Low-carbon production process of cereal meal replacement powder based on process adjustment
By analyzing the contour and wrinkle characteristics of peas during steaming, and using neural network to control the boiling steaming time, the problem of uneven maturation of peas is solved, and the quality and taste consistency of cereal meal replacement powder are improved.
Patent Information
- Application Number
- CN202410625880.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-20
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-05-20
Smart Images

Figure CN118542432B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of cereal meal replacement powder production, and specifically to a low-carbon production process for cereal meal replacement powder based on process parameter adjustment. Background Art
[0002] Cereal meal replacement powder is a powdered instant product made from grass plants as the main raw materials, among which peas are one of the important raw materials. Peas are rich in high-quality plant protein and dietary fiber and have high nutritional value. In order to make the taste of peas more delicate, they are often cooked by steaming. During the steaming process, it is necessary to set the appropriate temperature, water ratio and boiling steaming time to ensure that the peas have the best taste and nutritional quality.
[0003] In the production process, the freshness and particle size of the raw peas will affect the boiling time. If the boiling time is too long, the peas may be over-softened and lose their original taste, and the nutrients in the peas may be destroyed or lost at high temperatures, reducing the nutritional value of the cereal meal replacement powder; while too short a cooking time may cause the peas to fail to fully mature, affecting the taste and quality of the cereal meal replacement powder; inappropriate cooking time may lead to a decline in the quality of the finished cereal meal replacement powder, and problems such as poor taste and nutrient loss will affect the quality of the final meal replacement powder. Summary of the invention
[0004] In view of the above, it is necessary to provide a low-carbon production process for cereal meal replacement powder based on process adjustment, to control the boiling time of peas, to retain the original taste and nutrients of peas, and to improve the quality of the finished product of cereal meal replacement powder.
[0005] One embodiment of the present application provides a low-carbon production process for cereal meal replacement powder based on process parameter adjustment, the process comprising:
[0006] Soak quinoa in water, drain the water, and cook;
[0007] Low temperature roasting of white kidney beans and oats;
[0008] Steaming the peas and controlling the boiling and steaming time of the peas;
[0009] Collect the pea steaming temperature sequence and the pea steaming state diagram at each moment;
[0010] According to the pea steaming state diagram at each moment, all the suspected pea contours and suspected pea wrinkles at each moment are obtained;
[0011] According to the distribution of all the suspected pea wrinkles in each suspected pea outline combined with the shape characteristics, the relative roundness of each suspected pea outline is obtained;
[0012] According to the change characteristics of the relative roundness of all the suspected pea contours in the pea steaming state diagram at continuous moments, the boiling steaming time of the peas is controlled;
[0013] Fry the brown rice;
[0014] Drying the cooked quinoa and peas;
[0015] Grind the dried quinoa and peas, the low-temperature baked white kidney beans and oats, and the fried brown rice respectively, and sieve them to obtain quinoa powder, white kidney bean powder, pea powder, oat powder, and brown rice powder;
[0016] Quinoa flour, white kidney bean flour, pea flour, oat flour, brown rice flour, guar gum, microcrystalline cellulose and erythritol are mixed to obtain a cereal meal replacement powder.
[0017] In one embodiment, the cooking time is 5 minutes from the time the water boils.
[0018] In one embodiment, the low-temperature baking is performed at a temperature of 130° C. and a time of 1 hour.
[0019] In one embodiment, the process of obtaining all the suspected pea contours and suspected pea wrinkles at each moment is as follows:
[0020] A contour detection algorithm is used to obtain all the highest-level contours in the pea steaming state diagram and all the secondary contours inside each highest-level contour, all the highest-level closed contours are saved as suspected pea contours, and all the secondary contours inside the highest-level closed contours are saved as suspected pea wrinkles.
