32results about How to "Avoid Evaluation Errors" patented technology

The invention relates to a wind turbine generator bearing fault diagnosis method for a multi-channel deep convolutional neural network. The method comprises the steps of: simultaneously acquiring high-frequency vibration acceleration signals of a drive end and a non-drive end of a test bearing in various states by using a vibration acceleration sensor; analyzing the acquired vibration signals by using a time frequency analysis technology to obtain corresponding time frequency spectra; establishing a deep convolutional neural network diagnosis model, and training the diagnosis model by using the time frequency spectra and the states of the bearing as a training sample; evaluating the diagnosis model, and applying the diagnosis model to a bearing to be monitored. The method can realize automatic feature learning, avoids feature engineering, effectively utilizes multi-channel vibration signals, and has good universality and extensibility.

The invention discloses an objective evaluation method for quality of VoIP non-reference video communication based on a neural network, is mainly applicable to monitoring the quality of the VoIP video communication under a real-time communication scene, and belongs to the field of objective evaluation of video quality. The method provided by the invention is implemented by the following steps of extracting a network parameter during a VoIP video communication process, meanwhile performing an objective test to score the video, performing standardization treatment and dimension reduction treatment on the extracted network parameter, using acquired dimension-reduced data as an input of the neural network, and using an objective test score as a reference output of the neural network to perform neural network training, thus acquiring a weight and a threshold of each neural node, that is so say building of the neural network is completed, wherein the output of the neural network is the objective quality score acquired through mapping according to the input parameter, and the objective quality score is used for objectively evaluating the quality of the VoIP non-reference video communication. According to the method provided by the invention, the quality of the VoIP video can be accurately evaluated in real time.

The invention discloses a LINUX kernel reliability evaluating system based on source code analysis. The LINUX kernel reliability evaluating system comprises a master control end and an object end, wherein the master control end runs in an independent system, and comprises a control module with control logics, a fault injector module, a communication module, a fault load generator module and a data analysis module; and the object end comprises an injection actuator module, a work load generator module and a result collecting and performance monitoring module. Evaluating errors generated by the traditional method can be avoided effectively, analog internal memory mistakes are injected in a kernel of an object operating system, response of the object system to injected fault is observed, experiment information is collected, the collected experiment information is counted and analyzed, an experiment process of a relevant result is provided for a user, fault injection success rate and fault coverage rate are increased, detection coverage rate and recovery coverage rate of the system are monitored accurately, and accurate evaluation reliability of the system is improved.

The invention relates to a classified estimation method and device for vehicle insurance and belongs to the technical field of intelligent vehicles. The method comprises the following steps: risk characteristic extraction is performed firstly, risk characteristics of a driver and a driving vehicle are obtained, and then 8-dimensional risk characteristics describing driving behaviors of the driver are defined by combining with vehicle-mounted remote information; then a mathematical model for the risk characteristics and loss is established through logistic regression, model parameters are estimated on the basis of historical data with a maximum likelihood method, and value-at-risk thresholds of different risk ranking groups are determined after the model parameters are obtained; finally, risk characteristics and risk values of a to-be-estimated customer are calculated, and risk ranking is performed according to a risk rank table. According to the method, vehicle risks can be ranked through effective combination of driver information, driving vehicle information and driving behavior characteristics, artificial participation is not needed in the whole process, dependence on personal experience is avoided, and the method is direct, effective and convenient to use.

The invention discloses a quick and precise high-throughput drug screening system based on deep learning. The drug screening system comprises a picture preprocessing module and a neural network module, wherein the picture preprocessing module comprises a channel merging module and a picture standardization module; the channel merging module merges different cell single-color channel pictures intothe multi-channel picture representation, wherein the merged picture tensors are represented as [H,W,C]; the picture standardization module standardizes the input multi-channel picture data into the tensor representation of [70,70,C]; the neural network module is connected with the picture standardization module, the input data of the neural network module is standardized picture tensors, and finally the trained neural network is subjected to final prediction classification prediction. The drug screening system DeepScreen based on deep learning has the advantages of being high in throughput, precise, efficient, fast, convenient, low in cost and resistant to interference, and has a worth-concerning practical and application prospect.

The invention is applicable to the technical field of aircraft icing detection, and provides an improved icing sensor mounting position determination method. The method comprises the following steps: calculating an air flow field of an aircraft with a sensor; calculating the ratio beta1 / beta2 of the water collection coefficient beta1 of the position where the sensor is located to the maximum water collection coefficient beta2 of the wing; if the ratio beta 1 / beta 2 is greater than 1, calculating the ratio h1 / h2 of the average icing thickness h1 on the sensor to the average icing thickness h2 on the windward side of the wing; if the ratio h1 / h2 is greater than 1, determining the position as the installation position of the sensor; if the ratio h1 / h2 is less than or equal to 1, determining that the position is not suitable for installing the sensor. According to the method, ice type calculation and liquid water analysis are coupled to judge the mounting position of the sensor, so evaluation errors caused by low freezing rate are avoided, and the evaluation reliability is higher.

