Food safety traceability detection method and system based on Internet of Things

Abstract

The invention discloses a food safety traceability detection method and system based on the Internet of Things, and relates to the field of food safety traceability detection.The food safety traceability detection system comprises a data acquisition module, a finished product module, a raw material module, a processing module, a storage and transportation module and a judgment module.The method comprises the following steps that meat prefabricated dish finished products are analyzed to obtain different values of the prefabricated dish finished products; the method comprises the following steps: sending a corresponding prefabricated vegetable safety quality abnormity tracing signal, judging and analyzing a meat prefabricated vegetable raw material to obtain a meat prefabricated vegetable raw material safety quality difference value, and judging and analyzing a processing environment, a preservative and a prefabricated vegetable cleaning state of the meat prefabricated vegetable to obtain a meat prefabricated vegetable rotting residual value; storage and transportation of abnormal meat prefabricated dishes are judged and analyzed, storage and transportation different values of the meat prefabricated dishes are obtained, processing of the prefabricated dishes in each process is analyzed to obtain abnormal processes affecting food problems of the meat prefabricated dishes, and the prefabricated dishes in the abnormal state can be analyzed from multiple dimensions and multiple directions; and the production cost of the prefabricated dishes of enterprises is reduced.

Description

Technical Field

[0001] The present invention relates to the field of food safety traceability detection, and specifically to a food safety traceability detection method and system based on the Internet of Things. Background Art

[0002] Traceability testing for the safety of prepared meat dishes is very important. Traditional traceability testing for the safety of prepared meat dishes relies too much on manual monitoring and is unable to monitor and trace the quality and safety status of prepared dishes in real time.

[0003] When running, traditional food safety traceability detection methods are unable to accurately identify abnormal safety conditions of pre-prepared meat dishes in real time, and are even more unable to analyze abnormal pre-prepared dishes from multiple dimensions and directions. As a result, the image of the company's pre-prepared dishes has been greatly reduced in the eyes of many consumers, increasing the company's cost of pre-prepared dish production. At the same time, it is also unable to detect violations and safety hazards of pre-prepared dishes, increasing the company's potential losses and operating risks.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] In order to solve the technical problems raised by the above background technology, the present invention is proposed. The embodiments of the present invention provide a food safety traceability detection method and system based on the Internet of Things.

[0006] The purpose of the present invention can be achieved by the following technical solution: A food safety traceability detection method based on the Internet of Things comprises the following steps: S1: The data acquisition module collects the finished product information, raw material information, processing information and storage and transportation information of the prepared meat dishes, and sends it to the finished product module, raw material module, processing module and storage and transportation module; S2: The finished product module analyzes the oil and fat chemical composition, protein structure, carbohydrate content, and microbial indicators of the meat pre-prepared dishes to obtain abnormal values ​​of the pre-prepared dishes, and compares them with the set comparison interval to issue a signal for abnormal safety and quality of the pre-prepared dishes; S3: Receive raw material information and pre-prepared food safety and quality anomaly traceability signals through the raw material module, conduct judgment and analysis on the muscle fiber bundles, sensory state, bioelectric characteristics, and protein carbonyl groups of the meat pre-prepared food raw materials, and obtain the safety and quality anomaly values ​​of the meat pre-prepared food raw materials; S4: receiving the processing information of the prepared meat dishes and the abnormal traceability signal of the safety and quality of the prepared dishes through the processing module, determining and analyzing the processing environment, preservatives, and cleaning status of the prepared meat dishes, and obtaining the residual value of the prepared meat dishes; S5: receiving the storage and transportation information of the prepared meat dishes and the abnormal traceability signal of the safety and quality of the prepared dishes through the storage and transportation module, making judgments and analyzing the storage and transportation of the abnormal prepared meat dishes, and obtaining the abnormal values ​​of the storage and transportation of the prepared meat dishes; S6: The judgment module receives the abnormal values ​​of safety and quality of raw materials of pre-prepared meat dishes, the residual values ​​of pre-prepared meat dishes, and the abnormal values ​​of storage and transportation of pre-prepared meat dishes, and analyzes the processing of each process of the pre-prepared dishes to obtain the abnormal processes that affect the food problems of the pre-prepared meat dishes.

[0007] Furthermore, the steps of analysing the signal of tracing the source of abnormal quality of prepared food are as follows: Normalize the finished oil oxygenation value, the finished egg change value, the finished carbohydrate reduction value and the finished fungal disease value of the prepared food product, and obtain the finished product abnormal value of the prepared food product through graph construction processing; Compare the abnormal value of the pre-prepared food product with the set comparison intervals CX1 and CX2, where the comparison interval CX1>CX2. When the abnormal value of the pre-prepared food product is in the comparison interval CX1, the quality of the corresponding pre-prepared food product is abnormal, and a pre-prepared food safety and quality abnormality traceability signal is issued and sent to the raw material module, processing module and storage and transportation module. When the abnormal value of the pre-prepared food product is in the comparison interval CX2, the quality of the corresponding pre-prepared food product is normal.

[0008] Furthermore, the steps for analyzing the oil oxygenation value of the prepared dish product, the egg change value of the prepared dish product, the carbohydrate reduction value of the prepared dish product and the fungal disease value of the prepared dish product are as follows: The oil chemical composition is the sum of the oil peroxide value, oil acid value and oil carbonyl value of the meat pre-prepared dish product to obtain the oil oxidation value of the pre-prepared dish product. The protein structure refers to the sum of the low and high molecular weight values ​​of the band, the band width value and the band tailing degree to obtain the protein change value of the pre-prepared dish product. The protein is extracted from the pre-prepared dish product by protein extraction buffer, and through gel electrophoresis experiment, according to the molecular weight value in c1 and c2 markers, the area with a molecular weight less than c1 in the gel electrophoresis experiment corresponds to the low molecular weight area, and the area greater than c2 corresponds to the high molecular weight area. The number of bands and the integrated optical density values ​​in the low molecular weight area and the high molecular weight area are counted and summed to obtain the low and high molecular weight values ​​of the band. The sharpness value on the band is lower than the set When the sharpness threshold is set, it corresponds to tailing. The distance from the end of the normal part of the strip to the last position of the tailing identified by the cursor is counted and marked as the tailing length of the strip. The tailing length of each strip is counted and marked as the tailing degree of the strip. The carbohydrate content refers to the reaction of distilled water and anthrone reagent in the pre-prepared dish product, and the absorbance is measured by a spectrophotometer at a certain wavelength. The organic acid in the mixed solution of distilled water of the pre-prepared dish product is titrated with a standard sodium hydroxide solution, and the consumption of sodium hydroxide is counted. The measured absorbance is added to the consumption of sodium hydroxide, and the result is multiplied by the correction factor coefficient to obtain the carbohydrate reduction value of the pre-prepared dish product. The microbial index refers to the total number of colonies, the number of coliform bacteria, and the content of pathogenic bacteria to obtain the bacterial disease value of the pre-prepared dish product.

