Intelligent management system and method for feed processing process

Abstract

The invention discloses an intelligent management system for feed processing technology, which belongs to the field of processing management. The invention analyzes turbidity change scores through average grayscale change values ​​and grayscale value variance change values, and combines the two to accurately evaluate changes in the dispersion state of oil and fat, improve the accuracy and reference of turbidity change scores, and then comprehensively evaluate the state of oil and fat through oil temperature changes, turbidity change scores and shearing machine torque changes, and then adjust the shearing speed to ensure that the shearing process is always in an optimized state. The shearing speed is intelligently adjusted to efficiently and energy-savingly allow the oil and fat to reach a higher dispersion state.

Description

Technical Field

[0001] The present invention relates to the technical field of processing management, and in particular to an intelligent management system and method for a feed processing process. Background Art

[0002] During feed processing, emulsified oil is added to the feed through formula preparation to improve feed nutrition.

[0003] Emulsified oil is made by shearing the oil through a shearing machine and then adding it to a homogenizer for homogenization and emulsification. The shearing machine generates a strong shear force through the high-speed rotating blades, which disperses large or viscous oil into smaller oil droplets. This step creates favorable conditions for the subsequent emulsification process. Smaller oil droplets are more likely to form a stable emulsion during the homogenization stage. Pre-reducing the oil droplet size through shearing can reduce the workload of the homogenizer, reduce the pressure and energy required for homogenization, and thus improve the efficiency of the entire emulsification process.

[0004] If the shearing speed of the shearing machine is too low, it will not generate enough shear force, the oil will not be fully dispersed, and the oil droplet size will be large, which is not conducive to the subsequent emulsification process and may form an unstable emulsion. If the shearing speed of the shearing machine is too high, it may destroy the emulsifier molecules, resulting in excessive consumption of the emulsifier, affecting the long-term stability of the emulsified oil, and may cause the oil temperature to rise sharply, accelerating the oxidation process of the oil.

[0005] Therefore, how to intelligently manage and adjust the shearing speed during the oil shearing process has become an urgent problem to be solved. Summary of the invention

[0006] In order to solve the technical problems existing in the prior art, the present invention provides an intelligent management system for feed processing process, comprising:

[0007] Recipe management module, used to set feed recipes;

[0008] A production module, used for producing mixed feed and mixed fat according to the feed formula;

[0009] A shearing processing module, used for shearing the mixed oil at high speed;

[0010] The emulsification and homogenization processing module is used to homogenize the sheared mixed oil to form emulsified oil;

[0011] An oil spraying module, used for spraying the emulsified oil on the mixed material through an oil pump;

[0012] The shear management module specifically includes:

[0013] A first data acquisition module is used to acquire the shear spindle torque, the mixed grease temperature and the mixed grease image in real time;

[0014] An image analysis module is used to analyze the turbidity change score C of the mixed oil according to the mixed oil image, ,in, represents the average grayscale change between the initial grease image and the real-time grease image, Indicates the gray value variance change between the initial fat image and the real-time fat image;

[0015] The status score calculation module is used to calculate the status score S of the current mixed grease. ,in, represents the torque weight, represents the temperature weight, represents the turbidity weight, A represents the current shear axis torque, represents the initial shear spindle torque, B represents the current mixed grease temperature, Indicates the initial mixed grease temperature;

[0016] The speed control module is used to adjust the shear speed of the shear management module according to the current state score S of the mixed grease, specifically:

[0017] when <J, adjust the shear speed to , ,like > ,but = ;

[0018] When J< < When the shear speed is adjusted to , ;

[0019] when ≥ When , the shear management module is controlled to stop shearing;

[0020] in, Indicates the new speed, represents the maximum shearing speed of the shearing management module, represents the initial shear speed, K represents the gain coefficient, Indicates the preset status score, J is less than The preset threshold value.

[0021] Furthermore, the feed formula specifically includes:

[0022] A feed raw material formula for obtaining the mixed feed;

[0023] Feed fat formula, used to obtain mixed fat;

[0024] The oil-feed mixing formula is used to illustrate the mixing ratio of the emulsified oil and the mixed feed in the feed.

