6results about How to "Improve evaluation ability" patented technology

The invention discloses a potato waxiness evaluation model as well as a construction method and application thereof, and belongs to the technical field of food detection. The model construction method comprises the following steps: firstly, analyzing the waxy quality of potatoes in chewing and swallowing processes through sensory evaluation; then, stress relaxation testing is combined with a Maxwell model, and the mechanical property of the sample in the solid state in the chewing stage is measured; measuring the mechanical properties of the fluid phase sample in the swallowing stage by adopting frequency scanning and amplitude scanning in combination with an Ostwald-de Wavele power law model; and according to the correlation between the mechanical indexes and the taste scores, establishing a mechanical analysis-based potato waxiness evaluation model. According to the method, dynamic phase change and mechanical property analysis are combined for the first time to evaluate the waxy quality, so that waxy evaluation is more accurate and conforms to actual eating experience.

The present invention provides an electromagnetic identification method for the morphology of metal surface defects with a protective layer, which relates to the field of nondestructive testing technology. The method forms an induced eddy current on the metal surface by inputting an excitation coil of a square wave signal excitation source, collects magnetic field signals in a direction perpendicular to the metal surface, transmits them to a signal processing unit for conversion, and displays a real-time image to complete the identification and detection of metal surface defects. The present invention can quickly and effectively obtain morphological information of metal surface defects with a protective layer, including morphological detection of irregular defects, and realizes the identification of the location of defects on the metal surface, thereby improving the accuracy and evaluation capability of traditional electromagnetic nondestructive testing, and can fully meet the target requirements for defect status detection in industrial production, and has good application prospects for nondestructive testing and safety assessment of in-service equipment.

The present invention discloses a method for classifying fatty liver B-ultrasound images using an adaptive coordinated attention network, including a base plate. The method is designed to perform data enhancement preprocessing operations such as image histogram equalization, grayscale linear transformation, ROI selection, and average grayscale ratio comparison. The method uses an EfficientNet network combined with label smoothing and Adaptive Coordinate Attention to only use the pixels and labels of the original B-ultrasound image as input, thereby avoiding the decoupling of feature extraction and classification and achieving end-to-end automatic classification and recognition. The method is a lightweight network with fast training and reasoning, small model parameters, and based on adaptive coordinated attention, the method can adaptively encode horizontal and vertical position information as channel attention, while retaining position information in other spatial directions to enhance the representation of the attention object. Based on the method, the recognition ability of fatty liver B-ultrasound images has exceeded manual recognition and is also superior to other methods.

The invention relates to the field of environmental assessment systems, and in particular to a rural environmental assessment system based on a county scale, comprising: a data acquisition module for collecting environmental impact data information within the county scale; a subdomain division module for determining the divided subdomains according to industrial impact assessment values ​​and commercial characteristic area ratios; an indicator evaluation module for determining the county environmental assessment based on environmental impact parameters of corresponding subdomains, determining the extraction ratio of the sample number of positive environmental impact indicators to the sample number of negative environmental impact indicators according to subdomain type characteristic values, and determining whether the extraction number of negative environmental impact indicators meets a preset standard according to historical ecological stability characteristic values; and a neighborhood impact module for increasing the absolute value of the assigned value of the negative environmental impact indicator when determining that the neighborhood has a negative impact on the environment within the county according to the vegetation coverage rate within a preset boundary range, thereby improving the accuracy of the environmental assessment.

The present application belongs to the field of petroleum geology, and particularly relates to a method for evaluating oil and gas maturity in a fluid inclusion by using infrared spectrum. First, a fluid inclusion slice prepared from a stratum rock sample in a sedimentary basin is obtained; a filling sequence of diagenetic minerals in the stratum rock is determined; different occurrences of oil and gas are judged by petrographic characteristics under a microscope and fluorescence spectrum characteristics of the rock slice; infrared spectrum testing is performed on the oil and gas inclusions with different occurrences, and infrared spectrum characteristics of inclusions in different stages are obtained; a required spectrum range peak area is extracted from a spectrum diagram and brought into a formula; and an effective parameter for evaluating oil and gas maturity in the inclusions is obtained by using the formula and is sorted. The instrument used in the present application eliminates the requirement and limitation of traditional infrared spectrum on the size of the inclusions, and can measure and evaluate most oil and gas inclusions with smaller size.

The invention relates to the technical field of vehicle energy management, in particular to a calibration optimization method and device for vehicle energy management, a vehicle and a storage medium, and the method comprises the steps: obtaining a driving data set of various vehicle types, determining the actual driving data corresponding to each vehicle type, and obtaining the driving cycle of each vehicle type; determining an optimal power distribution strategy corresponding to the driving cycle of each vehicle type based on a preset dynamic programming algorithm, generating a calibration MAP of the power distribution strategy, calculating a fuel consumption value of the calibration MAP in an energy keeping mode under the driving cycle of each vehicle type, and evaluating the optimal power distribution strategy based on the fuel consumption value, and obtaining an energy management comprehensive energy consumption evaluation result of the vehicle. Therefore, the problems that an energy management method in the related technology cannot accurately and quantitatively evaluate the advantages and disadvantages of the calibration result in actual driving of the user, a large number of test resources are occupied, and the workload is increased are solved.