CN-122022606-A - Comprehensive evaluation method and system for meat packaging performance of supply chain

CN122022606ACN 122022606 ACN122022606 ACN 122022606ACN-122022606-A

Abstract

The invention provides a comprehensive evaluation method and system for meat packaging performance of a supply chain, and relates to the technical field of food quality safety monitoring. The method comprises the steps of carrying out hazard analysis on each link of a meat supply chain based on HACCP, determining influence factors, setting data acquisition items according to the influence factors, acquiring quality indexes, key micro-environment parameters and economic factors, converting the data acquisition items into digital quantities, carrying out evaluation classification on meat quality by utilizing knowledge rules, constructing a quality evaluation prediction model based on the quality indexes and the key micro-environment parameters, realizing meat quality shelf life prediction, constructing a packaging performance comprehensive evaluation model based on the quality indexes, the key micro-environment parameters and the economic factors, completing comprehensive evaluation of meat packaging performance of the supply chain, realizing unified classification and prediction on meat quality states and packaging performance, and providing decision support for packaging selection and supply chain management.

Inventors

XU JINCHAO
YAN DONGWEI

Assignees

山东工商学院

Dates

Publication Date: 20260512
Application Date: 20260416

Claims (9)

1. A method for comprehensively evaluating the packaging performance of supply chain meat, comprising the steps of: Analyzing a meat supply chain process based on HACCP, performing hazard analysis on each link to form a hazard analysis result, performing key point control and knowledge acquisition based on the hazard analysis result, and determining influencing factors influencing the meat supply chain process; determining a data acquisition item according to the influencing factors so as to acquire quality indexes, key micro-environment parameters and economic elements in the meat supply chain process, and recording the acquired quality indexes, key micro-environment parameters and economic elements and converting the acquired quality indexes, key micro-environment parameters and economic elements into digital quantities; according to the quality index, meat quality evaluation grading based on knowledge rules is realized; Constructing a quality evaluation prediction model according to the quality index and the key micro-environment parameters so as to realize meat quality shelf life prediction; And constructing a packaging performance comprehensive evaluation model according to the quality index, the key microenvironment parameter and the economic element so as to realize comprehensive evaluation of the packaging performance of the meat of the supply chain.
2. The method for comprehensively evaluating the packaging performance of the meat in the supply chain according to claim 1, wherein the influencing factors comprise environmental factors, quality factors and economic factors, wherein the environmental factors comprise temperature, humidity and gas environment, the economic factors comprise labor cost, storage cost, supply chain transportation cost, packaging cost and comprehensive management, and the quality factors comprise sensory evaluation, physicochemical indexes and microbial indexes.
3. The method of claim 2, wherein the step of collecting quality metrics, key microenvironment parameters, and economic factors during the meat supply chain process comprises: Obtaining the quality index by adopting a chemical test; acquiring the key microenvironment parameters by adopting a sensor; and acquiring the economic element by adopting a questionnaire and a practical investigation.
4. The method of claim 1, wherein the training process of the quality assessment prediction model comprises: performing normalization processing on the input data of the quality evaluation prediction model, and determining the input, output and hidden layer number of the quality evaluation prediction model; determining a model scale N, an error parameter E, iteration times T and a space dimension D; Calculating fitness based on errors between desired and actual output values The adaptation degree The calculation formula of (2) is as follows: Wherein, the method comprises the steps of, In order to achieve the desired output value, In order to be able to output the value of the actual output, For the spatial vector of the ith particle in D-dimensional space, ; Determining velocity of movement of particles in D-dimensional space Wherein, the method comprises the steps of, ; Obtaining the best position And global optimal solution Wherein, the method comprises the steps of, , , ; Updating and iterating the position and the movement speed of the particles according to the inertia weight and the learning factor, and outputting the optimal position when the iteration number T reaches the maximum iteration number T max or is smaller than the error precision Otherwise, training is carried out again; the update iteration formula is as follows: Wherein c 1 ,c 2 is a learning factor, W is the weight of inertia, W ma and w min are the upper and lower limits, respectively, for calculating the inertial weight w, d 1 ,d 2 ,d 3 is a random variable, , V max is the maximum absolute boundary of the velocity component of the particle in D-dimensional space, and X max is the maximum absolute boundary of the position component of the particle in D-dimensional space.
5. The method of claim 4, wherein the training process of the quality assessment prediction model further comprises: Will be the optimal position An initial value of a combination weight and a threshold value as the quality evaluation prediction model; selecting a sample from a sample set as input, and calculating ideal model output, wherein the calculation formula of the ideal model output is as follows: Wherein, the method comprises the steps of, For the ideal output of the model, For weights before the hidden layer and the output layer, y i is the hidden node output, i represents the number of hidden layers, p represents the number of output layers, The model learning rate is given by eta, which is the weight before the hidden layer and the input layer, net p is the net input of the p-th output node of the output layer, which is the weighted summation result of the output node to the output of the upper layer, net i is the net input of the i-th node of the hidden layer, W ij is the connection weight from the j-th node of the input layer to the i-th node of the hidden layer, x j is the input value of the j-th input node of the input layer, and f (·) is an activation function.
