51888 results about "Raw material" patented technology

The invention discloses a method of preparing aluminum oxide-silicon carbide compound porous ceramic by aluminum-silicon industrial waste residues. The primary raw materials comprise industrial waste residues, carbon powder, a pore forming substance and an adhesive. The aluminum oxide-silicon carbide compound porous ceramic is prepared by the following steps of mixing, drying, forming and sintering to obtain a final product. Treatment and high additional value utilization of the industrial waste residues are achieved. The prepared porous ceramic is remarkable in performance, and can be applied to the fields of filtration, sound isolation, heat isolation, fire fighting and the like. The method is simple in process flow and convenient for industrialized promotion; and the cost is good to control and the method has extreme economical value.

The invention relates to a preparation method of phenylmethylamine. The technical scheme adopted by the invention for mainly solving the problems of high catalyst loss, low production efficiency and high intermittent operation labor intensity is as follows: the preparation method of the phenylmethylamine comprises the following steps: mixing the raw material of cyanobenzene with a solvent material or at least one of one part of product materials in a mixing unit, introducing the mixture into a fixed bed hydrogenation reactor to be in contact with hydrogen and a catalyst and carry out multi-phase continuous hydrogenation reaction to obtain a product material containing phenylmethylamine, separating the product material to obtain a phenylmethylamine product, wherein the catalyst is a metal loaded catalyst; and the metal is selected from at least one of Pd, Pt, Cu, Ni, Mo and Fe. The preparation method can be used for preparing phenylmethylamine.

The invention discloses a fiber foamed concrete and a preparation method thereof. The fiber foamed concrete comprises the following raw materials in parts by weight: 5290 parts of cement, 4965 parts of water, 1.361 part of foaming solution, 1.2964 part of fly ash and 10 parts of fiber. The preparation method comprises the following steps: proportionally weighing the components; sequentially adding the cement and fly ash into a stirrer, proportionally weighing the water, uniformly stirring the mixture by the stirrer, and adding the fiber; preparing and adding the foaming solution; gradually adding the foam into the mixture, and continuously stirring until all the components are uniformly mixed; pouring the mixture into a mold on which lubricating oil is brushed, and curing in a curing chamber; after 24 hours, removing the mold; and respectively curing for 3 days, 7 days and 28 days for experimental detection. The fiber foamed concrete has the advantages of favorable thermal insulation property, favorable compression resistance and favorable bending resistance, and is applicable to a railway bed strengthening layer.

The invention relates to the technical field of automobile part manufacturing, and discloses an automobile injection molding part production process control system and method, and the system comprises the following modules: a data collection module which is used for collecting technological parameters, molds, raw materials and equipment operation original data, attaching timestamps, and storing the data in a database; the process parameter prediction module is used for reading original data to construct a time sequence data set, inputting the time sequence data set into a TFT model to obtain a pre-training model, and predicting a short-term process parameter fluctuation range in combination with current production working condition parameters; and the quality risk index acquisition module is used for inputting the process parameter data and the mold data into a quality risk index calculation formula to obtain a quality risk index. Through the system, data-driven comprehensive production optimization is realized, the process control accuracy and adaptability are improved, the quality control scientificity and reliability are enhanced, the intelligent level of the production process is improved, the production efficiency is effectively improved, the defective rate is reduced, and the product quality is stabilized. The problem that process control lacks system intelligence is solved.

The invention provides a solid waste filling material ratio optimization method of a magnesium slag-steel slag composite cementing material, and relates to the technical field of solid waste filling. The method comprises the following steps: mixing magnesium slag, steel slag, desulfurized gypsum and mineral slag to prepare a cementing material, and carrying out pretreatment and physicochemical property analysis on raw materials by taking tailings and waste rocks as filling aggregates; then designing a cementing material proportioning scheme and carrying out strength test to obtain an optimal ratio of the cementing material; then considering different slurry concentrations and plastic-to-bone ratios, and carrying out an all-solid waste filling slurry rheological test and an all-solid waste cementitious body strength test; and finally, according to the two test results, establishing a multi-objective optimization model taking the on-way resistance and the filling material cost as optimization objectives and taking the strengths of cementitious bodies at different ages as constraint conditions, and determining optimal parameters of the full-solid waste filling material. According to the invention, resource utilization of the metallurgical solid waste and the mine solid waste is realized, the bottlenecks of high carbon emission and high cost of a cement-based filling material are broken through, and a solution is provided for co-processing of the mine solid waste.

