjac production characteristics, and a set of sample performance impact parameters until the test is passed. For example, the sample konjac product category set, sample konjac production characteristic set, and sample performance impact parameter set are randomly divided into a training set and a test set, for example, 80% for training and 20% for testing. The training set data is input into the model, and the mean squared error is used as the loss function. The Adam optimizer is used for iterative training until a preset number of iterations is reached, such as 500. The parameters from the test set are used for testing and verification. The sample konjac product categories and sample konjac production characteristics are input into the test set, and the absolute error between the predicted performance impact parameters and the sample performance impact parameters is calculated. For example, if the absolute error is less than 2°C, the test is considered passed, and the performance impact predictor training is complete.

[0048] The initial konjac product and initial konjac production characteristics are input into the performance impact predictor, and the output is the performance impact parameters, which include at least the equipment temperature.

[0049] Performance impact analysis maps initial production characteristics to performance impact parameters that directly characterize the current state of the mixing and stirring process. This makes the impact of preceding production on the production line measurable and assessable, providing a scientific quantitative basis for subsequent optimization of production line control strategies.

[0050] S30: Obtain the switching konjac production characteristics after switching production to produce konjac products. Based on the performance impact parameters, optimize the control and management parameters of the mixing and stirring process after the production line switch to obtain the optimal control and management parameters. The control and management parameters are optimized according to the weights configured based on the switching konjac production characteristics.

[0051] Having clarified the impact of preceding production processes on equipment performance, it is necessary to formulate optimal control strategies for the new products to be produced. Existing technologies typically employ default parameters, neglecting the interplay between the effects of preceding performance and the production requirements of the new product. For example, different new products have different ideal production characteristics, and their sensitivities and requirements regarding equipment status also vary. If the specific production characteristics of the new product are not comprehensively considered for optimization, the set control parameters may either fail to meet the quality requirements of the new product or incur excessively high management costs in achieving those requirements.

[0052] Step S30 in the method provided in this application embodiment includes:

[0053] After switching production, obtain the switching konjac production characteristics for the konjac product to be produced. The switching konjac production characteristics include production volume.

[0054] Obtain the control and management parameter space for co-production of konjac, and obtain the default production management parameters for switching konjac products for production management. The default production management parameters include at least the stirring temperature.

[0055] Within the control and management parameter space, the default production management parameters are randomly adjusted to obtain the first production management parameters. Combined with the performance impact parameters, the konjac characteristics of the switched konjac product production are predicted to obtain the first konjac characteristics and the first adjustment range of the first production management parameters.

[0056] Within the control and management parameter space, the default production management parameters are randomly adjusted to obtain a first production management parameter. Combined with the performance impact parameters, konjac characteristic prediction for switching konjac product production is performed to obtain a first konjac characteristic, and a first adjustment range of the first production management parameter is obtained, including:

[0057] Based on the production record data of switching konjac products over a historical period, a set of sample production management parameters and a set of sample performance influence parameters were collected. The product characteristics of the switched konjac products under different sets of sample production management parameters and sample performance influence parameters were also collected as a set of sample konjac characteristics. Each sample konjac characteristic includes at least the product moisture content.

[0058] A konjac feature predictor is constructed based on machine learning. The konjac feature predictor is trained in a supervised manner using the sample production management parameter set, the sample performance influence parameter set, and the sample konjac feature set until it passes the test.

[0059] The first production management parameter and performance impact parameter are input into the konjac feature predictor, and the first konjac feature is obtained by outputting the first konjac feature.

[0060] Obtain the adjustment range between the first production management parameter and the default production management parameter, and use it as the first adjustment range;

[0061] Based on the weights configured according to the switching konjac production characteristics, and combined with the first konjac characteristic and the first adjustment range, the management fitness is calculated to obtain the first management fitness.

