Feed particle processing method and system using fermented silkworm excrement as raw material

Abstract

The invention belongs to the technical field of anomaly recognition, and provides a feed particle processing method and system with fermented silkworm excrement as a raw material, and the method specifically comprises the steps: firstly, arranging an infrared thermal imager in a conditioner in a feed granulator, collecting and storing infrared images in real time through the infrared thermal imager in a low-temperature granulation process, obtaining an infrared image sequence, and carrying out the low-temperature granulation process through the infrared image sequence; the method comprises the following steps of: acquiring a plurality of infrared images, performing regional division on the infrared images to obtain a plurality of processing regions, performing gelatinization missing risk analysis on a low-temperature processing process of each micro-processing region to obtain a gelatinization null value, and performing gelatinization anomaly identification on the feed according to the gelatinization null value. The local gelatinization hysteresis phenomenon caused by micromechanisms such as heat transfer path delay, particle heat capacity difference and moisture migration limitation is accurately dealt with through gelatinization deletion risk analysis, and feed particles with the pulverization risk are positioned in the feed subjected to low-temperature treatment, so that the feed pulverization risk of the raw material prepared from the fermented silkworm excrement is reduced, and the feed pulverization risk of the raw material prepared from the fermented silkworm excrement is reduced. The feed quality is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of abnormality recognition, and in particular relates to a method and system for processing feed pellets using fermented silkworm excrement as raw materials. Background Art

[0002] Fermented silkworm excrement, as a feed ingredient, can significantly promote animal growth. This growth-boosting effect is primarily due to its ability to regulate the intestinal microbiome. Fermented silkworm excrement is rich in probiotics, typically lactic acid bacteria and yeasts. These beneficial bacteria significantly improve the balance of the animal's intestinal microbiome, enhancing digestive immunity and reducing the risk of intestinal diseases. Fermented silkworm excrement can also improve feed utilization. Silkworm excrement is rich in crude fiber. While cellulose and hemicellulose in silkworm excrement and basic feed are inherently difficult to digest, microbial fermentation degrades these components, making them more readily absorbed by animals. One method for making feed from fermented silkworm excrement is to mix it with other feed ingredients and then extrude it into pellets in a pelletizer to improve palatability and storage stability. However, the pelleting process requires high temperatures to gelatinize raw materials such as corn and rice bran, making the pellets more sticky and reducing the risk of powdering. However, high temperatures also inevitably kill a large number of probiotics in the fermented silkworm excrement. Therefore, low-temperature pelleting is preferred. The most direct drawback of low-temperature pelleting is powdering due to insufficient gelatinization. Therefore, there is an urgent need for a method and system for processing feed pellets using fermented silkworm excrement as raw material. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for processing feed pellets using fermented silkworm excrement as raw material, so as to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0004] In order to achieve the above object, according to one aspect of the present invention, a method for processing feed pellets using fermented silkworm excrement as raw material is provided, the method comprising the following steps: S100, equips feed pellet drying equipment with infrared thermal imager; S200, during the low-temperature granulation process, infrared images are collected and stored in real time by an infrared thermal imager to obtain an infrared image sequence; S300, dividing the infrared image into regions to obtain a plurality of processing regions; S400, performing gelatinization loss risk analysis on the low-temperature treatment process of each micro-treatment zone to obtain a gelatinization null value; S500: identifying gelatinization abnormality of the feed according to the gelatinization null value.

[0005] Furthermore, in step S100, the method for equipping the feed pellet drying device with an infrared thermal imager is as follows: the feed pellet drying device includes a low-temperature drying oven, a hot air drying oven, or a low-temperature air drying oven; and the infrared thermal imager is arranged in the feed pellet drying device so that the infrared thermal imager is arranged at a position where heat radiation from the surface of the feed pellet forming area can be seen.

[0006] Infrared thermal imagers can also be infrared scanners, near-infrared industrial cameras, or multispectral imagers. The structural designs of different feed pellet mills can vary significantly. If installation conditions are limited, such as space constraints or insufficient electromagnetic interference protection, hardware adaptation may be required through custom brackets or adapter modules.

[0007] In traditional feed pellet drying equipment, the low-temperature pelletizing strategy leads to uneven temperature distribution in the forming area, which can easily lead to insufficiently gelatinized pellets in areas with insufficient heat conduction, thus causing pulverization. This method uses an infrared thermal imaging device installed in the pelletizing channel or pellet extrusion outlet of the feed pellet processing equipment to capture real-time thermal radiation images of the surface of the pellets formed by extrusion of the feed raw materials during the pelletizing process. The infrared thermal imaging device uses non-contact infrared sensing to capture the temperature distribution status of various local areas during the pelletizing process. The image data obtained will subsequently serve as the basis for determining whether there are gelatinization voids.

