An online production detection method and device for feed

Abstract

The present invention is applicable to the technical field of feed production detection and control, and provides a method and device for on-line feed production detection; the on-line feed production detection method is applied to an on-line feed production detection control system, which includes a powder processing module, a hygiene detection module, a nutritional component module, a granule forming module, a granule detection module, a wireless communication module, an alarm, a memory, a processing center, and an intelligent remote control device; the powder processing module, the hygiene detection module, the nutritional component module, the granule forming module, the granule detection module, the wireless communication module, the alarm, and the memory are respectively connected to the processing center; the intelligent remote control device is automatically networked with the wireless communication module within the range of a wireless network or the Internet; a feed detection control device is also provided. The present invention can automatically detect the quality requirements, safety requirements, and nutritional components in feed powder on-line, achieve one-time detection in production, and improve production efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of feed production detection and control. More specifically, it relates to an on-line feed production detection method and device involving artificial intelligence. Background Art

[0002] In traditional animal feed production, finished products are randomly inspected after the feed pellets are produced, and it is impossible to conduct on-line production detection, which delays production time and reduces production efficiency. The existing "Automated On-line Detection and Preparation System and Method for Feed (Publication No.: CN113397191A)" discloses a structural technology for an automated on-line detection and preparation of feed and its system, but does not disclose artificial intelligence control technology. "On-line Feed Production Monitoring System Based on Big Data Analysis (Publication No.: CN117482827A)" discloses real-time quality monitoring of the entire feed production process from incoming material quality to process quality, but does not automate the detection of various performance indicators of the feed. "Method and System for On-line Feed Production Monitoring Based on Big Data Analysis (Publication No.: CN115860589B)" discloses accurate identification of hygiene and safety based on production big data in a relatively complex production line environment, mainly for automated monitoring of feed production quality, and also cannot automate the detection of various performance indicators of the feed. Summary of the Invention

[0003] In order to solve the deficiencies in the prior art, the purpose of the present invention is to provide an on-line feed production detection method and device. By setting up a quality detection module, a safety detection module, a nutrition detection module, a data processing module, and a batching adjustment module, it can automatically detect the quality requirements, safety requirements, and nutritional components in feed powder on-line, solve the problem of "inability to automate the detection of on-line animal feed production", achieve one-time in-place detection during production, improve production efficiency, and shorten production time.

[0004] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0005] An on-line feed production detection method is applied to an on-line feed production detection control system, including a quality detection module, a safety detection module, a nutrition detection module, a data processing module, a batching adjustment module, a wireless communication module, an alarm, a memory, a processing center, and an intelligent remote control device; the quality detection module, the safety detection module, the nutrition detection module, the data processing module, the batching adjustment module, the wireless communication module, the alarm, and the memory are respectively connected to the processing center; the intelligent remote control device includes a smart phone, a tablet computer, and an intelligent remote control, and automatically forms a network connection with the wireless communication module within the range of wireless network or Internet.

[0006] The wireless communication module is provided with various wireless network units, which are responsible for receiving and transmitting wireless network signals and automatically networking and connecting with the intelligent remote control device within the range of the wireless network or the Internet;

[0007] The alarm compares the contents of quality, safety, and nutritional components in the feed with the quality standards of various indicators of this feed stored in the memory. If the standards are not met, it will automatically sound an alarm and notify to adjust the ingredients and restart production;

[0008] The memory is responsible for storing the information of the quality detection module, safety detection module, nutritional detection module, data processing module, ingredient adjustment module, wireless communication module, and alarm, as well as storing the quality standards of various indicators of the feed;

[0009] The processing center is responsible for the information transfer of the quality detection module, safety detection module, nutritional detection module, data processing module, ingredient adjustment module, wireless communication module, alarm, and memory. It is the hub center of the system, and compares the contents of quality, safety, and nutritional components in the feed with the quality standards of various indicators of this feed stored in the memory: if the standards are met, production continues; if the standards are not met, it is transmitted to the alarm and notifies to adjust the ingredients and restart production;

[0010] The quality detection module includes an appearance detection unit, a color detection unit, and a texture detection unit, which obtain the surface quality information and production process parameters of the feed through feed quality detection equipment to ensure the accuracy and integrity of the data, and transmit it to the safety detection module;

[0011] The safety detection module includes an inorganic detection unit, a fungal detection unit, a toxin detection unit, a chlorine-containing detection unit, and a bacterial detection unit, which obtain the pollutant information of inorganic substances, mycotoxins, natural plant toxins, organochlorine, and microorganisms in the feed through feed safety detection equipment, and transmit it to the nutritional detection module;

[0012] The nutritional detection module includes a basic nutrition unit, a vitamin unit, a source component unit, and an enzyme activity component unit, which obtain the nutritional component contents of basic components, vitamins, source components, and enzyme activity components in the feed through feed nutritional component detection equipment, and transmit it to the data processing module;

[0013] The data processing module includes an information processing unit, a model training unit, and a model evaluation unit, which process and analyze the detection results through statistical methods and computer software to obtain the various indicators of feed quality, safety, and nutritional components, and transmit it to the processing center;

[0014] The ingredient adjustment module includes a formula reservation unit, an auxiliary material adjustment unit, a granule production unit, and a feed digestion unit, which are responsible for adjusting the ingredients according to the over-standard results of various feed indicators to make the quality, safety, and nutritional component indicators meet the standards, so as to meet the nutritional requirements of the corresponding animals for the feed.

[0015] A method for on-line production detection of feed provided by the present invention includes the following steps:

[0016] S10. During detection, the quality detection module obtains the surface quality information and production process parameters of the feed through the feed quality detection equipment to ensure the accuracy and integrity of the data, and transmits them to the safety detection module;

[0017] S20. The safety detection module obtains the pollutant information of inorganic substances, mycotoxins, natural plant toxins, organochlorines, and microorganisms in the feed through the feed safety detection equipment, and transmits them to the nutrition detection module;

[0018] S30. The nutrition detection module obtains the nutritional component contents of basic components, vitamins, source components, and enzyme activity components in the feed through the feed nutritional component detection equipment, and transmits them to the data processing module;

[0019] S40. The data processing module processes and analyzes the detection results through statistical methods and computer software to obtain the indicators of feed quality, safety, and nutritional components, and transmits them to the processing center;

[0020] S50. The processing center compares the content of each indicator in the feed with the quality standards of each indicator of the feed stored in the memory: if it meets the standard, continue production; if it does not meet the standard, transmit it to the alarm and notify to adjust the ingredients and produce again;

[0021] S60. The ingredient adjustment module adjusts the ingredients according to the over-standard results of various feed indicators to make the quality, safety, and nutritional component indicators meet the standards, so as to meet the nutritional requirements of the corresponding animals for the feed.