The invention discloses a method for evaluating the white blood cell image definition. The method comprises: acquiring an input original white blood cell image and converting the original white bloodcell image into a grayscale image; dividing the grayscale image into image blocks, and randomly extracting the to-be-analyzed image block; performing denoising on the extracted image block to obtain anoise reduction image; performing cell region segmentation of the noise reduction image by using the OTSU method to obtain an optimal segmentation threshold; performing low-pass filtering on the noise reduction image to acquire a degraded image; acquiring TenenGrad parameters of the noise reduction image and the degraded image corresponding to the noise reduction image, and calculating the definition of the image block, wherein the optimal segmentation threshold is used as a customization image threshold of a TenenGrad function; and calculating the mean of the definitions of all extracted image blocks, and analyzing samples to obtain a virtual focus degree threshold. The present invention achieves local evaluation of the image definition while evaluating the overall definition of the image by analyzing definition parameters at different positions of the image.

The invention provides a method and device for evaluating the influence of a drag torque on vehicle energy consumption. The method comprises a step of measuring a test vehicle equipped with a brake caliper through a chassis dynamometer to obtain first internal resistance, a step of performing an energy consumption test on the test vehicle equipped with the brake caliper to obtain first energy consumption, wherein the motor brake of the test vehicle equipped with a brake caliper can be carried out through an accelerator pedal, a step of carrying out internal resistance measurement on a test vehicle which is not equipped with the brake caliper to obtain second internal resistance through the chassis dynamometer, a step of performing an energy consumption test on the test vehicle which is notequipped with the brake caliper to obtain second energy consumption by using a single pedal gear, wherein the motor brake of the test vehicle which is not equipped with the brake caliper can be carried out through the accelerator pedal, and a step of evaluating the influence of the drag torque on the vehicle energy consumption according to the first internal resistance, the second internal resistance, the first energy consumption and the second energy consumption. In this way, the accuracy of evaluation can be improved.

The invention belongs to the field of uranium mine exploitation technology, and particularly relates to a comprehensive evaluating method for exploration and utilization of sandstone type uranium deposit. The comprehensive evaluating method is characterized in that restraining factors which affect deposit evaluation are preliminarily screened through restriction evaluation, thereby preventing evaluation error caused by factors with one ballot veto in the deposit; quantification of sandstone type uranium deposit exploitation performance is realized through comprehensive evaluation; integral determining for the sandstone type uranium deposit exploitation effect can be realized; and instructive opinion can be supplied for exploitation decision of the sandstone type uranium deposit. The comprehensive evaluating method for exploration and utilization of the sandstone type uranium deposit has beneficial effects of comprehensive system, strict logic, accurate and reliable result, high applicability, etc. Integral evaluation can be performed on the ore deposit before construction of a mine, thereby preventing blindness in early-period exploration of the deposit, and reducing risk in deposit exploration.

The embodiment of the invention provides a benchmark test method and device of a supervised learning algorithm in a distributed environment. The method comprises the steps that a first benchmark test result which is determined according to output data in a benchmark test is obtained; a distributed performance index in the benchmark test is obtained, and the distributed performance index is determined as a second benchmark test result; the first benchmark test result and the second benchmark test result are merged to obtain a benchmark test total result. According to a perfect scheme used for solving a benchmark test problem of the supervised learning algorithm in the distributed environment, the benchmark test method and device can assist technical staff to conduct accurate and quick assessment on the performance of the supervised learning algorithm.

The invention discloses a working efficiency evaluation system based on wearable equipment, comprises a wearable device and a data analysis platform, wherein the wearable device and the data analysisplatform collect working data by using the data platform and send the working data to the data analysis platform, and then the working analysis platform determines the identity, the workload and the working time of the staff according to the working data, and further calculates the working efficiency of the staff. The wearable device comprises a wearable device and a data analysis platform. Visible, the system collects working data through wearable equipment worn by staff, and calculates the working efficiency of staff according to the working data, effectively avoids the evaluation error caused by subjective evaluation, and improves the objectivity of the evaluation system. In addition, the invention also provides a working efficiency evaluation method based on a wearable device, the function of which corresponds to the function of the above-mentioned system.