[0009] Furthermore, the steps for analyzing the safety and quality of raw materials for prepared meat dishes are as follows: Obtain the sensory quality value, bioelectric special value, and protein carbonyl content in the meat pre-prepared dish raw material information, mark them as Gz, Tb, and Db, normalize them with the muscle fiber value JQz of the meat pre-prepared dish raw material, and substitute them into the set formula , the safety and quality difference value AZZ of meat pre-prepared food raw materials is calculated, where g1, g2, g3, g4, g5, g6, g7 and g8 are all set weight factor coefficients, and njz refers to the cohesion index of the pre-prepared food raw materials.

[0010] Furthermore, the steps for analyzing the muscle fiber value of the raw materials of the prepared meat dishes are as follows: Step 4: Divide the three-dimensional model of the muscle fiber bundle into several cubic units, which are marked as voxels. The ratio of the number of voxels occupied by the fiber bundle to the total number of voxels is counted and marked as the muscle fiber bundle space filling value. The muscle fiber bundle fractal value, muscle fiber bundle dispersion value, muscle fiber bundle neighbor value, and muscle fiber bundle space filling value are marked as fz, js, sl, and tc, respectively, and normalized with the muscle fiber bundle cocircle value Tyz, and substituted into the set formula The calculation is performed to obtain the muscle fiber value JQz of the raw materials for pre-prepared meat dishes, wherein th1, th2, th3, th4, th5, th6, th7, th8 and th9 are the set influencing factor coefficients, and e is a natural constant.

[0011] Furthermore, the muscle fiber bundle cocircularity value analysis steps are as follows: Step 3: The three-dimensional model of the muscle fiber bundle is fitted with a cylinder by the least squares method to obtain its central axis, and the distance from each point on the fiber bundle to the central axis is obtained, which is marked as the median value of each point in the fiber bundle. The absolute value of the difference between the median values ​​of adjacent points in the fiber bundle is counted. When the absolute value of the difference between the median values ​​is less than or equal to the set threshold, the adjacent points are classified into the concentric circle structure, and the number of concentric circle structures in the muscle fiber bundle is counted. The three-dimensional coordinates of the starting point of each concentric circle structure (xs n , ys n , zs n ) and the end point coordinates (xz n , yz n ,zz n ), n is the serial number of the concentric circle structure, and the pitch value jj of each concentric circle structure is obtained according to the formula n According to the formula, the cocircular distance value Txz of the muscle fiber bundle is obtained, the distance from each point in the concentric circle structure to the central axis is obtained and the average is taken to obtain the median distance of the concentric circle structure, and the median distance of each concentric circle structure is summed and divided by the number of concentric circle structures N to obtain the median cocircular distance of the muscle fiber bundle Jzz, the median cocircular distance of the muscle fiber bundle Jzz, the number of concentric circle structures N, and the cocircular distance value Txz of the muscle fiber bundle are calculated to obtain the cocircular value Tyz of the muscle fiber bundle.

[0012] Furthermore, the muscle fiber bundle fractionation value, muscle fiber bundle dispersion value and muscle fiber bundle neighbor value analysis steps are as follows: Step 1: Obtain the 3D data of the muscle fiber bundles of the raw materials of the meat pre-prepared dishes through a 3D microscope, and perform 3D reconstruction of the muscle fiber bundles to obtain the 3D shape of the muscle fiber bundles. Use a thinning algorithm to thin the 3D shape of the fiber bundles into a center line, and mark the center line as the skeleton of the fiber bundle. When the neighborhood of each point of the skeleton of the fiber bundle exceeds the connection in two directions, the point is determined to be a branch point, and all the skeleton points of each fiber bundle are traversed, and the total number of branch points is counted to obtain the muscle fiber bundle fractionation value; Step 2: Obtain the angles between branches of each branch point, and count the branch angles of all branch points in the muscle three-dimensional model to obtain branch angle data, calculate the standard deviation of the branch angle data, and mark it as the muscle fiber bundle dispersion value. If the distance between adjacent fiber bundles is less than the set threshold, the two fiber bundles are grouped in the same group. If the distance between a fiber bundle and each adjacent fiber bundle is greater than or equal to the set threshold, the fiber bundle is grouped together separately, and the fiber bundles in the three-dimensional model are traversed to obtain the grouping status of the muscle fiber bundles, and the number of independent groups is counted, which is marked as the muscle fiber bundle neighbor value.

[0013] Furthermore, the abnormal process analysis steps affecting the problem of prepared meat dishes are as follows: The meat pre-prepared dish raw material safety and quality abnormality value AZZ, the meat pre-prepared dish added spoilage residual value JFZ and the meat pre-prepared dish storage and transportation abnormality value CYZ are calculated according to the formula to obtain the meat pre-prepared dish raw material abnormality value YYZ. When the meat pre-prepared dish raw material abnormality value is greater than or equal to the set raw material abnormality value threshold, it means that the corresponding meat pre-prepared dish safety and quality abnormality is due to abnormal meat pre-prepared dish raw materials. When the meat pre-prepared dish raw material abnormality value is less than the set raw material abnormality value threshold, the formula is used to obtain the meat pre-prepared dish added abnormality value JYZ. When the meat pre-prepared dish added abnormality value is greater than or equal to the set pre-prepared dish added abnormality value threshold, it means that the corresponding meat pre-prepared dish safety and quality abnormality is due to abnormality in the meat pre-prepared dish processing process. When the meat pre-prepared dish added abnormality value is less than the set pre-prepared dish added abnormality value threshold, it means that the corresponding meat pre-prepared dish safety and quality abnormality is due to abnormality in the meat pre-prepared dish storage and transportation process.

