16results about How to "Predictive performance" patented technology

The invention discloses a method and a system for assisting material synthesis by utilizing a multi-mode large model and a storage medium, and the method comprises the following steps: establishing a corresponding relation between embedding of raw materials and a processing process and embedding of material performance by constructing a raw material and processing-performance multi-mode large model; in the application stage, the method can realize three reasoning functions: reasoning the material performance according to the raw materials and the processing process, reversely deducing the required material formula according to the target performance, and judging the credibility of the given formula. According to the method and system provided by the invention, the development efficiency of the material formula is remarkably improved, and meanwhile, the reliability of the formula is ensured. The method is suitable for formula development of various materials such as rubber, plastic and paint, and has important practical value.

This invention relates to the field of road engineering technology, and more particularly to a multi-objective performance coupling design method for warm-mix synchronously recycled SBS modified asphalt. The method determines the aging degree of aged SBS modified asphalt through testing, and accordingly determines the optimal dosage of the two-component synchronous recycling agent and the warm-mix agent. Subsequently, a diffusion model and a fusion degree calculation model for new and old SBS modified asphalt are established to quantitatively analyze the fusion degree of new and old asphalt under different temperatures and aged asphalt dosages. Based on this, a fusion degree spectrum is constructed, and by defining thresholds for each performance index, a feasible design scheme range for balanced performance is obtained, thereby determining the optimal mixing temperature and the maximum dosage of aged SBS modified asphalt. This invention can quickly determine the maximum allowable dosage of aged SBS modified asphalt and its corresponding optimal mixing temperature while considering multiple performance objectives, providing a reliable theoretical basis for the durability design of high-performance recycled SBS modified asphalt pavements.

The application relates to a UNet-based flow field prediction model training method and device, computer equipment and a storage medium. The method comprises the following steps: constructing grid data of a target cascade, and generating simulation flow field data corresponding to the target cascade according to the grid data and working condition conditions; inputting the grid data and the working condition conditions into a flow field prediction model constructed based on UNet to obtain predicted flow field data; determining a first loss value according to the gradient difference between the predicted flow field data and the simulation flow field data, determining a second loss value according to the difference between the predicted flow field data and the simulation flow field data of the surface area of each blade in the target cascade, and determining a target loss value according to the first loss value and the second loss value; and adjusting the flow field prediction model according to the target loss value to obtain a trained flow field prediction model. The method can improve the prediction accuracy of the model.

A rectifier blade welding repair method, comprising the following steps: step S1: based on the finite element method, a thermal coupling numerical model of the rectifier welding process is established, and a heat source model of argon arc welding and laser welding is established; step S2: setting the argon arc welding numerical simulation parameters and the laser welding numerical simulation parameters, respectively adopting the argon arc welding and the laser welding mode to carry out numerical simulation welding on the rectifier; step S3: comparing the temperature field at the moment of welding completion, the residual stress field after welding and the residual axial deformation after welding by using the two welding modes; step S4: according to the comparison result in step S3, the suitable welding mode is determined; step S5: through the actual welding test, the feasibility of the suitable welding mode determined in step S4 is verified; step S6: if the feasibility verification in step S5 is passed, the rectifier is clamped by using the welding tooling, and the blade to be welded is welded on the outer ring by using the welding mode determined in step S4.

The invention discloses an aggregate and asphalt interface self-healing evaluation method and system, and the method comprises the steps: respectively manufacturing limestone, granite and basalt aggregate test pieces, constructing a dynamic shear rheological test platform, testing the self-healing properties of asphalt interfaces with different lithology by using a dynamic shear rheometer, and evaluating the self-healing properties of the asphalt interfaces in a fatigue-intermittent-fatigue load mode. Parameters such as dynamic shear modulus and loading times are measured at intermittent time, and evaluation is performed by using self-healing indexes, so that not only can the influence of different lithologic aggregates on the asphalt interface interaction be judged, but also the self-healing capability of asphalt under different adhesion conditions, stress states, temperatures and damage conditions can be accurately evaluated, and the evaluation accuracy is improved. The optimal self-healing temperature and adaptive aggregate are obtained; in addition, the aggregate test piece can be used for evaluating the rheological properties of different types of asphalt and aggregate, and provides a basis for screening the optimal asphalt mixture under different traffic volumes and vehicle-mounted environments.