[0008] Furthermore, in step S200, during the low-temperature pelleting process, infrared images are captured and stored in real time using an infrared thermal imager. The infrared image sequence is obtained by capturing and storing infrared images in real time within the low-temperature drying oven when pelleting begins. This process continues until the pelleting process ends, with all infrared images forming an infrared image sequence. The capture interval is 5-20 seconds; that is, the captured images are stored at a set interval to form an infrared image sequence of the feed pellets during the drying process. The low-temperature pelleting process can last from 2 to 24 hours, so the total number of images in the infrared image sequence should be at least 500 to fully explore microscopic trends.

[0009] The infrared image reflects the temperature distribution state of the particle surface at any drying process moment. The continuously acquired infrared images constitute the temporal temperature evolution trajectory of the drying process, which is used for gelatinization risk assessment of each subdivided area in subsequent steps and is the core data basis for the subsequent optimization control of zoned heat treatment.

[0010] Furthermore, in step S300, the method for performing regional division from the infrared image to obtain a plurality of processing areas is as follows: performing regular spatial division on each frame of the infrared image in the infrared image sequence to obtain an image grid, which is recorded as a micro-processing area, and establishing an association relationship between each micro-processing area and a predetermined area in the drying box.

[0011] Regularized spatial partitioning involves processing infrared thermal images into two-dimensional grids according to uniform geometric rules to achieve a structured representation of the image space. This is implemented using the np.zeros() function in OpenCV. Regularized partitioning is a fixed grid slicing algorithm based on the image pixel matrix. It divides the original thermal image into m×n rectangular processing areas, or micro-processing areas. Each micro-processing area corresponds to a set of pixels in an area of ​​the image.

[0012] Furthermore, in step S400, the method for performing gelatinization missing risk analysis on the low-temperature treatment process of each micro-processed area to obtain gelatinization null values ​​is as follows: recording the median value of the pixel value of the micro-processed area as its corresponding grayscale value to form a grayscale value time series of the micro-processed area in the infrared image sequence; performing first-order difference on the grayscale value time series to extract the grayscale change rate of each frame; The first-order difference refers to the subtraction of any element from the first element in the reverse time direction, and the ratio of the difference obtained to the first element in the reverse time direction is the grayscale change rate; Identify a continuous frame segment with a change rate amplitude lower than a preset fluctuation threshold as a plateau period, and extract the number of frames in this segment as the plateau period length Tf; The preset fluctuation threshold is ε∈[0.3%, 1.5%]. If the thermal inertia of the heating process is large, it is recommended to set a smaller fluctuation threshold. The large thermal inertia of the heating process can also be converted to the heating rate of the heating process. Or if the infrared image noise is low, the preset fluctuation threshold can be set to a small threshold. A continuous frame segment is composed of each consecutive moment with a change rate amplitude lower than the preset fluctuation threshold. Each moment with a change rate amplitude lower than the preset fluctuation threshold belongs to only one continuous frame segment. Extract the starting time position Ts of the plateau period; where the starting time position is the serial number of the frame in the gray value time series; A weighted function is constructed based on Tf and Ts to obtain the gelatinization null value of the micro-processing area.

[0013] The specific process is as follows: the ratio of the plateau length to the total length of the grayscale value time series is the participation weight Pwt, the ratio of the starting time position to the total length of the grayscale value time series is the trigger position weight Tpwt, and the gelatinization null value is Gnv = Pwt × exp(-α × Tpwt); where α is the preset plateau concern coefficient, and its value range is [0.3, 1]. The shorter the platform segment, the greater the need to improve the sensitivity of the gelatinization null value, and a larger platform concern coefficient is taken. Otherwise, a smaller value is taken. The default value is 1. In the case of the same feed material ratio, the platform concern coefficient can use the same value.