[0022] Furthermore, the step S10 includes the following steps:

[0023] S11. The appearance detection unit obtains the surface appearance quality information of the shape of the feed and its integrity, particle size and its uniformity through the set high-definition camera, and transmits it to the color detection unit;

[0024] S12. The color detection unit obtains the surface gloss quality information of the color of the feed and its uniformity, glossiness and its consistency through the set intelligent sensor, and transmits it to the texture detection unit;

[0025] S13. The texture detection unit obtains the quality information of the hardness, temperature, humidity, viscosity, and peculiar smell of the feed through the set intelligent sensors, which serves as the basis for subsequent index judgment.

[0026] Further, the step S20 includes the following steps:

[0027] S21. The inorganic detection unit obtains the contents of various inorganic pollutants such as total arsenic, lead, mercury, cadmium, chromium, fluorine, and nitrite in the feed through the intelligent sensor and transmits them to the fungal detection unit;

[0028] S22. The fungal detection unit obtains the contents of various fungi in the feed sample powder through the set feed mycotoxin detector and transmits them to the toxin detection unit;

[0029] S23. The toxin detection unit obtains the contents of various natural plant toxins in the feed sample powder through the set intelligent biosensor and transmits them to the chlorine-containing detection unit;

[0030] S24. The chlorine-containing detection unit obtains the contents of various organochlorine pollutants in the feed sample powder through the set organochlorine content detector and transmits them to the bacterial detection unit;

[0031] S25. The bacterial detection unit obtains the contents of various bacteria such as Salmonella, mold, total bacteria count, coliform group, Shigella, and Staphylococcus in the feed sample powder through the bacteria detector.

[0032] Further, the step S30 includes the following steps:

[0033] S31. The basic nutrition unit obtains the contents of the basic nutritional components required by animals in the feed sample powder through the near-infrared spectrometer and the intelligent biosensor and transmits them to the vitamin unit;

[0034] S32. The vitamin unit detects the contents of the nutritional components of 11 vitamins and 7 acids in the feed sample powder by high performance liquid chromatography (HPLC) and transmits them to the origin component unit;

[0035] S33. The origin component unit obtains the contents of various animal and plant origin components in the feed sample powder through the set PCR detector and transmits them to the enzyme activity component unit;

[0036] S34. The enzyme activity component unit obtains the contents of various enzyme activity components in the feed sample powder through the set feed mycotoxin detector.

[0037] Further, the step S40 includes the following steps:

[0038] S41. The information processing unit preprocesses the detection data by data cleaning, data transformation, and feature selection to eliminate noise and redundant information, improve the accuracy of the detection model, and transmit it to the model training unit;

[0039] S42. The model training unit calculates according to the support vector machine algorithm formula , where f(X) is the regression model function of SVR, α is the updated Lagrange multiplier, X is the feature vector, b is the bias term, * is the dual variable, and T is the transpose of the vector or matrix, to train the processed data model and transmit it to the model evaluation unit;

[0040] S43. The model evaluation unit calculates the evaluation results of the samples based on the specific detection data through accuracy, precision, and recall, and displays them in text description and charts for the judgment of feed indicators.

[0041] Further, before step S60, the following steps are included:

[0042] S61. The formula reservation unit obtains the main raw materials and their formula ratio information of the animals corresponding to the feed by connecting to the industry database and transmits it to the auxiliary material adjustment unit;

[0043] S62. The auxiliary material adjustment unit obtains the corresponding auxiliary substance information required for the growth of the animals according to the growth cycle information of the animals, adds it to the feed powder and stirs it evenly, and transmits it to the granule production unit;

[0044] S63. The granule production unit makes the feed granule size from the feed powder according to the granule size and hardness information of the feed for the same kind of animals through the granule production equipment and transmits it to the feed digestion unit;

[0045] S64. The feed digestion unit obtains the information of the feed nutrients contained in the feces of the animals after eating the feed through the laboratory equipment as a reference for the formula of the feed production for the same animals in the future.

[0046] A feed online production detection control system provided by the present invention further includes a computer device and a computer-readable storage medium; the computer device includes a memory and each functional module, the memory stores a computer program, and each functional module implements the steps of a feed online production detection method as described in any one of the above when executing the computer program; a computer program is stored on the computer-readable storage medium, and the computer program implements the steps of a feed online production detection method as described in any one of the above when executed by each functional module.

[0047] The present invention also provides a feed detection control device implemented by using the feed online production detection method described above.

[0048] Advantages of the present invention compared with the prior art:

[0049] By setting up a quality detection module, a safety detection module, a nutrition detection module, a data processing module, and a batching adjustment module, it is possible to automatically detect the quality requirements, safety requirements, and nutritional components in feed powder online, solving the problem of "inability to automatically detect the online production of animal feed", achieving one-time in-place detection during production, improving production efficiency, and shortening production time. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or exemplary technical descriptions. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 It is a schematic diagram of the system modules of the present invention;

[0052] Figure 2 It is a schematic diagram of the quality detection module of the present invention;

[0053] Figure 3 It is a schematic diagram of the safety detection module of the present invention;

[0054] Figure 4 It is a schematic diagram of the nutrition detection module of the present invention;

[0055] Figure 5 It is a schematic diagram of the data processing module of the present invention;

[0056] Figure 6 It is a schematic diagram of the batching adjustment module of the present invention;

[0057] Figure 7 It is a schematic diagram of the method flow program of the present invention;

[0058] Figure 8 It is a schematic diagram of the program decomposition of step S10 in the method flow of the present invention;

[0059] Figure 9 It is a schematic diagram of the program decomposition of step S20 in the method flow of the present invention;

[0060] Figure 10 It is a schematic diagram of the program decomposition of step S30 in the method flow of the present invention;

[0061] Figure 11 It is a schematic diagram of the program decomposition of step S40 in the method flow of the present invention;

[0062] Figure 12It is a schematic diagram of the program decomposition before step S60 in the method flow of the present invention. Specific embodiments

[0063] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] The following describes the specific implementation of the present invention in detail with specific embodiments:

[0065] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] It should be noted that when a module is referred to as "disposed" or "disposed on" another module, it can be directly on the other module or indirectly on the other module. When a module is referred to as "connected" or "connected to" another module, it can be directly connected to the other module or indirectly connected to the other module.