[0021] In one embodiment, the method for obtaining the relative roundness of each of the suspected pea contours is:
[0022] For the pea steaming state diagram at each moment, the minimum circumscribed rectangle of each suspected pea wrinkle in any suspected pea outline is obtained, and the contrast of the gray level co-occurrence matrix in each preset direction of the minimum circumscribed rectangle is saved as the suspected wrinkle contrast in each preset direction of each suspected pea wrinkle;
[0023] For any of the suspected pea contours, the wrinkle pixel ratio of each suspected pea wrinkle is obtained, and the ratio of the mean to the variance of the suspected wrinkle contrast of each suspected pea wrinkle in all preset directions is obtained, and saved as the contrast dispersion; the wrinkle intensity of each suspected pea wrinkle shows a consistent trend relationship with the contrast dispersion and the wrinkle pixel ratio;
[0024] According to the shape characteristics of each suspected pea outline in the pea steaming state diagram, the pea roundness of each suspected pea outline is obtained;
[0025] For the pea steaming state diagram at each moment, the difference in pea roundness between any suspected pea outline and the other suspected pea outlines is saved as the roundness difference; the cumulative sum of all the roundness differences of any suspected pea outline is saved as the overall roundness difference; the cumulative sum of the wrinkle strength of all suspected pea wrinkles in any suspected pea outline is saved as the overall wrinkle strength; the relative roundness granularity of any suspected pea outline shows a consistent trend relationship with the overall roundness difference and the total number of pixels in any suspected pea outline, and shows an opposite trend relationship with the overall wrinkle strength.
[0026] In one embodiment, the step of obtaining the pea roundness of each suspected pea outline comprises:
[0027] The center point of each suspected pea contour is taken as each suspected pea center, and the Euclidean distance from each contour point in each suspected pea contour to the corresponding suspected pea center is taken as the pea contour deviation distance of each contour point; the sequence composed of all the pea contour deviation distances in each suspected pea contour is taken as each contour deviation distance sequence, and the natural breakpoint algorithm is used to obtain each center deviation group;
[0028] The distance between the corresponding contour points of any two elements in each center deviation group is obtained, and the cumulative sum of all the distances of each center deviation group is used as the deviation roundness weight; the element mean of each center deviation group is used as the deviation strength; the element mean of the contour deviation distance sequence is used as the contour average skewness; the absolute value of the difference between the deviation strength of each center deviation group and the contour average skewness is used as the deviation difference, and the ratio of the deviation roundness weight of each center deviation group to the deviation difference is calculated and saved as the roundness factor of each center deviation group; the cumulative sum of the roundness factors of all center deviation groups is used as the pea roundness of each suspected pea contour.
[0029] In one embodiment, the step of controlling the boiling steaming time of the peas comprises:
[0030] Obtaining the relative roundness of all suspected pea contours in the pea steaming state diagram at any moment, arranging all the relative roundness in ascending order, and sequentially counting the number of suspected pea contours corresponding to each relative roundness to form a particle size distribution sequence at any moment;
[0031] The sequence composed of the pea steaming state diagrams at any moment and a preset number of moments before and after is used as the local extended sequence at any moment; the DTW distance between the pea steaming temperature difference and the particle size distribution sequence at each moment and the next moment is obtained respectively; the ratio of the pea steaming temperature difference to the DTW distance is obtained and saved as the steaming change index; the steaming change intensity factor at any moment is a measure of the central tendency of the steaming change index at all moments in the local extended sequence at any moment;
[0032] The particle size distribution sequence at any moment is fitted to obtain the particle size distribution curve at any moment; a peak detection algorithm is used to obtain the relatively rounded particle size, peak height and peak width corresponding to the maximum peak in the particle size distribution curve to form the pea particle size peak distribution vector at each moment;
[0033] A sequence composed of components in the pea particle size peak distribution vector at all times in the local extended sequence at any time is obtained, recorded as each extended particle size peak component sequence, and a trend test algorithm is used to obtain the trend test statistic of each extended particle size peak component sequence; the steaming expansion feedback index at any time and the sum of all the trend test statistics of the local extended sequence at the corresponding time and the steaming change intensity factor show a consistent trend relationship;
[0034] The steaming expansion feedback indexes at all times are combined into a steaming feedback sequence; and the boiling steaming time of the peas is obtained according to the steaming feedback sequence and the pea steaming temperature sequence in combination with a neural network.
[0035] In one embodiment, the specific operation of frying the brown rice is to put the brown rice into an oil-free pan and dry-fry the brown rice for 7 minutes.
[0036] In one embodiment, the drying temperature is 55° C. and the drying time is 48 hours.
[0037] In one embodiment, the mass ratio of quinoa flour, white kidney bean flour, pea flour, oat flour, brown rice flour, guar gum, microcrystalline cellulose and erythritol is 40:25:25:18:4:2.5:0.25:0.25.