6. The method for comprehensively evaluating the packaging performance of supply chain meats of claim 5, further comprising: when the expected output error of the quality evaluation prediction model does not meet the preset error precision threshold, performing back propagation training, and obtaining an error by calculating the difference between the actual output and the ideal output of the model Error of sample set Output node error Implicit node error ; Wherein, the For each layer of the actual output values of the neurons, For the ideal output value of each layer of neurons, In order to be able to output the value of the actual output, Is an ideal output value; and adjusting the coupling weight and the threshold value according to the output node error and the hidden node error until the expected output error meets the preset error precision threshold value and outputting a quality shelf life prediction result.
7. The method for comprehensive assessment of packaging performance of supply chain meat according to claim 1, wherein the expression of the comprehensive assessment model of packaging performance is: ; Wherein I is a packaging comprehensive effect evaluation factor set, I 1 ,i 2 ,…,i n is n influence indexes participating in packaging comprehensive performance evaluation, A is a packaging evaluation influence factor weight vector set, Weight vectors of elements in the evaluation index set formed for influencing the packaging effect; R represents an evaluation index gray evaluation weight matrix; the gray evaluation weight vector of each index evaluation index is represented, the vector B represents the membership degree of the final evaluation result of each index, The membership degree of the corresponding evaluation result is evaluated for each index; Represents the final evaluation result of the integrated packaging performance, wherein, Indicating the packaging effect, classifying the evaluation results according to different categories, ; Indicating the specific packaging practice to be performed, ; Representing the performance under the microenvironment so as to reflect or restrict the physiological and biochemical reaction of the mutton through the dynamic changes of temperature, humidity and gas; Indicating a loss of quality of mutton; the cost characteristics of the packaging materials are represented, and the economical efficiency and the environmental protection performance of the packaging materials used in the packaging process, and the aspects of transportation and information management are represented; factor weights representing different effects in the evaluation, V represents a package comprehensive performance evaluation set, Respectively corresponding to five grades in the package form.
8. The method for comprehensively evaluating the packaging performance of supply chain meats according to claim 7, wherein the evaluation result is obtained by a method comprising: By evaluating and grading single indexes, determining a packaging performance evaluation standard and constructing an evaluation matrix E and a whitening weight function And carrying out clustering division, wherein the expression of the evaluation matrix E is as follows: ; evaluating the index for the q-th pair The evaluation is made and the result is that, The whitening weight function is used for dividing n values related to the index J into k gray classes, and the whitening weight of the e-th evaluation gray class of each evaluation index is ; For evaluation index Belonging to the first Gray evaluation coefficient of each evaluation gray And the total gray evaluation coefficient The method comprises the following steps of: , Wherein, the method comprises the steps of, Total number of evaluations for a single evaluation index; calculating the ratio of the gray evaluation coefficient to the total gray evaluation coefficient To obtain the evaluation index belonging to ash Gray evaluation weight of (2) and corresponding the same evaluation index Gray evaluation weight vectors constituting the evaluation index; Forming a gray evaluation weight matrix R of the evaluation index according to the gray evaluation weight vectors of the evaluation indexes; performing matrix operation on the packaging evaluation influence factor weight vector set A and the evaluation index gray evaluation weight matrix R to obtain a vector B, namely And outputting a packaging comprehensive performance evaluation result based on the corresponding relation between the vector B and the packaging comprehensive performance evaluation set V.
9. A supply chain meat packaging performance integrated assessment system, comprising: The flow analysis unit is used for analyzing the flow of the meat supply chain based on the HACCP, performing hazard analysis on each link to form hazard analysis results, performing key point control and knowledge acquisition based on the hazard analysis results, and determining influencing factors influencing the meat supply chain process; The data acquisition unit is used for determining a data acquisition item according to the influence factors so as to acquire quality indexes, key micro-environment parameters and economic elements in the meat supply chain process, and recording the acquired quality indexes, key micro-environment parameters and economic elements and converting the acquired quality indexes, key micro-environment parameters and economic elements into digital quantities; the evaluation grading unit is used for realizing meat quality evaluation grading based on knowledge rules according to the quality index; The prediction model construction unit is used for constructing a quality evaluation prediction model according to the quality index and the key micro-environment parameters so as to realize meat quality shelf life prediction; And the evaluation model construction unit is used for constructing a packaging performance comprehensive evaluation model according to the quality index, the key micro-environment parameter and the economic element so as to realize comprehensive evaluation of the packaging performance of the supply chain meat.

