15 results about "Product distribution" patented technology

The invention discloses a biomass gasification experimental design and performance prediction method based on support vector and transfer learning, which comprises the following steps: establishing an Aspen plus simulation model, adjusting the gasification temperature to air equivalence ratio in the Aspen plus model, and obtaining a biomass gasification simulation data set covering wide boundary operation conditions; taking the simulation data set as a training sample, constructing a simulation agent model, and searching an optimal hyper-parameter; extracting a support vector sample through a support vector regression method, designing experimental working condition points, and collecting experimental data to obtain an experimental data set; taking the experimental data set as a model input sample, and outputting a predicted value by the model; performing linear migration on a model prediction result; and performing secondary correction on the difference between the migrated result and the experimental data to obtain a high-precision calibration model fusing linear migration and residual correction. According to the method, the problems of high acquisition cost of biomass gasification experiment data, limited simulation data precision and the like are effectively solved, a model with better generalization ability and higher interpretability is constructed under limited experiment samples, and accurate prediction of product distribution is realized.

The invention discloses a biomass pyrolytic reaction network prediction method based on a graph theory and quantum chemistry, which comprises the following steps: analyzing the molecular structure of a biomass initial reactant, abstracting the molecular structure into a directed graph molecular model, marking a potential conversion path after molecular mechanics optimization, generating a unique identifier by using an atom numbering rule and a Hash algorithm, and predicting the biomass pyrolytic reaction network. Functional groups are extracted and packaged into sub-graph modules, chemical bond parameters are obtained in combination with quantum chemistry calculation and are converted into fracture probabilities, basic reaction building blocks are predefined to traverse and mark breakable bonds, fragments are recombined and then de-weighted through Hash, and then reaction activation energy weights are given to side chemical bond fracture reactions; an energy optimal path is screened by means of a priority queue search algorithm, accurate analysis of a chemical bond fracture path and intermediate product conversion in the biomass pyrolysis reaction network is finally achieved, reaction path and product distribution are efficiently predicted, and the calculation efficiency and precision of a complex system are balanced.

The invention relates to the technical field of chemical experiments, and discloses an AI-driven chemical experiment simulation and result prediction system. According to the system, multi-modal data is collected through an experimental data acquisition module, spectral features are extracted through a spectral feature analysis module, a coupling kinetic model is constructed through a reaction kinetic modeling module, a product distribution probability is predicted through a dynamic result prediction module, reaction conditions are optimized, and reaction parameters are adjusted in real time through an experimental parameter feedback module. In addition, the system also comprises a reaction safety evaluation model which is used for identifying risks and providing a safety protection scheme. The system realizes comprehensive simulation and accurate result prediction of chemical experiments, can effectively optimize reaction conditions, improves reaction efficiency and safety, and has wide application prospects in the fields of chemical experiment research, chemical production and the like.

The invention discloses a product distribution strategy optimization method considering the endogenous influence of a distribution network on a demand, and the method comprises the steps: 1, considering the endogenous influence of the distribution network on the demand, taking the minimization of the total logistics time consumption in the distribution network as a target, and building a distribution strategy optimization model; 2, analyzing historical demand data, constructing product attribute proxy features, forming a demand feature vector with historical logistics service quality and regional economic development level of a cargo distribution network, training in combination with a random forest prediction algorithm to obtain a prediction model, predicting product demand, and providing input for a cargo distribution strategy optimization model; and 3, constructing an iterative solution framework of product demand prediction and product distribution strategy optimization, and outputting a stable distribution decision. According to the method, the distribution network is dynamically adjusted by introducing a feedback mechanism, so that the total logistics time consumption in the distribution network is effectively shortened, the logistics operation efficiency of an enterprise is improved, and a systematic solution is provided for a product distribution strategy optimization problem in a complex environment.

The present invention relates to the field of chemical experiment technology and discloses an AI-driven chemical experiment simulation and result prediction system. The system collects multimodal data through an experimental data acquisition module, extracts spectral features through a spectral feature analysis module, constructs a coupled kinetic model through a reaction kinetic modeling module, predicts product distribution probabilities and optimizes reaction conditions through a dynamic result prediction module, and adjusts reaction parameters in real time through an experimental parameter feedback module. In addition, the system also includes a reaction safety assessment model for identifying risks and providing safety protection solutions. The system realizes comprehensive simulation and accurate result prediction of chemical experiments, can effectively optimize reaction conditions, and improve reaction efficiency and safety. It has broad application prospects in fields such as chemical experimental research and chemical production.

The present invention provides a product distribution prediction method and device, comprising: inputting key parameters of a catalytic cracking reaction into a distribution prediction model to obtain product prediction results output by the distribution prediction model; the distribution prediction model is trained using sample key parameters and sample product distribution information corresponding to the sample key parameters; the key parameters and product prediction results are input into a target optimization model to determine product distribution information after product hydrogen distribution optimization. The product distribution prediction method and device provided by the present invention utilize the distribution prediction model and the target optimization model to perform target optimization and judgment on the key parameters and product prediction results, rapidly calculating product distribution information after hydrogen distribution optimization in a catalytic cracking reaction, and automatically calculating the optimal solution for product hydrogen content distribution.

This invention provides a prediction system and method for the distribution of delayed coking products. The prediction system includes: a delayed coking unit library, comprising multiple delayed coking units and delayed coking product yield data for each unit using at least one industrial raw material; a heavy oil thermal processing performance evaluation device for obtaining test product yield data; a reference unit selection module for selecting the delayed coking unit corresponding to the minimum Euclidean distance of any industrial raw material as the reference unit for that industrial raw material; and a data processing module for calculating the ratio of the delayed coking product yield data of the reference unit to the test product yield under the test conditions, and for calculating the product of each test product yield and the ratio corresponding to each product, and performing normalization processing to obtain the predicted product distribution. The above prediction system is applicable to any conventional industrial raw material and has high adaptability and accuracy.