The invention relates to the technical field of metallurgical raw material batching control, and discloses a bottom blowing smelting furnace automatic batching intelligent control method and system based on deep learning, and the method comprises the steps: achieving intelligent batching through multi-source data fusion, physical constraint modeling and dynamic optimization control; edge calculation is adopted to realize data space-time alignment and purification, and physical and economic mixed features are constructed; modeling a reaction path based on a graph neural network, and embedding conservation law constraint to synchronously predict key process parameters; and finally, in combination with gradient sensitivity analysis and reinforcement learning, constructing a differentiable optimization framework to realize multi-target dynamic ratio decision and real-time compensation control, and forming a perception-decision-execution closed loop. The system comprises a global sensing and data purification module, an intelligent decision-making and optimization batching module and a high-precision execution and closed-loop control module. According to the invention, the batching strategy is adaptively adjusted, and optimal resource allocation and maximum economic benefit are realized.

The invention discloses a catalyst used for preparing acrylic acid and butyl ester by the dehydration of butyl lactate and a preparation method thereof. The catalyst is a composite catalyst, comprising a main catalyst A and auxiliary catalysts B, C, D and E, wherein, A is calcium sulphate, B is sulphuric acid, C is phosphate, D is alkaline matter and E is promoter. The preparation method comprises the steps as follows: five compositions A, B, C, D and E are sufficiently mixed, baked for 2-10 hours at the temperature of 200-800DEG C and formed for standby. The catalyst has high catalytic activation; under the catalysis of the catalyst, the molar yield reaches 75.1 percent and the molar selectivity of the acrylic acid and butyl ester reaches 71.5 percent. The preparation method has the advantages that the crystal structure of the main catalyst can be improved so as to be beneficial for carrying out the reaction; and the introduction of different auxiliary catalysts and quantities is helpful to improve the conversion ratio of the raw material and the product selectivity and is beneficial for improving the strength of the catalyst.

The invention discloses a concrete mix proportion optimization method and system based on machine learning, and particularly relates to the technical field of intelligent proportioning of building materials, and the method comprises the following steps: constructing a mapping model of target performance indexes by using raw material performance parameters and historical trial matching data, cross-station mix proportion optimization is carried out based on real-time sensing data of a plurality of mixing stations, the resonance relation between the moisture content of raw materials and the iteration frequency of a model is monitored in the dynamic construction process, and a parameter smoothing and disturbance suppression mechanism is triggered to correct a mix proportion scheme. The corrected mix proportion adjustment scheme is applied to raw material controlled feeding of multiple mixing stations; according to the method, the quality of training samples is improved through unified data processing, a multi-dimensional mapping model is constructed to realize cross-mixing-station performance consistency optimization, and a resonance detection and disturbance suppression mechanism is introduced to ensure the stability and anti-interference capability of mix proportion adjustment under a dynamic construction condition; therefore, high-performance, low-cost and high-robustness concrete intelligent optimization control is realized.

The invention discloses a batch circulation method for a tobacco primary processing workshop, and the method comprises the steps: generating a unique batch code based on raw material warehousing information, binding a two-dimensional code with an RFID dual identifier, and enabling the batch code to comprise a date, a production line code, a raw material batch number and a sequence number; the tobacco shred making process is divided into the working procedures of raw material moisture regaining, slicing / tip cutting, feeding and leaf moistening, shredding, tobacco shred drying, blending and perfuming and tobacco shred storing, and each working procedure is provided with an independent operation unit and an electronic lock. Intelligent temporary storage bins are arranged at a cut tobacco drying outlet and a blending and perfuming inlet, inter-process residence time is monitored through an MES system, early warning is triggered when time is out, and batches are frozen; when the batch enters each process, the preset process parameter range is automatically loaded, and the equipment is only allowed to operate in the parameter compliance range; process data and quality inspection results of all procedures are collected in real time, and raw material batches and finished silk boxes are associated to form a forward / reverse tracing chain; and starting freezing, reviewing and reworking / scrapping processes for the batches which are detected to be abnormal, and synchronously triggering an equipment self-cleaning program.