[0014] The gelatinization void value calculated at each time point quantifies the response time difference from initial heating to the formation of the thermal equilibrium interval, and uses the plateau stability as a weighted correction to microscopically map the degree of thermal response lag caused by differences in regional heat capacity, fiber distribution, or moisture content. Since it is a measurement method based on time series feature extraction, it does not rely on the structure of the pellet machine or drying device and direct material detection, effectively exploring the reproducibility and quantifiability of the thermal state evolution in the time dimension, thereby providing a mathematical basis for further precise identification of the internal thermal field uniformity of complex granulation systems or compensation measures. However, the above-mentioned gelatinization void value constructed based on the starting frame and duration of the platform segment has quantified the trend of thermal response lag in the region in the time dimension, but it still has two key limitations: On the one hand, it is overly dependent on the accurate identification of the platform segment. When the image grayscale signal fluctuates greatly or the platform segment itself is short, the plateau boundary is easily disturbed by noise, which will lead to increased volatility of the gelatinization void value; on the other hand, this process relies on overall thermal stability, but fails to further characterize the boundary clarity and persistence of the abnormal area in the spatial distribution, making it difficult to effectively identify high-risk areas with significant local thermal lag. Therefore, this method also provides another method for calculating the gelatinization void value as follows: Furthermore, in step S400, a method for performing gelatinization loss risk analysis on the low-temperature treatment process of each micro-processing area to obtain a gelatinization null value is as follows: the lower quartile value of each pixel value in the micro-processing area is recorded as an inefficiency mark value, and the difference between the inefficiency mark value and the minimum pixel value in the micro-processing area is defined as an inefficiency interval; the difference between the inefficiency mark value at any moment and the previous moment is defined as an inefficiency mark increment; if the value of the inefficiency mark increment is a negative number, it is marked that an inefficiency event has occurred at the corresponding moment, and the ratio of the number of moments when the inefficiency event occurred to the number of moments when the inefficiency event did not occur is recorded as the inefficiency coefficient Tsic; The ratio of the inefficiency interval to the inefficiency mark value is recorded as the inefficiency product Iev. The median of the inefficiency product at the time of the inefficiency event is the product level Iev.base. If the inefficiency product corresponding to an inefficiency event is less than the product level, the moment is marked as a preheating void point. If the preheating void point is smaller than the inefficiency product corresponding to the first inefficiency event in the reverse time direction, the moment is defined as the first gelatinization void point. For any first gelatinization void point, the time of the first inefficiency event with an inefficiency product greater than the product level is searched in the forward time direction. The number of time intervals between the obtained time and any first gelatinization void point is recorded as the cavitation recovery distance Crd. The gelatinization void value Gnv is calculated based on the cavitation recovery distance of the first gelatinization void point and the lateral inefficiency coefficient. Its mathematical expression is as follows: ; Where i1 is the cumulative variable, lg() is the logarithmic function with base 10, exp() is the exponential function with the natural constant e as the base, Crd i1 and Ievi1 They represent the cavitation recovery distance and inefficiency product corresponding to the i1th first gelatinization void point, and num is the number of the first gelatinization void points.

[0015] The previous moment refers to the moment in the reverse time direction; the normalization process uses the minmax method to limit all values ​​to between 0 and 1.

[0016] Beneficial effects: By modeling the time series changes in the grayscale values ​​of the infrared images of the treatment area during the drying process, the behavioral characteristics reflecting the hysteresis of heat absorption or abnormal temperature response are extracted to calculate the gelatinization void value, thereby achieving a quantitative assessment of the risk of gelatinization loss at a local spatial scale, and quantifying the gelatinization hysteresis behavior caused by internal heat transfer obstacles, heat capacity differences or water migration speed differences in the material, thereby providing data support for subsequent abnormal area identification and differentiated heat supplementation intervention, making the pelleting process more dynamic and responsive, and significantly improving the consistency and controllability of feed pellets.

[0017] Furthermore, in step S500, the method for identifying gelatinization abnormalities of feed based on gelatinization null values ​​is as follows: gelatinization null values ​​corresponding to each micro-processing area are formed into a gelatinization null value set and standardized, and the upper quartile value and standard deviation of the null value set are respectively recorded as the first abnormal threshold and threshold gradient; the micro-processing area corresponding to the element greater than the upper quartile value in the null value set is recorded as the first abnormal area, and the difference between the gelatinization null value and the threshold gradient of the first abnormal area is recorded as the second abnormal threshold; if the set consisting of the gelatinization null values ​​corresponding to the eight neighborhoods of the first abnormal area is recorded as the gelatinization gradient set, if more than half of the elements in the gelatinization gradient set are greater than the second abnormal threshold, it is determined that gelatinization abnormality occurs in the first abnormal area, otherwise, no gelatinization abnormality occurs.

[0018] This step identifies anomalies based on the distribution pattern of the gelatinization void value set and the behavior of local spatial thermal diffusion. By introducing the upper quartile and standard deviation to characterize globally high-value areas, the local gradient response is extracted based on the changing trend of the gelatinization void value in the eight-neighborhood region. This microscopically maps the continuity principle and the minimum heat consumption path principle in the heat conduction process. Because thermal energy diffusion tends to flow toward areas with large temperature gradients, if the gelatinization void value in a treatment area is significantly higher than that in the surrounding area and the surrounding areas also show a synchronous upward trend, it indicates that there is energy retention or imbalance in the thermal resistance of the material, which violates the trend of uniform heat conduction and suggests that local gelatinization obstruction has occurred in the actual granulation process. Therefore, this method achieves accurate gelatinization anomaly determination from two dimensions: data distribution statistics and spatial thermal field disturbance.