[0038] This application has at least the following beneficial effects:
[0039] Based on the contour roundness and internal wrinkle distribution of peas during the steaming process, combined with the contour detection algorithm and the grayscale co-occurrence matrix, a relative roundness particle size is constructed to reflect the possibility that the suspected pea contour belongs to a round pea and the particle size of the round pea. Its beneficial effect is to comprehensively consider the possible sharpness and fineness of the pea hilum, improve the distinction between the roundness characteristics of peas with sharp hilums and peas with full hilums, and increase the accuracy of subsequent pea particle size distribution judgment; according to the characteristic changes of pea distribution during the steaming process, the steaming expansion feedback index of all pea steaming state diagrams can be obtained, reflecting the short-term The steaming time control model is used to control the boiling steaming time according to the rounded particle size and expansion quality of the peas during the steaming process, so as to avoid large fluctuations in the quality of peas in different batches and the inability to determine the boiling steaming time of different batches of peas. It also prevents the loss of the original taste and nutrients of the peas due to inappropriate boiling steaming time, which directly affects the quality of the finished product of the cereal meal replacement powder. It ensures that the nutritional value of the cereal meal replacement powder is retained while improving the taste and flavor consistency of the cereal meal replacement powder, which helps the cereal meal replacement powder maintain its market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 A flow chart of the low-carbon production process of cereal meal replacement powder based on process parameter adjustment provided in this application;
[0041] Figure 2 A schematic diagram of the steaming state diagram of peas provided for this application;
[0042] Figure 3 Schematic diagram of the steaming profile of peas provided for this application;
[0043] Figure 4 A schematic diagram of the particle size distribution curve provided for this application;
[0044] Figure 5 A control flow chart for the boiling steaming time of peas provided in this application. DETAILED DESCRIPTION
[0045] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.
[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.
[0047] It should also be noted that the terms "first" and "second" in the specification and drawings of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the original purpose, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.
[0048] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0049] The present application embodiment first proposes a low-carbon production process for cereal meal replacement powder based on process parameter adjustment, which is applied to the technical field of cereal meal replacement powder production. Figure 1 , the process comprises the following steps:
[0050] For the Quinoa Soak:
[0051] The quinoa is soaked in water to remove saponin. As an embodiment of the present application, the mass ratio of quinoa to water is 1:1, and the soaking time is 10 minutes.
[0052] Quinoa Cooking:
[0053] The soaked quinoa is filtered and boiled with water. As an embodiment of the present application, the mass ratio of quinoa to water is 1:1, the boiling temperature is 100° C., and the boiling time is 5 minutes from the boiling of the water.
[0054] White Bean Oatmeal Cooking:
[0055] Low-temperature baking is used for the ripening treatment of white kidney beans and oats; as an embodiment of the present application, the baking temperature is 130° C. and the baking time is 1 hour.
[0056] Cooking peas:
[0057] The peas are cooked by steaming; as an embodiment of the present application, the mass ratio of peas to water is 1:1.
[0058] Peas are rich in beneficial ingredients, such as vitamin C, vitamin K and dietary fiber, and the boiling and steaming time also has an important impact on the taste of peas. For example, if the steaming time is short, the peas will remain crisp and tender, and if the steaming time is long, the peas will become too soft and lose their original taste. The peas used in the production process are all commercially available products, and the quality of peas from different batches varies greatly. Therefore, by adjusting the boiling and steaming time, it is possible to ensure that the nutritional value of peas is retained to the maximum extent while the peas are cooked. Based on this, the boiling and steaming time of peas is controlled:
[0059] The first sub-step: collecting the pea steaming temperature sequence and the pea steaming state diagram at each moment.
[0060] During the pea cooking process, a temperature measuring device is installed to measure the temperature of the water used to steam the peas in real time as the actual temperature of the peas. The moment when the actual temperature of the peas just reaches the preset temperature is taken as the acquisition starting point. A high-resolution optical camera is used to capture images of the pea water solution to obtain a pea steaming diagram. The pea steaming diagram is processed to obtain a pea steaming state diagram at each moment. The actual steaming temperature of the peas is obtained through the temperature measuring device, and the pea steaming temperature sequence is obtained in ascending time order.
[0061] Among them, the temperature measuring device in this embodiment adopts a temperature sensor; the preset temperature is 50°C; the interval between adjacent acquisition moments in this embodiment is set to 2s, and the total acquisition time in this embodiment is set to 2min; the process of image processing of the pea steaming diagram is: converting the pea steaming diagram at each moment into a grayscale image, and then using a wavelet threshold denoising algorithm to obtain the pea steaming state diagram at each moment; it should be noted that grayscale conversion and wavelet threshold denoising algorithm are both well-known technologies, and the specific process will not be repeated.
[0062] The second sub-step: obtaining all suspected pea contours and suspected pea wrinkles at each moment according to the pea steaming state diagram at each moment.