The invention relates to the field of coating material production, and discloses a coating formula calculation method and system based on self-learning feedback parameter correction, and the method comprises the steps: obtaining raw material basic parameters, target performance requirements and process feedback data of historical production batches, combining a material screening mechanism and an environment working condition correction strategy, and calculating a coating formula; constructing a coating formula initial input matrix; performing multi-dimensional variable normalization processing on the initial input matrix of the coating formula, introducing a feature sensitivity analysis model, and extracting a key variable group influencing the coating performance in the feature sensitivity analysis model; based on the performance response relation mapping model, analyzing error distribution between model prediction output and actual detection data by using a prediction deviation recognition mechanism, and extracting learning error features; a self-learning feedback updating mechanism is introduced, and dynamic weight optimization is conducted on the parameter correction factor set; and performing sample test and performance verification on the corrected candidate formula set. The method has the advantage that the coating formula precision is improved.

The invention relates to the technical field of industrial production intelligent process control, in particular to an AI-based electrolytic manganese process production quality intelligent prediction method and system, and the system comprises a drift calibration module, a structure matching module, a process parameter inversion module, a path correction module and a deviation verification module. According to the method, dynamic compensation of deviation between input parameter drift and output parameters is achieved through the response relation between input and output of all links, the actual influence degree of fluctuation of all the parameters on the target control parameters and product quality is effectively recognized according to correlation matching of the periodic change of the production process and the fluctuation frequency of the target control parameters, and the accuracy of the product quality is improved. Potential interference of key process parameters on stability of each process is locked in time, diffusion starting time and space of impurities are clearly traced through path judgment of residual liquid concentration trend and raw material adding position, and migration path parameters are further adjusted based on ion retention behaviors of boundary detection points.

A boron-containing polyethylene glycol fatty acid ester surfactant belongs to the field of organic chemistry and functional materials. The boron-containing polyethylene glycol fatty acid ester surfactant is prepared as follows: polyethylene glycol (PEG), boric acid and fatty acid are used as raw materials, first esterification reaction of the PEG and the boric acid is performed, then esterification reaction of the PEG and the fatty acid is performed to obtain boron-containing poly ethylene glycol fatty acid ester; by changing the species of fatty acids and catalysts and molecular weight of the PEG, the esterification rate can be enhanced, the boron-containing poly ethylene glycol fatty acid ester product can be used as a surfactant, and the boron-containing poly ethylene glycol fatty acid ester can reduce water surface tension and has good emulsifying properties.

The invention discloses a multi-source data fusion foam concrete construction process monitoring method and system, and relates to the technical field of concrete construction, the method comprises the following steps: obtaining a standard response data set of foam concrete, including raw material ratio parameters and performance index parameters which are stored in an associated manner; constructing and training a hybrid hierarchical performance prediction model, wherein the model comprises a shared prediction layer based on integrated learning and a plurality of independent output layers connected with the shared prediction layer; in combination with a multi-objective optimization algorithm, by taking compressive strength and cost optimization as an objective, constructing an evaluation function for global optimization, and obtaining a target mix proportion scheme; acquiring real-time process data associated with the target mix proportion scheme, and inputting the real-time process data into the mixing layering performance prediction model to obtain a prediction result; and comparing with a preset design target, and generating an adjustment instruction for adjusting the matching parameters of the subsequent stirring batches. The problem that in the prior art, the performance fluctuation of foam concrete of different batches is large due to the fact that the construction condition cannot be dynamically adjusted in real time is solved.

