313results about How to "Guaranteed to be scientific" patented technology

The invention discloses an urban storm flood monitoring and traffic controlling and guiding system and method. The urban storm flood monitoring and traffic controlling and guiding system comprises a water depth data collecting and rectifying unit, a unit for analyzing and predicting water depth and on-off control of a drainage pump station and an early warning issuing and traffic controlling and guiding processing unit. The water depth data collecting and rectifying unit is used for performing comparison and check analysis by collecting water depth data of different types at water accumulating spots and obtaining water depths at the water accumulating spots. The unit for analyzing and predicting water depth and on-off control of the drainage pump station is used for performing trend analysis and rolling correction on the water depths of the water accumulating spots by combining zone rainfall data of surrounding rainfall stations on the basis of the water depths obtained by the water depth data collecting and rectifying unit and achieving automatic on-off of a drainage pump unit according to an accumulating water depth predicting curve. The early warning issuing and traffic controlling and guiding unit is used for processing obtained traffic controlling and guiding information and sending the information to a controller and early warning and instructing pedestrians and vehicle drivers in various manners according to safety pass standards of water-accumulating roads. The urban storm flood monitoring and traffic controlling and guiding system and method have the advantages of being reliable in data, stable in communication, comprehensive in function, professional in handling and the like.

The invention relates to a fast human face recognition method based on geometric proportion characteristic of five sense organs, an object to be recognized and searched is a human front face image, two-dimensional coordinates of the characteristics of eyes, noses, mouths and the like are got according to different gray values of all parts of a human face, and coordinate points are connected appropriately so as to be combined into angle, length and other information. By performing matching analysis on two human faces, the matching rate of the eyes and the nose, the eyes and the mouth, and the nose and the mouth and the comprehensive matching rate can be further got. Simultaneously, the obtained two-dimensional coordinates and the human face image, as well as the information of an individual to which the human face belongs, are saved in a database together. The human face to be recognized is contrasted and matched with the human faces in the database one by one, and the human face with the highest comprehensive matching rate is further extracted, thereby realizing fast search of the human face.

The invention discloses an epidemic situation predicting and early warning method of infectious diseases, particularly a network early warning system of relevant public health events of infectious diseases in countries, provinces, cities (regions) and districts (counties). The method comprises the steps of integrating adverse reaction information data which are collected by the server side, calculating and determining the early warning threshold of public health events according to the quantities of the symptoms of adverse reactions on the basis of the operation of a time sequence analysis statistic model and automatically carrying out early warning in real time at any time. The method comprises the following specific steps of: (1) integrating information from different channels; (2) executing a path I: analyzing tasks; and (3) executing a path II: predicting and early warning. Once the quantity of monitoring data meets the traditional basic requirements of a tome sequence analysis method for considering the periodicity, the seasonal nature, long term tend and the like of diseases, the conclusion having relative-high value can be obtained to play important roles of early finding epidemic situations, taking measures as soon as possible, preventing the spread of the epidemic situations and preliminarily establishing an epidemic situation monitoring and early warning system and a working mechanism of the province.

The invention relates to the field of disaster information management, in particular to a method for establishing a flood disaster geographical analysis and evaluation dynamic model. The method includes the steps that initial data of a region to be analyzed are collected, compressed and then stored in an established lightweight class spatial database; the initial data are retrieved, an established flood inundation analysis model is initialized, and a final flood inundated region areal map and a water depth classification map are acquired through a seed point spreading algorithm; integrated data of the final flood inundated region areal map and the water depth classification map are input to a flood disaster loss evaluation mathematical model and a flood risk evaluation mathematical model for calculation, and then the economic loss condition and the potential flood-hit risk degree of villages in a flood storage and detention region after flood inundation are acquired. A spatial database system and the flood inundation analysis model which are excellent in performance and stable and reliable in operation are established, the organization and management method of image raster data is optimized, the flood inundation condition of the flood storage and detention region under a given condition is visually displayed, and the consequential loss evaluation function is provided.

The invention discloses a psychological stress training system and method.The psychological stress training system comprises a plurality of training terminals and a pulse oximeter connected with the training terminals.The terminals are further connected with a helmet.The helmet is of a closed structure, and a screen is arranged before the eye part of the helmet and connected with the terminals through interfaces.The terminals are connected with a master control server through a network to form a network of the psychological stress training system.The master control server provides training management for the terminals through the network, and the terminals send detected human body reaction information to the master control server through the network and conduct autonomous training according to the task arrangement and materials of the master control server.The system is refined in structure, and easy and convenient to install and use; according to the method, a scientific stress training mode is adopted, the stress levels of trainers in stress training are collected according to a base line, an analyzing basis is provided for further training through file storage, and the training scientificity is ensured.

The invention discloses a method and a device of car emission fault detection and diagnosis based on fuzzy reasoning and self-learning and belongs to the field of car maintenance and diagnosis. The method of the car emission fault detection and diagnosis based on the fuzzy reasoning and the self-learning comprises collecting all data values of a to-be-tested car exhaust gas under different working conditions, comparing the data values with standard values, if the data values reach the standard values, then the diagnosis is finished, if the data values do not reach the standard values, then confirming the possible corresponding causes of the problem according to a built fuzzy diagnosis matrix through a fuzzy reasoning method and outputting a diagnosis result, implementing maintenance according to the diagnosis result until the data value reaches the standard value through staff, and at last correspondingly updating vehicle profile information and the right fault diagnosis information of the diagnosis result to a data base to be used for self-learning and adjusting the fuzzy diagnosis matrix. According to the method and the device of the car emission fault detection and diagnosis based on the fuzzy reasoning and the self-learning, a car emission fault example is studied through the fuzzy reasoning, fault features are extracted from a large amount of samples, detection accuracy is high, dependency of the technical merit of the operators is low, and operation is convenient.