A method of selecting one or more reference features for characterizing a random effect in a patterning process is disclosed, the method comprising: obtaining a plurality of product features associated with a pattern for patterning on a substrate in the patterning process; obtaining product distribution data related to one or more random parameters characterizing a random effect of the plurality of product features; one or more reference features are selected as an appropriate subset of the plurality of product features, where the one or more reference features are selected to optimize an estimate of the product distribution data according to reference distribution data that has been measured from the one or more reference features.

This invention discloses a multi-level supply chain collaborative distribution method, comprising constructing a consumer demand-based collaborative cigarette distribution recommendation system framework, collecting and preprocessing multi-source review data, performing in-depth analysis of consumer demand characteristics based on the preprocessed data, clustering the analyzed demands and calculating product similarity, and adjusting the product distribution ratio based on the clustered demands and calculated product similarity. This invention, through multi-source data collection and in-depth analysis, accurately captures consumer demand characteristics, and combines cluster analysis and product similarity calculation to achieve dynamic and intelligent adjustment of product distribution ratios. This effectively improves the accuracy and flexibility of collaborative distribution, reduces supply-demand imbalances, optimizes supply chain resource allocation, enhances market responsiveness, and provides scientific methodological support for efficient collaboration in multi-level supply chains.

The present invention provides a method and apparatus for obtaining a petroleum catalytic cracking scheme, comprising: inputting basic device data and operating data of a catalytic cracking reaction into a catalytic cracking reaction model, obtaining product flow rate data and hydrogen content distribution data output by the catalytic cracking reaction model through catalytic cracking reaction calculations and heat balance calculations; and inputting the basic device data and operating data, as well as the product flow rate data and hydrogen content distribution data, into a target optimization model to determine a petroleum catalytic cracking scheme after hydrogen distribution optimization. The method and apparatus for obtaining a petroleum catalytic cracking scheme provided by the present invention, using only basic device data and operating data, can predict product flow rate and hydrogen distribution using the catalytic cracking reaction model and the target optimization model, and perform target optimization to obtain an optimized hydrogen distribution scheme for the catalytic cracking reaction, thereby achieving product distribution with essentially optimal hydrogen content distribution.

The present disclosure relates to training a machine learning model based on a dataset comprising sales volume, product distribution logistics records, and product manufacturing data. The present disclosure further relate to extracting from the model a prediction of at least one item selected from a group consisting of future sales volume of an existing product, consumer interest for new products, and failure rates for product distribution equipment.

To provide a genuine product distribution management device, a genuine product distribution management method, and a genuine product distribution management program that can reduce work man-hours and reduce mistakes.SOLUTION: A genuine product distribution management device of an embodiment refers to a customer master, a billing master, and a destination product name master, acquires a billing destination corporation code corresponding to an inputted customer and a billing destination code corresponding to an inputted product code, determines whether the corporation code matches the billing destination code of the destination product name master according to the input product code and outputs, if it is determined that the corporate code and the billing destination code of the destination product name master corresponding to the inputted product code do not match, information that there is an input restriction.SELECTED DRAWING: Figure 1

The application discloses a biomass gasification experiment design and performance prediction method based on support vectors and migration learning, and comprises the following steps: establishing an Aspen plus simulation model, adjusting the gasification temperature and the air equivalent ratio in the Aspen Plus model, and obtaining a biomass gasification simulation data set covering wide boundary operation conditions; taking the simulation data set as a training sample, constructing a simulation proxy model, and searching for optimal hyperparameters; extracting support vector samples through a support vector regression method, designing experiment working points, and collecting experiment data to obtain an experiment data set; taking the experiment data set as model input samples, and outputting predicted values of the model; linearly migrating the model prediction results; performing secondary correction on the difference between the migrated results and the remaining experiment data, and obtaining a high-precision calibration model fused with linear migration and residual correction. The application effectively solves problems such as high cost of biomass gasification experiment data acquisition and limited simulation data precision, constructs a model with better generalization ability and stronger interpretability under limited experiment samples, and realizes accurate prediction of product distribution.

The present disclosure relates to training a machine learning model based on a dataset comprising sales volume, product distribution logistics records, and product manufacturing data. The present disclosure further relate to extracting from the model a prediction of at least one item selected from a group consisting of future sales volume of an existing product, consumer interest for new products, and failure rates for product distribution equipment.

The invention discloses a logistics intelligent distribution method and system based on data analysis, and relates to the technical field of logistics distribution. A product distribution area is divided into a grid map; carrying out attribute assignment on each grid in the grid map; based on the vehicle capacity constraint and the product demand time constraint, establishing a target function by taking minimization of the delivery cost as a target; extracting parameters related to the target function from the grid map and mapping the parameters to the target function; a population is initialized, each particle in the population represents a distribution scheme, and a corresponding distribution path is recorded in the distribution scheme; the distribution cost is used as a fitness value, and the fitness value of each particle is calculated; iteratively updating the speed and the position of each particle, and recalculating the fitness value of each particle after iteration updating; and when an iteration stop condition is met, taking the distribution scheme corresponding to the particle with the lowest fitness value as a final distribution scheme. According to the invention, the distribution of a large number of distribution point products can be completed in time with low distribution cost.