[0025] Furthermore, the average grayscale change value between the initial grease image and the real-time grease image , the specific formula is:

[0026]

[0027]

[0028]

[0029] in, represents the average gray value of the initial oil image, represents the average gray value of the real-time grease image, W represents the image width, and H represents the image height. Represents the grayscale matrix of the initial oil image, Represents the grayscale matrix of the real-time fat image, x represents the image horizontal coordinate, and y represents the image vertical coordinate.

[0030] Furthermore, the gray value variance change value between the initial grease image and the real-time grease image , the specific formula is:

[0031]

[0032]

[0033]

[0034] in, represents the gray value variance of the initial oil image, Represents the gray value variance of the real-time fat image.

[0035] Furthermore, it also includes a homogenization management module, which specifically includes:

[0036] The second data acquisition module is used to acquire in real time a homogenized oil image, a qualified emulsified oil image and a preset homogenization pressure P, wherein the homogenized oil image is an image of the mixed oil after the mixed oil is sheared;

[0037] The cycle number prediction module is used to predict the required number of homogenization cycles N of the sheared mixed oil based on the data acquired by the second data acquisition module.

[0038] Furthermore, the predicted number of homogenization cycles N required for the sheared mixed oil is specifically:

[0039] Calculate the turbidity change score C1 of the current homogeneous oil image and the turbidity change score C2 of the qualified emulsified oil image, and the calculation method of C1 and C2 is the same as the calculation method of the turbidity change score C of the mixed oil;

[0040] The required number of homogenization cycles N is predicted by the trained deep learning model:

[0041]

[0042] in, , Represents model parameters, obtained through model training historical data, Represents the model error term. When N is a decimal, N is rounded up to a positive integer.

[0043] Furthermore, the fuel injection module comprises two or more fuel injection pipes, each of which is provided with a plurality of nozzles;

[0044] The system also includes an oil injection management module, which is used to control the oil injection time t1 of the oil injection module and the oil pumping time t0 of the oil pump according to the feed formula.

[0045] Furthermore, the oil injection time t1 of the oil injection module and the oil pumping time t0 of the oil pump are controlled according to the feed formula, specifically:

[0046] Calculate the required amount of emulsified oil L according to the feed formula and the total amount of the mixed material;

[0047] Obtain the oil pumping volume L0 of the oil pump in unit time, the total oil injection volume L1 of all the nozzles in unit time, and the average historical residual oil volume L2 in all the oil injection pipes;

[0048] The injection time t1 of the injection module and the pumping time t0 of the oil pump are calculated according to the following equations:

[0049] L0×t0=L1×t1+L2;

[0050] L=L1×t1.

[0051] The present invention also provides a feed processing process intelligent management method, comprising the following steps:

[0052] S1. Obtaining mixed feed and mixed oil through feed formula preparation;

[0053] S2, subjecting the mixed oil to high-speed shearing, and adjusting the shearing speed during the shearing process;

[0054] S3, homogenizing and emulsifying the sheared mixed oil to obtain emulsified oil;

[0055] S4, spraying emulsified oil on the mixture;

[0056] The adjusting of the shearing speed during the shearing process specifically includes:

[0057] S21, real-time acquisition of shear spindle torque, mixed grease temperature and mixed grease image;

[0058] S22, analyzing the turbidity change score C of the mixed oil according to the mixed oil image, ,in, represents the average grayscale change between the initial grease image and the real-time grease image, Indicates the gray value variance change between the initial fat image and the real-time fat image;

[0059] S23, calculating the state score S of the current mixed oil, ,in, represents the torque weight, represents the temperature weight, represents the turbidity weight, A represents the current shear axis torque, represents the initial shear spindle torque, B represents the current mixed grease temperature, Indicates the initial mixed grease temperature;

[0060] S24, adjusting the shearing speed of the shearing management module, specifically:

[0061] when <J, adjust the shear speed to , ,like > ,but = ;

[0062] When J< < When the shear speed is adjusted to , ;

[0063] when ≥ When , the shear management module is controlled to stop shearing;

[0064] in, Indicates the new speed, represents the maximum shearing speed of the shearing management module, represents the initial shear speed, K represents the gain coefficient, Indicates the preset status score, J is less than The preset threshold value.