The invention relates to the technical field of carbon emission, in particular to a full-life-cycle carbon footprint tracking management platform for power equipment. The platform collects carbon emission parameters in the whole process from raw material input to scrap recovery in real time through a monitoring equipment network and a sensor array to generate an original monitoring data stream; performing multi-source fusion and deviation correction on the data stream to generate a standardized carbon footprint sequence; a carbon emission trend model is constructed based on sequence extraction correlation features, and a dynamic adjustment strategy is generated when an integration fracture risk or emission abnormity is detected; transmitting an abnormal signal through a mobile terminal interface, receiving an adjustment instruction, and generating a closed-loop control signal; storing the extended carbon footprint data to construct a full life cycle file; estimating emission fluctuation to generate a stability strengthening strategy; and a monitoring-analysis-control-prediction four-order optimization link is formed. According to the invention, accurate tracking and dynamic optimization of carbon emission are realized, data integrity and management timeliness are improved, and technical support is provided for green manufacturing of power equipment.

The invention relates to a comprehensive utilization method of fluosilicic acid containing hydrogen fluoride, which comprises the following steps: 1) reacting a stock solution containing fluosilicic acid with a potassium fluoride raw material, and carrying out solid-liquid separation to obtain potassium fluosilicate and a hydrofluoric acid solution; 2) reacting potassium fluosilicate with a sodium hydroxide raw material, and carrying out solid-liquid separation to obtain a mixture of a potassium fluoride solution, sodium fluoride and silicon dioxide; and returning the potassium fluoride solution to the step 1) to be recycled as a potassium fluoride raw material. According to the scheme, hydrofluoric acid is prepared from fluosilicic acid containing hydrogen fluoride, sodium fluoride and water glass products are produced at the same time, no other byproduct waste is produced, and the raw material utilization rate is high. And meanwhile, the method has the advantages of low raw material cost, low equipment cost and low energy consumption cost, can generate remarkable economic benefits, and is suitable for popularization and application.

The invention relates to the field of oil well opening and killing fluid production, in particular to a solid-free well killing fluid for shale oil reservoir and a preparation method of the solid-free well killing fluid. The solid-free well killing fluid for the shale oil reservoir comprises the following raw materials in parts by mass: 50-70 parts of water, 10-30 parts of a density regulator, 3-6 parts of a copolymer tackifier, 1-3 parts of a dispersant, 3-7 parts of a filtrate reducer and 2-4 parts of a corrosion inhibitor. The copolymer tackifier is obtained by initiating copolymerization by taking acrylamide, a quaternary ammonium salt-containing monomer, an unsaturated silane coupling agent and polyethylene glycol diacrylamide as monomer free radicals, and the dispersing agent comprises gas-phase nano silicon dioxide and a fluorine-containing surfactant. Through reasonable compatibility of all the components in the formula, especially the copolymer tackifier, the effect that one agent has multiple functions is achieved, and meanwhile the high temperature resistance, the corrosion inhibition performance and the clay stability of the well killing fluid are improved.

The invention relates to the technical field of chemical raw material processing, and discloses a petroleum coke particle size grading and batching system which comprises a raw material pretreatment module, a multi-stage dynamic screening module, a particle size real-time monitoring module, an intelligent batching decision module and a closed-loop control execution module. The classification definiteness of materials with different particle sizes is ensured; meanwhile, through a particle size monitoring feedback mechanism, the particle size distribution abnormal state in the screening process is recognized in real time, the material purity within the target particle size range is guaranteed, the particle size grading accuracy is improved, a closed-loop matching decision module is arranged, particle matching weight parameters are dynamically optimized in combination with the electrolytic aluminum process requirement, and the particle size grading accuracy is improved. The deviation degree between the ingredient proportion and the target performance can be judged in real time; the speed ratio of the conveying belt and the opening degree of the stock bin are automatically corrected through the executing mechanism, it is guaranteed that the mixing proportion of coarse particles, medium particles and fine particles is always in the optimal interval matched with electrolytic aluminum anode production, and the quality stability of anode carbon blocks is improved.