[0067] In the description of the present application, "a plurality" means two or more, unless otherwise specifically defined. "Several" means one or more, unless otherwise specifically defined.

[0068] In the description of the present application, it should be noted that unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations. The terms "including", "comprising", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0069] Please refer to Figure 1As shown in the figure, the present invention provides an on-line production detection method for feed, which is applied to an on-line production detection control system for feed, and includes a quality detection module, a safety detection module, a nutrition detection module, a data processing module, a batching adjustment module, a wireless communication module, an alarm, a memory, a processing center, and an intelligent remote control device; the quality detection module, the safety detection module, the nutrition detection module, the data processing module, the batching adjustment module, the wireless communication module, the alarm, and the memory are respectively connected to the processing center; the intelligent remote control device includes a smart phone, a tablet computer, and an intelligent remote controller, and automatically forms a network connection with the wireless communication module within the range of a wireless network or the Internet.

[0070] The wireless communication module is provided with various wireless network units, which are responsible for receiving and transmitting wireless network signals, and automatically form a network connection with the intelligent remote control device within the range of a wireless network or the Internet.

[0071] The alarm compares the contents of the quality, safety, and nutrition components in the feed with the quality standards of each index of this feed stored in the memory. If the standards are not met, it is transmitted to the alarm and notifies to adjust the batching and produce again.

[0072] The memory is responsible for storing the information of the quality detection module, the safety detection module, the nutrition detection module, the data processing module, the batching adjustment module, the wireless communication module, and the alarm, as well as storing the quality standards of each index of the feed.

[0073] Furthermore, the feed quality standards include: the hygienic requirements of the feed powder, the nutrition components meeting the standards, the particle size / hardness meeting the standards, the particle size being uniform / consistent / complete, the components being evenly mixed, and the powdering rate, gelatinization degree, pepsin digestibility, and water stability of the particles all meeting the standards.

[0074] The processing center is responsible for the information transmission of the quality detection module, the safety detection module, the nutrition detection module, the data processing module, the batching adjustment module, the wireless communication module, the alarm, and the memory, and is the hub center of the system. It compares the contents of the quality, safety, and nutrition components in the feed with the quality standards of each index of this feed stored in the memory: if the standards are met, the production continues; if the standards are not met, it is transmitted to the alarm and notifies to adjust the batching and produce again.

[0075] Please refer to Figure 2 As shown in the figure, the quality detection module includes an appearance detection unit, a color detection unit, and a texture detection unit, and obtains the surface quality information and production process parameters of the feed through detection equipment to ensure the accuracy and integrity of the data, and transmits them to the safety detection module.

[0076] Furthermore, the appearance detection unit obtains the surface appearance quality information of the feed, such as its shape, integrity, particle size, and uniformity, through the set high-definition camera, and transmits it to the color detection unit; the color detection unit obtains the surface gloss quality information of the feed, such as its color, uniformity, glossiness, and consistency, through the set intelligent sensor, and transmits it to the texture detection unit; the texture detection unit obtains the quality information of the hardness, temperature, humidity, viscosity, and peculiar smell of the feed through the set intelligent sensor, which serves as the direct basis for subsequent index judgment.

[0077] Please refer to Figure 3 As shown, the safety detection module includes an inorganic detection unit, a fungal detection unit, a toxin detection unit, a chlorine-containing detection unit, and a bacterial detection unit, which obtain the pollutant information of inorganic substances, mycotoxins, natural plant toxins, organochlorines, and microorganisms in the feed through safety detection equipment, and transmit it to the nutrition detection module.

[0078] Furthermore, the inorganic detection unit obtains the contents of various inorganic pollutants such as total arsenic, lead, mercury, cadmium, chromium, fluorine, and nitrite in the feed through an intelligent sensor, and transmits it to the fungal detection unit; the fungal detection unit obtains the contents of various fungi in the feed sample powder through the set feed mycotoxin detector, and transmits it to the toxin detection unit; the toxin detection unit obtains the contents of various natural plant toxins in the feed sample powder through the set intelligent biosensor, and transmits it to the chlorine-containing detection unit; the chlorine-containing detection unit obtains the contents of various organochlorine pollutants in the feed sample powder through the set organochlorine content detector, and transmits it to the bacterial detection unit; the bacterial detection unit obtains the contents of various bacteria such as Salmonella, mold, total bacteria count, coliforms, Shigella, and Staphylococcus in the feed sample powder through a bacteria detector.

[0079] Please refer to Figure 4 As shown, the nutrition detection module includes a basic nutrition unit, a vitamin unit, a source component unit, and an enzyme activity component unit, which obtain the nutritional component contents of the basic components, vitamins, source components, and enzyme activity components in the feed through feed nutritional component detection equipment, and transmit it to the data processing module.

[0080] Further, the basic nutrition unit obtains the content of the basic nutrients required by animals in the feed sample powder through a near-infrared spectrometer or an intelligent biosensor, and transmits it to the vitamin unit; the vitamin unit detects the content of the nutrients of 11 vitamins and 7 acids in the feed sample powder by high performance liquid chromatography (HPLC), and transmits it to the source ingredient unit; the source ingredient unit obtains the content of various animal and plant source ingredients in the feed sample powder through a set PCR detector, and transmits it to the enzyme activity ingredient unit; the enzyme activity ingredient unit obtains the content of various enzyme activity ingredients in the feed sample powder through a set feed mycotoxin detector.

[0081] Please refer to Figure 5 As shown, the data processing module includes an information processing unit, a model training unit, and a model evaluation unit, which processes and analyzes the detection results through statistical methods and computer software to obtain various indicators of feed quality, safety, and nutritional components, and transmits them to the processing center.

[0082] Further, the information processing unit performs preprocessing of data cleaning, data transformation, and feature selection on the detection data, eliminates noise and redundant information to improve the accuracy of the detection model, and transmits it to the model training unit; the model training unit calculates according to the support vector machine algorithm formula where f(X) is the regression model function of SVR, α is the updated Lagrange multiplier, X is the feature vector, b is the bias term, * is the dual variable, and T is the transpose of the vector or matrix to train the processed data model, and transmits it to the model evaluation unit; the model evaluation unit calculates the evaluation results of the samples according to the specific detection data through accuracy, precision, and recall rate, and displays them in the form of reports such as text descriptions and charts for the judgment of feed indicators.