[0065] Furthermore, in the process of homogenizing and emulsifying the sheared mixed oil to obtain the emulsified oil, the following steps are also included:

[0066] S31, real-time acquisition of homogenized oil image, qualified emulsified oil image and preset homogenization pressure P;

[0067] S32, calculating the turbidity change score C1 of the current homogeneous oil image and the turbidity change score C2 of the qualified emulsified oil image, the calculation method is the same as the calculation method of the turbidity change score C of the mixed oil;

[0068] S33. Predict the required number of homogenization cycles N through the trained deep learning model.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] 1. The present invention comprehensively evaluates the state of the grease through the change of grease temperature, turbidity change score and shearing machine torque change, and then adjusts the shearing speed to ensure that the shearing process is always in the optimal state. The torque change indicates the shearing load situation, and the turbidity change is an intuitive reflection of the dispersion state of the grease. The shearing speed is intelligently adjusted to achieve a higher dispersion state of the grease in an efficient and energy-saving manner.

[0071] 2. By adopting image recognition technology, the turbidity change score is analyzed using the average grayscale change value and the grayscale value variance change value. The average grayscale change value reflects the increase or decrease trend of the overall turbidity of the oil, while the grayscale value variance change value reveals the consistency or dispersion of the brightness distribution in the image. The combination of the two can more accurately evaluate the changes in the dispersion state of the oil, improve the accuracy and reference of the turbidity change score, and thus improve the accuracy of the oil state assessment.

[0072] 3. The present invention also uses a homogenization management module to predict the required number of homogenization cycles according to the homogenized oil image, the qualified emulsified oil image and the preset homogenization pressure, so as to avoid too few homogenization times and ensure the stability of the emulsified oil. At the same time, it also avoids too many homogenization times leading to increased energy consumption and destruction of the balance between the emulsifier and the oil droplets, thereby reducing the stability of the emulsified oil, and avoids too many homogenization times leading to accelerated oxidation of the emulsified oil and reducing the nutritional value of the emulsified oil.

[0073] 4. The present invention also controls the injection time t1 of the injection module and the oil pumping time t0 of the oil pump according to the feed formula through the oil injection management module, so as to avoid spraying too much emulsified oil into the mixture, and at the same time avoid too much emulsified oil being pumped into the oil injection pipe by the oil pump, thereby causing too much emulsified oil to remain in the oil injection pipe when spraying is stopped. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0075] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0076] Figure 1 It is a structural block diagram of the system of the present invention;

[0077] Figure 2 is a structural block diagram of a shear management module of the system of the present invention;

[0078] Figure 3 It is a structural block diagram of the homogenization management module of the system of the present invention;

[0079] Figure 4 is a flow chart of the method of the present invention;

[0080] Figure 5 is a flow chart of step S2 of the method of the present invention. DETAILED DESCRIPTION

[0081] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0082] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0083] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0084] See also Figure 1 As shown, the present invention provides an intelligent management system for feed processing process, comprising:

[0085] A recipe management module, a production module, a shear processing module, a shear management module, an emulsification and homogenization processing module, an oil injection module, and a central controller that is communicatively connected to the above modules.

[0086] Recipe management module, used to set feed recipes.

[0087] The feed formula includes: feed raw material formula, feed oil formula and oil mixed formula.

[0088] The feed raw material formula describes the types of feed raw materials and the corresponding weight ratios, and the mixed material is obtained according to the feed raw material formula;

[0089] The feed oil formula describes the type of oil used in the feed and the corresponding weight ratio, the weight ratio of water, the weight ratio of emulsifier and the weight ratio of antioxidant, and the mixed oil is obtained according to the feed oil formula;

[0090] The oil-feed mixing formula describes the ratio of the emulsified oil to the mixed feed.