The embodiment of the invention discloses an audio call assessment method, assessment equipment and a computer storage medium. The audio call assessment method is applied to the assessment equipment,and comprises the following steps: a recognition text of received audio is obtained, wherein the recognition text is a recognition result of the received audio after transmission of reference audio attransmit-receive dual ends; and by combining the recognition text and a reference text corresponding to the reference audio, an effect assessment value of the audio call is obtained.

The invention relates to a wind turbine generator bearing fault diagnosis method for a multi-channel deep convolutional neural network. The method comprises the steps of: simultaneously acquiring high-frequency vibration acceleration signals of a drive end and a non-drive end of a test bearing in various states by using a vibration acceleration sensor; analyzing the acquired vibration signals by using a time frequency analysis technology to obtain corresponding time frequency spectra; establishing a deep convolutional neural network diagnosis model, and training the diagnosis model by using the time frequency spectra and the states of the bearing as a training sample; evaluating the diagnosis model, and applying the diagnosis model to a bearing to be monitored. The method can realize automatic feature learning, avoids feature engineering, effectively utilizes multi-channel vibration signals, and has good universality and extensibility.

The invention relates to a classification model, and provides a quota prediction method and device and a computer readable storage medium. According to the invention, subsequent insurance amount estimation is carried out only when the risk level is detected to be within a certain range, so that possible negative effects caused by continuous insurance buying of customers with relatively high risk levels are avoided; risk assessment is carried out by selecting the risk assessment model corresponding to the insurance type of this time, so that assessment errors caused by different insurance typesare avoided; a risk assessment model is obtained by using feature engineering and machine learning training, and target features are obtained by using the risk assessment model, so that a risk assessment result finally obtained by the risk assessment model is more accurate; the insurance amount range that the client can understand at present is predicted by synthesizing the previous insurance information and the amount adjustment factor, so that the insurance amount information that can be insured and conforms to the actual situation can be obtained during the current insurance. In addition,the invention also relates to a blockchain technology, and the previous insurance information can be stored in the blockchain.

The invention discloses an oil and gas pipeline geological disaster evaluation method based on an information amount-neural network, and the method comprises the following steps: determining a research region, and dividing grid units; carrying out geological disaster susceptibility evaluation; evaluating the vulnerability of the pipeline; dividing standards according to the failure consequences and determining the levels of the failure consequences; and determining the risk level of the pipeline geological disaster by using the pipeline failure probability and the failure consequence level. According to the technical scheme, geological disaster susceptibility evaluation is optimized by using a method of combining the information amount and the artificial neural network, and an accurate pipeline risk evaluation result is obtained after geological disaster susceptibility evaluation, pipeline vulnerability evaluation and pipeline failure consequence evaluation are performed on each grid unit by using the GIS. And evaluation errors caused by only considering a single factor are avoided.

The invention discloses a method for evaluating the shale stratum borehole wall stabilizing capacity of drilling fluid based on acoustoelectric response. The method comprises the steps: carrying out well drilling, coring and drying on a shale stratum to be drilled; calculating the density, the longitudinal wave velocity and the resistivity of a test sample; putting the sample into an aging tank ora high-temperature and high-pressure water loss instrument, adding a drilling fluid to be evaluated, enabling the drilling fluid to completely immerse a plunger core sample, applying pressure, and enabling the aging tank or the high-temperature and high-pressure water loss instrument to be at a soaking temperature; after soaking is finished, carrying out cooling, releasing the pressure, and taking out the soaked sample; measuring the length, the diameter and the mass of the sample soaked in the drilling fluid, calculating the density, testing the longitudinal wave velocity and the resistivityof the sample, and calculating the acoustoelectric disturbance comprehensive index; and judging the shale stratum borehole wall stabilizing capacity of the drilling fluid according to the acoustoelectric disturbance comprehensive index. The method provided by the invention provides an efficient and reliable experimental method for drilling fluid performance design, performance optimization and drilling fluid formula system optimization of the shale stratum.

The invention belongs to the technical field of electrical equipment fault diagnosis, and discloses a weighted KNN algorithm-based moisture content evaluation method considering a transformer aging effect. The method comprises the steps of: preparing and measuring FDS data of insulating paperboard samples in different aging states and moisture contents; extracting FDS curve characteristic parameters of the samples; fitting and constructing a database for representing water content information of the samples by using the characteristic parameters; constructing a moisture content evaluation model based on a KNN classification algorithm; testing the accuracy of the model by using laboratory samples; and applying the model to on-site transformer testing. According to the method, the FDS and KNN technologies are combined to construct the transformer oil paper insulation moisture content evaluation model considering the aging effect, the problem that the aging effect and the moisture content cannot be distinguished in a traditional FDS testing process is solved, and a basis is provided for deep mining of internal information of an FDS curve and accurate judgment of the moisture content of a field transformer.