[0062] Specifically, the first management fitness is calculated by configuring weights based on the switching konjac production characteristics, combining the first konjac characteristic and the first adjustment range, and including:

[0063] Obtain the standard konjac characteristics for switching konjac products;

[0064] Calculate the similarity between the first konjac feature and the standard konjac feature to obtain the fitness of the first konjac feature;

[0065] Calculate the first management cost adaptability based on the first adjustment range;

[0066] Obtain the maximum switching konjac production characteristics within the historical time period of switching konjac products;

[0067] The ratio of the switching konjac production characteristic to the maximum switching konjac production characteristic is calculated as the konjac characteristic weight, and the management cost weight is also calculated.

[0068] Based on the konjac feature weight and management cost weight, the first konjac feature fitness and the first management cost fitness are weighted and calculated to obtain the first management fitness.

[0069] Continue adjusting and optimizing the production management parameters until convergence is achieved, obtaining the optimal control management parameters with the highest management adaptability.

[0070] In this embodiment of the application, the switching konjac production characteristics are obtained after the switching production process, wherein the switching konjac production characteristics include the production volume. For example, if the switching konjac product is konjac noodles, the switching konjac production characteristic is 6000 kg / day.

[0071] The system acquires the control and management parameter space for co-production of konjac and obtains the default production management parameters for switching konjac products during production management. These default parameters include at least the stirring temperature. Different konjac products require different production line control and management parameters, which need to be adjusted within the production line's control and management parameter range. The control and management parameter space for co-production of konjac refers to the adjustment range of the production line's control and management parameters during the konjac production process. For example, the control and management parameter space can be from 30℃ to 60℃, and a default production management parameter can be 45℃.

[0072] Within the control and management parameter space, the default production management parameters are randomly adjusted to obtain the first production management parameter. Combined with the performance impact parameters, the konjac characteristics of the switched konjac product production are predicted to obtain the first konjac characteristic and the first adjustment range of the first production management parameter.

[0073] Specifically, within the control management parameter space, the default production management parameters are randomly adjusted to obtain the first production management parameter. For example, a random number generator is used to obtain a random adjustment range of 3°C, so that a default production management parameter of 45°C is adjusted to 45+2=48°C, which is then used as the first production management parameter.

[0074] Based on historical production records of konjac products, a set of sample production management parameters and a set of sample performance impact parameters were collected. Product characteristics of the switched konjac products under different sets of sample production management parameters and sample performance impact parameters were also collected as a sample konjac characteristic set. Each sample konjac characteristic includes at least the product moisture content. Product moisture content can be obtained by testing the moisture content of konjac, for example, by drying. The measured moisture content is expressed as a percentage (%).

[0075] A konjac feature predictor is constructed based on machine learning. An exemplary three-layer structure is adopted: the input layer has two nodes to receive production management parameters and performance impact parameters; the hidden layer has eight nodes using the sigmoid activation function; and the output layer has one node using the linear activation function to output the predicted konjac features. Using a set of sample production management parameters, a set of sample performance impact parameters, and a set of sample konjac features, the konjac feature predictor is trained in a supervised manner using gradient descent with mean squared error as the loss function, until a test is passed. The konjac feature predictor is considered successfully trained if the average error between the predicted konjac features and the sample konjac features is within ±2%.

[0076] The first production management parameter and performance impact parameter are input into the konjac feature predictor, and the first konjac feature is obtained by outputting it.

[0077] Obtain the adjustment range between the first production management parameter and the default production management parameter, and use this as the first adjustment range. Calculate the ratio of the absolute difference between the first production management parameter and the default production management parameter to the default production management parameter, and use this as the first adjustment range. The first adjustment range = |first production management parameter - default production management parameter| ÷ default production management parameter. For example, if the first production management parameter is 48℃ and the default production management parameter is 45℃, then the first adjustment range = |48 - 45| ÷ 45 = 0.067.

[0078] Based on the weights configured according to the switching konjac production characteristics, and combined with the first konjac characteristic and the first adjustment range, the management fitness is calculated to obtain the first management fitness.