The invention provides a methanol reforming hydrogen production fuel cell modeling simulation method, which comprises the following steps: acquiring current, voltage, temperature, gas flow and methanol concentration data in real time, inputting the data into a trained performance prediction model to obtain a performance prediction value, and calculating an efficiency prediction value by combining a voltage value. Meanwhile, current, temperature, gas flow and methanol concentration data are input into the efficiency compensation model to obtain an efficiency error prediction value, the efficiency prediction value is compensated, and finally an accurate efficiency detection result is obtained. The operation stability and efficiency of the fuel cell can be improved, the energy consumption is reduced, and technical support is provided for optimization control and performance improvement of the methanol reforming hydrogen production fuel cell.

The present application relates to the technical field of backward reactions in the field of chemistry, and provides a reactant molecule prediction method and apparatus, a training method and apparatus, and an electronic device. The method comprises: extracting features of a product molecule to obtain the features of the product molecule; on the basis of the features of the product molecule, predicting a conversion path from the product molecule to a plurality of reactant molecules by using a backward reaction prediction model; and predicting synthons and completed synthons according to the conversion path to obtain the plurality of reactant molecules corresponding to the product molecule. The method provided by the present application can reduce the prediction complexity of reactant molecules, improve the generalization performance of reactant molecule prediction, and also can improve the prediction performance of the reactant molecules.

The invention discloses a checking method for preventing GGNMOS misconnection in a layout, and relates to the technical field of integrated circuits. The method comprises the following steps: writing a design rule check file, and identifying a silicide barrier layer region in a layout; analyzing hierarchical connection according to a written design rule check file, and judging whether a silicide barrier layer region is correctly connected to a drain end or not; the connection condition of the GGNMOS is automatically checked through layout design verification software, and the misconnection problem in the layout is recognized; the method is used for preventing a GGNMOS from being misconnected in an integrated circuit layout, accurately identifying and verifying the position and connection of a silicide blocking layer area, ensuring correct electrical connection with a drain end, optimizing a connection path, improving the accuracy of circuit design, predicting circuit performance through SPICE model simulation, and improving the reliability of circuit design. And the checking result is visually displayed through a graphical result checking and analyzing tool, so that errors in manual checking are reduced, and the design efficiency is improved.

The invention belongs to the crossing field of artificial intelligence and geophysics, and particularly discloses a transient electromagnetic forward modeling method and system considering an induced polarization effect based on deep learning, and the method comprises the steps: inputting Cole-Cole key parameters representing the induced polarization effect into a CNN-LSTM mixed deep learning network model for forward modeling, and obtaining transient electromagnetic response data; wherein Cole-Cole key parameters representing the induced polarization effect serve as multi-dimensional input features of the CNN-LSTM mixed deep learning network model, transient electromagnetic response data of a corresponding time channel serve as output, and the CNN-LSTM mixed deep learning network model is trained by adopting a segmented weighted mean square error loss function. According to the method, the segmented weighted mean square error loss function is adopted in the training stage, higher weights are given to the symbol inversion points and the prediction errors of the adjacent time windows, and the reliability of all-time response prediction is guaranteed.

The invention provides a soft robot performance and service life prediction method based on artificial intelligence, which relates to the technical field of soft robots, and comprises the following steps of: combining key machine data obtained after data preprocessing is carried out on collected test data and finite element simulation data of a soft robot under different test working conditions with a deep learning algorithm to obtain a soft robot performance and service life prediction model; constructing a life and performance prediction model for life and performance prediction to obtain a key prediction result; and the software robot design is optimized according to the key prediction result. According to the method, key machine data obtained after data preprocessing is conducted on collected test data and finite element simulation data of the soft robot is combined with a deep learning algorithm, and a service life and performance prediction model is constructed to predict the service life and performance of the soft robot to obtain a key prediction result; the software robot design is optimized according to the key prediction result, the performance and the service life of the software robot can be efficiently predicted, data support is provided for design optimization, and the research and development cost is reduced.