[0091] The production module is used to produce mixed materials and mixed fats according to the feed formula.

[0092] Specifically, the mixed material is prepared according to the feed raw material formula, and the mixed fat is prepared according to the feed fat formula.

[0093] The shearing processing module is used to shear the mixed oil at high speed.

[0094] The shearing processing module is specifically a high-speed shearing machine.

[0095] In the scheme of the present invention, the purpose of high-speed shearing of the mixed oil is to improve the dispersibility of the oil droplets. The oil often exists in large clumps or droplets without treatment, which may lead to low homogenization efficiency and insufficient homogenization. Large oil droplets are prone to agglomeration in the emulsion, destroying the stability of the emulsion, causing oil-water stratification or emulsion rupture. Therefore, through high-speed shearing, the oil is divided into smaller oil droplets, so that in the subsequent homogenization process, a more stable emulsion structure can be better formed, thereby improving the homogenization emulsification efficiency.

[0096] The shearing management module is used to adjust the shearing speed of the shearing processing module according to the state of the mixed oil during the shearing process of the mixed oil.

[0097] See also Figure 2As shown, the shearing management module includes: a first data acquisition module, an image analysis module, a state score calculation module and a rotation speed control module.

[0098] The first data acquisition module is used to acquire the shear spindle torque, the mixed grease temperature and the mixed grease image in real time.

[0099] The shear spindle torque can be obtained by monitoring the torque of the shear processing module spindle through a torque sensor;

[0100] The temperature of the mixed grease can be obtained by monitoring the temperature of the mixed grease with a temperature sensor;

[0101] The mixed grease image can be obtained by photographing the mixed grease with a high-definition camera, and the mixed grease image includes an initial grease image and a real-time grease image.

[0102] The image analysis module is used to analyze the turbidity change score C of the mixed oil according to the mixed oil image:

[0103]

[0104] in, Represents the average grayscale change value between the initial grease image and the real-time grease image, Represents the gray value variance change between the initial fat image and the real-time fat image.

[0105] As the grease is sheared, the distribution and size of the grease droplets in the image will change, which will cause a change in the grayscale value distribution. The average grayscale change value describes the difference in the overall grayscale value distribution of the image before and after grease dispersion (i.e., the initial grease image and the real-time grease image). The grayscale value variance change value describes the uniformity of the grayscale value in the image. The better the grease is dispersed, the smaller the grayscale value variance, and the higher the turbidity change score, the more uniform the grease dispersion.

[0106] Before shearing begins, oil usually exists in the form of larger oil droplets or clumps, and the turbidity is relatively low at this time because large oil droplets scatter less light. In this state, the distribution of oil is usually uneven. As the oil is sheared, the oil is quickly dispersed into smaller oil droplets, the number of oil droplets increases, and the total surface area increases. Due to the enhanced scattering effect of small oil droplets on light, the turbidity begins to rise until the oil droplet size stabilizes, and the change in turbidity gradually slows down, indicating that the oil has reached a higher dispersion state and is suitable for further homogenization and emulsification treatment.

[0107] Before the image analysis module analyzes the turbidity change score of the mixed oil, image preprocessing is performed, including: denoising, image standardization, background removal and grayscale conversion, etc.

[0108] Calculate the average grayscale change value between the initial grease image and the real-time grease image And gray value variance change value , can be calculated as follows:

[0109]

[0110]

[0111]

[0112]

[0113]

[0114]

[0115] in, represents the average gray value of the initial oil image, Represents the average gray value of the real-time oil image, represents the gray value variance of the initial oil image, represents the gray value variance of the real-time oil image, W represents the image width, H represents the image height, Represents the grayscale matrix of the initial oil image, Represents the grayscale matrix of the real-time fat image, x represents the image horizontal coordinate, and y represents the image vertical coordinate.

[0116] The state score calculation module is used to calculate the state score S of the current mixed oil.