[0079] Specifically, based on the konjac product production standards, the standard konjac characteristics for switching konjac products are obtained. For example, when switching konjac products to konjac noodles, the standard konjac characteristic is a moisture content of 80%.

[0080] Calculate the similarity between the first konjac feature and the standard konjac feature to obtain the fitness of the first konjac feature. For example, the fitness of the first konjac feature = 1 - |first konjac feature - standard konjac feature| ÷ [(first konjac feature + standard konjac feature) ÷ 2]. The higher the similarity, the closer the konjac feature is to the standard, and the higher the quality. For example, if the first konjac feature is 93% and the standard konjac feature is a water content of 80%, then the fitness of the first konjac feature = 1 - |93 - 80| ÷ [(93 + 80) ÷ 2] = 0.85.

[0081] Calculate the first management cost fitness level based on the first adjustment range. First management cost fitness level = 1 - first adjustment range. A larger adjustment range results in higher production line adjustment costs, higher management costs, and a lower management cost fitness level. For example, if the first adjustment range is 0.067, then the first management cost fitness level = 1 - 0.067 = 0.933.

[0082] Obtain the maximum switching konjac production characteristic within the historical timeframe for switching konjac products. For example, the historical timeframe is set to the past 60 days to prevent obtaining information from too far back with low reference value. The maximum switching konjac production characteristic refers to the maximum value of the production characteristic of the switching konjac product; for example, within the past 60 days, the maximum production characteristic of konjac noodles was a moisture content of 86%.

[0083] The ratio of the switched konjac production characteristic to the maximum switched konjac production characteristic is calculated as the konjac characteristic weight, and the management cost weight is also calculated. Konjac characteristic weight = switched konjac production characteristic ÷ maximum switched konjac production characteristic; management cost weight = 1 - konjac characteristic weight. The closer the konjac production characteristic is to the maximum switched konjac production characteristic, the greater the need to improve konjac quality, meaning a larger konjac characteristic weight and a smaller corresponding management cost weight.

[0084] The first management fitness is calculated by weighting the konjac feature weight and the first management cost fitness based on the konjac feature weight and the management cost weight. First management fitness = Konjac feature weight × First konjac feature fitness + Management cost weight × First management cost fitness. For example, when the konjac feature weight is 0.6, the management cost weight = 1 - 0.6 = 0.4. When the first konjac feature fitness is 0.85 and the first management cost fitness is 0.933, then the first management fitness = 0.6 × 0.85 + 0.4 × 0.933 = 0.8832.

[0085] Continue adjusting and optimizing the production management parameters until convergence, obtaining multiple control management parameters and their corresponding management fitness. Select the control management parameter with the highest management fitness as the optimal control management parameter.

[0086] By integrating performance-influencing parameters and the characteristics of konjac production switching, optimization can dynamically obtain the optimal control and management parameters best suited to the current operating conditions, based on the combination of historical legacy states and new product production demands at each production switch. Optimization is achieved by configuring weights according to the characteristics of konjac production switching, intelligently balancing multiple optimization objectives such as product quality and management costs. For example, for products with high production volume and high quality requirements, the algorithm automatically tends to prioritize product quality; conversely, it may place more emphasis on controlling adjustment costs. This dynamic weighting mechanism ensures that the final optimal parameter set is not only technically feasible but also economically and efficiently reasonable, thus achieving a high degree of personalization, precision, and economy in the control strategy after production line switching, fundamentally improving the overall efficiency of mixed-line production.

[0087] S40: Using the aforementioned optimal control and management parameters, production line control and management are carried out after the konjac production line switches production.

[0088] In this embodiment, optimal control and management parameters are used to control and manage the konjac production line after it switches to new production.