[0019] Furthermore, in step S500, the method for identifying abnormal gelatinization of feed according to the gelatinization empty value further includes: screening feed particles corresponding to the micro-processing area where abnormal gelatinization occurs, and then performing steam high-temperature gelatinization treatment.

[0020] Since low-temperature granulation is intended to retain the activity of active probiotics such as lactic acid bacteria and yeast in fermented silkworm feces, it is easy to cause local heat deficiency, resulting in incomplete gelatinization of particles, loose structure or increased pulverization rate. If the entire batch of feed is heated at high temperature, it will cause large-scale inactivation of probiotics, which violates the original intention of low-temperature granulation. Therefore, the present invention accurately locates abnormal areas through image recognition, and only performs local steam high-temperature gelatinization treatment on the identified gelatinization abnormality treatment area. While ensuring the quality of particle formation, it retains the overall probiotic activity to the greatest extent, achieving dual protection of feed functionality and structural performance.

[0021] Preferably, all undefined variables in the present invention, if not clearly defined, can be manually set thresholds.

[0022] The present invention also provides a feed pellet processing system using fermented silkworm excrement as raw material. The feed pellet processing system using fermented silkworm excrement as raw material includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the feed pellet processing method using fermented silkworm excrement as raw material are implemented. The feed pellet processing system using fermented silkworm excrement as raw material can be run on computing devices such as desktop computers, laptop computers, PDAs, and cloud data centers. The executable system may include, but is not limited to, a processor, a memory, and a server cluster. The processor executes the computer program to run in the following system units: Infrared thermal imaging arrangement unit, used for arranging an infrared thermal imager in the conditioner of the feed pellet machine; A real-time monitoring unit is used to collect and store infrared images in real time during the low-temperature granulation process using an infrared thermal imager to obtain an infrared image sequence; A region division unit, used for performing region division on the infrared image to obtain a plurality of processing regions; The gelatinization loss analysis unit is used to perform gelatinization loss risk analysis on the low-temperature treatment process of each micro-treatment zone to obtain gelatinization null values; The gelatinization abnormality identification unit is used to identify gelatinization abnormality of feed according to the gelatinization empty value.

[0023] The beneficial effects of the present invention are as follows: based on the thermal response hysteresis characteristics of fermented silkworm feces under low-temperature granulation conditions, and targeting microstructural factors such as high cellulose and hemicellulose content, uneven water migration channels, and complex heat capacity distribution, an identification method for identifying feed gelatinization deficiency is proposed. By quantifying the gelatinization void value, the image thermal response data is used to objectively characterize the degree of local gelatinization deficiency caused by factors such as heat conduction hysteresis, heat capacity differences, or limited water migration in the particles during the low-temperature granulation process. This effectively solves the problem of local powdering caused by insufficient overall heat while protecting the activity of probiotics in fermented silkworm feces during low-temperature granulation. This breaks the limitation of traditional processes that it is difficult to balance gelatinization uniformity and bacterial activity protection, and significantly improves feed quality factors such as the structural stability and storage palatability of feed particles. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and other features of the present invention will become more apparent through a detailed description of the embodiments shown in conjunction with the accompanying drawings. In the drawings of the present invention, the same reference numerals represent the same or similar elements. Obviously, the drawings described below are only some embodiments of the present invention. It is possible for a person skilled in the art to derive other drawings based on these drawings without inventive effort. In the drawings: Figure 1 Shown is a flow chart of a method for processing feed pellets using fermented silkworm excrement as raw material; Figure 2 Shown is a structural diagram of a feed pellet processing system using fermented silkworm feces as raw material. DETAILED DESCRIPTION

[0025] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless there is a conflict.

[0026] Example 1 like Figure 1 The figure shows a flow chart of a feed pellet processing method using fermented silkworm excrement as raw material. Figure 1 A method for processing feed pellets using fermented silkworm excrement as raw material according to an embodiment of the present invention is described, the method comprising the following steps: S100, equips feed pellet drying equipment with infrared thermal imager; S200, during the low-temperature granulation process, infrared images are collected and stored in real time by an infrared thermal imager to obtain an infrared image sequence; S300, dividing the infrared image into regions to obtain a plurality of processing regions; S400, performing gelatinization loss risk analysis on the low-temperature treatment process of each micro-treatment zone to obtain a gelatinization null value; S500: identifying gelatinization abnormality of the feed according to the gelatinization null value.

[0027] Furthermore, in step S100, the method for equipping the feed pellet drying device with an infrared thermal imager is as follows: the feed pellet drying device includes a low-temperature drying oven, a hot air drying oven, or a low-temperature air drying oven; and the infrared thermal imager is arranged in the feed pellet drying device so that the infrared thermal imager is arranged at a position where heat radiation from the surface of the feed pellet forming area can be seen.