[0083] Please refer to Figure 6 As shown, the ingredient adjustment module includes a formula reservation unit, an auxiliary material adjustment unit, a granule production unit, and a feed digestion unit, which is responsible for adjusting the ingredients according to the over-standard results of various feed indicators to make its quality, safety, and nutritional component indicators meet the standards to meet the nutritional needs of the corresponding animals for the feed.

[0084] Further, the formula predetermination unit obtains the main raw materials and their formula ratio information of the animals corresponding to the feed by networking with the industry database, and transmits it to the auxiliary material adjustment unit; the auxiliary material adjustment unit obtains the corresponding auxiliary substance information required for the growth of the animals according to the growth cycle information of the animals and adds it to the feed powder and stirs it evenly, and transmits it to the pellet making unit; the pellet making unit makes the feed pellet size from the feed powder through the pellet making equipment according to the pellet size and hardness information of the same kind of animals, and transmits it to the feed digestion unit; the feed digestion unit obtains the feed nutrient information contained in the feces after the animals eat the feed through the testing equipment, which is used as a formula reference for the subsequent feed production of the same animals.

[0085] System working principle:

[0086] During detection, the quality detection module obtains the surface quality information and production process parameters of the feed through the feed quality detection equipment to ensure the accuracy and integrity of the data, and transmits it to the safety detection module; then the safety detection module obtains the inorganic substances, mycotoxins, natural plant toxins, organochlorines, and microbial pollutant information in the feed through the feed safety detection equipment, and transmits it to the nutrition detection module; the control nutrition detection module obtains the nutrient content of the basic components, vitamins, source components, and enzyme activity components in the feed through the feed nutrient component detection equipment, and transmits it to the data processing module; then the data processing module processes and analyzes the detection results through statistical methods and computer software to obtain the various indicators of the feed quality, safety, and nutrient components, and transmits them to the processing center; through the processing center, the various contents of the quality, safety, and nutrient components in the feed are compared with the various index quality standards of the feed stored in the memory: if it meets the standard, production continues, if it does not meet the standard, it is transmitted to the alarm and the adjustment of the ingredients is notified to re-produce; through the ingredient adjustment module, the ingredients are adjusted according to the over-standard results of the various feed indicators to make the quality, safety, and nutrient component indicators all meet the standards to meet the nutritional requirements of the corresponding animals for the feed.

[0087] When the staff or manager is outdoors or in other places, they use a smart phone or tablet computer to automatically form a network connection with the wireless communication module within the range of the wireless network or the Internet, thereby controlling or monitoring the feed detection situation, realizing intelligent and networked management, and improving the detection efficiency.

[0088] Please refer to Figure 7 As shown, a feed online production detection method provided by the present invention includes the following steps:

[0089] S10. During detection, the quality detection module obtains the surface quality information and production process parameters of the feed through the detection equipment to ensure the accuracy and integrity of the data, and transmits it to the safety detection module;

[0090] Please refer toFigure 8 As shown, step S10 includes the following steps:

[0091] S11. The appearance detection unit obtains surface appearance quality information of the feed, such as its shape, integrity, particle size, and uniformity, through the set high-definition camera, and transmits it to the color detection unit;

[0092] Further explanation: By using the high-definition camera, the cylindrical shape of ordinary feed, or the fluffy and porous structure of expanded feed, as well as the small particles of piglet feed and the large particles of growing and finishing pig feed, can be obtained. The particle size has different effects on animals at different stages, and these information are very important for subsequent evaluation of the quality and applicability of the feed, directly affecting the digestion, absorption, and healthy growth of animals; the appearance quality requirements include regular particle shape, smooth surface without burrs, etc.

[0093] S12. The color detection unit obtains surface gloss quality information of the feed, such as its color, uniformity, glossiness, and consistency, through the set intelligent sensor, and transmits it to the texture detection unit;

[0094] Further explanation: By using the high-definition camera, the cylindrical shape of ordinary feed, or the fluffy and porous structure of expanded feed, as well as the small particles of piglet feed and the large particles of growing and finishing pig feed, can be obtained. The particle size has different effects on animals at different stages, and these information are very important for subsequent evaluation of the quality and applicability of the feed, directly affecting the digestion, absorption, and healthy growth of animals; the color quality requirements include that the appearance color of the feed is slightly yellow and has a certain gloss on the surface.

[0095] S13. The texture detection unit obtains quality information of the feed, such as hardness, temperature, humidity, viscosity, and peculiar smell, through the set intelligent sensor, as the basis for subsequent index judgment.

[0096] Further explanation: By using the intelligent sensor, the texture of high-quality silage feed with moisture content in the feed can be obtained to judge its softness and humidity, and the raw state of the raw materials is maintained (while poor-quality silage feed is sticky or dry and hard). These information are very important for subsequent evaluation of the quality and applicability of the feed, directly affecting the digestion, absorption, and healthy growth of animals.

[0097] S20. The safety detection module obtains pollutant information of inorganic substances, mycotoxins, natural plant toxins, organochlorines, and microorganisms in the feed through safety detection equipment, and transmits it to the nutrition detection module;

[0098] Please refer to Figure 9 As shown, step S20 includes the following steps:

[0099] S21. The inorganic detection unit obtains the contents of various inorganic pollutants such as total arsenic, lead, mercury, cadmium, chromium, fluorine, and nitrite in the feed through intelligent sensors and transmits them to the fungal detection unit;

[0100] Further explanation: The inorganic pollutants refer to minerals such as copper and zinc added in excess in the feed powder, as well as inorganic environmental pollutants such as total arsenic, lead, mercury, cadmium, chromium, fluorine, and nitrite; the addition amount of copper is 250 mg per kilogram of feed, and the addition amount of zinc is 3000 mg per kilogram of feed. If the amount is excessive, it will cause poisoning of cultured organisms. Especially, copper is likely to accumulate in the liver. If humans ingest pork liver with high copper and zinc residues, it may endanger human health. A large amount of copper and zinc are excreted with feces, seriously polluting the environment; the absorption rate of arsenic is low, and it is excreted into farmland and rivers through feces and urine, which can seriously pollute the environment.

[0101] S22. The fungal detection unit obtains the contents of various fungi in the feed sample powder through the set feed mycotoxin detector and transmits them to the toxin detection unit;

[0102] Further explanation: Through the feed mycotoxin detector, using the principle of fluorescence quantitative rapid detection, the contents of various fungi such as aflatoxin B1, zearalenone, T-2 toxin, ochratoxin A, deoxynivalenol (vomitoxin), fumonisin B1, and fumonisin B2 in the animal feed powder are detected, avoiding the contact between the operator and vomitoxin, protecting the safety of the operator, having no requirement for the amount of the detected feed sample, and being able to detect single or small samples at any time as they arrive, or a large number of samples can be detected simultaneously, and on-site online detection can be achieved.