[0063] Peas with high freshness are bright green or dark green with uniform color, round and smooth surface without wrinkles, dents or damage, high water content, tender texture, fast heat transfer inside the peas, and shorter boiling and steaming time. At the same time, peas with smaller particle size transfer heat more fully during the steaming process, which shortens the boiling and steaming time for the peas to complete maturation.
[0064] In the pea steaming state diagram, the outline of the peas is obvious, and for peas with low freshness, the loss of water may cause the surface of the peas to shrink, forming complex, non-straight, and grooved wrinkles. The pea wrinkles are also prominent in the pea steaming state diagram.
[0065] Based on this, the suspected pea outline and suspected pea wrinkles of the pea steaming state diagram are obtained:
[0066] As an embodiment of the present application, the process of obtaining suspected pea contours and suspected pea wrinkles in a pea steaming state diagram is as follows: using the Sobel edge detection algorithm and the expansion and corrosion algorithm to obtain all edges of the pea steaming state diagram, and then using the cv2.findContours function in the OpenCV library to obtain all the highest-level contours in the pea steaming state diagram and all the secondary contours inside each highest-level contour, saving all the highest-level closed contours as suspected pea contours, and saving all the secondary contours inside the highest-level closed contours as suspected pea wrinkles.
[0067] Among them, the outline diagram of the pea steaming state diagram is as follows: Figure 2 As shown; Schematic diagram of pea steaming, as shown Figure 3 shown.
[0068] It should be noted that the Sobel edge detection algorithm, the expansion corrosion algorithm, and the cv2.findContours function are all existing well-known technologies for edge detection, which will not be described in detail in this application. In addition, based on obtaining the suspected pea contour and the suspected pea wrinkles, the implementer may also choose other implementation methods, which are not limited in this application.
[0069] The third sub-step: according to the distribution of all the suspected pea wrinkles in each suspected pea contour combined with the shape characteristics, the relative roundness of each suspected pea contour is obtained.
[0070] Round peas are more likely to be heated evenly during steaming because they have a relatively small surface area, allowing heat to be conducted more easily to the inside of the peas. In contrast, if the peas are not round but irregularly shaped or of varying sizes, some peas may be heated unevenly, with some peas being cooked through and others not fully cooked.
[0071] Based on this, the relative roundness of each suspected pea outline is obtained:
[0072] For the pea steaming state diagram at each moment, the minimum circumscribed rectangle of each suspected pea wrinkle in any suspected pea outline is obtained, and the contrast of the grayscale co-occurrence matrix in each preset direction of the minimum circumscribed rectangle is saved as the suspected wrinkle contrast in each preset direction of each suspected pea wrinkle.
[0073] As an embodiment of the present application, the preset directions are specifically: 0°, 45°, 90°, 135°; in addition, the calculation methods of the minimum circumscribed rectangle and the grayscale co-occurrence matrix contrast are both well-known technologies, and the specific process will not be repeated in this application.
[0074] For any of the suspected pea contours, the wrinkle pixel ratio of each suspected pea wrinkle is obtained, and the ratio of the mean to the variance of the suspected wrinkle contrast of each suspected pea wrinkle in all preset directions is obtained, and saved as the contrast discreteness; the wrinkle intensity of each suspected pea wrinkle shows a consistent trend relationship with the contrast discreteness and the wrinkle pixel ratio.
[0075] It should be noted that the consistent trend relationship specifically means that as one variable increases or decreases, another variable also increases or decreases. Based on the consistent trend relationship, the implementer can flexibly choose a suitable method to determine the variable, and this application does not impose any restrictions on this.
[0076] As an embodiment of the present application, the product of the contrast dispersion and the wrinkle pixel ratio is used as the wrinkle intensity of each suspected pea wrinkle.
[0077] It should be understood that when the mean of the suspected wrinkle contrast in all directions of the wrinkle test area is larger and the variance is smaller, the contrast dispersion is larger, indicating that the groove texture of the suspected pea wrinkles in all directions is deeper, and the suspected pea wrinkles are less biased towards a certain direction, the suspected pea wrinkles are more likely to be wrinkles with complex morphology and significant grooves inside the pea. At the same time, the higher the proportion of wrinkle pixels, the larger the proportion of wrinkles with complex morphology and significant grooves inside the pea, the higher the intensity of the pea wrinkles, the more serious the water loss, and the greater the wrinkle intensity.