[0089] Example 2, as Figure 2 As shown, based on the same inventive concept as the production line management method for mixed konjac production provided in Embodiment 1, this embodiment of the invention also provides a production line management system for mixed konjac production, including:

[0090] The feature acquisition module 100 is used to acquire the initial konjac production features of the initial konjac product before the production switch when switching konjac production lines.

[0091] The performance impact analysis module 200 is used to perform performance impact analysis on the mixing and stirring process within the konjac production line based on the initial konjac production characteristics, and to obtain performance impact parameters.

[0092] The control parameter optimization module 300 is used to acquire the switching konjac production characteristics after switching production and switching konjac products. Based on the performance impact parameters, the control management parameters of the mixing and stirring process after the production line switch are optimized to obtain the optimal control management parameters. The control management parameters are optimized according to the weights configured based on the switching konjac production characteristics.

[0093] The production line control management module 400 is used to perform production line control management after the konjac production line switches production, using the optimal control management parameters.

[0094] In one embodiment, the feature acquisition module 100 is further configured to:

[0095] When switching konjac production lines, determine the initial konjac products to be produced before the switch and the konjac products to be produced after the switch.

[0096] The initial konjac production characteristics are collected before switching to production from the initial konjac product, wherein the initial konjac production characteristics include production volume.

[0097] In one embodiment, the performance impact analysis module 200 is further configured to:

[0098] Obtain a performance impact predictor;

[0099] The performance impact predictor includes:

[0100] Based on historical production data from the konjac production line, a set of sample konjac product categories and a set of sample konjac production characteristics were collected.

[0101] The performance impact parameters of the mixing and stirring process in the konjac production line were collected under different konjac product categories and konjac production characteristics. The sample performance impact parameter set was obtained by labeling. Among them, each sample performance impact parameter includes at least the equipment temperature.

[0102] A network architecture for building a performance impact predictor based on machine learning;

[0103] Using the sample konjac product category set, sample konjac production characteristic set, and sample performance impact parameter set, the performance impact predictor is supervised and trained until it passes the test.

[0104] The initial konjac product and initial konjac production characteristics are input into the performance impact predictor, and the output is the performance impact parameters, wherein the performance impact parameters include at least the equipment temperature.

[0105] In one embodiment, the control parameter optimization module 300 is further configured to:

[0106] After switching production, obtain the switching konjac production characteristics for the konjac product to be produced. The switching konjac production characteristics include production volume.

[0107] Obtain the control and management parameter space for co-production of konjac, and obtain the default production management parameters for switching konjac products for production management. The default production management parameters include at least the stirring temperature.

[0108] Within the control and management parameter space, the default production management parameters are randomly adjusted to obtain the first production management parameters. Combined with the performance impact parameters, the konjac characteristics of the switched konjac product production are predicted to obtain the first konjac characteristics and the first adjustment range of the first production management parameters.

[0109] Within the control and management parameter space, the default production management parameters are randomly adjusted to obtain a first production management parameter. Combined with the performance impact parameters, konjac characteristic prediction for switching konjac product production is performed to obtain a first konjac characteristic, and a first adjustment range of the first production management parameter is obtained, including:

[0110] Based on the production record data of switching konjac products over a historical period, a set of sample production management parameters and a set of sample performance influence parameters were collected. The product characteristics of the switched konjac products under different sets of sample production management parameters and sample performance influence parameters were also collected as a set of sample konjac characteristics. Each sample konjac characteristic includes at least the product moisture content.

[0111] A konjac feature predictor is constructed based on machine learning. The konjac feature predictor is trained in a supervised manner using the sample production management parameter set, the sample performance influence parameter set, and the sample konjac feature set until it passes the test.

[0112] The first production management parameter and performance impact parameter are input into the konjac feature predictor, and the first konjac feature is obtained by outputting the first konjac feature.

[0113] Obtain the adjustment range between the first production management parameter and the default production management parameter, and use it as the first adjustment range;

[0114] Based on the weights configured according to the switching konjac production characteristics, and combined with the first konjac characteristic and the first adjustment range, the management fitness is calculated to obtain the first management fitness.