[0103] S23. The toxin detection unit obtains the contents of various natural plant toxins in the feed sample powder through the set intelligent biosensor and transmits them to the chlorine-containing detection unit;

[0104] Further explanation: The intelligent biosensor uses immobilized biological active substances such as enzymes, antibodies, antigens, microorganisms, cells, tissues, and nucleic acids as the recognition elements of the biological sensitive material, which can specifically recognize and bind to the substance to be detected. When the substance to be detected binds to the sensitive material, a biological reaction or molecular recognition will occur. The information generated by these reactions or recognitions is converted into quantifiable and displayable electrical signals through appropriate physicochemical transducers such as oxygen electrodes, photosensitive tubes, field effect transistors, and piezoelectric crystals. The converted electrical signals are amplified by a signal amplification device and finally output as measurable electrical signals, which can detect the contents of various natural plant toxins such as cyanide, free gossypol, isothiocyanate (calculated as allyl isothiocyanate), and oxazolidinethione (calculated as 5-vinyl-oxazole-2-thione) in the feed sample powder.

[0105] S24. The chlorine-containing detection unit obtains the contents of various organochlorine pollutants in the feed sample powder through the set organochlorine content detector and transmits them to the bacteria detection unit;

[0106] Further explanation: The organochlorine content detector can generate products with different color depths through the specific reaction of relevant components in the feed sample powder with the color reagent under certain conditions, and selectively absorb visible light of different wavelengths. The depth of color, that is, the level of absorbance, is correlated with the concentration of the target component in the feed sample and obeys the Lambert-Beer law within an appropriate concentration range. Therefore, the detected absorbance is automatically calculated by the built-in standard curve software to obtain the contents of organochlorine pollutants such as polychlorinated biphenyls, hexachlorocyclohexanes, dichlorodiphenyltrichloroethanes, and hexachlorobenzene in the feed sample and the results of whether they exceed the standard.

[0107] S25. The bacteria detection unit obtains the contents of various bacteria such as Salmonella, mold, total bacteria count, coliforms, Shigella, and Staphylococcus in the feed sample powder through the bacteria detector.

[0108] Further explanation: The bacteria detector uses ATP (adenosine triphosphate) as an indicator of biomass to detect the contents of various bacteria in the feed powder based on biochemical reactions and optical detection technologies. A special ATP swab containing a reagent that can lyse cell membranes is used to collect the sample to release intracellular ATP, which reacts with the specific enzyme in the swab to generate a light signal. The light signal is measured by a fluorometer. The intensity of the light signal is directly related to the number of microorganisms. The number of microorganisms in the sample is quantified by measuring the intensity of the light signal, and the test results are compared with the data in the known database to identify the categories and quantities of Salmonella, mold, total bacteria count, coliforms, Shigella, and Staphylococcus in the feed sample powder.

[0109] S30. The nutrition detection module obtains the contents of basic components, vitamins, source components, and enzyme activity components in the feed through the feed nutrition component detection equipment and transmits them to the data processing module;

[0110] Please refer to Figure 10 As shown, step S30 includes the following steps:

[0111] S31. The basic nutrition unit obtains the contents of basic nutrition components required by animals in the feed sample powder through a near-infrared spectrometer and an intelligent biosensor and transmits them to the vitamin unit;

[0112] Furthermore, the basic nutritional components of the feed include crude protein, crude fat, crude fiber, crude ash, calcium and phosphorus, water-soluble chlorides, 19 amino acids, and 8 trace elements (calcium, copper, iron, magnesium, manganese, potassium, sodium, zinc); the 19 amino acids include 4 essential amino acids, namely lysine, methionine, threonine, and tryptophan, and 15 non-essential amino acids, namely glycine, alanine, leucine, isoleucine, valine, cystine, cysteine, methionine, serine, phenylalanine, tyrosine, proline, hydroxyproline, glutamic acid, and aspartic acid; the near-infrared spectrometer can detect the contents of crude protein, crude fat, crude fiber, crude ash, calcium and phosphorus in the feed; other nutritional components are detected by intelligent biosensors.

[0113] S32. The vitamin unit detects the contents of 11 vitamins and 7 acid nutritional components in the feed sample powder by high performance liquid chromatography (HPLC) and transmits them to the source component unit;

[0114] Further explanation: The high performance liquid chromatography (HPLC) uses a liquid chromatograph to separate each component in the sample through a specific chromatographic column, then detects through a detector and processes the data through software, and finally obtains the content of the target component vitamin in the feed sample, including: passing the feed sample to be tested through steps such as extraction and purification to obtain a pure vitamin solution; liquid chromatography analysis: injecting the pure vitamin solution into the liquid chromatograph, separating the vitamins through the chromatographic column, and then measuring through the detector; processing and analyzing the experimental data to obtain the contents of various vitamins; the 11 vitamins in the feed include vitamin B1, vitamin B2, vitamin B6, vitamin B12, vitamin E, vitamin A, vitamin C, vitamin D3, vitamin K3, vitamin H, vitamin B7, etc.; the 7 acids in the feed include nicotinic acid, folic acid, pantothenic acid, choline chloride, choline, folic acid, nicotinamide, etc.

[0115] S33. The source component unit obtains the contents of various animal and plant source components in the feed sample powder through a set PCR detector and transmits them to the enzyme activity component unit;

[0116] Further explanation: The PCR detector obtains the contents of various animal and plant-derived components in the feed sample powder through polymerase chain reaction; PCR is the abbreviation of the English Polymerase Chain Reaction, that is, polymerase chain reaction. That is, when DNA denatures at a high temperature of 90 °C in vitro, it becomes single-stranded. At low temperature (60 °C), the primer binds to the single-stranded according to the principle of base complementary pairing. Then, the temperature is adjusted to the optimal reaction temperature of DNA polymerase (about 72 °C). DNA polymerase synthesizes a complementary strand along the direction from phosphate to pentose sugar (5'-3'). By simulating mixed samples containing different proportions of animal-derived components, the proportion and presence of animal-derived components in the feed can be effectively detected to determine the contents of various animal and plant-derived components, including: under the action of heat, the temperature is 90-96 °C, and the hydrogen bonds of the double-stranded DNA template break to form single-stranded DNA; the system temperature is annealed and reduced to 60-65 °C, and the primer binds to the DNA template to form a local double-strand; under the action of Taq enzyme at 70-75 °C (the best at 72 °C), using dNTP as a raw material, starting from the 3′ end of the primer, extending in the direction from 5′→3′, synthesizing a DNA strand complementary to the template; the various plant-derived components in the feed include transgenic qualitative and quantitative, soybean transgenic components, corn transgenic components, etc.; the various animal-derived components in the feed include animal-derived components such as mink, goose, dog, fox, quail, duck, turkey, duck, chicken, poultry-derived, donkey, horse, cow, buffalo, sheep, pig, cat, rabbit, fish, etc.

