35results about How to "Fast and accurate evaluation" patented technology

The invention discloses a device for evaluating image quality of a near-eye display optical lens and is applicable to rapid detection in commercial production. The device comprises a micro display screen, an optical lens to be evaluated, a first CCD camera, an image collection card and a computer, wherein the micro display screen is used for displaying a standard test plate pattern; the pattern is taken as an object; images formed after transmitting by the optical lens are received by CCD camera; the image collection card is used for collecting the images and subsequently displaying the images on the computer. With the adoption of the micro display, the operation is greatly simplified without the process of manufacturing the standard test plate; the test plate is colorful and capable of testing the color reduction degree of an optical system; a plurality of physical parameters for expressing the optical lens to be evaluated can be obtained by detecting at one time, and the physical parameters include a field angle, the color reduction degree, a contrast ratio, a resolution ratio, an MTF value and the like. According to the technical scheme, the device can be used for quickly and accurately evaluating the imaging quality or the performance level of the optical lens and is relatively convenient to use.

The invention provides a pavement disease recognition method based on image analysis. The pavement disease recognition method based on image analysis comprises the following steps: step one, acquiring pavement images; step two, preprocessing the pavement images; step three, carrying out segmentation processing on the diseases in the preprocessed pavement images; step four, carrying out feature extraction and measurement on the diseases in the pavement images, specifically carrying out feature extraction and measurement on the diseases in the pavement images in the step three by using an outline area algorithm and an edge detection algorithm successively; and step five, outputting results, specifically accurately positioning the classified and measured diseases on the basis of the geographical location information in the step one through a controller and then outputting the results. By the technical scheme of the invention, labor can be relieved, interference of artificial subjective factors is eliminated, road conditions can be evaluated quickly and accurately, and the shortcomings that cracks are classified by manual judgment, working efficiency is low, error rate is relatively high and the like are overcome.

Embodiments of the invention provide a neural network-based reservoir micropore structure evaluation method and device. The method comprises steps of: acquiring rock core pore structure data obtainedbased on a rock core high pressure mercury experiment, and the type of a rock core pore structure corresponding to the rock core pore structure data; aligning rock core depth and well measurement depth according to a density curve in rock core density and well measurement data, obtaining well measurement data corresponding to the rock core, and obtaining pre-processed well measurement data; training an initial neural network model with pre-processed well measurement data as input and the type of the rock core pore structure as output, and obtaining a trained neural network model; and inputtingtarget well measurement data into the trained neural network model when the reservoir microstructure of the target well needs to evaluate, and obtaining pore type corresponding to the target well measurement data. The reservoir micropore structure can be evaluated rapidly and accurately.

The invention provides a quantitative assessment method and system of coal seam stability. The method comprises the steps that parameter information of a target object is obtained, and the parameter information comprises a coal point sum, a coal point number, measured thickness of each coal point and average coal seam thickness, wherein the coal seam thickness of the coal point number is larger than or equal to coal seam minimum recoverable thickness; according to the coal point sum and the coal point number of the target object, a coal seam recoverability index of the target object is obtained; according to the measured thickness of each coal point, the coal point sum and the average coal seam thickness, a mean square error value of the target object is obtained; according to the averagecoal seam thickness and the mean square error value, a coal seam thickness variable coefficient of the target object is obtained; according to the coal seam recoverability index of the target object and the coal seam thickness variable coefficient of the target object, the coal seam stability of the target object is assessed, operation is simple, the coal seam stability can be assessed faster andmore accurately, and coal mining design is better served.

The invention discloses an image measuring method for evaluating oil pipe pitting behaviors. By means of the corrosion weight loss method and the micro-measurement technology, a proper datum plane is built on the surface of a slide through a coating method, proper temperature, proper pressure and a proper medium are selected, different corrosion time is controlled, the number and the size of pitting generated on the surface of the slide are effectively controlled, then large-scale image scanning is conducted on the slide through a measurement microscope, image information of a metal surface at the same position before corrosion and after corrosion is compared, and accordingly evaluation in the aspects of generation and development positions of pitting on the surface of an oil pipe, the number, the pit size and appearance is achieved. Relative information of a large amount of pitting can be obtained qualitatively and quantitatively, important bases are provided for researching generation and development of the oil pipe pitting behaviors, and the method has important research and application value.

The invention provides a portable water and soil conservation benefit evaluation device based on a water and soil loss calculation equation. The device comprises a shell, a control unit in the shell and a remote data server, wherein the control unit uploads obtained data to the remote data server through a wireless network and comprises a data processing unit, a storage unit with a database, a wireless communication unit and a GPS navigation unit, wherein the storage unit, the wireless communication unit and the GPS navigation unit are respectively in communication connection with the data processing unit. According to the invention, the water and soil loss calculation equation is combined with the water and soil conservation benefit evaluation, the water and soil loss evaluation value of a piece of land is obtained by calculating the water and soil loss quantity of the land under different water and soil conservation measures, and the water and soil loss situation can be quantitatively evaluated in a scientific and normative manner; moreover, the water and soil conservation measures for the land can be evaluated under three conditions.