[0078] The center point of each suspected pea outline is taken as each suspected pea center, and the Euclidean distance from each outline point in each suspected pea outline to the corresponding suspected pea center is taken as the pea outline deviation distance of each outline point; the sequence composed of all the pea outline deviation distances in each suspected pea outline is taken as each outline deviation distance sequence, and the natural break algorithm is used to obtain each center deviation group.
[0079] As an embodiment of the present application, the mean method is used to obtain the center point of each suspected pea outline; in addition, the natural breakpoint algorithm is an existing well-known technology and will not be described in detail in this application.
[0080] It should be noted that each element in the center deviation group is a pea contour deviation distance, and each pea contour deviation distance corresponds to a contour pixel point.
[0081] The Euclidean distance between the corresponding contour points of any two elements in each center deviation group is obtained, and the cumulative sum of all the Euclidean distances of each center deviation group is used as the deviation roundness weight; the mean of the elements of each center deviation group is used as the deviation intensity; the mean of the elements of the contour deviation distance sequence is used as the average skewness of the contour; the absolute value of the difference between the deviation intensity of each center deviation group and the average skewness of the contour is used as the deviation difference, and the ratio of the deviation roundness weight of each center deviation group to the deviation difference is calculated and saved as the roundness factor of each center deviation group; the pea roundness of each suspected pea contour and the cumulative sum of the roundness factors of all center deviation groups show a consistent trend.
[0082] As an embodiment of the present application, the cumulative sum of the roundness factors of all center deviation groups is used as the pea roundness of each suspected pea contour.
[0083] It should be understood that the farther the coordinates of any contour pixel points in the center deviation group are from each other, the more the contour pixel points with larger coordinates are consistent with the center point of the suspected pea contour, and the more the center deviation group can reflect the rounded characteristics of the suspected pea contour. Among them, the deviation from roundness comprehensively considers that the pea hilum (the part where the pea bean is connected to the mother plant during the development process) may be sharp and small, avoiding the problem of low distinction between the roundness of peas with sharp hilums and peas with full hilums, and improving the accuracy of subsequent pea size judgment; when the deviation intensity is smaller than the difference between the average skewness of the contour, it indicates that the overall suspected pea contour has the rounded characteristics of fresh peas, and the roundness of the pea contour is greater.
[0084] For the pea steaming state diagram at each moment, the difference in pea roundness between any suspected pea outline and the other suspected pea outlines is saved as the roundness difference; the cumulative sum of all the roundness differences of any suspected pea outline is saved as the overall roundness difference; the cumulative sum of the wrinkle strength of all suspected pea wrinkles in any suspected pea outline is saved as the overall wrinkle strength; the relative roundness granularity of any suspected pea outline shows a consistent trend relationship with the overall roundness difference and the total number of pixels in any suspected pea outline, and shows an opposite trend relationship with the overall wrinkle strength.
[0085] As an embodiment of the present application, the ratio of the overall roundness difference of any suspected pea outline to the overall wrinkle intensity is saved as an overall roundness parameter; and the normalized value of the product of the overall roundness parameter and the total number of pixels in any suspected pea outline is used as the relative roundness granularity of any suspected pea outline.
[0086] It should be understood that, when the suspected pea outline is more rounded than other suspected pea outlines in the pea steaming state diagram, and the intensity of the pea wrinkles is lower, it means that in the pea steaming state diagram, the water loss is less, the suspected pea outline is more likely to be a fresh pea, and the more the number of all pixels in the suspected pea outline is, the larger the rounded pea particle size corresponding to the suspected pea outline is, and the larger the relative rounded particle size is.
[0087] The fourth sub-step: controlling the boiling steaming time of the peas according to the changing characteristics of the relative roundness of all the suspected pea contours in the pea steaming state diagram within continuous moments.
[0088] The size and shape of the peas will affect the steaming time. Generally speaking, larger or irregularly shaped peas take longer to fully steam, while smaller, rounded peas may take less time. Therefore, the steaming time can be adjusted according to the roundness of the peas to ensure that all peas reach the appropriate taste and doneness. Based on this, control the boiling steaming time of peas:
[0089] Obtaining the relative roundness of all suspected pea contours in the pea steaming state diagram at any moment, arranging all the relative roundness in ascending order, and sequentially counting the number of suspected pea contours corresponding to each relative roundness to form a particle size distribution sequence at any moment;
[0090] A sequence consisting of pea steaming state diagrams at any moment and a preset number of moments before and after is used as a local extended sequence at any moment; the local extended sequence at any moment respectively obtains the pea steaming temperature difference and the DTW distance between the particle size distribution sequences at each moment and the next moment; the ratio of the pea steaming temperature difference to the DTW distance is obtained and saved as a steaming change index; the steaming change intensity factor at any moment is a measure of the central tendency of the steaming change index at all moments in the local extended sequence at any moment.