[0014] Furthermore, the steps for analyzing the residual value of the prepared meat dishes after spoilage are as follows: The processing information of meat pre-prepared dishes contains the residual value of the processing ring, the amount of preservatives, and the meat clear value, which are marked as jhc, ffj, and rqg, respectively, and normalized according to the formula JFZ=[h1×jhc+h2×(ffj-A2) 2] / (h3×rqg), and the residual value of meat pre-prepared dishes JFZ is calculated, where h1, h2 and h3 are the set influencing factor coefficients, and A2 is the set reference amount of preservatives.

[0015] Furthermore, the steps of analyzing the outliers in the storage and transportation of prepared meat dishes are as follows: The storage abnormality value, transportation vibration impulse value, and transportation temperature control abnormality value in the storage and transportation information of pre-prepared meat dishes are obtained, marked as cyz, yzc, and kyw respectively, and the storage and transportation abnormality value CYZ of pre-prepared meat dishes is calculated according to the set formula CYZ=t1×cyz+t2×yzc+t3×kyw, where t1, t2, and t3 are all set weight factor coefficients.

[0016] The food safety traceability detection system based on the Internet of Things is characterized by including: The data collection module is used to collect the finished product information, raw material information, processing information and storage and transportation information of the prepared meat dishes, and send it to the finished product module, raw material module, processing module and storage and transportation module; Finished product module is used to analyze the oil chemical composition, protein structure, carbohydrate content, and microbial index of meat pre-prepared dishes, obtain abnormal values ​​of pre-prepared dishes, and compare them with the set comparison interval to issue a signal for abnormal safety and quality of pre-prepared dishes; The raw material module is used to receive raw material information and pre-prepared food safety and quality anomaly traceability signals, and to determine and analyze the muscle fiber bundles, sensory states, bioelectric characteristics, and protein carbonyl groups of meat pre-prepared food raw materials to obtain the safety and quality anomaly values ​​of meat pre-prepared food raw materials; The processing module is used to receive the processing information of the prepared meat dishes and the traceability signal of the safety and quality abnormalities of the prepared meat dishes, judge and analyze the processing environment, preservatives, and cleaning status of the prepared meat dishes, and obtain the residual value of the prepared meat dishes; The storage and transportation module is used to receive the storage and transportation information of prepared meat dishes and the abnormal traceability signal of the safety and quality of prepared dishes, judge and analyze the storage and transportation of abnormal prepared meat dishes, and obtain the abnormal value of storage and transportation of prepared meat dishes; The judgment module is used to receive abnormal values ​​of safety and quality of raw materials of pre-prepared meat dishes, residual values ​​of pre-prepared meat dishes, and abnormal values ​​of storage and transportation of pre-prepared meat dishes, and analyze the pre-prepared dish processing in each process to obtain abnormal processes that affect the food problems of pre-prepared meat dishes.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention analyzes the oil and fat chemical composition, protein structure, carbohydrate content, and microbial index of the meat pre-prepared dish finished product through the finished product module to obtain the abnormal value of the pre-prepared dish finished product, and compares it with the set comparison interval, and sends out a pre-prepared dish safety and quality abnormality tracing signal; receives the raw material information and the pre-prepared dish safety and quality abnormality tracing signal through the raw material module, and makes judgments and analyses on the muscle fiber bundles, sensory state, bioelectric characteristics, and protein carbonyl groups of the meat pre-prepared dish raw materials to obtain the meat pre-prepared dish raw material safety and quality abnormality value; receives the meat pre-prepared dish processing information and the pre-prepared dish safety and quality abnormality tracing signal through the processing module, and makes judgments and analyses on the processing environment, preservatives, and pre-prepared dish cleaning state of the meat pre-prepared dish to obtain the meat pre-prepared dish spoilage residual value; receives the meat pre-prepared dish storage and transportation information and the pre-prepared dish safety and quality abnormality tracing signal through the storage and transportation module, and makes judgments and analyses on the storage and transportation of abnormal meat pre-prepared dishes to obtain the meat pre-prepared dish storage and transportation abnormality value, which can accurately identify the abnormal safety state of meat pre-prepared dishes in real time, and can analyze the abnormal pre-prepared dishes from multiple dimensions and directions.

[0018] 2. The present invention receives the abnormal values ​​of safety and quality of raw materials of pre-prepared meat dishes, the residual values ​​of pre-prepared meat dishes and the abnormal values ​​of storage and transportation of pre-prepared meat dishes through the judgment module, and analyzes the pre-prepared dish processing in each process of the pre-prepared dish to obtain the abnormal processes that affect the food problems of the pre-prepared meat dishes. This can improve the image of the enterprise in the eyes of many consumers, reduce the cost of the enterprise in the production of pre-prepared dishes, and at the same time can discover violations and safety hazards of pre-prepared dishes, reducing the potential losses and operating risks of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. The following drawings are not intentionally scaled to the actual size, and the focus is on illustrating the main purpose of the present invention.

[0020] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present invention.

[0022] like Figure 1 As shown, the food safety traceability detection system based on the Internet of Things includes a data acquisition module, a finished product module, a raw material module, a processing module, a storage and transportation module, and a judgment module.