[0028] Infrared thermal imagers can also be infrared scanners, near-infrared industrial cameras, or multispectral imagers. The structural designs of different feed pellet mills can vary significantly. If installation conditions are limited, such as space constraints or insufficient electromagnetic interference protection, hardware adaptation may be required through custom brackets or adapter modules.

[0029] Furthermore, in step S200, during the low-temperature pelleting process, infrared images are captured and stored in real time using an infrared thermal imager. The infrared image sequence is obtained by capturing and storing infrared images in real time within the low-temperature drying oven when pelleting begins. This process continues until the pelleting process ends, with all infrared images forming an infrared image sequence. The capture interval is 5-20 seconds; that is, the captured images are stored at a set interval to form an infrared image sequence of the feed pellets during the drying process. The low-temperature pelleting process can last from 2 to 24 hours, so the total number of images in the infrared image sequence should be at least 500 to fully explore microscopic trends.

[0030] Furthermore, in step S300, the method for performing regional division from the infrared image to obtain a plurality of processing areas is as follows: performing regular spatial division on each frame of the infrared image in the infrared image sequence to obtain an image grid, which is recorded as a micro-processing area, and establishing an association relationship between each micro-processing area and a predetermined area in the drying box.

[0031] Regularized spatial partitioning involves processing infrared thermal images into two-dimensional grids according to uniform geometric rules to achieve a structured representation of the image space. This is implemented using the np.zeros() function in OpenCV. Regularized partitioning is a fixed grid slicing algorithm based on the image pixel matrix. It divides the original thermal image into m×n rectangular processing areas, or micro-processing areas. Each micro-processing area corresponds to a set of pixels in an area of ​​the image.

[0032] Furthermore, in step S400, the method for performing gelatinization missing risk analysis on the low-temperature treatment process of each micro-processed area to obtain gelatinization null values ​​is as follows: recording the median value of the pixel value of the micro-processed area as its corresponding grayscale value to form a grayscale value time series of the micro-processed area in the infrared image sequence; performing first-order difference on the grayscale value time series to extract the grayscale change rate of each frame; The first-order difference refers to the subtraction of any element from the first element in the reverse time direction, and the ratio of the difference obtained to the first element in the reverse time direction is the grayscale change rate; Identify a continuous frame segment with a change rate amplitude lower than a preset fluctuation threshold as a plateau period, and extract the number of frames in this segment as the plateau period length Tf; The preset fluctuation threshold is ε∈[0.3%, 1.5%]. If the thermal inertia of the heating process is large, it is recommended to set a smaller fluctuation threshold. The large thermal inertia of the heating process can also be converted to the heating rate of the heating process. Or if the infrared image noise is low, the preset fluctuation threshold can be set to a small threshold. A continuous frame segment is composed of each consecutive moment with a change rate amplitude lower than the preset fluctuation threshold. Each moment with a change rate amplitude lower than the preset fluctuation threshold belongs to only one continuous frame segment. Extract the starting time position Ts of the plateau period; where the starting time position is the serial number of the frame in the gray value time series; A weighted function is constructed based on Tf and Ts to obtain the gelatinization null value of the micro-processing area.

[0033] The specific process is as follows: the ratio of the plateau length to the total length of the grayscale value time series is the participation weight Pwt, the ratio of the starting time position to the total length of the grayscale value time series is the trigger position weight Tpwt, and the gelatinization null value is Gnv = Pwt × exp(-α × Tpwt); where α is the preset plateau concern coefficient, and its value range is [0.3, 1]. The shorter the platform segment, the greater the need to improve the sensitivity of the gelatinization null value, and a larger platform concern coefficient is taken. Otherwise, a smaller value is taken. The default value is 1. In the case of the same feed material ratio, the platform concern coefficient can use the same value.

[0034] Furthermore, in step S500, the method for identifying gelatinization abnormalities of feed based on gelatinization null values ​​is as follows: gelatinization null values ​​corresponding to each micro-processing area are formed into a gelatinization null value set and standardized, and the upper quartile value and standard deviation of the null value set are respectively recorded as the first abnormal threshold and threshold gradient; the micro-processing area corresponding to the element greater than the upper quartile value in the null value set is recorded as the first abnormal area, and the difference between the gelatinization null value and the threshold gradient of the first abnormal area is recorded as the second abnormal threshold; if the set consisting of the gelatinization null values ​​corresponding to the eight neighborhoods of the first abnormal area is recorded as the gelatinization gradient set, if more than half of the elements in the gelatinization gradient set are greater than the second abnormal threshold, it is determined that gelatinization abnormality occurs in the first abnormal area, otherwise, no gelatinization abnormality occurs.