[0091] It should be noted that the measure of central tendency measures the degree of centralized distribution of a set of data, which may be: mean, median, mode, etc., and this application does not impose any restrictions on this.
[0092] As an embodiment of the present application, the preset number is 7, that is, the length of the local extended sequence is 7.
[0093] As an embodiment of the present application, the average value of the steaming change index at all moments in the local expansion sequence at any moment is taken as the steaming change intensity factor at each moment.
[0094] It should be understood that the faster the pea steaming temperature rises in the local expansion sequence and the greater the difference in the pea particle size distribution sequence, it means that during the pea steaming process, the pea steaming heat transfer is faster, the pea particle size has more significant changes, and the pea changes caused by steaming are stronger, that is, the steaming change intensity factor is larger.
[0095] The particle size distribution sequence at any moment is fitted to obtain the particle size distribution curve at any moment; a peak detection algorithm is used to obtain the relatively rounded particle size, peak height and peak width corresponding to the maximum peak in the particle size distribution curve to form the pea particle size peak distribution vector at each moment.
[0096] Among them, the particle size distribution curve diagram is as follows: Figure 4 As shown; the horizontal axis is the relative roundness of the particles; the vertical axis is the number of suspected pea outlines.
[0097] As an embodiment of the present application, the peak detection algorithm used is the Adaptive Multi-scale Peak Detection (AMPD) algorithm to obtain the pea particle size distribution vector; the AMPD algorithm is an existing well-known technology and will not be described in detail in this application.
[0098] It should be noted that the implementer may choose other methods to obtain the data corresponding to the maximum peak of the curve, the height of the peak, and the width of the peak, and this application does not impose any restrictions on this.
[0099] A sequence composed of components in the pea particle size peak distribution vector at all moments in the local extended sequence at any moment is obtained, recorded as each extended particle size peak component sequence, and a trend test algorithm is used to obtain the trend test statistic of each extended particle size peak component sequence; the steaming expansion feedback index at any moment and the sum of all the trend test statistics of the local extended sequence at the corresponding moment and the steaming change intensity factor present a consistent trend relationship.
[0100] As an embodiment of the present application, the trend test algorithm adopts the Mann-Kendall trend test algorithm. Among them, the Mann-Kendall trend test algorithm is an existing well-known technology and is not described in detail in this application. In addition, the implementer can flexibly adjust the length of the local extension sequence, and the selection of the trend test algorithm is not limited in this application.
[0101] As an embodiment of the present application, the product of the sum of all the trend test statistics of the local expansion sequence at any moment and the steaming change intensity factor is used as the steaming expansion feedback index at any moment.
[0102] It should be understood that when the trend test statistic is larger, it means that the particle size distribution has an increasing trend during the pea steaming process. The peas expand more significantly and the degree of pea maturity is higher during the steaming time. At this time, a shorter boiling steaming time should be used to prevent the boiling steaming time from being too long, which will cause the peas to expand too much, become too soft, and lose their original taste and nutrients.
[0103] The steaming expansion feedback index at all times is combined into a steaming feedback sequence, and the steaming feedback sequence and the pea steaming temperature sequence are used as inputs of the steaming time control model. In the embodiment of the present application, the steaming time control model adopts an LSTM (Long Short-Term Memory) neural network, the loss function is the Huber loss, the optimization function is the Adagrad function, and the output is the steaming optimization time. The steaming optimization time is used as the boiling steaming time in the pea ripening process.
[0104] Among them, the control flow chart of the boiling steaming time of peas is as follows: Figure 5 shown.
[0105] At this point, according to the steaming expansion state and expansion change of the peas, the optimal steaming time is obtained as the boiling steaming time in the pea ripening process, so as to obtain ripe peas with full ripening and high nutritional value retention.
[0106] Brown rice cooking:
[0107] The brown rice is cooked by frying; as an embodiment of the present application, the brown rice is put into an oil-free pan and dry-fried for 7 minutes.
[0108] Drying peas and quinoa:
[0109] Quinoa and peas are dried after being ripened; as an embodiment of the present application, the drying time is 48 hours and the drying temperature is 55°C.
[0110] Grinding and sieving:
[0111] The dried quinoa and peas, the low-temperature baked white kidney beans and oats, and the fried brown rice are ground into powder respectively, and passed through an 80-mesh sieve to obtain quinoa powder, white kidney bean powder, pea powder, oat powder, and brown rice powder.