[0023] The data acquisition module is used to collect the finished product information, raw material information, processing information and storage and transportation information of the prepared meat dishes, and send it to the finished product module, raw material module, processing module and storage and transportation module; The finished product module is used to determine the quality and safety of meat pre-prepared dishes by analyzing the oil and fat chemical composition, protein structure, carbohydrate content, and microbial indicators of the meat pre-prepared dishes, obtain the abnormal values ​​of the pre-prepared dishes, and compare them with the set comparison interval to issue a signal for abnormal safety and quality of the pre-prepared dishes. The specific analysis is as follows: The quality and safety of the finished meat pre-prepared dishes are judged and analyzed by the oil and fat chemical composition, protein structure, carbohydrate content and microbial indicators of the finished meat pre-prepared dishes. The oil and fat chemical composition is the sum of the oil peroxide value, oil acid value and oil carbonyl value of the finished meat pre-prepared dishes to obtain the oil peroxide value of the pre-prepared dishes. The protein structure refers to the sum of the low and high molecular weight values ​​of the band, the band width value and the band tailing degree to obtain the protein change value of the pre-prepared dishes. It should be noted that the protein of the pre-prepared dishes is extracted by protein extraction buffer, and through gel electrophoresis experiment, according to the molecular weight value in c1 and c2 markers, the area with a molecular weight less than c1 in the gel electrophoresis experiment corresponds to the low molecular weight area, and the area greater than c2 corresponds to the high molecular weight area. The number of bands and the integrated optical density values ​​in the low molecular weight area and the high molecular weight area are counted and summed to obtain the low and high molecular weight values ​​of the bands, where the optical density The integral value is obtained through the optical density analysis software. When the sharpness value on the strip is lower than the set sharpness threshold, it corresponds to tailing. The distance from the end of the normal part of the strip to the last position of the tailing identified by the cursor is counted and marked as the tailing length of the strip. The tailing length of each strip is counted and marked as the strip tailing degree. The carbohydrate content refers to the reaction of the pre-prepared dish finished product with distilled water and anthrone reagent. The absorbance is measured by a spectrophotometer at a certain wavelength. The organic acid in the mixed solution of the pre-prepared dish finished product distilled water is titrated with a sodium hydroxide standard solution. The consumption of sodium hydroxide is counted, and the measured absorbance is added to the consumption of sodium hydroxide, and multiplied by the correction factor coefficient to obtain the carbohydrate reduction value of the pre-prepared dish finished product. The microbial index refers to the total number of colonies, the number of coliform bacteria, and the content of pathogenic bacteria to obtain the bacteriological value of the pre-prepared dish finished product, among which the pathogenic bacteria are specifically Staphylococcus aureus, Salmonella, and Listeria monocytogenes. Normalize the finished oil oxidation value, the finished egg change value, the finished carbon water abnormal value and the finished fungus disease value of the pre-prepared dish product, take the finished oil oxidation value of the pre-prepared dish product as the length of the cuboid, take the finished egg change value of the pre-prepared dish product as the width of the cuboid, take the finished carbon water abnormal value of the pre-prepared dish product as the height of the cuboid, take the upper surface center point of the cuboid as the center of the sphere, take the finished fungus disease value of the pre-prepared dish product as the radius of the sphere to establish a sphere, identify the irregular volume formed by the sphere and the cuboid, and mark it as the finished product abnormal value of the pre-prepared dish product; Compare the abnormal value of the finished pre-prepared dish with the set comparison intervals CX1 and CX2, where the comparison interval CX1>CX2. When the abnormal value of the finished pre-prepared dish is in the comparison interval CX1, the quality of the corresponding finished pre-prepared dish is abnormal, and a pre-prepared dish safety and quality abnormality traceability signal is issued and sent to the raw material module, processing module and storage and transportation module to analyze the raw materials, processing and storage and transportation of the pre-prepared dish. When the abnormal value of the finished pre-prepared dish is in the comparison interval CX2, the quality of the corresponding finished pre-prepared dish is normal and no corresponding operation is required; The raw material module receives raw material information and pre-prepared food safety and quality anomaly traceability signals, and makes judgments and analyses on the muscle fiber bundles, sensory states, bioelectric characteristics, and protein carbonyl groups of meat pre-prepared food raw materials to obtain the safety and quality anomaly values ​​of meat pre-prepared food raw materials. The specific analysis is as follows: Step 1: Obtain the 3D data of the muscle fiber bundles of the raw materials of the meat pre-prepared dishes through a 3D microscope, and perform 3D reconstruction of the muscle fiber bundles to obtain the 3D shape of the muscle fiber bundles. Use a thinning algorithm to thin the 3D shape of the fiber bundles into a center line, and mark the center line as the skeleton of the fiber bundle. When the neighborhood of each point of the skeleton of the fiber bundle exceeds the connection in two directions, the point is determined to be a branch point, and all the skeleton points of each fiber bundle are traversed, and the total number of branch points is counted to obtain the muscle fiber bundle fractionation value; Step 2: Obtain the angles between branches of each branch point, and count the branch angles of all branch points in the muscle three-dimensional model to obtain branch angle data, calculate the standard deviation of the branch angle data, and mark it as the muscle fiber bundle dispersion value. If the distance between adjacent fiber bundles is less than the set threshold, the two fiber bundles are classified into the same group. If the distance between a fiber bundle and each adjacent fiber bundle is greater than or equal to the set threshold, the fiber bundle is grouped separately, and each fiber bundle in the three-dimensional model is traversed to obtain the grouping status of the muscle fiber bundle, and the number of independent groups is counted and marked as the muscle fiber bundle neighbor value. The smaller the muscle fiber bundle neighbor value is, the better the cell structure and muscle integrity can be maintained during freezing and storage. Step 3: The three-dimensional model of the muscle fiber bundle is fitted with a cylinder by the least squares method to obtain its central axis, and the distance from each point on the fiber bundle to the central axis is obtained, which is marked as the median value of each point in the fiber bundle. The absolute value of the difference between the median values ​​of adjacent points in the fiber bundle is counted. When the absolute value of the difference between the median values ​​is less than or equal to the set threshold, the adjacent points are classified into the concentric circle structure, and the number of concentric circle structures in the muscle fiber bundle is counted. The three-dimensional coordinates of the starting point of each concentric circle structure (xs n , ys n , zs n ) and the end point coordinates (xz n , yz n ,zz n ), n is the serial number of the concentric circle structure, n=1, 2, ..., N, N is the maximum serial number of the concentric circle structure, according to the formula , get the pitch value jj of each concentric circle structure n , according to the formula , the muscle fiber bundle cocircle distance value Txz is obtained, λ is the set correction factor coefficient, the distance from each point in the concentric circle structure to the central axis is obtained and the average is taken to obtain the median distance of the concentric circle structure, and the median distance of each concentric circle structure is summed and divided by the number of concentric circle structures N to obtain the median distance of the muscle fiber bundle cocircle Jzz, the median distance of the muscle fiber bundle cocircle Jzz, the number of concentric circle structures N, and the muscle fiber bundle cocircle distance value Txz are normalized according to the set formula Tyz=(a2×N+a3×Txz) / [a1×(Jzz-A1) 2 +1.025], and calculate the muscle fiber bundle cocircular value Tyz, where a1, a2 and a3 are respectively the median of the muscle fiber bundle cocircular distance, the number of concentric circle structures, and the weight factor coefficient of the muscle fiber bundle cocircular distance value. The specific values ​​are determined by personnel in this professional field. A1 is the set standard value of the muscle fiber bundle cocircular distance. It should be noted that the more the number of concentric circle structures, the larger the muscle fiber bundle cocircular distance value, the more uniform the force is when bearing, and the more it can increase the overall mechanical stability of the muscle; Step 4: Divide the three-dimensional model of the muscle fiber bundle into several cubic units, which are marked as voxels. The ratio of the number of voxels occupied by the fiber bundle to the total number of voxels is counted and marked as the muscle fiber bundle space filling value. The muscle fiber bundle fractal value, muscle fiber bundle dispersion value, muscle fiber bundle neighbor value, and muscle fiber bundle space filling value are marked as fz, js, sl, and tc, respectively, and normalized with the muscle fiber bundle cocircle value Tyz, and substituted into the set formula The muscle fiber value JQz of the raw material of meat pre-prepared dishes is calculated, where th1, th2, th3, th4, th5, th6, th7, th8 and th9 are the set influencing factor coefficients, specifically th1>th6, th2>th7, th3>th8, th9>th5, e is a natural constant with a value of 2.718. When the muscle fiber bundle space