[0117] S34. The enzyme activity component unit obtains the contents of various enzyme activity components in the feed sample powder through the set feed mycotoxin detector.

[0118] Further explanation: The feed mycotoxin detector can be a detection device for quickly and quantitatively detecting multiple mycotoxins in the feed. By putting the mycotoxin detection strip into the detector and adding the sample to the detection strip, the system can automatically identify the color of the ROSA detection strip and automatically select the required detection channel according to the color. Just select the sample type and dilution factor, and the EZ-M can automatically select the correct incubation temperature and incubation time and automatically display the detection result; the enzyme activity components in the feed include urease activity, cellulase activity, β-glucanase activity, acid / neutral protease activity, xylanase activity, pectinase activity, phytase activity, α-amylase activity, lipase activity, etc.

[0119] S40. The data processing module processes and analyzes the detection results through statistical methods and computer software to obtain various indicators of feed quality, safety, and nutritional components, and transmits them to the processing center;

[0120] Please refer to Figure 11 As shown, the step S40 includes the following steps:

[0121] S41. The information processing unit preprocesses the detection data through data cleaning, data transformation, and feature selection to eliminate noise and redundant information, improve the accuracy of the detection model, and transfer it to the model training unit;

[0122] Specifically, the data cleaning refers to formatting, normalizing, deduplicating, removing noise and outliers, etc. from the detection data, and completing operations such as data deduplication, trimming, replacement, filling, normalization, and missing value processing to ensure the quality and correctness of the data; the data transformation refers to performing operations such as field definition, type conversion, and encoding conversion on the cleaned data, and converting it into analyzable data formats such as CSV, JSON, or XML for subsequent data analysis and mining; the feature selection refers to integrating datasets from multiple data sources into one dataset, and judging and selecting the data sources to avoid data duplication and conflict problems.

[0123] S42. The model training unit trains the processed data model according to the support vector machine algorithm calculation formula , where f(X) is the regression model function of SVR, α is the updated Lagrange multiplier, X is the feature vector, b is the bias term, * is the dual variable, and T is the transpose of a vector or matrix, and transfers it to the model evaluation unit;

[0124] Specifically, the updated Lagrange multiplier α, feature vector X, and bias term b are known parameters, and their function values are obtained according to their calculation formulas; appropriate algorithms and model architectures are selected through the support vector machine algorithm, and the collected data is used for training, and parameters such as the learning rate and regularization parameter of the model are adjusted to improve the performance of the model; the dual variable * is used to distinguish the upper and lower bound constraints, such as α i * paired with α i and the non-zero α i * or α i corresponding samples are support vectors, which determine the shape of the regression model.

[0125] S43. The model evaluation unit calculates the evaluation results of the samples based on the specific detection data through accuracy, precision, and recall, and displays them in the form of reports such as text descriptions and charts for the judgment of feed indicators.

[0126] Further explanation: The accuracy rate is obtained for the feed sample detection data according to the accuracy rate calculation formula "Ac = (TP + TN) / [(TP + FN)+(FP + TN)], where Ac is the accuracy rate, TP is the number of samples that are actually positive and predicted to be positive, TN is the number of samples that are actually negative and predicted to be negative, TP + FN is the number of samples that are actually positive, and FP + TN is the number of samples that are actually negative"; the precision rate is obtained for the feed sample detection data according to the precision rate calculation formula "Pr = TP / (TP + FP), where Pr is the precision rate, TP is the number of samples that are actually positive and predicted to be positive, and TP + FP is the number of all samples predicted to be positive"; the recall rate is obtained for the feed sample detection data according to the recall rate calculation formula "Re = TP / (TP + FN), where Re is the recall rate, TP is the number of samples that are actually positive and predicted to be positive, and TP + FN is the number of samples that are actually positive", where FN is the number of samples that are actually positive but predicted to be negative, FP is the number of samples that are actually negative but predicted to be positive, and FN + TN is the number of all samples predicted to be negative; if the model evaluation result is not ideal, the performance of the model is improved by adjusting the model parameters or increasing the training data.

[0127] S50. The processing center compares the contents of the quality, safety, and nutritional components in the feed with the respective index quality standards of this feed stored in the memory: If it meets the standards, production continues; if it does not meet the standards, it is transmitted to the alarm and notifies to adjust the ingredients and re - produce.

[0128] Further explanation: The respective index quality standards of the feed include having burrs or protrusions on the surface, being relatively large and irregular in particles; having a certain viscosity; having a smooth surface, soft to the touch, and uniform particle size; having relatively large gaps between particles and a certain fluidity; having a faint wheat fragrance, a fresh fragrance, and no peculiar smell; and the safety index and nutritional component content both meeting the national standards.

[0129] S60. The ingredient adjustment module adjusts the ingredients according to the results of the exceeding - standard of the feed indexes, so that the quality, safety, and nutritional component indexes all meet the standards to meet the nutritional requirements of the corresponding animals for this feed.

[0130] Please refer to Figure 12 As shown, before the step S60, the following steps are included:

[0131] S61. The formula reservation unit obtains the main raw materials and their formula ratio information of the animals corresponding to this feed by connecting to the industry database and transmits it to the auxiliary material adjustment unit.

[0132] Further explanation: By feeding this kind of animal with different ratios of feed raw materials, the species of the same kind of animal, its weight gain information, and growth change information such as the luster of animal hair or fish scales can be obtained. Through comparative analysis of its growth change information, the best growth information of the animal can be obtained. The number of the same kind of animals fed with different ratios of feed raw materials is greater than or equal to 1. The more animals there are, the more accurate the obtained animal change information will be. The animal growth change value is the average value of the animals fed with the same ratio of feed raw materials. According to the best growth information of the animal, such as the highest weight gain and the brightest luster of animal hair or fish scales during growth, the corresponding feed raw materials and their ratios for the animal can be obtained.