[0117] The state score calculation module calculates the state score S of the current mixed grease, and the specific formula is:

[0118]

[0119] in, represents the torque weight, represents the temperature weight, represents the turbidity weight, ,and Greater than , Greater than , A represents the current shear spindle torque, represents the initial shear spindle torque, B represents the current mixed grease temperature, Indicates the initial mixed grease temperature.

[0120] As the grease is sheared, the change in the shearing machine torque reflects the change in the flow characteristics of the grease during the shearing process. When shearing begins, the grease has not been significantly sheared, its internal structure is relatively complete, and its fluidity is poor, especially for high-viscosity grease. At this time, the shearing machine needs to overcome greater resistance to shear the large oil droplets of the grease into smaller oil droplets, so the torque is higher. When most of the large oil droplets in the grease are successfully sheared into small oil droplets, the overall fluidity and shearability of the grease are enhanced, the shear resistance is reduced, and the torque of the shearing machine also decreases. That is, in this process, the torque change increases. Therefore, the torque parameter is added to the scheme of the present invention to calculate the state score of the current mixed grease.

[0121] The high-speed shearing machine will generate a large amount of mechanical energy during operation. This part of energy will be converted into heat energy during the shearing process, causing the temperature of the oil to rise. This is because the shearing force will cause friction between oil molecules, thereby generating heat. In this process, the change in the temperature of the mixed oil increases. Therefore, the temperature parameter is added to the solution of the present invention to calculate the state score of the current mixed oil.

[0122] The speed control module is used to adjust the shearing speed of the shearing management module according to the current state score S of the mixed grease.

[0123] The speed control module adjusts the shearing speed of the shearing management module, specifically:

[0124] when <J, adjust the shear speed to , ,like > ,but = ;

[0125] When J< < When the shear speed is adjusted to , ;

[0126] when ≥ When , the shear management module is controlled to stop shearing;

[0127] in, Indicates the new speed, represents the maximum shearing speed of the shearing management module, Indicates the initial shear speed, which is set manually, K indicates the gain coefficient, Indicates the preset status score, J is less than The preset threshold value.

[0128] In the scheme of the present invention, after the mixed oil is sheared at high speed, the oil particles reach a higher dispersion state, and the oil particles become smaller, reaching 1-5 μm, so that the digestibility and utilization rate of the oil is improved.

[0129] The emulsification and homogenization processing module is used to homogenize the sheared mixed oil to form emulsified oil.

[0130] The emulsification and homogenization processing module is specifically a high-pressure homogenizer.

[0131] The oil spraying module is used for spraying the emulsified oil onto the mixed material through an oil pump.

[0132] In some embodiments, the system of the present invention further includes a homogenization management module for predicting the required number of homogenization cycles N of the sheared mixed oil.

[0133] See also Figure 3 As shown, the homogenization management module includes: a second data acquisition module and a cycle number prediction module.

[0134] The second data acquisition module is used to acquire the homogenized oil image, the qualified emulsified oil image and the preset homogenization pressure P in real time.

[0135] The homogenized oil image is the mixed oil image after the mixed oil is sheared.

[0136] The cycle number prediction module is used to predict the required number of homogenization cycles N of the sheared mixed oil according to the data acquired by the second data acquisition module, specifically:

[0137] Calculate the turbidity change score C1 of the current homogeneous oil image and the turbidity change score C2 of the qualified emulsified oil image. The calculation method is the same as the calculation method of the turbidity change score C of the mixed oil, which will not be repeated here;

[0138] The required number of homogenization cycles N is predicted by the trained deep learning model.

[0139] In some embodiments, the required number of homogenization cycles N can be calculated by the following formula:

[0140]

[0141] in, , Represents model parameters, obtained through model training historical data, Represents the model error term. When N is a decimal, N is rounded up to a positive integer.

[0142] In some embodiments, the system of the present invention further includes: a fuel injection management module.

[0143] The fuel injection module comprises two or more fuel injection pipes, each of which is provided with a plurality of nozzles.