filling value is between 40% and 60%, the damage of ice crystals to muscle tissue can be reduced during freezing. At the same time, within this range, there are more gaps between muscle fiber bundles, which is conducive to water evaporation and air circulation, and inhibits the generation of microorganisms. Obtain the sensory quality value, bioelectric special value, and protein carbonyl content in the meat pre-prepared dish raw material information, mark them as Gz, Tb, and Db, normalize them with the muscle fiber value JQz of the meat pre-prepared dish raw material, and substitute them into the set formula , the safety and quality difference value AZZ of meat pre-prepared food raw materials is calculated, where g1, g2, g3, g4, g5, g6, g7 and g8 are all set weight factor coefficients, and g1>g5>g2>g6>g3>g7>g4>g8, njz refers to the cohesion index of pre-prepared food raw materials. It can be seen from the formula that when the cohesion index of pre-prepared food raw materials is greater than or equal to 70%, the internal structure is tight and the cohesion is good; It should be noted that the sensory quality concentration value of the pre-prepared food raw material is obtained by subjecting the pre-prepared food raw material to two consecutive compression cycles through a texture analyzer, and respectively establishing compression curves of force versus displacement, and dividing the area under the second compression curve by the area under the first compression curve to obtain the cohesiveness index of the pre-prepared food raw material, and marking the maximum peak force in the first compression cycle as the hardness peak value of the pre-prepared food raw material, and calculating the ratio of the height recovered by the sample after the first compression to the original height, which is marked as the elastic height value of the pre-prepared food raw material, and adding the cohesiveness index, hardness peak value, and elastic height value of the pre-prepared food raw material to obtain the sensory quality concentration value of the pre-prepared food raw material; the bioelectric characteristic value of the sensory quality concentration value of the pre-prepared food raw material refers to the conductivity of the pre-prepared food raw material divided by the sum of the electrical impedance, capacitance value, and charge transfer coefficient, to obtain; The processing module receives the processing information of pre-prepared meat dishes and the abnormal traceability signal of pre-prepared food safety and quality, and makes judgments and analyses on the processing environment, preservatives, and cleaning status of pre-prepared meat dishes to obtain the residual value of pre-prepared meat dishes. The specific analysis is as follows: The processing information of meat pre-prepared dishes contains the residual value of the processing ring, the amount of preservatives, and the meat clear value, which are marked as jhc, ffj, and rqg, respectively, and normalized according to the formula JFZ=[h1×jhc+h2×(ffj-A2) 2 ] / (h3×rqg), and the meat pre-prepared dish spoilage residual value JFZ is calculated, where h1, h2 and h3 are the set influencing factor coefficients of the processing ring micro-residue value, the amount of preservatives, and the meat clear light value, respectively, and A2 is the set reference amount of preservatives; It should be noted that the micro-residue value of the meat pre-prepared dish processing ring refers to the sum of the diversity value of the microbial community in the processing environment, the average particle size of the residual oil aggregates on the surface of the processing environment, the distribution width of the residual oil aggregate particle size, and the order of the residual oil molecular layer divided by the concentration of negative air ions, wherein the diversity value of the microbial community in the processing environment is the maximum percentage difference of the nucleotides between different individuals of the microbial community in the processing environment; the meat clearness value refers to the sum of the glossiness and cleanliness of the surface of the washed meat pre-prepared dish divided by the arithmetic mean roughness. The cleanliness is obtained by graying the collected surface image of the washed meat pre-prepared dish, dividing the surface grayscale image into several areas. When the grayscale value is greater than the set grayscale threshold, it corresponds to the meat part, and the regional quantity proportion of the meat part is counted; The storage and transportation module receives the storage and transportation information of prepared meat dishes and the abnormal traceability signal of the safety and quality of prepared dishes, and makes judgments and analyses on the storage and transportation of abnormal prepared meat dishes, and obtains the abnormal values ​​of storage and transportation of prepared meat dishes. The specific analysis is as follows: Obtain storage abnormality value, transportation vibration impulse value, transportation temperature control abnormal stability value in the storage and transportation information of meat pre-prepared dishes, mark them as cyz, yzc and kyw respectively, and calculate to obtain the storage and transportation abnormality value CYZ of meat pre-prepared dishes according to the set formula CYZ=t1×cyz+t2×yzc+t3×kyw, where t1, t2 and t3 are all set weight factor coefficients, and the specific value range is determined by personnel in this professional field; It should be noted that the storage abnormality value of meat pre-prepared dishes refers to the value obtained by dividing the humidity of the storage environment by the sum of the ambient temperature and the bag damage value. The bag damage value refers to the total value of damage, cracks and pinholes in the entire bag; the transportation vibration impact value refers to the value obtained by adding the vibration acceleration, impact number and impact intensity of the meat pre-prepared dishes during transportation; the transportation temperature control abnormal stability value refers to the temperature fluctuation amplitude of the meat pre-prepared dishes within a certain period of time during transportation; The judgment module receives the abnormal values ​​of safety and quality of raw materials of pre-prepared meat dishes, the residual values ​​of pre-prepared meat dishes, and the abnormal values ​​of storage and transportation of pre-prepared meat dishes, and analyzes the processing of pre-prepared dishes in each process to obtain the abnormal processes that affect the food problems of pre-prepared meat dishes. The specific analysis is as follows: The meat pre-prepared dish raw material safety and quality abnormality value AZZ, meat pre-prepared dish spoilage residual value JFZ, and meat pre-prepared dish storage and transportation abnormality value CYZ are normalized, and the meat pre-prepared dish raw material abnormality value YYZ is obtained according to the set formula model YYZ=Ψ×AZZ / (JFZ+CYZ), where Ψ is the correction factor coefficient. When the meat pre-prepared dish raw material abnormality value is greater than or equal to the set raw material abnormality threshold, it corresponds to the meat pre-prepared dish safety and quality abnormality due to the meat pre-prepared dish raw material abnormality. When the meat pre-prepared dish raw material abnormality value is less than When the raw material abnormal evaluation threshold is set, the set formula JYZ=Υ×JFZ / CYZ is used to obtain the meat pre-prepared dish abnormal evaluation value JYZ, where Υ is the correction factor coefficient. When the meat pre-prepared dish abnormal evaluation value is greater than or equal to the set pre-prepared dish abnormal evaluation threshold, the corresponding meat pre-prepared dish safety and quality abnormality is due to the abnormality of the meat pre-prepared dish processing process; when the meat pre-prepared dish abnormal evaluation value is less than the set pre-prepared dish abnormal evaluation threshold, the corresponding meat pre-prepared dish safety and quality abnormality is due to the abnormality of the meat pre-prepared dish storage and transportation process; The food safety traceability detection method based on the Internet of Things includes the following steps: S1: The data acquisition module collects the finished product information, raw material information, processing information and storage and transportation information of the prepared meat dishes, and sends it to the finished product module, raw material module, processing module and storage and transportation module; S2: The finished product module analyzes the oil and fat chemical composition, protein structure, carbohydrate content, and microbial indicators of the meat pre-prepared dishes, determines the quality and safety of the meat pre-prepared dishes, obtains the abnormal value of the pre-prepared dishes, and compares it with the set comparison interval, and issues a signal for tracing the abnormal quality of the pre-prepared dishes. S3: Receive raw material information and pre-prepared food safety and quality anomaly traceability signals through the raw material module, conduct judgment and analysis on the muscle fiber bundles, sensory state, bioelectric characteristics, and protein carbonyl groups of the meat pre-prepared food raw materials, and obtain the safety and quality anomaly values ​​of the meat pre-prepared food raw materials; S4: receiving the processing information of the prepared meat dishes and the abnormal traceability signal of the safety and quality of the prepared dishes through the processing module, determining and analyzing the processing environment, preservatives, and cleaning status of the prepared meat dishes, and obtaining the residual value of the prepared meat dishes; S5: receiving the storage and transportation information of the prepared meat dishes and the abnormal traceability signal of the safety and quality of the prepared dishes through the storage and transportation module, making judgments and analyzing the storage and transportation of the abnormal prepared meat dishes, and obtaining the abnormal values ​​of the storage and transportation of the prepared meat dishes; S6: The judgment module receives the abnormal values ​​of safety and quality of raw materials of pre-prepared meat dishes, the residual values ​​of pre-prepared meat dishes, and the abnormal values ​​of storage and transportation of pre-prepared meat dishes, and analyzes the processing of each process of the pre-prepared dishes to obtain the abnormal processes that affect the food problems of the pre-prepared meat dishes.