A device (100) for processing an input signal (102), the device (100) comprising a delay unit (104) adapted for delaying the input signal (102) by a predefined delay time, at least one phase shifting unit (106) each adapted for phase shifting the delayed input signal (108) by an assigned phase value, a plurality of mixer units (110) each adapted for mixing the input signal (102) with the delayed input signal (108) or with one of the at least one phase shifted signal (112), and an extraction unit (114) adapted for extracting information from each of the mixed signals (116).

The invention relates to the technical field of teaching management systems, in particular to a checking system of an electronic class card machine for student homework. The system comprises a management host, the management host is connected with a plurality of class management modules through a network, each class management module comprises a control mainboard, and the control mainboard is connected with a network transmission module through a wire. The network transmission module is in signal connection with the management host through a network, the control mainboard is connected with a homework management module and a touch display screen through wires, the touch display screen is used for achieving man-machine interaction, and the homework management module comprises an homework publishing module and an homework uploading module. The homework publishing module and the homework uploading module are jointly connected with a review scoring module through wires, an automatic scoringmodule is connected with a comparison module through a wire, and the review scoring module is connected with a chart display module through a wire. The system can achieve the publishing, uploading and checking of the homework of students, and facilitates the teaching management.

The invention discloses an intelligent diagnosis method and diagnosis system for an in-vehicle jitter problem under a vehicle start-stop working condition. The method comprises the following steps: 1) carrying out band-pass filtering on acceleration time domain data of a steering wheel and a seat in a vehicle start-stop process, and then carrying out effective data segment interception; 2) calculating an acceleration four-power vibration dose value of the effective data segment, and judging the in-vehicle jitter degree; 3) when the in-vehicle jitter is abnormal, performing spectral analysis on the abnormal acceleration time domain data segment to find out the main problem frequency of the in-vehicle jitter; and 4) obtaining the reason and solution suggestion of the in-vehicle jitter by using an in-vehicle jitter problem matching model. According to the method, the in-vehicle jitter degree is judged by utilizing the vibration dose of the acceleration of 4 times, the judgment result is accurate and rapid, meanwhile, the in-vehicle jitter abnormal reason and solution suggestion can be obtained, and the in-vehicle jitter diagnosis problem under the vehicle start-stop working condition is well solved.

The invention relates to a partial reference quality evaluation method for a super-resolution reconstructed image based on wavelet transform. According to the technical scheme, the method comprises the following steps of firstly, carrying out blocking operation on a low-resolution image Io and a super-resolution reconstructed image Is to respectively obtain M image blocks; respectively carrying out wavelet transformation on the M image blocks; determining a threshold T, fitting the wavelet sub-band coefficient c'ji corresponding to the wavelet sub-band of the lth image block of the low-resolution image Io with the variance greater than the threshold T into a generalized Gaussian model; fitting the wavelet sub-band coefficient of the lth image block of the low-resolution image Io to a firstfitting parameter ol and a second fitting parameter ol of a generalized Gaussian model; correspondingly, obtaining a first fitting parameter sl and a second fitting parameter sl of the lth image block of the super-resolution reconstruction image Is; and finally obtaining an image quality evaluation value D. According to the method, the quality of the super-resolution reconstructed image Is can berapidly and accurately evaluated only by utilizing the information of the low-resolution image Io, and the robustness is high.

The invention discloses a reinforced concrete member anti-collision performance prediction method based on machine learning, and the method comprises the following steps: obtaining impact test parameters and member characteristic parameters of a reinforced concrete member, constructing a data set, and randomly dividing the data set into a training set and a prediction set; determining an artificial neural network topological structure, and obtaining a trained residual performance prediction model; adopting a prediction set to check the prediction performance of the trained model until the appropriate prediction precision is achieved; and for a specific reinforced concrete member, performing predicting by utilizing the trained residual performance prediction model to obtain a vulnerable curved surface of the reinforced concrete member. According to the invention, based on a machine learning algorithm, the residual performance of the RC component after impact is used as an index, and a rapid and reliable method for predicting and evaluating the impact resistance of the RC component is established. By fully using the existing historical test data, the impact resistance of the RC component can be evaluated more quickly and accurately.

The invention discloses a personal credit rating evaluation method and device, which can be applied to the field of big data or finance, and comprises the steps of determining an attribute value of attribute information of a customer, establishing an attribute coordinate system according to the attribute information and the attribute value, determining a coordinate value from the attribute coordinate system according to the attribute value, and evaluating the personal credit rating. Determining each attribute standard interval corresponding to the customer in a preset attribute standard interval set, judging whether all the coordinate values are matched with each attribute standard interval or not, and if alternative attribute standard intervals which are not matched with all the coordinate values exist in each attribute standard interval, calculating to obtain a similar value corresponding to each alternative attribute standard interval, and determining the alternative attribute standard interval corresponding to the maximum similar value as a target attribute standard interval, determining a credit level corresponding to the target attribute standard interval, and determining the credit level corresponding to the target attribute standard interval as the personal credit level of the customer. By applying the method provided by the invention, the personal credit rating of the customer can be quickly and accurately evaluated.