The invention relates to the technical field of commodity traceability, in particular to a commodity wholesale traceability tracking method based on a block chain, a block chain platform hybrid architecture is constructed based on a private chain and a public chain, hierarchical application of a consensus mechanism is realized, the private chain adopts a rights proof PoS or a practical Byzantine fault-tolerant PBFT to realize lightweight storage, and the public chain adopts a public chain to realize public chain traceability. The public chain adopts the PoW, and the security of the root node is guaranteed by using the decentration characteristic of the PoW. According to the invention, unique marking of the commodity and a distributed storage and sharing mechanism of the block chain are realized through the RFID technology, so that all participants can acquire and check complete traceability information of the commodity in real time, consumers can clearly understand the source and production process of the commodity, the block chain can ensure that the traceability information cannot be maliciously tampered, and the traceability efficiency is improved. According to the invention, the whole-process traceability of commodities from raw material production, processing, packaging and circulation is realized, and the problems of incoherent information, easy tampering, low traceability efficiency and the like in the existing commodity traceability system are solved.

A surround hot air slow drying device and a three-stage baking method for pet food processing are provided. The surround hot air slow drying device for pet food processing includes a drying box. A hot air drying unit is provided at an inner bottom of the drying box, a circulating conveying unit is provided inside the drying box, a plurality of drying frames are evenly distributed on the circulating conveying unit, a material turning mechanism is provided inside the drying frames, and a positioning component is provided inside the drying box. The material turning mechanism cooperates with the positioning component to turn the raw materials in the drying frames.

The invention discloses a solvent-resistant foaming material and a preparation method thereof, and relates to the technical field of high-molecular compound rubber foaming materials. The solvent-resistant foaming material is prepared from the following raw materials in parts by mass: 90 parts of a basic polymer, 5-25 parts of a chemical foaming agent, 0.5-5 parts of a cross-linking agent, 0.5-8 parts of a foaming aid, 5-40 parts of filler, 10-30 parts of a solvent-resistant modifier, 0.5-5 parts of a processing aid and 0.5-1.5 parts of an anti-aging agent. Through the synergistic effect of the base polymer (the nitrile rubber and the butadiene rubber are mixed according to the ratio of 1: 1) and the solvent-resistant modifier (such as polytetrafluoroethylene powder), the problem that a traditional foaming material is easy to swell and deform in an organic solvent environment is solved. On the trend, the volume swelling rate and the mass change of the material in a solvent are effectively reduced, the infiltration resistance is enhanced, the structural integrity of the material is kept when the material is in contact with lubricating oil or an alcohol solvent for a long time, and therefore the service life of a sealing piece is prolonged.

The invention discloses a biomass asphalt composite derivative hard carbon material and a preparation method and application thereof, and the preparation method comprises the following steps: step (1), placing biomass raw material powder in an acid pickling solvent for acid pickling, washing to be neutral after acid pickling, and drying to obtain a biomass precursor; (2) mixing the biomass precursor with asphalt to obtain a precursor mixture; and (3) carrying out low-temperature pre-oxidation on the precursor mixture, and then carrying out high-temperature carbonization, so as to obtain the biomass asphalt composite derivative hard carbon material after the high-temperature carbonization is finished. The prepared biomass asphalt composite derivative hard carbon material is used for preparing a sodium ion battery negative electrode. The technical problems that an existing biomass hard carbon material is low in capacity and tap density, difficult in impurity removal and the like can be solved, the biomass hard carbon material can be used for a sodium-ion battery negative electrode, and the sodium storage performance of a sodium-ion battery is improved.