[0035] This step identifies anomalies based on the distribution pattern of the gelatinization void value set and the behavior of local spatial thermal diffusion. By introducing the upper quartile and standard deviation to characterize globally high-value areas, the local gradient response is extracted based on the changing trend of the gelatinization void value in the eight-neighborhood region. This microscopically maps the continuity principle and the minimum heat consumption path principle in the heat conduction process. Because thermal energy diffusion tends to flow toward areas with large temperature gradients, if the gelatinization void value in a treatment area is significantly higher than that in the surrounding area and the surrounding areas also show a synchronous upward trend, it indicates that there is energy retention or imbalance in the thermal resistance of the material, which violates the trend of uniform heat conduction and suggests that local gelatinization obstruction has occurred in the actual granulation process. Therefore, this method achieves accurate gelatinization anomaly determination from two dimensions: data distribution statistics and spatial thermal field disturbance.

[0036] Furthermore, in step S500, the method for identifying abnormal gelatinization of feed according to the gelatinization empty value further includes: screening feed particles corresponding to the micro-processing area where abnormal gelatinization occurs, and then performing steam high-temperature gelatinization treatment.

[0037] Since low-temperature granulation is intended to retain the activity of active probiotics such as lactic acid bacteria and yeast in fermented silkworm feces, it is easy to cause local heat deficiency, resulting in incomplete gelatinization of particles, loose structure or increased pulverization rate. If the entire batch of feed is heated at high temperature, it will cause large-scale inactivation of probiotics, which violates the original intention of low-temperature granulation. Therefore, the present invention accurately locates abnormal areas through image recognition, and only performs local steam high-temperature gelatinization treatment on the identified gelatinization abnormality treatment area. While ensuring the quality of particle formation, it retains the overall probiotic activity to the greatest extent, achieving dual protection of feed functionality and structural performance.

[0038] Example 2 Example 2 uses the same gelatinization anomaly identification method as Example 1, except that, in step S400, gelatinization loss risk analysis is performed on the low-temperature treatment process of each micro-processing zone to obtain a gelatinization null value. The lower quartile value of each pixel value in the micro-processing zone is recorded as an inefficiency mark value, and the difference between the inefficiency mark value and the minimum pixel value in the micro-processing zone is defined as the inefficiency interval. The difference between the inefficiency mark value at any moment and the previous moment is defined as the inefficiency mark increment. If the value of the inefficiency mark increment is a negative number, an inefficiency event is marked as occurring at the corresponding moment. The ratio of the number of moments when inefficiency events occur to the number of moments when inefficiency events do not occur is recorded as the inefficiency coefficient Tsic. The ratio of the inefficiency interval to the inefficiency mark value is recorded as the inefficiency product Iev. The median of the inefficiency product at the time of the inefficiency event is the product level Iev.base. If the inefficiency product corresponding to an inefficiency event is less than the product level, the moment is marked as a preheating void point. If the preheating void point is smaller than the inefficiency product corresponding to the first inefficiency event in the reverse time direction, the moment is defined as the first gelatinization void point. For any first gelatinization void point, the time of the first inefficiency event with an inefficiency product greater than the product level is searched in the forward time direction. The number of time intervals between the obtained time and any first gelatinization void point is recorded as the cavitation recovery distance Crd. The gelatinization void value Gnv is calculated based on the cavitation recovery distance of the first gelatinization void point and the lateral inefficiency coefficient. Its mathematical expression is as follows: ; Where i1 is the cumulative variable, lg() is the logarithmic function with base 10, exp() is the exponential function with the natural constant e as the base, Crd i1 and Iev i1 They represent the cavitation recovery distance and inefficiency product corresponding to the i1th first gelatinization void point, and num is the number of the first gelatinization void points.

[0039] The previous moment refers to the moment in the reverse time direction; the normalization process uses the minmax method to limit all values ​​to between 0 and 1.

[0040] In order to verify the effect of the gelatinization abnormality identification and supplementary heat treatment method proposed in the present invention on alleviating the powdering problem during the low-temperature granulation process, the following experimental scheme was designed and the following comparative data were obtained. The same batch of fermented silkworm feces feed raw materials were selected, and three groups of control experiments were set up: the comparative example, Example 1 and Example 2. Among them, the comparative example only adopted the traditional low-temperature granulation method, and did not introduce any infrared image recognition mechanism and subsequent supplementary heat mechanism; Example 1 identified gelatinization abnormalities in the micro-processed area based on the first-order difference of the image platform period and the fluctuation threshold; Example 2 performed abnormality assessment based on the platform grayscale change rate and the system determination coefficient. After granulation and screening, the weight of the three groups of feed particles was measured, and the weight of the identified abnormal area, the weight of the correctly identified powdered area, and the weight of the misidentified area were respectively measured, and the powdering recognition accuracy was calculated accordingly. Among them, Example 1 and Example 2 took half of the weight of the identified abnormal area and applied it to the subsequent supplementary heat mechanism, and reversed it to the complete treatment weight to obtain the differentiation rate result after supplementary heat.