The invention discloses a high-strength corrosion-resistant geopolymer mortar proportioning parameter optimization method and a model construction method thereof, and the method comprises the following steps: constructing a geopolymer slurry ternary interaction model of interaction influence between geopolymer slurry rheological properties and blast furnace slag powder mass fraction, coal series kaolinite powder mass fraction and exciting agent mass fraction; determining the optimal proportioning parameter of the geopolymer slurry according to the optimal proportioning parameter of the geopolymer slurry; the aggregate gradation is optimized by adopting a directional gradation composite technology so as to determine the optimal aggregate gradation; the geopolymer mortar is soaked in a magnesium sulfate and sodium chloride composite solution, and the formula of the high-strength corrosion-resistant mortar is determined on the basis. According to the high-strength corrosion-resistant geopolymer mortar proportioning parameter optimization method and the model construction method thereof provided by the invention, a high-strength corrosion-resistant mortar product which can meet the requirements of a harsh service environment can be obtained.

The present invention relates to the technical field of quality and safety assessment, and in particular to a method and system for quality and safety assessment of a multi-winding design of a dry-type transformer, the method comprising: establishing a dry-type transformer database; assessing the quality and safety load according to power grid environment information and external environment information; constructing a quality and safety simulation space for the dry-type transformer based on basic parameter information and multi-winding design information, and performing an operation simulation on the multi-winding design of the dry-type transformer; loading the quality and safety load in the quality and safety simulation space, and setting an acceleration control time, performing an operation simulation on several load stages of the dry-type transformer based on the acceleration control time, and obtaining a quality and safety assessment result through the load simulation result. Through the present invention, by establishing a database containing detailed parameters and scenario information, and using the simulation space to quickly simulate power grid and environmental conditions, the long-term performance and safety of the transformer can be accelerated.

The invention belongs to the technical field of intelligent control of diesel engine emissions, and discloses an intelligent control method and system based on diesel engine aftertreatment system emissions, and the method comprises the steps: constructing a multi-head sensor neural network model, setting multiple hidden layers of the model, and dividing the neural network into a plurality of channels from the second hidden layer, a plurality of channels predict different parameters respectively; training data are input into the model, and a prediction result of emission of the diesel engine aftertreatment system is obtained; a loss function is defined, model parameters are optimized, and the trained model is used for prediction; and relevant input of the post-processing system is adjusted according to the predicted result, and intelligent control over emissions of the diesel engine post-processing system is achieved. According to the method, a neural network and feedback control combined method is adopted, the emission of the diesel engine aftertreatment system is predicted, then related input of the aftertreatment system is adjusted according to predicted data information, and intelligent control over the emission of the diesel engine aftertreatment system is achieved.

The embodiment of the invention provides an end wall grooving method, device and equipment for a cascade test, and the method comprises the steps: obtaining geometric parameters of a cascade according to the size of a test bench and a target two-dimensional blade profile of a plane cascade test; performing three-dimensional flow simulation calculation on the cascade by utilizing computational fluid mechanics based on the geometric parameters of the cascade; post-processing the simulation calculation result to obtain a surface streamline of the blade grid; according to the surface streamline of the blade grid, obtaining separation data of blade grid corner separation; determining slot parameters of the cascade according to at least one of the geometric parameters, the separation data and the slot parameters of the cascade; and based on the geometric parameters and the groove parameters of the blade grid, blade grid machining and end wall grooving are carried out. According to the embodiment of the invention, AVDR in a plane cascade test can be effectively reduced, and a test result can better reflect the performance of a two-dimensional blade profile.

Provided are a method and system for determining a population pharmacokinetic model of propofol and a derivative thereof. The method comprises determining a population pharmacokinetic model of a compound of formula (I) or propofol, wherein an equation of pharmacokinetic parameters in the population pharmacokinetic model of the compound of formula (1) comprises: CLi=exp4.20+0.349⋅logWT / 63.9−0.749⋅logTP / 72.4+0.238⋅SITE+ηCL,i; an equation of pharmacokinetic parameters in the population pharmacokinetic model of propofol comprises: CLi=exp4.56+ηCL,i.