8results about How to "Avoid prediction" patented technology

The invention discloses a method for measuring Joule-Thomson coefficients of hydrocarbon fuel and cracking products thereof. The method comprises the following steps: pumping a target substance into an experimental tube, and heating from room temperature to target temperature; monitoring the temperature of the target substance at the inlet and outlet of the experiment tube, the wall surface temperature distribution of the experiment tube, the system pressure at two ends of the experiment tube, and current and voltage applied to two ends of the experiment tube in real time; according to the parameters monitored in real time, a function H (T) of the constant-pressure enthalpy value of the target substance changing along with the temperature is obtained on line based on a calorimetric model; when cooling to room temperature, changing the pressure and continuing the steps to obtain H (T) under different pressures; and based on H (T) under different pressures, establishing a Joule-Thomson coefficient calculation model containing a pressure-temperature-constant pressure enthalpy value function relationship, and calculating the change condition of the Joule-Thomson coefficient of the target substance along with the temperature. The invention further discloses a corresponding measuring device. According to the method and the device, accurate measurement of the Joule-Thomson coefficient is realized.

The invention belongs to the field of computational mechanics, and discloses a dynamic modeling method for parameters of a large-flexibility mooring anchor chain. On the basis of concentrated mass method modeling, the parameter variation principle is introduced, the nonlinear tension and the nonlinear seabed contact force of the mooring anchor chain are arranged into a unified expression containing parameters in a segmented expression form, and the nonlinear behavior of the anchor chain can be corrected by updating and iterating the parameters. The prediction of the motion state of the anchor chain at the next moment according to the motion state at the current moment in the traditional algorithm is avoided, the dynamic modeling simulation precision of the mooring anchor chain is greatly improved, and a foundation is laid for the subsequent dynamic algorithm solution of the mooring anchor chain.

This invention discloses a frequency-domain guided multi-scale deformable alignment method and system for UAV target detection. The method first acquires and preprocesses a dataset of UAV aerial images. Next, it improves the YOLOv8 model, performing target detection based on the preprocessed UAV aerial image dataset and outputting the target detection results. Finally, the improved YOLOv8 model is integrated into a pre-configured training environment, using training and validation images from the UAV aerial image dataset for training and validation. This invention significantly enhances the model's ability to perceive small targets, thereby significantly improving the localization and classification accuracy of small targets, reducing detection errors, and improving overall accuracy.

The application discloses a kind of weakly supervised image semantic understanding methods based on multi-task learning, comprising the following steps: obtaining task missing image, constructing multi-level task sharing encoder, extracting high-level semantic information layer by layer, input corresponding decoder branch;Construct public space-task space feature mapping module, through the unaligned task fusion module and task interaction mapping module, update each subtask feature by mapping;Task adaptive feature update module is constructed, and multi-level iterative update unaligned task feature;Task adaptive weakly supervised image semantic understanding framework is constructed, model loss function is established, image data with task missing is input into model, and obtains multi-task prediction result such as semantic segmentation, depth estimation, surface normal estimation.The application is according to the data information of task label unaligned, through the mapping interaction of public space and task space, fully fuses unaligned task feature, iteratively generates high-quality multi-task prediction result, can effectively handle weakly supervised problem with task missing, and simultaneously improves each task prediction accuracy.

The embodiment of the application relates to the technical field of data processing, in particular to a graph representation learning method and device for out-of-distribution generalization, equipment and a storage medium, aiming to obtain adaptive graph structure data representation of out-of-distribution environment and improve the accuracy of graph structure data related prediction. The method comprises the following steps: inputting an original graph data set into a graph structure data representation network, identifying stable subgraphs and noise subgraphs, performing representation processing on the identified graph structure data, obtaining vectorized representation of the stable subgraphs and vectorized representation of the noise subgraphs; simulating a multi-distribution environment, under the multi-distribution environment, performing prediction according to the vectorized representation of the stable subgraphs to obtain corresponding prediction results; performing loss function calculation on the prediction results and labels of the original graph structure data, optimizing parameters of the graph structure data representation network, and obtaining a graph structure data representation model; and performing a graph data related task through the model to obtain a target result of the graph data related task.

The invention discloses a polyimide performance prediction method and system, a polyimide structure design method and system, electronic equipment, a computer readable storage medium and a computer product. The polyimide performance prediction method comprises the following steps: inputting a first molecular descriptor into an AFP model to obtain a to-be-measured physical property parameter; the first molecular descriptor is a molecular descriptor of polyimide to be detected; the AFP model is obtained through training of a training data set, and the training data set comprises a second molecular descriptor and a first physical property parameter; the second molecular descriptor and the first physical property parameter are a molecular descriptor and a physical property parameter of known polyimide respectively; each of the first molecular descriptor and the second molecular descriptor comprises a node feature and an edge feature, and the type of the first molecular descriptor is the same as that of the second molecular descriptor; the type of the to-be-measured physical property parameter is the same as that of the first physical property parameter. The method has high accuracy, and the effectiveness and reliability of de novo design are improved.

The invention discloses a bank suspicious transaction feature automatic identification method and device. Bank transaction records are collected, standardization processing is carried out on texts in the records, and the processing content comprises common transaction types such as transfer, consumption and ATM withdrawal. Then, word segmentation processing is carried out on the standardized text, key information vocabularies are extracted, a vocabulary list is constructed, and the vocabulary list is used for subsequent Word2Vec model training; the Word2Vec model adopts a Skip-Gram architecture, word vectors are trained and generated by predicting context words, the semantic relation between transaction feature vocabularies is captured, and the model calculation amount is reduced by adopting a negative sampling method. In the training process, a maximum log-likelihood function is used as a loss function, and model parameters are optimized. After training is completed, the recognition precision of the model on suspicious transaction features is evaluated by verifying the generated word vector, and model parameters are further adjusted according to a verification result, so that a more accurate suspicious transaction recognition model is obtained.

The invention provides a short-term wind power plant power prediction method and device, equipment and a medium, and belongs to the technical field of wind power data processing. The method comprises the steps of obtaining a predicted wind speed and a wind direction angle of a target height of a wind power plant, classifying and identifying the wind direction angle, and determining a time category and a wind direction category; after correcting the abnormal wind speed, calculating the total power at each moment by using a wind speed-total power curve, and calculating the average ratio of the power at each moment to the total power according to the wind speed and wind direction categories; and the wind power at each moment is obtained through product, and power prediction of the wind power plant is realized. According to the method, higher prediction precision and a finer time scale are realized by focusing on generation power prediction of the wind power plant in a specific time period and utilizing a simple statistical method and an empirical model, meanwhile, the technical complexity is reduced, and the operation efficiency of the wind power plant is remarkably improved.