[0133] S62. The auxiliary material adjustment unit obtains the corresponding auxiliary substance information required for the growth of the animal according to the growth cycle information of this kind of animal, adds it to the feed powder and stirs evenly, and then transfers it to the pellet making unit.

[0134] Further explanation: In order to enable the target animal to grow healthily, a certain amount of drugs to enhance resistance can be fed to the target animal. For example, when poultry are in the young growth period, broad-spectrum antibacterial drugs can be fed to strengthen the resistance of poultry in the young period. If manual feeding is used, it is too time-consuming. Therefore, the drugs can be added to the feed, which is convenient and time-saving.

[0135] S63. The pellet making unit makes the feed powder into feed pellets according to the pellet size and hardness information of the same kind of animals through pellet making equipment, and then transfers it to the feed digestion unit.

[0136] Further explanation: Different kinds of animals have different forms, and there are also differences in their digestive functions and mouth shapes. For example, before 6 weeks of growth, poultry are fed with 1-3 mm powder, which is beneficial to the absorption of the digestive system of young poultry. After adulthood, poultry can be fed with feed pellets larger than 3 mm. By feeding different pellet sizes of feed pellets to animals at different growth stages, the feed pellets can be completely absorbed. Cows and horses have large mouths, so their feed pellets can be relatively larger, while shrimps have small mouths, so their feed pellets are relatively smaller. The size of the feed pellets must be determined according to the body size, mouth size and digestive ability of different animals.

[0137] S64. The feed digestion unit obtains the information of the feed nutrients contained in the feces of the animal after eating the feed through a testing device, which is used as a reference for the formula of the feed production of the same kind of animals in the future.

[0138] Further explanation: If the animal is in a good growth state and the animal feces still contain feed nutrients, it indicates that the nutrients in the feed have not been fully absorbed and the nutrients in the feed particles have not been fully utilized. If reducing the particle size of the corresponding feed raw materials can increase the absorption surface of the animal digestive system and there are still feed nutrients in the animal feces, then reduce the proportion of the raw materials corresponding to the feed nutrients to save raw material costs. Among them, whether the animal has a disease can be obtained through subsequent animal status tracking, for example: obtaining feedback information from each breeding farm or feedback information from the breeder to get information about whether the animal has a disease.

[0139] Further explanation: The above steps are shown in sequence according to the arrows, but these steps do not necessarily need to be executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps. These steps can also be executed according to other orders. Moreover, some steps can include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily need to be completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in rotation with at least a part of other steps or sub-steps or stages of other steps.

[0140] A feed online production detection control system provided by the present invention further includes a computer device and a computer-readable storage medium; the computer device includes a memory and each functional module. The memory stores a computer program, and when each functional module executes the computer program, it realizes the steps of a feed online production detection method described in any one of the above; the computer-readable storage medium stores a computer program, and when the computer program is executed by each functional module, it realizes the steps of a feed online production detection method described in any one of the above.

[0141] Further explanation: The computer-readable storage medium includes a memory, which can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the programs and instructions corresponding to a feed online production detection method in an embodiment of the present invention, including information transfer instructions for each module; the memory executes various functional applications and data processing of each module by running the stored non-volatile software programs and instructions, that is, realizes a feed online production detection method in the above method embodiment; one or more units are stored in the memory, and when executed by the one or more modules, they execute a feed online production detection method in any of the above method embodiments; the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by one or more modules, they can also be a feed online production detection method in any of the above method embodiments.

[0142] Further explanation, the present invention is described in accordance with the content implemented by the software program of an on-line production detection and control system for feed. For each on-line production detection method of feed, it is divided into several modules or units to implement the software program instructions generated by each step. The software program instructions include the above-mentioned on-line production detection method of feed.

[0143] The present invention also provides a feed detection control device, which is implemented by using the above-mentioned on-line production detection method of feed.

[0144] Further explanation, the feed detection control device includes a quality detection device, a safety detection device, and a nutrition detection device for feed. These devices can be assembled and connected according to the detection process to achieve integrated detection support, or the independence of each detection device can be realized. The feed samples to be detected are transmitted through a transmission device to ensure the convenience of detection; they can also be directly set on the feed production equipment and effectively connected through a data line via a wireless network.

[0145] For those skilled in the art, it is obvious that this application is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of this application, this application can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of this application is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in this application.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not restrictive. Although this application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of this application can be modified or equivalently replaced, and all should be included in the protection scope of this application.

Claims

1. An on-line production detection method for feed, characterized in that: Applied to an on-line production detection and control system for feed, which includes a quality detection module, a safety detection module, a nutrition detection module, a data processing module, a batching adjustment module, a wireless communication module, an alarm, a memory, a processing center, and an intelligent remote control device: The quality detection module, the safety detection module, the nutrition detection module, the data processing module, the batching adjustment module, the wireless communication module, the alarm, and the memory are respectively connected to the processing center; The intelligent remote control device includes a smart phone, a tablet computer, and an intelligent remote control, and automatically forms a network connection with the wireless communication module within the range of wireless network or Internet; The method includes the following steps: S10. During detection, the quality detection module obtains the surface quality information and production process parameters of the feed through detection equipment to ensure the accuracy and integrity of the data, and transmits them to the safety detection module, including the following steps: S11. The appearance detection unit obtains the surface appearance quality information of the shape of the feed, its integrity, particle size and its uniformity through the set high-definition camera, and transmits it to the color detection unit; S12. The color detection unit obtains the surface gloss quality information of the color of the feed, its uniformity, gloss and its consistency through the set intelligent sensor, and transmits it to the texture detection unit; S13. The texture detection unit obtains the quality information of the hardness, temperature, humidity, viscosity, and peculiar smell of the feed through the set intelligent sensor, as the basis for subsequent index judgment: S20. The safety detection module obtains the pollutant information of inorganic substances, mycotoxins, natural plant toxins, organochlorines, and microorganisms in the feed through intelligent sensors, and transmits it to the nutrition detection module: S30. The nutrition detection module obtains the nutrient content of the basic components, vitamins, source components, and enzyme activity components in the feed through feed nutrient component detection equipment, and transmits it to the data processing module; S40. The data processing module processes and analyzes the detection results through statistical methods and computer software to obtain various indicators of feed quality, safety, and nutritional components, and transmits them to the processing center, including the following steps: S41. The information processing unit performs preprocessing of data cleaning, data transformation, and feature selection on the detection data to eliminate noise and redundant information, so as to improve the accuracy of the detection model, and transmits it to the model training unit; S42. The model training unit calculates according to the support vector machine algorithm formula " , where f(X) is the regression model function of SVR, o is the updated Lagrange multiplier, X is the feature vector, b is the bias term, * is the dual variable, and T is the transpose of a vector or matrix", trains the processed data model, and transfers it to the model evaluation unit: S43. The model evaluation unit calculates the evaluation results of the samples according to the specific detection data through accuracy, precision, and recall rate, and displays them in text description and charts for the judgment of feed indicators; S50. The processing center compares the content of each index in the feed with the standard content of each index of this feed stored in the memory: If it meets the standard, continue production; if it does not meet the standard, transmit it to the alarm and notify to adjust the batching and produce again: S60. The batching adjustment module adjusts the batching according to the over-standard results of each feed index, so that the quality, safety, and nutritional component indexes all meet the standards to meet the nutritional needs of the corresponding animals for this feed.