[0112] Mixed flour:
[0113] Quinoa flour, white kidney bean flour, pea flour, oat flour, brown rice flour, guar gum, microcrystalline cellulose and erythritol are mixed to obtain a cereal meal replacement powder.
[0114] As an embodiment of the present application, quinoa flour, white kidney bean flour, pea flour, oat flour, brown rice flour, guar gum, microcrystalline cellulose, and erythritol are mixed in a mass ratio of 40:25:25:18:4:2.5:0.25:0.25.
[0115] The embodiment of the present application provides a low-carbon production process of cereal meal replacement powder based on process parameter adjustment, the method comprising: based on the roundness of the contour and the distribution of internal wrinkles of peas during the pea steaming process, combining the contour detection algorithm and the grayscale co-occurrence matrix, constructing a relatively rounded particle size, reflecting the possibility that the suspected pea contour belongs to a rounded pea and the particle size of the rounded pea, the beneficial effect of which is that the sharpness and fineness of the pea hilum are comprehensively considered, the distinction between the roundness characteristics of peas with sharp hilums and peas with full hilums is improved, and the accuracy of subsequent pea particle size distribution judgment is increased; according to the characteristic changes of the pea distribution during the pea steaming process, the relative roundness of all pea steaming can be obtained. The steaming expansion feedback index of the state diagram reflects the significant degree of steaming expansion of peas in a short period of time. The steaming time control model is adopted to control the boiling steaming time according to the rounded particle size and expansion quality of the peas during the steaming process, so as to avoid large fluctuations in the quality of different batches of peas and the inability to determine the boiling steaming time of different batches of peas. It also prevents the loss of the original taste and nutrients of peas due to inappropriate boiling steaming time, which directly affects the quality of the finished product of cereal meal replacement powder, ensures that the nutritional value of cereal meal replacement powder is retained, and improves the taste and flavor consistency of cereal meal replacement powder, which helps cereal meal replacement powder maintain its market competitiveness.
[0116] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.
[0117] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive.
Claims
1. A low-carbon production process for cereal meal replacement powder based on process parameter adjustment, characterized in that: The process includes: Soak quinoa in water, drain the water, and cook; Low temperature roasting of white kidney beans and oats; Steaming the peas and controlling the boiling and steaming time of the peas; Collect the pea steaming temperature sequence and the pea steaming state diagram at each moment; According to the pea steaming state diagram at each moment, all the suspected pea contours and suspected pea wrinkles at each moment are obtained; According to the distribution of all the suspected pea wrinkles in each suspected pea outline combined with the shape characteristics, the relative roundness of each suspected pea outline is obtained; According to the change characteristics of the relative roundness of all the suspected pea contours in the pea steaming state diagram at continuous moments, the boiling steaming time of the peas is controlled; Fry the brown rice; Drying the cooked quinoa and peas; Grind the dried quinoa and peas, the low-temperature baked white kidney beans and oats, and the fried brown rice respectively, and sieve them to obtain quinoa powder, white kidney bean powder, pea powder, oat powder, and brown rice powder; Mix quinoa flour, white kidney bean flour, pea flour, oat flour, brown rice flour, guar gum, microcrystalline cellulose, and erythritol to obtain a cereal meal replacement powder; The acquisition process of all the suspected pea contours and suspected pea wrinkles at each moment is as follows: A contour detection algorithm is used to obtain all the highest-level contours in the pea steaming state diagram and all the secondary contours inside each highest-level contour, and all the highest-level closed contours are saved as suspected pea contours, and all the secondary contours inside the highest-level closed contours are saved as suspected pea wrinkles; The method for obtaining the relatively rounded particle size of each suspected pea outline is as follows: For the pea steaming state diagram at each moment, the minimum circumscribed rectangle of each suspected pea wrinkle in any suspected pea outline is obtained, and the contrast of the gray level co-occurrence matrix in each preset direction of the minimum circumscribed rectangle is saved as the suspected wrinkle contrast in each preset direction of each suspected pea wrinkle; For any of the suspected pea contours, the wrinkle pixel ratio of each suspected pea wrinkle is obtained, and the ratio of the mean to the variance of the suspected wrinkle contrast of each suspected pea wrinkle in all preset directions is obtained, and saved as the contrast dispersion; the wrinkle intensity of each suspected pea wrinkle shows a consistent trend relationship with the contrast dispersion and the wrinkle pixel ratio; According to the shape characteristics of each suspected pea outline in the pea steaming state diagram, the pea roundness of each suspected pea outline is obtained; For the pea steaming state diagram at each moment, the difference between the pea roundness of any suspected