[0024] The above is an explanation of the present invention and should not be considered as a limitation thereof. Although several exemplary embodiments of the present invention have been described, it will be readily appreciated by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present invention. Therefore, all such modifications are intended to be included within the scope of the present invention as defined in the claims. It should be understood that the above is an explanation of the present invention and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present invention is defined by the claims and their equivalents.

Claims

1. A food safety traceability detection method based on the Internet of Things, characterized in that: The following steps are involved: S1: Collect information on finished products, raw materials, processing, storage and transportation of prepared meat dishes; S2: Analyze the oil and fat chemical composition, protein structure, carbohydrate content, and microbial indicators of the finished meat pre-prepared dishes to obtain abnormal values ​​of the finished pre-prepared dishes, and compare them with the set comparison interval to issue a signal for abnormal safety and quality of the pre-prepared dishes; S3: Receive raw material information and pre-prepared food safety and quality anomaly traceability signals, conduct judgment and analysis on the muscle fiber bundles, sensory state, bioelectric characteristics, and protein carbonyl groups of the meat pre-prepared food raw materials, and obtain the safety and quality anomaly values ​​of the meat pre-prepared food raw materials; S4: receiving the processing information of the prepared meat dishes and the abnormal traceability signal of the safety and quality of the prepared dishes, making judgments and analyses on the processing environment, preservatives and cleaning status of the prepared meat dishes, and obtaining the residual value of the prepared meat dishes; S5: receiving the storage and transportation information of prepared meat dishes and the abnormal traceability signal of the safety and quality of the prepared dishes, making judgments and analyzing the storage and transportation of abnormal prepared meat dishes, and obtaining abnormal values ​​of storage and transportation of prepared meat dishes; S6: Receive the abnormal values ​​of safety and quality of raw materials of pre-prepared meat dishes, the residual values ​​of pre-prepared meat dishes, and the abnormal values ​​of storage and transportation of pre-prepared meat dishes, and analyze the processing of each process of pre-prepared dishes to obtain the abnormal processes that affect the food problems of pre-prepared meat dishes.