[0144] The oil injection management module is used to control the oil injection time t1 of the oil injection module and the oil pumping time t0 of the oil pump according to the feed formula, specifically:

[0145] Calculate the required amount of emulsified oil L according to the feed formula and the total amount of the mixed material;

[0146] Obtain the oil pumping volume L0 of the oil pump in unit time, the total oil injection volume L1 of all the nozzles in unit time, and the average historical residual oil volume L2 in all the oil injection pipes;

[0147] The injection time t1 of the injection module and the pumping time t0 of the oil pump are calculated according to the following equations:

[0148] L0×t0=L1×t1+L2;

[0149] L=L1×t1.

[0150] See also Figure 4 As shown, the present invention also provides a feed processing process intelligent management method, comprising the following steps:

[0151] S1. Obtaining mixed feed and mixed oil through feed formula preparation;

[0152] S2, subjecting the mixed oil to high-speed shearing, and adjusting the shearing speed during the shearing process;

[0153] S3, homogenizing and emulsifying the sheared mixed oil to obtain emulsified oil;

[0154] S4, spraying the emulsified oil on the mixed material.

[0155] See also Figure 5 As shown, for step S2, adjusting the shearing speed during the shearing process specifically includes the following steps:

[0156] S21, real-time acquisition of shear spindle torque, mixed grease temperature and mixed grease image;

[0157] S22, analyzing the turbidity change score C of the mixed oil according to the mixed oil image, ,in, represents the average grayscale change between the initial grease image and the real-time grease image, Indicates the gray value variance change between the initial fat image and the real-time fat image;

[0158] S23, calculating the state score S of the current mixed oil, ,in, represents the torque weight, represents the temperature weight, represents the turbidity weight, A represents the current shear axis torque, represents the initial shear spindle torque, B represents the current mixed grease temperature, Indicates the initial mixed grease temperature;

[0159] S24, adjusting the shearing speed of the shearing management module according to the state score S, specifically:

[0160] when <J, adjust the shear speed to , ,like > ,but = ;

[0161] When J< < When the shear speed is adjusted to , ;

[0162] when ≥ When , the shear management module is controlled to stop shearing;

[0163] in, Indicates the new speed, represents the maximum shearing speed of the shearing management module, represents the initial shear speed, K represents the gain coefficient, Indicates the preset status score, J is less than The preset threshold value.

[0164] Regarding step S3, in the process of homogenizing and emulsifying the sheared mixed oil to obtain the emulsified oil, the following steps are also included:

[0165] S31, real-time acquisition of homogenized oil image, qualified emulsified oil image and preset homogenization pressure P;

[0166] S32, calculating the turbidity change score C1 of the current homogeneous oil image and the turbidity change score C2 of the qualified emulsified oil image, the calculation method is the same as the calculation method of the turbidity change score C of the mixed oil;

[0167] S33. Predict the required number of homogenization cycles N through the trained deep learning model.

[0168] Regarding step S4, in the process of spraying the emulsified oil on the mixed material, the oil injection time t1 and the oil pumping time t0 of the oil pump are controlled, which specifically includes the following steps:

[0169] Calculate the required amount of emulsified oil L according to the feed formula and the total amount of the mixed material;

[0170] Obtain the oil pumping volume L0 of the oil pump in unit time, the total oil injection volume L1 of all the nozzles in unit time, and the average historical residual oil volume L2 in all the oil injection pipes;

[0171] The injection time t1 and the pumping time t0 of the oil pump are calculated according to the following equations:

[0172] L0×t0=L1×t1+L2;

[0173] L=L1×t1.

[0174] The beneficial effects of the present invention are:

[0175] 1. The present invention comprehensively evaluates the state of the grease through the change of grease temperature, turbidity change score and shearing machine torque change, and then adjusts the shearing speed to ensure that the shearing process is always in the optimal state. The torque change indicates the shearing load situation, and the turbidity change is an intuitive reflection of the dispersion state of the grease. The shearing speed is intelligently adjusted to achieve a higher dispersion state of the grease in an efficient and energy-saving manner.

