18 results about "Quality characteristics" patented technology

The invention relates to the technical field of food quality detection, in particular to a diester oil quality detection method and system based on multi-source data, and the method comprises the steps: collecting multi-source heterogeneous data, carrying out feature extraction and dimension reduction, and generating a quality feature vector; multi-source data fusion is realized through a dynamic weight distribution model, and time sequence quality evaluation data is generated; performing error compensation on the low-confidence data by adopting a self-adaptive correction algorithm, and performing chain verification on the high-confidence data; and through bidirectional consistency verification, optimizing path planning, generating optimization feedback data and finishing final quality confirmation. Through multi-source data fusion, real-time analysis and automatic verification, the accuracy and efficiency of diester oil quality detection are remarkably improved, and the modern industrial intelligent requirement is met.

The invention provides a dairy product quality monitoring method and system based on big data, and relates to the technical field of big data processing. The method comprises the following steps: acquiring historical batch quality monitoring data of dairy products of the same type, extracting quality feature information based on production batches, and forming historical batch quality feature information corresponding to different production batches; performing range control clustering analysis based on content coincidence on the historical batch quality feature information corresponding to different batches to form batch content range control clustering data; and obtaining quality sampling data of the current batch of dairy products, and performing quality monitoring analysis by combining the batch content range control clustering data to form a real-time dairy product batch quality monitoring result. According to the method, more reasonable and accurate milk powder quality monitoring is realized through reasonable milk powder batch component content analysis, and the milk powder production quality is fully and effectively guaranteed.

The application relates to a product quality feature data monitoring method based on key feature extraction, which comprises the following steps: in a product production process, quality monitoring is performed on the product according to the importance ranking of features; the importance ranking of features is obtained through the following steps: 1) obtaining several types of feature data of the product and performing pretreatment; 2) clustering each type of feature data through a clustering algorithm to obtain a clustering center of each type of feature data; 3) performing dimension reduction processing on each type of feature data through a trained autoencoder to obtain reduced dimension data; 4) calculating the feature weight of each type of feature through a ReliefF algorithm according to the reduced dimension data and the clustering center; and 5) ranking the importance of each type of feature according to the feature weight. Compared with the prior art, the application can extract the key quality characteristics of the product, strengthen the monitoring and optimization of the production link corresponding to the key quality characteristics, and improve the product fault diagnosis accuracy and the detection time.

The invention discloses a protein beverage production process regulation and control method and system based on digital twinning, belongs to the technical field of food industry intelligent manufacturing, and aims at solving the problems that an existing protein beverage production quality detection method has hysteresis quality, and the production cost is low due to the limitation of a production environment. And real-time and even advanced risk early warning and multi-parameter adjustment cannot be realized in the production process of each working procedure, so that the improvement of the production efficiency and quality of the protein beverage is hindered. The method comprises the following steps: collecting protein beverage production data through a multi-element online monitoring unit, and performing feature extraction to obtain protein beverage quality features; analyzing the quality characteristics of the protein beverage in real time through a deep learning model, and outputting multiple key quality index estimated values; performing risk simulation based on the key quality index estimated value, and determining a risk quality index; and based on the risk quality index, performing analog calculation in the digital twin model, and determining an optimal parameter combination capable of avoiding the risk.

The invention discloses an uncertainty quality design method based on double specification limit constraints, which comprises the following steps: determining the distribution condition of product quality characteristics after processing or reworking, judging which category the product belongs to, and then calculating the probability that the product type n1 is changed into the product type n2; the reworking stations are queues, and the utilization rate and the average waiting time of the stations are calculated; considering the reliability of which the quality characteristic is truncated normal distribution, determining a quality guarantee cost model, and capturing customer perception limited by specifications; and establishing a product profit model by considering the full life cycle cost of the product, and optimizing the double-specification limited-term profit model through an optimization algorithm to obtain an optimal profit value. According to the method, after double specification limit constraints are adopted, the long-term average profit is increased to 18.84 from 7.18, and the amplification exceeds 160%; meanwhile, the fault risk of the qualified product is described by introducing truncation distribution, so that the quality guarantee cost prediction is more accurate, and the deviation is obviously reduced; the utilization rate of the reworking station is improved, and the waiting time is shortened.

The present application relates to the technical field of meat detection, and particularly relates to a data-driven meat quality rapid detection method and system, which collects the physical and chemical data such as spectrum, image, pH value, temperature and humidity, volatile gas and the like of a meat sample through a multi-modal sensor, constructs a meat quality characteristic map, analyzes the map by using a machine learning algorithm, identifies key influencing factors and extracts quality characteristic data such as spectrum, texture and chemistry, analyzes the influence law of different factors on quality based on the characteristic data, obtains meat quality influence data, determines the judgment parameters of each quality grade in combination with the influence data, constructs and trains a deep learning detection model, inputs the real-time data of the meat to be detected into the model, realizes rapid identification and evaluation of quality, makes grade judgment according to the evaluation result, and automatically executes classification processing, improves detection accuracy and stability, and realizes non-destructive, intelligent and efficient meat quality detection.