2. The food safety traceability detection method based on the Internet of Things according to claim 1 is characterized in that: The steps for analysing the signal for tracing the source of abnormal safety and quality of prepared dishes are as follows: Normalize the finished oil oxygenation value, the finished egg change value, the finished carbohydrate reduction value and the finished fungal disease value of the prepared food product, and obtain the finished product abnormal value of the prepared food product through graph construction processing; Compare the abnormal value of the pre-prepared food product with the set comparison intervals CX1 and CX2. When the abnormal value of the pre-prepared food product is in the comparison interval CX1, the quality of the corresponding pre-prepared food product is abnormal, and a pre-prepared food safety and quality abnormality traceability signal is issued. When the abnormal value of the pre-prepared food product is in the comparison interval CX2, the quality of the corresponding pre-prepared food product is normal.

3. The food safety traceability detection method based on the Internet of Things according to claim 2 is characterized in that: The analysis steps of the oil oxidation value of the prepared dish product, the egg change value of the prepared dish product, the carbohydrate reduction value of the prepared dish product and the fungal disease value of the prepared dish product are as follows: The oil chemical composition is the sum of the oil peroxide value, oil acid value and oil carbonyl value of the meat pre-prepared dish product to obtain the oil oxidation value of the pre-prepared dish product. The protein structure refers to the sum of the low and high molecular weight values ​​of the band, the band width value and the band tailing degree to obtain the protein change value of the pre-prepared dish product. The protein is extracted from the pre-prepared dish product by protein extraction buffer, and through gel electrophoresis experiment, according to the molecular weight value in c1 and c2 markers, the area with a molecular weight less than c1 in the gel electrophoresis experiment corresponds to the low molecular weight area, and the area greater than c2 corresponds to the high molecular weight area. The number of bands and the integrated optical density values ​​in the low molecular weight area and the high molecular weight area are counted and summed to obtain the low and high molecular weight values ​​of the band. The sharpness value on the band is lower than the set When the sharpness threshold is set, it corresponds to tailing. The distance from the end of the normal part of the strip to the last position of the tailing identified by the cursor is counted and marked as the tailing length of the strip. The tailing length of each strip is counted and marked as the tailing degree of the strip. The carbohydrate content refers to the reaction of distilled water and anthrone reagent in the pre-prepared dish product, and the absorbance is measured by a spectrophotometer at a certain wavelength. The organic acid in the mixed solution of distilled water of the pre-prepared dish product is titrated with a standard sodium hydroxide solution, and the consumption of sodium hydroxide is counted. The measured absorbance is added to the consumption of sodium hydroxide, and the result is multiplied by the correction factor coefficient to obtain the carbohydrate reduction value of the pre-prepared dish product. The microbial index refers to the total number of colonies, the number of coliform bacteria, and the content of pathogenic bacteria to obtain the bacterial disease value of the pre-prepared dish product.

4. The food safety traceability detection method based on the Internet of Things according to claim 1 is characterized in that: The steps for analyzing the safety and quality of raw materials for prepared meat dishes are as follows: Obtain the sensory quality value, bioelectric special value, and protein carbonyl content in the meat pre-prepared dish raw material information, mark them as Gz, Tb, and Db, normalize them with the muscle fiber value JQz of the meat pre-prepared dish raw material, and substitute them into the set formula , the safety and quality difference value AZZ of meat pre-prepared food raw materials is calculated, where g1, g2, g3, g4, g5, g6, g7 and g8 are all set weight factor coefficients, and njz refers to the cohesion index of the pre-prepared food raw materials.

5. The food safety traceability detection method based on the Internet of Things according to claim 4 is characterized in that: The steps for analyzing the muscle fiber value of the raw materials of the prepared meat dishes are as follows: Step 4: Divide the three-dimensional model of the muscle fiber bundle into several cubic units, which are marked as voxels. The ratio of the number of voxels occupied by the fiber bundle to the total number of voxels is counted and marked as the muscle fiber bundle space filling value. The muscle fiber bundle fractal value, muscle fiber bundle dispersion value, muscle fiber bundle neighbor value, and muscle fiber bundle space filling value are marked as fz, js, sl, and tc, respectively, and normalized with the muscle fiber bundle cocircle value Tyz, and substituted into the set formula The calculation is performed to obtain the muscle fiber value JQz of the raw materials for pre-prepared meat dishes, wherein th1, th2, th3, th4, th5, th6, th7, th8 and th9 are the set influencing factor coefficients, and e is a natural constant.

6. The food safety traceability detection method based on the Internet of Things according to claim 5 is characterized in that: The muscle fiber bundle cocircularity analysis steps are as follows: Step 3: The three-dimensional model of the muscle fiber bundle is fitted with a cylinder by the least squares method to obtain its central axis, and the distance from each point on the fiber bundle to the central axis is obtained, which is marked as the median value of each point in the fiber bundle. The absolute value of the difference between the median values ​​of adjacent points in the fiber bundle is counted. When the absolute value of the difference between the median values ​​is less than or equal to the set threshold, the adjacent points are classified into the concentric circle structure, and the number of concentric circle structures in the muscle fiber bundle is counted. The three-dimensional coordinates of the starting point of each concentric circle structure (xs n , ys n , zs n ) and the end point coordinates (xz n , yz n ,zz n ), n is the serial number of the concentric circle structure, and the pitch value jj of each concentric circle structure is obtained according to the formula n According to the formula, the cocircular distance value Txz of the muscle fiber bundle is obtained, the distance from each point in the concentric circle structure to the central axis is obtained and the average is taken to obtain the median distance of the concentric circle structure, and the median distance of each concentric circle structure is summed and divided by the number of concentric circle structures N to obtain the median cocircular distance of the muscle fiber bundle Jzz, the median cocircular distance of the muscle fiber bundle Jzz, the number of concentric circle structures N, and the cocircular distance value Txz of the muscle fiber bundle are calculated to obtain the cocircular value Tyz of the muscle fiber bundle.