[0176] 2. By adopting image recognition technology, the turbidity change score is analyzed using the average grayscale change value and the grayscale value variance change value. The average grayscale change value reflects the increase or decrease trend of the overall turbidity of the oil, while the grayscale value variance change value reveals the consistency or dispersion of the brightness distribution in the image. The combination of the two can more accurately evaluate the changes in the dispersion state of the oil, improve the accuracy and reference of the turbidity change score, and thus improve the accuracy of the oil state assessment.

[0177] 3. The present invention also uses a homogenization management module to predict the required number of homogenization cycles according to the homogenized oil image, the qualified emulsified oil image and the preset homogenization pressure, so as to avoid too few homogenization times and ensure the stability of the emulsified oil. At the same time, it also avoids too many homogenization times leading to increased energy consumption and destruction of the balance between the emulsifier and the oil droplets, thereby reducing the stability of the emulsified oil, and avoids too many homogenization times leading to accelerated oxidation of the emulsified oil and reducing the nutritional value of the emulsified oil.

[0178] 4. The present invention also controls the injection time t1 of the injection module and the oil pumping time t0 of the oil pump according to the feed formula through the oil injection management module, so as to avoid spraying too much emulsified oil into the mixture, and at the same time avoid too much emulsified oil being pumped into the oil injection pipe by the oil pump, thereby causing too much emulsified oil to remain in the oil injection pipe when spraying is stopped.

[0179] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0180] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An intelligent management system for feed processing technology, characterized in that: include: Recipe management module, used to set feed recipes; A production module, used for producing mixed feed and mixed fat according to the feed formula; A shearing processing module, used for shearing the mixed oil at high speed; The emulsification and homogenization processing module is used to homogenize the sheared mixed oil to form emulsified oil; An oil spraying module, used for spraying the emulsified oil on the mixed material through an oil pump; The shear management module specifically includes: A first data acquisition module is used to acquire the shear spindle torque, the mixed grease temperature and the mixed grease image in real time; An image analysis module is used to analyze the turbidity change score C of the mixed oil according to the mixed oil image, ,in, represents the average grayscale change between the initial grease image and the real-time grease image, Indicates the gray value variance change between the initial fat image and the real-time fat image; The status score calculation module is used to calculate the status score S of the current mixed grease. ,in, represents the torque weight, represents the temperature weight, represents the turbidity weight, A represents the current shear axis torque, represents the initial shear spindle torque, B represents the current mixed grease temperature, Indicates the initial mixed grease temperature; The speed control module is used to adjust the shear speed of the shear management module according to the current state score S of the mixed grease, specifically: when <J, adjust the shear speed to , ,like > ,but = ; When J< < When the shear speed is adjusted to , ; when ≥ When , the shear management module is controlled to stop shearing; in, Indicates the new speed, represents the maximum shearing speed of the shearing management module, represents the initial shear speed, K represents the gain coefficient, Indicates the preset status score, J is less than The preset threshold value.

2. The feed processing process intelligent management system according to claim 1, characterized in that: The feed formula specifically includes: A feed raw material formula for obtaining the mixed feed; Feed fat formula, used to obtain mixed fat; The oil-feed mixing formula is used to illustrate the mixing ratio of the emulsified oil and the mixed feed in the feed.

3. The feed processing process intelligent management system according to claim 1, characterized in that: The average grayscale change value between the initial grease image and the real-time grease image , the specific formula is: in, represents the average gray value of the initial oil image, represents the average gray value of the real-time grease image, W represents the image width, and H represents the image height. Represents the grayscale matrix of the initial oil image, Represents the grayscale matrix of the real-time fat image, x represents the image horizontal coordinate, and y represents the image vertical coordinate.

4. The feed processing process intelligent management system according to claim 3, characterized in that: The gray value variance change value between the initial grease image and the real-time grease image , the specific formula is: in, represents the gray value variance of the initial oil image, Represents the gray value variance of the real-time fat image.