Provide are a manufacturing condition management method and similar with which a highly accurate design design space can be efficiently created while taking various factors and parameters into consideration. This manufacturing condition management method has: a first extraction step (S12) for extracting quality characteristic candidates or similar pertaining to quality in the manufacture of an objective finished good; a first designation step (S13) for designating a quality characteristic or similar under consideration, on the basis of evidence with regard to the extracted quality characteristic candidates or similar; a discrimination step (S14) for discriminating between a normal state and an abnormal state pertaining to a manufacturing step by which a product is manufactured; a selection step (S15) for selecting a timing at which to create a design space (DS) within the manufacturing step; a second extraction step (S16) for extracting candidates for an important step parameter that is a cause of the designated quality characteristic or similar; a second designation step (S17) for designating an important step parameter from among the candidates for the important step parameter; a creation step (S18) for determining a range for the important step parameter and creating the DS; and a determination step (S19) for determining a manufacturing condition on the basis of the DS.

The present invention discloses a ceramic quality anomaly detection method for a multi-recipe production line, comprising: step S1: collecting detection data from each sensor of the production line, and performing alignment and preprocessing; step S2: constructing a feature extraction and classification model based on a deep convolutional network, performing convolution in the time dimension through convolution kernels of different scales, and pre-training the network through supervised learning to achieve mapping of three-dimensional monitoring data tensors to quality indicators; step S3: perturbing the tensor data through a data enhancement method, performing causal inference based on the distribution of the perturbed feature vectors, and judging the causal relationship between different variables and quality characteristics; the present invention aims to provide a ceramic quality anomaly detection method for a multi-recipe production line, by extracting features of profiling tensor data, screening variables that have a causal relationship with quality indicators, and selecting different important variables, so that when the production line recipe changes, the model can perform quality anomaly detection.

The invention relates to the technical field of beverage quality control, in particular to a quality control method and system for herbal beverages. The method comprises the following steps: establishing a quality feature set and a feature matrix of the herbal beverage by performing preprocessing and feature extraction on production data of the herbal beverage; constructing a quality monitoring model based on the characteristic matrix to monitor production data of the herbal beverage in real time, and optimizing and trimming the quality monitoring model by adopting a sliding window mechanism; and predicting the production data of the herbal beverage based on the quality monitoring model, and adjusting the feature weight of each quality feature in the quality feature set based on a prediction result. According to the invention, comprehensive monitoring of the quality of the herbal beverage is realized, the quality control level of the herbal beverage is improved, and the stability of the product quality is guaranteed.

The invention provides a multi-modal data combined food processing quality dynamic evaluation method and system, and belongs to the technical field of food processing quality evaluation.The method comprises the steps that firstly, morphological representation data, component response data, environment adaptation data and other multi-source parallel data of the whole food processing flow are obtained; generating a processing data dynamic association network based on the time evolution and action conduction relationship of the source parallel data; then, extracting quality association features from the processing data dynamic association network, and generating enhanced quality features through cross-node interaction and multi-round cyclic enhancement; inputting the enhanced quality features into a pre-trained dynamic quality evaluation model to generate a real-time evaluation result; and finally, identifying a quality optimization node according to a real-time evaluation result, generating a processing condition adjustment instruction and sending the processing condition adjustment instruction to a food processing execution system. According to the invention, comprehensive, dynamic and accurate evaluation of the food processing quality is realized, the processing conditions can be adjusted in time, and the food processing quality is effectively improved.

The invention discloses a method and system equipment for rapidly detecting food quality based on an intelligent metamaterial, relates to the technical field of food quality detection, and aims to eliminate environmental interference and food adhesion interference through calibration of detection equipment and improve the detection reference precision; the multi-frequency-band response characteristic of the intelligent metamaterial sensor array is utilized, food reflection signals are accurately collected, and the characteristics of moisture, components and the like are synchronously obtained, compared with a traditional method, signal collection time is shortened, the radio-frequency-band electromagnetic response characteristic and a built-in database are combined, food types are automatically recognized, manual classification errors are reduced, and the classification efficiency is improved. The corresponding quality feature library is called for multi-dimensional comparison analysis, whether the quality is qualified or not is judged through the comprehensive standard reaching rate, the detection objectivity is improved, finally, the result is visually fed back through a user interface, full-process automatic operation is achieved, the detection speed and accuracy are both considered, the method is suitable for food production, circulation and other scenes, and the efficient quality inspection requirement is effectively met.

A method for determining quality characteristics of a rod and ball lattice (400) is provided. The method includes: determining a quality characteristic of each ball (410, 420, 430) in a lattice; determining, for each rod (440, 450), a mass characteristic of a portion comprising an interbody volume between the end balls (410, 420, 430) of the rod (440, 450); generating an initial estimate of the mass characteristics for the lattice (400) based on the mass characteristics of the ball (410, 420, 430) and the portion of the rod (440, 450); and identifying, for each ball (410, 420, 430), an overlap portion (460) terminating between a pair of rods (440, 450) of the ball (410, 420, 430), and estimating a quality characteristic of each identified overlap portion (460); and modifying the initial estimate of the quality characteristic of the lattice (400) based on the estimate of the quality characteristic of the overlapping portion (460).