7. The food safety traceability detection method based on the Internet of Things according to claim 5 is characterized in that: The muscle fiber bundle fractionation value, muscle fiber bundle dispersion value and muscle fiber bundle neighbor value analysis steps are as follows: Step 1: Obtain the 3D data of the muscle fiber bundles of the raw materials of the meat pre-prepared dishes through a 3D microscope, and perform 3D reconstruction of the muscle fiber bundles to obtain the 3D shape of the muscle fiber bundles. Use a thinning algorithm to thin the 3D shape of the fiber bundles into a center line, and mark the center line as the skeleton of the fiber bundle. When the neighborhood of each point of the skeleton of the fiber bundle exceeds the connection in two directions, the point is determined to be a branch point, and all the skeleton points of each fiber bundle are traversed, and the total number of branch points is counted to obtain the muscle fiber bundle fractionation value; Step 2: Obtain the angles between branches of each branch point, and count the branch angles of all branch points in the muscle three-dimensional model to obtain branch angle data, calculate the standard deviation of the branch angle data, and mark it as the muscle fiber bundle dispersion value. If the distance between adjacent fiber bundles is less than the set threshold, the two fiber bundles are grouped in the same group. If the distance between a fiber bundle and each adjacent fiber bundle is greater than or equal to the set threshold, the fiber bundle is grouped together separately, and the fiber bundles in the three-dimensional model are traversed to obtain the grouping status of the muscle fiber bundles, and the number of independent groups is counted, which is marked as the muscle fiber bundle neighbor value.

8. The food safety traceability detection method based on the Internet of Things according to claim 1 is characterized in that: The abnormal process analysis steps that affect the prepared meat food problem are as follows: The meat pre-prepared dish raw material safety and quality abnormality value AZZ, the meat pre-prepared dish added spoilage residual value JFZ and the meat pre-prepared dish storage and transportation abnormality value CYZ are calculated according to the formula to obtain the meat pre-prepared dish raw material abnormality value YYZ. When the meat pre-prepared dish raw material abnormality value is greater than or equal to the set raw material abnormality value threshold, it means that the corresponding meat pre-prepared dish safety and quality abnormality is due to abnormal meat pre-prepared dish raw materials. When the meat pre-prepared dish raw material abnormality value is less than the set raw material abnormality value threshold, the formula is used to obtain the meat pre-prepared dish added abnormality value JYZ. When the meat pre-prepared dish added abnormality value is greater than or equal to the set pre-prepared dish added abnormality value threshold, it means that the corresponding meat pre-prepared dish safety and quality abnormality is due to abnormality in the meat pre-prepared dish processing process. When the meat pre-prepared dish added abnormality value is less than the set pre-prepared dish added abnormality value threshold, it means that the corresponding meat pre-prepared dish safety and quality abnormality is due to abnormality in the meat pre-prepared dish storage and transportation process.

9. The food safety traceability detection method based on the Internet of Things according to claim 8 is characterized in that: The steps for analyzing the residual value of pre-prepared meat dishes are as follows: The processing information of meat pre-prepared dishes contains the residual value of the processing ring, the amount of preservatives, and the meat clear value, which are marked as jhc, ffj, and rqg, respectively, and normalized according to the formula JFZ=[h1×jhc+h2×(ffj-A2) 2 ] / (h3×rqg), and the residual value of meat pre-prepared dishes JFZ is calculated, where h1, h2 and h3 are the set influencing factor coefficients, and A2 is the set reference amount of preservatives; The steps of analyzing the outliers in the storage and transportation of prepared meat dishes are as follows: The storage abnormality value, transportation vibration impulse value, and transportation temperature control abnormality value in the storage and transportation information of pre-prepared meat dishes are obtained, marked as cyz, yzc, and kyw respectively, and the storage and transportation abnormality value CYZ of pre-prepared meat dishes is calculated according to the set formula CYZ=t1×cyz+t2×yzc+t3×kyw, where t1, t2, and t3 are all set weight factor coefficients.

10. The food safety traceability detection system based on the Internet of Things is characterized by: The method for food safety traceability detection based on the Internet of Things is applied to implement any one of claims 1 to 9, comprising: The data collection module is used to collect the finished product information, raw material information, processing information and storage and transportation information of the prepared meat dishes, and send it to the finished product module, raw material module, processing module and storage and transportation module; Finished product module is used to analyze the oil chemical composition, protein structure, carbohydrate content, and microbial index of meat pre-prepared dishes, obtain abnormal values ​​of pre-prepared dishes, and compare them with the set comparison interval to issue a signal for abnormal safety and quality of pre-prepared dishes; The raw material module is used to receive raw material information and pre-prepared food safety and quality anomaly traceability signals, and to determine and analyze the muscle fiber bundles, sensory states, bioelectric characteristics, and protein carbonyl groups of meat pre-prepared food raw materials to obtain the safety and quality anomaly values ​​of meat pre-prepared food raw materials; The processing module is used to receive the processing information of the prepared meat dishes and the traceability signal of the safety and quality abnormalities of the prepared meat dishes, judge and analyze the processing environment, preservatives, and cleaning status of the prepared meat dishes, and obtain the residual value of the prepared meat dishes; The storage and transportation module is used to receive the storage and transportation information of prepared meat dishes and the abnormal traceability signal of the safety and quality of prepared dishes, judge and analyze the storage and transportation of abnormal prepared meat dishes, and obtain the abnormal value of storage and transportation of prepared meat dishes; The judgment module is used to receive abnormal values ​​of safety and quality of raw materials of pre-prepared meat dishes, residual values ​​of pre-prepared meat dishes, and abnormal values ​​of storage and transportation of pre-prepared meat dishes, and analyze the pre-prepared dish processing in each process to obtain abnormal processes that affect the food problems of pre-prepared meat dishes.

Images