5. The feed processing process intelligent management system according to claim 1, characterized in that: It also includes a homogenization management module, including: The second data acquisition module is used to acquire in real time a homogenized oil image, a qualified emulsified oil image and a preset homogenization pressure P, wherein the homogenized oil image is an image of the mixed oil after the mixed oil is sheared; The cycle number prediction module is used to predict the required number of homogenization cycles N of the sheared mixed oil based on the data acquired by the second data acquisition module.

6. The feed processing process intelligent management system according to claim 5, characterized in that: The predicted number of homogenization cycles N required for the sheared mixed oil is specifically: Calculate the turbidity change score C1 of the current homogeneous oil image and the turbidity change score C2 of the qualified emulsified oil image, and the calculation method of C1 and C2 is the same as the calculation method of the turbidity change score C of the mixed oil; The required number of homogenization cycles N is predicted by the trained deep learning model: in, , Represents model parameters, obtained through model training historical data, Represents the model error term. When N is a decimal, N is rounded up to a positive integer.

7. The feed processing process intelligent management system according to claim 1, characterized in that: The fuel injection module comprises two or more fuel injection pipes, each of which is provided with a plurality of nozzles; The system also includes an oil injection management module, which is used to control the oil injection time t1 of the oil injection module and the oil pumping time t0 of the oil pump according to the feed formula.

8. The feed processing intelligent management system according to claim 7, characterized in that: The control of the injection time t1 of the injection module and the pumping time t0 of the oil pump according to the feed formula is specifically as follows: Calculate the required amount of emulsified oil L according to the feed formula and the total amount of the mixed material; Obtain the oil pumping volume L0 of the oil pump in unit time, the total oil injection volume L1 of all the nozzles in unit time, and the average historical residual oil volume L2 in all the oil injection pipes; The injection time t1 of the injection module and the pumping time t0 of the oil pump are calculated according to the following equations: L0×t0=L1×t1+L2; L=L1×t1.

9. A method for intelligent management of feed processing process, characterized in that: The following steps are involved: S1. Obtaining mixed feed and mixed oil through feed formula preparation; S2, subjecting the mixed oil to high-speed shearing, and adjusting the shearing speed during the shearing process; S3, homogenizing and emulsifying the sheared mixed oil to obtain emulsified oil; S4, spraying emulsified oil on the mixture; The adjusting of the shearing speed during the shearing process specifically includes: S21, real-time acquisition of shear spindle torque, mixed grease temperature and mixed grease image; S22, analyzing the turbidity change score C of the mixed oil according to the mixed oil image, ,in, represents the average grayscale change between the initial grease image and the real-time grease image, Indicates the gray value variance change between the initial fat image and the real-time fat image; S23, calculating the state score S of the current mixed oil, ,in, represents the torque weight, represents the temperature weight, represents the turbidity weight, A represents the current shear axis torque, represents the initial shear spindle torque, B represents the current mixed grease temperature, Indicates the initial mixed grease temperature; S24, adjusting the shearing speed of the shearing management module, specifically: when <J, adjust the shear speed to , ,like > ,but = ; When J< < When the shear speed is adjusted to , ; when ≥ When , the shear management module is controlled to stop shearing; in, Indicates the new speed, represents the maximum shearing speed of the shearing management module, represents the initial shear speed, K represents the gain coefficient, Indicates the preset status score, J is less than The preset threshold value.

10. The feed processing intelligent management method according to claim 9, characterized in that: In the process of homogenizing and emulsifying the sheared mixed oil to obtain the emulsified oil, the following steps are also included: S31, real-time acquisition of homogenized oil image, qualified emulsified oil image and preset homogenization pressure P; S32, calculating the turbidity change score C1 of the current homogeneous oil image and the turbidity change score C2 of the qualified emulsified oil image, the calculation method is the same as the calculation method of the turbidity change score C of the mixed oil; S33. Predict the required number of homogenization cycles N through the trained deep learning model.

Images