The present invention relates to a channel appraising apparatus used in a wireless local area network. The appraising apparatus carries out the modulation of the channel response in a frequency-region during transmitting a signal package by using a simplified type of a channel pre-appraising controller of recursion of least square (RLS) and by using a data-reconstruction apparatus, and its modulating action is flexible, the adaptability modulation being performed at any time during transmitting a signal package, so that the quick convergence and the best effect of the channal appraisement can be achieved effectively.

The invention provides a motor spindle lubricating oil quality detector. The motor spindle lubricating oil quality detector comprises an upper box body, a lower box body, a driving unit and a liquid level display, a torque sensor, a resistance display screen, a conductor, a liquid level display and an external display scree; a cover plate is designed on the upper box body, two change-over switchesare arranged above the cover plate, a temperature regulator is designed in the middle, two detection rods are arranged below the torque sensor, an electric heating plate is designed on the inner layer of the lower box body, a temperature sensor is designed on the outer wall of the inner layer, and a liquid level display is arranged on the side face of the lower box body and connected with a liquid level sensor; and the detection rods are provided with external sleeve rods. The viscosity of the lubricating oil and the content of metal particles can be detected; whether the quality of the lubricating oil meets the use standard or not is judged through the detection result, evaluation errors caused by personal subjective experience and use time judgment are avoided, the lubricating oil of the motor main shaft is blindly replaced in advance, the service life of the motor main shaft is shortened, and meanwhile the use cost is reduced.

The invention provides a method and device for evaluating the influence of a drag torque on vehicle energy consumption. The method comprises a step of measuring a test vehicle equipped with a brake caliper through a chassis dynamometer to obtain first internal resistance, a step of performing an energy consumption test on the test vehicle equipped with the brake caliper to obtain first energy consumption, wherein the motor brake of the test vehicle equipped with a brake caliper can be carried out through an accelerator pedal, a step of carrying out internal resistance measurement on a test vehicle which is not equipped with the brake caliper to obtain second internal resistance through the chassis dynamometer, a step of performing an energy consumption test on the test vehicle which is notequipped with the brake caliper to obtain second energy consumption by using a single pedal gear, wherein the motor brake of the test vehicle which is not equipped with the brake caliper can be carried out through the accelerator pedal, and a step of evaluating the influence of the drag torque on the vehicle energy consumption according to the first internal resistance, the second internal resistance, the first energy consumption and the second energy consumption. In this way, the accuracy of evaluation can be improved.

The invention relates to a rail transit station vulnerability evaluation method based on a PSR model, and the method comprises the following steps: S1, obtaining data, and storing the related data of an urban rail transit system in a database; s2, establishing an evaluation index system based on a PSR model, including a pressure P index based on human and environmental factors, a state S index based on equipment factors, and a response R index based on management factors; s3, determining an index data type in the evaluation system, and extracting to-be-evaluated site information data in the database for dimensionless standardization processing; s4, determining the index weight of each index by using an expert scoring method and an analytic hierarchy process-entropy weight combination method; s5, performing unification processing on the data after the dimensionless standardization processing in the step S3; and S6, performing vulnerability scoring based on a superior and inferior solution distance method. According to the method, the vulnerability of the rail transit station can be quantitatively evaluated in multiple directions, and the method is more practical and universal.

The invention is applicable to the technical field of aircraft icing detection, and provides an improved method for determining the installation position of the icing sensor: calculating the air flow field of the aircraft with the sensor; calculating the water collection coefficient β1 at the position of the sensor and the The ratio β1 / β2 of the maximum water collection coefficient β2; if the ratio β1 / β2 is greater than 1, calculate the ratio h1 / h2 of the average icing thickness h1 on the sensor to the average icing thickness h2 on the windward side of the wing; if the ratio h1 / h2 is greater than 1, then this position is determined as the installation position of the sensor; if the ratio h1 / h2 is less than or equal to 1, then this position is not suitable for installing the sensor. The invention couples the ice type calculation with the liquid water analysis to judge the installation position of the sensor, avoids the evaluation error caused by the low freezing rate, and has higher evaluation reliability.