The invention provides a counting and sampling inspection method for small-batch multi-feature products, and relates to the technical field of aero-engine manufacturing. The method comprises the following steps: measuring and calculating a process capability index of a part, and then calculating a virtual batch of products; if the product batch is N and each product has M quality characteristics, calculating a virtual batch P = N * M; checking the sample size character code to obtain the sample size character code; checking the normal inspection sampling scheme table once through the sample size character code and the receiving quality limit AQL to obtain a virtual sample size n; according to the virtual sample size n, the actual sampling inspection number X = n / M of the batch of products is calculated, and if the calculation result is not an integer, an integer is taken through carry; the final sampling inspection scheme is that X products are extracted from the current product batch N to carry out full inspection on the M quality characteristics; sPC process control is continuously carried out on the size of the product subjected to sampling inspection.

The application provides a plant meat quality prediction method and system based on SPI raw material iterative analysis, and relates to the field of food science and technology, including the following steps: constructing a raw material characteristic index database; determining the quality characteristics of plant meat prepared in advance by soybean protein isolate raw material, and constructing a plant meat quality characteristic index database according to the quality characteristic determination results; based on the raw material characteristic index database and the plant meat quality characteristic index database, respectively constructing and training an elastic network regression model and a genetic algorithm-multivariate linear regression model; using the elastic network regression model and the genetic algorithm-multivariate linear regression model to preliminarily predict the quality of the plant meat, and combining a ternary group wisdom information evidence fusion method to fuse the preliminary prediction results to obtain the final plant meat quality prediction results. The application is helpful to more accurately grasp the quality of plant meat, and provides strong support for the production and optimization of plant meat.

The present application relates to the technical field of food quality detection, and in particular to a diester oil quality detection method and system based on multi-source data, which includes collecting multi-source heterogeneous data and performing feature extraction and dimensionality reduction to generate quality feature vectors; realizing multi-source data fusion through a dynamic weight distribution model to generate time series quality assessment data; using an adaptive correction algorithm to perform error compensation on low-confidence data and perform chain verification on high-confidence data; optimizing path planning through bidirectional consistency verification, generating optimized feedback data and completing final quality confirmation. Through multi-source data fusion, real-time analysis and automated verification, the present application significantly improves the accuracy and efficiency of diester oil quality detection, meeting the needs of modern industrial intelligence.

This invention relates to the field of probiotic preparation technology, and provides a method for preparing a probiotic preparation for improving egg quality. The method includes: collecting functional characteristic parameters of a target probiotic strain during a screening period, analyzing the functional characteristic values, and determining whether the target strain meets the standard; in response to the target strain meeting the standard, acquiring cell activity, stability, and synergistic parameters during a co-fermentation treatment period, analyzing the cell activity, stability, and synergistic values, and determining whether the reliability of the anaerobic fermenter in the co-fermentation process meets the standard; in response to the anaerobic fermenter's reliability meeting the standard, collecting quality characteristic parameters, analyzing the quality characteristic values, and determining whether the target product meets the standard; and in response to the target product not meeting the standard, determining the adjustment range of the cell activity, stability, and synergistic characterization threshold. This invention improves the DHA deposition effect in egg yolks and enhances the flavor and quality of eggs.

The invention provides a plant meat quality prediction method and system based on SPI raw material iterative analysis, and relates to the technical field of food science, and the method comprises the following steps: constructing a raw material characteristic index database; the method comprises the following steps: carrying out quality characteristic determination on plant meat prepared from a soybean protein isolate raw material in advance, and constructing a plant meat quality characteristic index database according to a quality characteristic determination result; based on the raw material characteristic index database and the plant meat quality characteristic index database, respectively constructing and training an elastic network regression model and a genetic algorithm-multiple linear regression model; and preliminarily predicting the quality of the plant meat by using an elastic network regression model and a genetic algorithm-multiple linear regression model, and fusing preliminary prediction results in combination with an evidence fusion method of ternary crowd-sourcing information to obtain a final prediction result of the quality of the plant meat. According to the method, the quality of the plant meat can be mastered more accurately, and powerful support is provided for production and optimization of the plant meat.

This application discloses a mechanism- and data-driven product quality control method and related apparatus, relating to the field of product quality control technology. The method includes: acquiring multiple sets of historical measurement data; using the process characteristics and quality characteristics of each step in a preset process as nodes; calculating the comprehensive grey relational degree between nodes based on the multiple sets of historical measurement data; constructing a Bayesian network; acquiring the real-time values ​​of the process characteristics and quality characteristics of the preset steps in the preset process; using these real-time values ​​as input; and using the Bayesian network for inference to predict the predicted value of the quality characteristic of the last step in the preset process, thereby further controlling product quality. This application combines mechanism and data to control product quality, enabling accurate prediction and timely intervention of quality problems, achieving the high requirements of lean manufacturing.