[0115] Specifically, the first management fitness is calculated by configuring weights based on the switching konjac production characteristics, combining the first konjac characteristic and the first adjustment range, and including:

[0116] Obtain the standard konjac characteristics for switching konjac products;

[0117] Calculate the similarity between the first konjac feature and the standard konjac feature to obtain the fitness of the first konjac feature;

[0118] Calculate the first management cost adaptability based on the first adjustment range;

[0119] Obtain the maximum switching konjac production characteristics within the historical time period of switching konjac products;

[0120] The ratio of the switching konjac production characteristic to the maximum switching konjac production characteristic is calculated as the konjac characteristic weight, and the management cost weight is also calculated.

[0121] Based on the konjac feature weight and management cost weight, the first konjac feature fitness and the first management cost fitness are weighted and calculated to obtain the first management fitness.

[0122] Continue adjusting and optimizing the production management parameters until convergence is achieved, obtaining the optimal control management parameters with the highest management adaptability.

[0123] In summary, the embodiments of this application have at least the following technical effects:

[0124] This application proposes a production line management method and system for mixed-production konjac. By collecting and analyzing initial production characteristics before production line switchover and quantifying their performance impact on the mixing process, the optimal control and management parameters are dynamically optimized based on these impact parameters and the production characteristics of subsequent products. This significantly improves the quality control stability and production line operating efficiency of mixed-production konjac after product switchover. Specifically, through precise performance impact analysis, the cumulative effect of preceding production on equipment conditions such as residual temperature can be effectively analyzed and quantified, providing a scientific basis for subsequent parameter optimization. This significantly reduces fluctuations in key characteristics of konjac products caused by production line switchover, ensuring the consistency and compliance of product quality across different batches. Secondly, by introducing a weight-based optimization algorithm, the system can achieve an optimal balance between quality and efficiency while ensuring product quality approaches standard characteristics and considering management costs. This avoids energy waste and equipment damage caused by excessive parameter adjustments. Finally, by constructing and applying a performance impact predictor and a konjac characteristic predictor, the production line management system is endowed with self-learning and adaptive capabilities, enabling it to continuously accumulate production data and optimize decisions, thus improving its adaptability to the co-production of multiple konjac product varieties. Compared with traditional methods, the technical solution provided in this application significantly overcomes the blindness caused by relying on fixed empirical parameters, and achieves the technical effects of improving the quality of konjac mixed production, optimizing the allocation of production resources, and reducing overall management costs.