The invention belongs to the technical field of PBT plastic particle injection molding, and particularly relates to a precise injection molding process control system for PBT plastic particles. The control system is composed of the following modules: a material characteristic sensing and modeling module, a multi-physical field simulation and parameter generation module, a distributed optical fiber global sensing module, a predictive closed-loop control module, and a digital twinning and full-period optimization module. The material characteristic sensing and modeling module is used for acquiring microscopic parameters of PBT raw materials through a near infrared spectrum sensor and constructing a material characteristic dynamic model; raw material characteristic fluctuation is pre-judged through near infrared spectrum dynamic modeling, technological parameter drift is predicted in advance in combination with an LSTM neural network, and feed-forward compensation is started before deviation is formed; compared with post correction in the prior art, the mechanism has the advantages that the parameter fluctuation control precision is improved, and the prevention efficiency for the problems of hydrolytic degradation, internal stress concentration and the like which are prone to occurring in PBT is improved.

The invention discloses a sheet metal flexible production line real-time scheduling method and system based on digital twinning, and relates to the technical field of production scheduling and optimizing.The method comprises the steps that according to production data, the deviation between a predicted value and an actual value of a digital twinning body is calculated; based on the deviation, dynamically correcting the mapping relation between the equipment processing efficiency and the output quality in the digital twin; scheduling deduction is carried out based on the corrected digital twinborn body, a scheduling scheme is generated, and the scheduling scheme fuses the corrected equipment processing efficiency and output quality constraint. According to the method, scheduling deduction is carried out by adopting a multi-objective optimization algorithm taking the punctual delivery rate, the equipment comprehensive efficiency, the energy consumption, the quality risk and the raw material overconsumption as optimization objectives based on the corrected digital twinborn body, so that the generated scheduling scheme can meet the multi-dimensional requirements of production efficiency, resource utilization, cost control, quality guarantee and the like; and the overall production benefit of the metal plate flexible production line is improved.

The invention discloses a mixed emulsion explosive one-key production control method and system, and relates to the field of automatic and intelligent control. By means of automatic and intelligent control means, the problems of low efficiency, high cost, quality fluctuation, process uncertainty and the like in traditional mixed emulsion explosive production are solved, accurate feeding of raw materials is achieved through a quality sensor array and a PID control algorithm, and the production efficiency is improved. The stability of production parameters is ensured through multi-sensor data fusion and an advanced control algorithm, so that the consistency of product quality is improved; meanwhile, a feedback control loop and a continuous learning mechanism are established, closed-loop control in the production process is achieved, technological parameters are optimized, the production stability and reliability are ensured, the production efficiency and the product quality are remarkably improved, and the labor cost is reduced.

The invention discloses a synthetic method of a water soluble ultraviolet light absorber BP-9. The method mainly comprises the following process steps: (1) carrying out methylation on the main raw materials of 2, 2', 4, 4'-tetrahydroxyl benzophenone, a transition metal salt catalyst and a mixed solvent which is prepared from dichloroethane and anhydrous ethanol in equal parts by weight to obtain 2, 2'-dihydroxyl-4, 4'-dimethoxyl benzophenone; (2) carrying out sulfonation reaction on the main raw materials of methylate, sulfamic acid and C1-C3 halohydrocarbon to obtain 2, 2'-dihydroxyl-4, 4'-dimethoxyl benzophenone-5, 5'-disulfonic acid; and (3) carrying out neutral reaction on the main raw materials of sulfonated product, inorganic base and ethanol water to finally obtain the BP-9 product. The synthetic method disclosed by the invention is few in reaction step, low in cost, high in product purity and stable in quality, and raw materials are easily available.

The invention discloses an artificial intelligence-based refining process efficiency optimization and real-time temperature control method and system, and the method achieves the efficient optimization and precise temperature control of a refining process through the innovation of four steps: 1, breaking through the limitation of traditional single-point monitoring, and deploying a multi-modal sensing array and a feed port near infrared spectrum sensor according to three-dimensional coverage; process-raw material two-dimensional data are collected in real time and associated, and the problem of data islands is solved; 2, innovatively constructing a'process-raw material 'two-dimensional feature vector, predicting a finished product rate by adopting an XGBoost model, and judging a dynamic power adjustment demand in combination with a threshold value to replace a traditional experience decision; thirdly, on the basis of the value output by the DQN model, an optimal dynamic temperature curve is calculated in a staged mode, and then the problem of fixed curve stiffness is solved through a generated precise power instruction; and fourthly, a three-level aging standard reaching mechanism is created for the first time, and an effect closed loop is formed corresponding to a differentiated scheme of model strengthening, local compensation and cross-furnace repairing.