The invention discloses a LINUX kernel reliability evaluating system based on source code analysis. The LINUX kernel reliability evaluating system comprises a master control end and an object end, wherein the master control end runs in an independent system, and comprises a control module with control logics, a fault injector module, a communication module, a fault load generator module and a data analysis module; and the object end comprises an injection actuator module, a work load generator module and a result collecting and performance monitoring module. Evaluating errors generated by the traditional method can be avoided effectively, analog internal memory mistakes are injected in a kernel of an object operating system, response of the object system to injected fault is observed, experiment information is collected, the collected experiment information is counted and analyzed, an experiment process of a relevant result is provided for a user, fault injection success rate and fault coverage rate are increased, detection coverage rate and recovery coverage rate of the system are monitored accurately, and accurate evaluation reliability of the system is improved.

The present invention relates to a channel estimator used in a wireless local area network, mainly by using a simplified least square recursion (RLS) channel estimation controller and using a data-reconstruction device, in the transmission of signal packets During the period, the action of adjusting the channel response in the frequency domain is performed, and the adjustment action is flexible and adaptively adjusted at any time point between a transmission signal packet, which can effectively achieve fast convergence and have the best execution channel. Evaluate the effect.

The invention discloses a respirator field protection factor evaluation system and method. The respirator field protection factor evaluation system comprises an outer sampling system, a power device, an exhaust heat dissipation hole, an inner sampling system, a respirator mask, a wearing device and a noxious substance detection system. According to different types of harmful substances, the internal / external sampling system respectively comprises a detachable dust sampling device, a detachable toxic and harmful gas sampling device and a detachable microorganism sampling device which can be selected; and the noxious substance detection system comprises an optional dust detection subsystem, a poisonous and harmful gas detection subsystem, a bacterium detection subsystem and a virus detection subsystem. According to the invention, the measurement of protection factors of different harmful substances by the respirator in a real operation site can be realized, the respiratory protection is scientifically guided, and the life safety and health are guaranteed. According to the invention, the measurement of protection factors of different harmful substances by the respirator in a real operation site can be realized, the respiratory protection is scientifically guided, and the life safety and health are guaranteed.

The invention discloses an objective evaluation method for quality of VoIP non-reference video communication based on a neural network, is mainly applicable to monitoring the quality of the VoIP video communication under a real-time communication scene, and belongs to the field of objective evaluation of video quality. The method provided by the invention is implemented by the following steps of extracting a network parameter during a VoIP video communication process, meanwhile performing an objective test to score the video, performing standardization treatment and dimension reduction treatment on the extracted network parameter, using acquired dimension-reduced data as an input of the neural network, and using an objective test score as a reference output of the neural network to perform neural network training, thus acquiring a weight and a threshold of each neural node, that is so say building of the neural network is completed, wherein the output of the neural network is the objective quality score acquired through mapping according to the input parameter, and the objective quality score is used for objectively evaluating the quality of the VoIP non-reference video communication. According to the method provided by the invention, the quality of the VoIP video can be accurately evaluated in real time.

The invention relates to the technical field of auxiliary equipment for tea leaf evaluation, in particular to an improved tea leaf evaluation device which comprises an evaluation table, a conveying belt, a clamping groove, tea leaf storage tanks, a strip-shaped groove, cover plates, a lifting mechanism, a cavity, an air hole, a connecting rod, a communicating groove, a pressure sensor, a storage groove, an LED lamp, a baffle and a driving mechanism. The method has the beneficial effects that a plurality of different types of tea leaves are placed in different tea leaf storage tanks respectively, so that smell channeling phenomenon is reduced to a certain degree; and in addition, notches of the tea leaf storage tanks are covered by the cover plates, negative pressure is generated by external negative pressure equipment, and air in the tea leaf storage tanks is pumped out, so that smell of previously stored tea leaves in the tea leaf storage tank can be dissipated, and smell mixing between the previously stored tea leaves and the tea leaves to be evaluated is avoided.

The invention discloses a method for evaluating the clarity of white blood cell images. The method includes: acquiring an input original white blood cell image and converting it into a grayscale image; dividing the grayscale image into blocks to form image blocks, and randomly extracting the white blood cell image to be analyzed. Image block; perform denoising on the extracted image block to obtain a denoised image; realize cell area segmentation of the denoised image through the maximum inter-class variance method to obtain the optimal segmentation threshold; perform low-pass operation on the denoised image. The filtering operation obtains the degraded image; obtains the TenenGrad parameter of the denoised image and the degraded image corresponding to the denoised image, and calculates the clarity of the image block; wherein, the optimal segmentation threshold is used as a customization of the TenenGrad function Image threshold; calculate the average sharpness of all extracted image blocks, and analyze the samples to obtain the defocus degree threshold. By analyzing the sharpness parameters at different positions of the image, the present invention not only evaluates the overall sharpness of the image, but also achieves local assessment of the sharpness of the image.