[0125] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0126] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0127] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A production line management method for mixed-production of konjac, characterized in that, The method includes: When switching konjac production lines, the initial konjac production characteristics of the initial konjac product before the switch are collected. Based on the initial konjac production characteristics, a performance impact analysis of the mixing and stirring process within the konjac production line was conducted to obtain performance impact parameters. The switching characteristics of konjac production after production line switching are obtained. Based on the performance impact parameters, the control and management parameters of the mixing and stirring process after production line switching are optimized to obtain the optimal control and management parameters. The optimization of these control and management parameters is based on weighted configurations according to the switching konjac production characteristics, including: After switching production, obtain the switching konjac production characteristics for the konjac product to be produced. The switching konjac production characteristics include production volume. Obtain the control and management parameter space for co-production of konjac, and obtain the default production management parameters for switching konjac products for production management. The default production management parameters include at least the stirring temperature. Within the control management parameter space, the default production management parameters are randomly adjusted to obtain a first production management parameter. Combined with the performance impact parameters, konjac characteristic prediction is performed for switching konjac product production to obtain a first konjac characteristic, and a first adjustment range of the first production management parameter is obtained, including: Based on the production record data of switching konjac products over a historical period, a set of sample production management parameters and a set of sample performance influence parameters were collected. The product characteristics of the switched konjac products under different sets of sample production management parameters and sample performance influence parameters were also collected as a set of sample konjac characteristics. Each sample konjac characteristic includes at least the product moisture content. A konjac feature predictor is constructed based on machine learning. The konjac feature predictor is trained in a supervised manner using the sample production management parameter set, the sample performance influence parameter set, and the sample konjac feature set until it passes the test. The first production management parameter and performance impact parameter are input into the konjac feature predictor, and the first konjac feature is obtained by outputting the first konjac feature. Obtain the adjustment range between the first production management parameter and the default production management parameter, and use it as the first adjustment range; Based on the weights configured according to the switching konjac production characteristics, and combining the first konjac characteristic and the first adjustment range, management fitness is calculated to obtain the first management fitness, including: Obtain the standard konjac characteristics for switching konjac products; Calculate the similarity between the first konjac feature and the standard konjac feature to obtain the fitness of the first konjac feature; Calculate the first management cost adaptability based on the first adjustment range; Obtain the maximum switching konjac production characteristics within the historical time period of switching konjac products; The ratio of the switching konjac production characteristic to the maximum switching konjac production characteristic is calculated as the konjac characteristic weight, and the management cost weight is also calculated. Based on the konjac feature weight and management cost weight, the first konjac feature fitness and the first management cost fitness are weighted and calculated to obtain the first management fitness. Continue to adjust and optimize the production management parameters until convergence, obtaining the optimal control management parameters with the greatest management adaptability; The optimal control and management parameters are used to control and manage the konjac production line after it switches to a new production line.

2. The production line management method for mixed-production of konjac according to claim 1, characterized in that, When switching konjac production lines, the initial konjac production characteristics of the initial konjac product before the switch are collected, including: When switching konjac production lines, determine the initial konjac products to be produced before the switch and the konjac products to be produced after the switch. The initial konjac production characteristics are collected before the initial konjac product is switched to production, wherein the initial konjac production characteristics include production volume.

3. The production line management method for mixed-production of konjac according to claim 1, characterized in that, Based on the initial konjac production characteristics, a performance impact analysis of the mixing and stirring process within the konjac production line was conducted to obtain performance impact parameters, including: Obtain a performance impact predictor; The initial konjac product and initial konjac production characteristics are input into the performance impact predictor, and the output is the performance impact parameters, wherein the performance impact parameters include at least the equipment temperature.

4. The production line management method for mixed-production of konjac according to claim 3, characterized in that, Obtain a performance impact predictor, including: Based on historical production data from the konjac production line, a set of sample konjac product categories and a set of sample konjac production characteristics were collected. The performance impact parameters of the mixing and stirring process in the konjac production line were collected under different konjac product categories and konjac production characteristics. The sample performance impact parameter set was obtained by labeling. Among them, each sample performance impact parameter includes at least the equipment temperature. A network architecture for building a performance impact predictor based on machine learning; Using the sample konjac product category set, sample konjac production characteristic set, and sample performance impact parameter set, the performance impact predictor is trained and tested under supervision until it passes the test.

5. A production line management system for mixed-production of konjac, characterized in that, The system for implementing the production line management method for mixed-line production of konjac as described in any one of claims 1-4, the system comprising: The feature acquisition module is used to collect the initial konjac production features of the initial konjac product before the production switch when switching konjac production lines. The performance impact analysis module is used to perform performance impact analysis on the mixing and stirring process within the konjac production line based on the initial konjac production characteristics, and to obtain performance impact parameters. The control parameter optimization module is used to acquire the switching konjac production characteristics after switching production and switching konjac products. Based on the performance impact parameters, the module optimizes the control management parameters of the mixing and stirring process after the production line switch to obtain the optimal control management parameters. The control management parameters are optimized by configuring weights according to the switching konjac production characteristics. The production line control and management module is used to perform production line control and management after the konjac production line switches production, using the optimal control and management parameters.

Images