The invention provides a feed fermentation parameter intelligent correction method based on the Internet of Things, and the method comprises the steps: carrying out the full-dimensional data collection from a microenvironment in a feed fermentation tank to a cross-regional macroenvironment, and generating a standardized data matrix; detecting communication time delay fluctuation characteristics based on the standardized data matrix, determining a fluctuation period and an amplitude range of a time delay abnormal point, and forming a time delay fluctuation characteristic spectrum; analyzing the influence of a raw material nutrition structure and logistics transportation time efficiency on the purity and concentration uniformity of metabolites through a regional differentiation regulation and control plan, and outputting associated feature distribution of quality control imbalance between regions; and updating an operation instruction of the feed fermentation equipment in real time according to the association feature distribution of the quality control imbalance between the regions, and obtaining equipment state operation feedback data after the operation instruction is updated.

The invention discloses an intelligent self-adaptive industrial raw material transportation system based on digital twinning, which comprises a multi-source positioning sensing module composed of a UWB positioning unit, an IMU compensation unit and an RFID verification unit, an edge calculation module and a dynamic actuator, the system integrates multi-sensor data through Kalman filtering to realize high-precision positioning, and based on a digital twinning model, the intelligent self-adaptive industrial raw material transportation system based on digital twinning is obtained. An improved deep reinforcement learning algorithm is adopted for dynamic obstacle prediction and real-time path planning, an optimal transportation path is generated, a dynamic actuator controls the transportation vehicle to move according to the planned path, and self-adaptive navigation and obstacle avoidance are achieved; through the improved deep reinforcement learning algorithm and in combination with dynamic obstacle prediction, the problem of path failure caused by a local optimal solution is effectively avoided, the path diversity exploration and dynamic obstacle avoidance capability in a complex environment is enhanced, and the planning robustness is improved.

The invention relates to the technical field of food industrial production, and discloses a food industrial production control method and system based on artificial intelligence, and the method comprises the steps: A, collecting the original attribute information of a to-be-processed raw material through a raw material data collection module before a food processing production line is started; b, in the food processing process, physical state parameters of the dough are obtained in real time; c, synchronously inputting the data obtained in the step A and the step B into a control system in which a multi-model fusion mechanism is constructed; d, the control system carries out dynamic recognition, difference comparison and trend evaluation on the current batch of raw materials and the process state, and process adjustment suggestions of corresponding stages are output based on feature weights learned in the training data; and E, converting the process adjustment suggestion into an instruction set, issuing the instruction set to a control executor, and integrating an advanced control method and system with intelligent prediction and adaptive control capabilities of multi-source information so as to realize the stabilization of the quality of the baked product.

The invention relates to the technical field of food safety intelligent tracing, and discloses a livestock and poultry product epidemic disease and tracing information quality tracing system based on artificial intelligence. The system comprises a raw material file construction module, an abnormal active prediction module, a multi-modal information fusion module, a tracing knowledge graph construction module and an intelligent tracing decision module. The system generates a raw material archive by collecting livestock and poultry raw material information, and analyzes production monitoring data in real time by using a time sequence model to actively predict abnormal nodes of epidemic diseases. After the abnormity is recognized, multi-link heterogeneous traceability information is synchronously called and fused, an abnormal event panorama is generated, and then a traceability knowledge graph is dynamically constructed in combination with an external knowledge base. And finally, automatically generating an optimized traceability query path according to the knowledge graph, and driving a precise traceability process. According to the invention, the conversion from passive recording to active early warning is realized, and the accuracy and efficiency of epidemic disease tracing are improved through deep fusion and intelligent reasoning of multi-source information.