Description

Comprehensive evaluation method and system for meat packaging performance of supply chain Technical Field The invention relates to the technical field of food quality safety monitoring, in particular to a comprehensive evaluation method and system for meat packaging performance of a supply chain. Background Meat supply chain process control is a complex and systematic dynamic process that is both related to the environmental factors in practice and is also affected by factors such as economics, quality itself, and external disturbances. Therefore, how to slow down the decay of the nutrition quality, comprehensively considering the factors influencing the meat packaging performance, and improving the safety evaluation precision of the meat of the supply chain has become an important research focus. Most current studies only consider the effect of a single index (different packaging materials or modes, simple temperature control and gas variation) on the final quality safety, but often neglect the comprehensive effect of economic factors, environmental fluctuations and quality variation on the packaging performance. Based on comprehensive evaluation of meat supply chains expected by environmental parameters, economic cost and quality change, the internal characteristics (package internal quality and micro-environment change) of meat are determined by selection and specific application combination of different elements, and external characteristics (economic characteristics and external interference) such as storage, transportation, information management and recycling are affected, so that the influence of the whole economical efficiency, environmental protection and safety on the meat supply chains is finally formed. Therefore, how to provide a comprehensive evaluation technology for the packaging performance of meat in a supply chain is a problem to be solved. Disclosure of Invention In order to overcome the defects of the prior art, the invention aims to provide a comprehensive evaluation method and a comprehensive evaluation system for the meat packaging performance of a supply chain, and by introducing a hazard analysis-driven data acquisition and comprehensive evaluation mechanism into the meat supply chain, the unified classification and prediction of the meat quality state and the packaging performance are realized, so that the integrity, comparability and decision support capability of the packaging performance evaluation result are improved. In order to achieve the above object, the present invention provides the following solutions: a comprehensive evaluation method for the packaging performance of supply chain meat comprises the following steps: Analyzing a meat supply chain process based on HACCP, performing hazard analysis on each link to form a hazard analysis result, performing key point control and knowledge acquisition based on the hazard analysis result, and determining influencing factors influencing the meat supply chain process; determining a data acquisition item according to the influencing factors so as to acquire quality indexes, key micro-environment parameters and economic elements in the meat supply chain process, and recording the acquired quality indexes, key micro-environment parameters and economic elements and converting the acquired quality indexes, key micro-environment parameters and economic elements into digital quantities; according to the quality index, meat quality evaluation grading based on knowledge rules is realized; Constructing a quality evaluation prediction model according to the quality index and the key micro-environment parameters so as to realize meat quality shelf life prediction; And constructing a packaging performance comprehensive evaluation model according to the quality index, the key microenvironment parameter and the economic element so as to realize comprehensive evaluation of the packaging performance of the meat of the supply chain. Preferably, the influencing factors comprise environmental factors, quality factors and economic factors, wherein the environmental factors comprise but are not limited to temperature, humidity and gas environment, the gas environment comprises but is not limited to oxygen, carbon dioxide, ammonia and hydrogen sulfide, the economic factors comprise but are not limited to labor cost, warehouse cost, supply chain transportation cost, packaging cost and comprehensive management cost, the quality factors comprise sensory evaluation indexes, physicochemical indexes and microorganism indexes, the physicochemical indexes comprise but are not limited to volatile basic nitrogen, the microorganism indexes comprise but are not limited to total bacterial colony count, and the quality indexes, the key microenvironment parameters and the economic factors respectively correspond to the quality factors, the environmental factors and the economic factors in the influencing factors. Preferably, collecting quality metrics, key microen