pea outline and the rest of the suspected pea outlines is saved as the roundness difference; the cumulative sum of all the roundness differences of any suspected pea outline is saved as the overall roundness difference; the cumulative sum of the wrinkle strength of all the suspected pea wrinkles in any suspected pea outline is saved as the overall wrinkle strength; the relative roundness granularity of any suspected pea outline shows a consistent trend relationship with the overall roundness difference and the total number of pixels in any suspected pea outline, and shows an opposite trend relationship with the overall wrinkle strength; The step of obtaining the pea roundness of each suspected pea outline comprises: The center point of each suspected pea contour is taken as each suspected pea center, and the Euclidean distance from each contour point in each suspected pea contour to the corresponding suspected pea center is taken as the pea contour deviation distance of each contour point; the sequence composed of all the pea contour deviation distances in each suspected pea contour is taken as each contour deviation distance sequence, and the natural breakpoint algorithm is used to obtain each center deviation group; Obtain the distance between the contour points corresponding to any two elements in each center deviation group, and use the cumulative sum of all the distances of each center deviation group as the deviation roundness weight; use the element mean of each center deviation group as the deviation strength; use the element mean of the contour deviation distance sequence as the contour average skewness; use the absolute value of the difference between the deviation strength of each center deviation group and the contour average skewness as the deviation difference, calculate the ratio of the deviation roundness weight of each center deviation group to the deviation difference, and save it as the roundness factor of each center deviation group; use the cumulative sum of the roundness factors of all center deviation groups as the pea roundness of each suspected pea contour; The step of controlling the boiling steaming time of the peas comprises: Obtaining the relative roundness of all suspected pea contours in the pea steaming state diagram at any moment, arranging all the relative roundness in ascending order, and sequentially counting the number of suspected pea contours corresponding to each relative roundness to form a particle size distribution sequence at any moment; The sequence composed of the pea steaming state diagrams at any moment and a preset number of moments before and after is used as the local extended sequence at any moment; the DTW distance between the pea steaming temperature difference and the particle size distribution sequence at each moment and the next moment is obtained respectively; the ratio of the pea steaming temperature difference to the DTW distance is obtained and saved as the steaming change index; the steaming change intensity factor at any moment is a measure of the central tendency of the steaming change index at all moments in the local extended sequence at any moment; The particle size distribution sequence at any moment is fitted to obtain the particle size distribution curve at any moment; a peak detection algorithm is used to obtain the relatively rounded particle size, peak height and peak width corresponding to the maximum peak in the particle size distribution curve to form the pea particle size peak distribution vector at each moment; A sequence composed of components in the pea particle size peak distribution vector at all times in the local extended sequence at any time is obtained, recorded as each extended particle size peak component sequence, and a trend test algorithm is used to obtain the trend test statistic of each extended particle size peak component sequence; the steaming expansion feedback index at any time and the sum of all the trend test statistics of the local extended sequence at the corresponding time and the steaming change intensity factor show a consistent trend relationship; The steaming expansion feedback indexes at all times are combined into a steaming feedback sequence; and the boiling steaming time of the peas is obtained according to the steaming feedback sequence and the pea steaming temperature sequence in combination with a neural network.
2. The low-carbon production process of cereal meal replacement powder based on process parameter adjustment according to claim 1, characterized in that: The cooking time is 5 minutes from the time the water boils.
3. The low-carbon production process of cereal meal replacement powder based on process parameter adjustment according to claim 1, characterized in that: The low-temperature baking is performed at a temperature of 130° C. and a time of 1 hour.
4. The low-carbon production process of cereal meal replacement powder based on process parameter adjustment according to claim 1, characterized in that: The specific operation of frying the brown rice is to put the brown rice into an oil-free pan and dry-fry the brown rice for 7 minutes.
5. The low-carbon production process of cereal meal replacement powder based on process parameter adjustment according to claim 1, characterized in that: The drying temperature is 55° C. and the drying time is 48 hours.
6. The low-carbon production process of cereal meal replacement powder based on process parameter adjustment according to claim 1, characterized in that: The mass ratio of mixing quinoa flour, white kidney bean flour, pea flour, oat flour, brown rice flour, guar gum, microcrystalline cellulose and erythritol is 40:25:25:18:4:2.5:0.25:0.25.