[0041] Table 1 Comparison of recognition rates of powdering anomalies

[0042] As shown in Table 1, under the same batch of feed raw materials and low-temperature granulation process conditions, both Example 1 and Example 2 showed significantly better pulverization anomaly recognition capabilities than the control example. Among them, Example 2 achieved a 93.5% pulverization recognition accuracy rate by constructing a combination mechanism between the grayscale change rate in the plateau period and the determination coefficient, which was significantly higher than 89.7% of Example 1 and 0% of the control example, indicating that it is more sensitive and accurate in judging grayscale differences in microscopic images. In contrast, the control example did not use infrared image analysis means and was unable to actively identify potential pulverization areas, resulting in the inability to perform subsequent high-temperature heating, which brought about the problem of insufficient feed quality. This method significantly improves the pertinence and efficiency of the heat treatment by accurately identifying the gelatinization lag area, and maximizes the protection of probiotic activity and the guarantee of particle stability, verifying the technical superiority and practical value of the present invention in the field of animal feed granulation.

[0043] The embodiment of the present invention provides a feed pellet processing system using fermented silkworm excrement as raw material, such as Figure 2 The figure shows a structural diagram of a feed pellet processing system using fermented silkworm excrement as raw material according to the present invention. The feed pellet processing system using fermented silkworm excrement as raw material in this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the embodiment of the feed pellet processing method using fermented silkworm excrement as raw material are implemented.

[0044] The system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following units of the system: Infrared thermal imaging arrangement unit, used for arranging an infrared thermal imager in the conditioner of the feed pellet machine; A real-time monitoring unit is used to collect and store infrared images in real time during the low-temperature granulation process using an infrared thermal imager to obtain an infrared image sequence; A region division unit, used for performing region division on the infrared image to obtain a plurality of processing regions; The gelatinization loss analysis unit is used to perform gelatinization loss risk analysis on the low-temperature treatment process of each micro-treatment zone to obtain gelatinization null values; The gelatinization abnormality identification unit is used to identify gelatinization abnormality of feed according to the gelatinization empty value.

[0045] The feed pellet processing system using fermented silkworm excrement as raw material can be run on computing devices such as desktop computers, laptops, PDAs, and cloud servers. Systems that can run on the feed pellet processing system using fermented silkworm excrement as raw material may include, but are not limited to, processors and memory. Those skilled in the art will understand that the example described is merely an illustration of a feed pellet processing system using fermented silkworm excrement as raw material and does not constitute a limitation on the entire feed pellet processing system. The system may include more or fewer components than the example, or a combination of certain components, or different components. For example, the feed pellet processing system using fermented silkworm excrement as raw material may also include input and output devices, network access devices, buses, and the like.

[0046] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the feed pellet processing system using fermented silkworm excrement as raw material, and utilizes various interfaces and circuits to connect various parts of the entire feed pellet processing system using fermented silkworm excrement as raw material.

[0047] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the feed pellet processing system using fermented silkworm excrement as raw material by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data and a phone book). Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0048] Although the present invention has been described in considerable detail and with particularity with respect to several embodiments, it is not intended to limit the present invention to any of these details or embodiments or any particular embodiment, so as to effectively encompass the intended scope of the present invention. In addition, the present invention has been described above with respect to embodiments foreseen by the inventors for the purpose of providing a useful description, and those insubstantial modifications of the present invention that are not currently foreseen may still represent equivalent modifications of the present invention.

Claims

1. A method for processing feed pellets using fermented silkworm excrement as raw material, characterized in that: The method comprises the following steps: S100, equips feed pellet drying equipment with infrared thermal imager; S200, during the low-temperature granulation process, infrared images are collected and stored in real time by an infrared thermal imager to obtain an infrared image sequence; S300, dividing the infrared image into regions to obtain a plurality of processing regions; S400, performing gelatinization loss risk analysis on the low-temperature treatment process of each micro-treatment zone to obtain a gelatinization null value; S500: identifying gelatinization abnormality of the feed according to the gelatinization null value.

2. The method for processing feed pellets using fermented silkworm excrement as raw material according to claim 1, characterized in that: In step S100, the method for equipping a feed pellet drying device with an infrared thermal imager comprises: the feed pellet drying device includes a low-temperature drying oven, a hot air drying oven, or a low-temperature air drying oven; and the infrared thermal imager is arranged in the feed pellet drying device so that the infrared thermal imager is arranged at a position where heat radiation from the surface of the feed pellet forming area can be seen.

3. The method for processing feed pellets using fermented silkworm excrement as raw material according to claim 1, characterized in that: In step S200, during the low-temperature granulation process, infrared images are collected and stored in real time by an infrared thermal imager. The method for obtaining an infrared image sequence is as follows: when the low-temperature drying oven starts low-temperature granulation, the infrared thermal imager collects the thermal radiation image in the low-temperature drying oven in real time and records it as an infrared image until the low-temperature granulation process is completed, and all infrared images are formed into an infrared image sequence.