2. The on-line production detection method for feed according to claim 1, wherein: The system further includes: The wireless communication module is provided with various wireless network units, which are responsible for receiving and transmitting wireless network signals and automatically networking and connecting with the intelligent remote control device within the range of the wireless network or the Internet; The alarm compares the contents of quality, safety, and nutritional components in the feed with the content standard of each index of the feed stored in the memory. If the standard is not met, it will automatically sound an alarm and notify to adjust the ingredients and produce again; The memory is responsible for storing the information of the quality detection module, safety detection module, nutritional detection module, data processing module, ingredient adjustment module, wireless communication module, and alarm, as well as storing the content standard of each index of the feed; The processing center is responsible for the information transfer of the quality detection module, safety detection module, nutritional detection module, data processing module, ingredient adjustment module, wireless communication module, alarm, and memory. It is the hub center of the system and compares the contents of quality, safety, and nutritional components in the feed with the content standard of each index of the feed stored in the memory: If the standard is met, production continues; if the standard is not met, it is transmitted to the alarm and notifies to adjust the ingredients and produce again; The quality detection module includes an appearance detection unit, a color detection unit, and a texture detection unit, which obtain the surface quality information and production process parameters of the feed through feed quality detection equipment to ensure the accuracy and integrity of the data, and transmit it to the safety detection module; The safety detection module includes an inorganic detection unit, a fungus detection unit, a toxin detection unit, a chlorine-containing detection unit, and a bacteria detection unit, which obtain the pollutant information of inorganic substances, mycotoxins, natural plant toxins, organochlorine, and microorganisms in the feed through feed safety detection equipment, and transmit it to the nutritional detection module; The nutritional detection module includes a basic nutrition unit, a vitamin unit, a source component unit, and an enzyme activity component unit, which obtain the nutritional component content of basic components, vitamins, source components, and enzyme activity components in the feed through feed nutritional component detection equipment, and transmit it to the data processing module; The data processing module includes an information processing unit, a model training unit, and a model evaluation unit, which process and analyze the detection results through statistical methods and computer software to obtain the indexes of quality, safety, and nutritional components of the feed, and transmit it to the processing center; The ingredient adjustment module includes a formula reservation unit, an auxiliary material adjustment unit, a granule production unit, and a feed digestion unit, which are responsible for adjusting the ingredients according to the exceeding standard results of each index of the feed to make the indexes of quality, safety, and nutritional components meet the standard to meet the nutritional needs of the corresponding animals for the feed; The step S20 includes the following steps: S21. The inorganic detection unit obtains the contents of various inorganic pollutants such as total arsenic, lead, mercury, cadmium, chromium, fluorine, and nitrite in the feed through intelligent sensors and transmits it to the fungus detection unit; S22. The fungus detection unit obtains the contents of various fungi in the feed sample powder through the set feed mycotoxin detector and transmits it to the toxin detection unit; S23. The toxin detection unit obtains the contents of various natural plant toxins in the feed sample powder through the set intelligent biosensor and transmits them to the chlorine-containing detection unit; S24. The chlorine-containing detection unit obtains the contents of various organochlorine pollutants in the feed sample powder through the set organochlorine content detector and transmits them to the bacteria detection unit; S25. The bacteria detection unit obtains the contents of various bacteria such as Salmonella, mold, total number of bacteria, coliform group, Shigella, and Staphylococcus in the feed sample powder through the bacteria detector.

3. A method for on-line production detection of feed according to claim 1, characterized in that: The step S30 includes the following steps: S31. The basic nutrition unit obtains the contents of the basic nutritional components required by animals in the feed sample powder through a near-infrared spectrometer and an intelligent biosensor and transmits them to the vitamin unit; S32. The vitamin unit detects the contents of the nutritional components of 11 vitamins and 7 acids in the feed sample powder by high performance liquid chromatography and transmits them to the source component unit; S33. The source component unit obtains the contents of various animal and plant source components in the feed sample powder through the set PCR detector and transmits them to the enzyme activity component unit; S34. The enzyme activity component unit obtains the contents of various enzyme activity components in the feed sample powder through the set feed mycotoxin detector; Before the step S60, the following steps are included: S61. The formula predetermination unit obtains the main raw materials and their formula ratio information of the animals corresponding to the feed by connecting to the industry database and transmits them to the auxiliary material adjustment unit; S62. The auxiliary material adjustment unit obtains the corresponding auxiliary substance information required for the growth of the animal according to the growth cycle information of the animal, adds it to the feed powder and stirs evenly, and transmits it to the granule making unit; S63. The granule making unit makes the feed granule size from the feed powder through the granule making equipment according to the granule size and hardness information of the feed for the same kind of animals and transmits it to the feed digestion unit; S64. The feed digestion unit obtains the information of the feed nutrients contained in the feces of the animals after eating the feed through the laboratory equipment, which is used as a formula reference for the production of the feed for the same kind of animals in the future.

4. A method for on-line production detection of feed according to any one of claims 1-3, characterized in that: The control system further includes a computer device and a computer-readable storage medium; the computer device includes a memory and each functional module, the memory stores a computer program, and when each functional module executes the computer program, it realizes the steps of a method for on-line production detection of feed according to any one of claims 1-3 above; the computer-readable storage medium stores a computer program, and when the computer program is executed by each functional module, it realizes the steps of a method for on-line production detection of feed according to any one of claims 1-3 above.

5. A feed detection and control device, characterized in that: It is realized by a method for on-line production detection of feed according to any one of claims 1-3 above.

Images