4. The method for processing feed pellets using fermented silkworm excrement as raw material according to claim 1, characterized in that: In step S300, the method for performing regional division on the infrared image to obtain a plurality of processing areas is as follows: performing regular spatial division on each infrared image frame in the infrared image sequence to obtain an image grid, which is recorded as a micro-processing area, and establishing an association relationship between each micro-processing area and a predetermined area in the drying box.

5. The method for processing feed pellets using fermented silkworm excrement as raw material according to claim 1, characterized in that: In step S400, the method for performing gelatinization missing risk analysis on the low-temperature treatment process of each micro-processing area to obtain the gelatinization null value is as follows: the median value of the pixel value of the micro-processing area is recorded as its corresponding grayscale value, which is enough to form the grayscale value time series of the micro-processing area in the infrared image sequence; the first-order difference of the grayscale value time series is performed to extract the grayscale change rate of each frame; the continuous frame segment with a change rate amplitude lower than the preset fluctuation threshold is identified as a plateau period, and the number of continuous frames of the segment is extracted as the plateau period length Tf; the starting time position Ts of the plateau period is extracted; and a weighting function is constructed according to Tf and Ts to obtain the gelatinization null value of the micro-processing area.

6. The method for processing feed pellets using fermented silkworm excrement as raw material according to claim 1, characterized in that: In step S400, a method for performing gelatinization loss risk analysis on the low-temperature treatment process of each micro-processing area to obtain a gelatinization null value is as follows: the lower quartile value of each pixel value in the micro-processing area is recorded as an inefficiency mark value, and the difference between the inefficiency mark value and the minimum pixel value in the micro-processing area is defined as an inefficiency interval; the difference between the inefficiency mark value at any moment and the previous moment is defined as an inefficiency mark increment; if the value of the inefficiency mark increment is a negative number, it is marked that an inefficiency event has occurred at the corresponding moment, and the ratio of the number of moments when the inefficiency event occurred to the number of moments when the inefficiency event did not occur is recorded as the inefficiency coefficient Tsic; The ratio of the inefficiency interval to the inefficiency mark value is recorded as the inefficiency product, and the median of the inefficiency product at the time when the inefficiency event occurs is the product level. If the inefficiency product corresponding to an inefficiency event is less than the product level, then the moment is marked as the preheating empty point; if the preheating empty point is smaller than the inefficiency product value corresponding to the first inefficiency event in the reverse time direction, then the moment is defined as the first gelatinization empty point. For any first gelatinization void point, search along the time direction for the moment when the first inefficiency product is higher than the product level and the moment when the inefficiency event occurs. The number of moments between the obtained moment and any first gelatinization void point is recorded as the cavitation recovery distance; the gelatinization void value is calculated based on the cavitation recovery distance of the first gelatinization void point and the lateral inefficiency coefficient.

7. The method for processing feed pellets using fermented silkworm excrement as raw material according to claim 1, characterized in that: In step S500, the method for identifying gelatinization abnormality of feed based on gelatinization null values ​​is as follows: gelatinization null values ​​corresponding to each micro-processing area are formed into a gelatinization null value set and standardized, and the upper quartile value and standard deviation of the null value set are recorded as the first abnormal threshold and threshold gradient, respectively; the micro-processing area corresponding to the element greater than the upper quartile value in the null value set is recorded as the first abnormal area, and the difference between the gelatinization null value and the threshold gradient of the first abnormal area is recorded as the second abnormal threshold; if the set consisting of the gelatinization null values ​​corresponding to the eight neighborhoods of the first abnormal area is recorded as the gelatinization gradient set, if more than half of the elements in the gelatinization gradient set are greater than the second abnormal threshold, it is determined that gelatinization abnormality occurs in the first abnormal area, otherwise, no gelatinization abnormality occurs.

8. The method for processing feed pellets using fermented silkworm excrement as raw material according to claim 7, characterized in that: In step S500, the method for identifying abnormal gelatinization of feed according to the gelatinization empty value further includes: screening feed particles corresponding to the micro-processing area where abnormal gelatinization occurs, and then performing steam high-temperature gelatinization treatment.

9. A feed pellet processing system using fermented silkworm excrement as raw material, characterized in that: The feed pellet processing system using fermented silkworm excrement as raw material includes: a processor, a memory, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the steps of the feed pellet processing method using fermented silkworm excrement as raw material described in any one of claims 1 to 8 are implemented. The feed pellet processing system using fermented silkworm excrement as raw material runs on computing devices such as desktop computers, laptop computers, PDAs, and cloud data centers.

Images