The invention provides an LED lighting quality evaluation method based on objective and subjective experiment data and a system. The method comprises the steps that subjective experiment data acquired from a preset LED lighting evaluation angle for light emitting samples are input; the subjective score mean of each group of light emitting sample is counted; for each group of light emitting sample, a spectroradiometer is used to measure spectral power distribution; data in a visible wavelength range are intercepted; objective evaluation indicators are calculated; a multiple nonlinear fitting method is used to construct an association model between the subjective score mean and a corresponding objective evaluation indicator under different light emitting sample conditions; for a light emitting sample to be evaluated, the spectroradiometer is used to measure the spectral power distribution; the data in the visible wavelength range are intercepted; the objective evaluation indicator is calculated; a corresponding score estimation value is acquired based on the association model; and the lighting quality of a light source is characterized. The LED lighting quality evaluation method provided by the invention has the advantages of flexible and targeted use, accurate evaluation and easy implementation.

The invention discloses a geographic information system (GIS) spatial information technology-based method for mobile patrol and real state monitoring. The method comprises the following steps of: accessing a security service through a virtual private network (VPN) mode when a mobile handheld device logs on a system, and calling an identification service registered in a unified data service by the security service to identify the legality of user information and the device; and after successfully logging on the system, sending the user information and device information to a token service through the security service, and returning a token by the token service according to service authorities corresponding to the user information and the device information so that the device acquires a valid token and then can successfully access to a mobile map service and acquire map data. By using the method, the security of map spatial data and services can be guaranteed, and the map data can be prevented from leaking and stealing.

The invention discloses a comprehensive metering control system for a coaler of a coal mine, belonging to the technical field of metering control systems. The system comprises the following structures of an entrance taring system, a coal loading system, a weighing system, a pricing system, an exit system, a server of a dispatch center monitoring room and a database, wherein the entrance taring system records the inert weight of the coaler, and transmits information of the coaler into the server of the dispatch center monitoring room; the coal loading system records the number of loaded coal of the coaler, and uploads the coal loading information to the server; the weighing system uploads the weighing information to the server of the dispatch center monitoring room in real time; the valuating system carries out valuation confirmation and financial settlement for the coaler through a coaler information card to complete sale transaction; the exit system transmits the information of the coaler information card to the server of the dispatch center monitoring room at the outlet; the server of the dispatch center monitoring room transmits a signal of going ahead or not to the entrance taring system and the exit system; and the database saves information of the coaler. The system accurately meters and calculates the coalers.

The invention provides a road traffic noise map updating method based on noise monitoring data. According to the method, noise monitoring and original traffic flow data are utilized, firstly, road section and monitoring point data are organized, and an effective road section set of each monitoring point is constructed; then, local correction is carried out, and the correcting difference value of each road section in the effective road section set of the monitoring points is calculated according to an energy conservation law; next, the local correction result is subjected to interval division; the correction difference value of other uncorrected road sections is determined according to an interval division result; finally, calculation and rendering are carried out, and an updated road traffic noise map is obtained. The road traffic noise map updating method is applied to the updating of the road traffic noise map, the calculation efficiency is high, and the updating effect is good.

The invention aims to further guarantee that the collected bottom mud is not disturbed on the premise of guaranteeing that the bottom mud which is subjected to sequence fidelity is collected. A portable fidelity cylindrical bottom mud sampler mainly comprises a bottom mud collection device and a storage device, wherein the collection device comprises a support, a sampling pipe, a piston, a sampling head, and the like; and the storage device comprises a storage pipe, a storage pipe foundation, a top cover and the like. When the bottom mud is collected, the storage pipe is connected to the lower part of the sampling pipe and is extended into the support; and the piston in the collection device can prevent water from being mixed with the bottom mud and can absorb the bottom mud into the storage pipe and the sampling pipe to ensure that the bottom mud is not distorted. After collection is completed, if the bottom mud is needed to be layered, the piston is pushed to push the bottom mud out for layering; and if the collected bottom mud is needed to be subjected to fidelity further, the sampling pipe can be separated from the storage pipe, and the storage pipe can be stored. The high-efficiency portable fidelity cylindrical sampler is particularly suitable for investigation of pollution characteristics and repair research of the bottom mud of shallow water.

The invention relates to a teaching and training management and assessment improvement system comprising a basic information setting module, an assessment base setting module, a registration management module, a participant management module, an assessment management module, a course management module, a course matching module, a teaching effect evaluation module, an after-sale management module and a statistic window module. The basic information setting module is used for setting the system basic information. The assessment base setting module is used for setting assessment base parameters. The registration management is used for managing relative registration information for participants. The participant management module is used for recording relative base and state information of the participants. The assessment management module is used for managing assessment conditions of the participants. The course management module is used for managing courses for the participants, such as course scheduling and adjusting and leave requests. The course matching module is used for generating teaching suggesting plans and course plans for the participants. The teaching effect evaluation module is used for evaluating the teaching effects of the teachers. The after-sale management module is used for performing participant retest following, participant communicating and feedback recording managements. The statistic window module is used for displaying data of the system in the graph way. The teaching and training management and assessment improvement system is multifunctional and high in automatic degree and allows scientificity, reasonability and professionality of the teaching and training to be improved.

The invention discloses a real-time city emergency evacuation simulating method based on mobile phone data. The method comprises the steps: 1) obtaining geographic information system (GIS) map information by using a GIS map information sub-system; 2) calculating personnel real-time distribution information by using a personnel real-time distribution mining sub-system through the mobile phone data and the information obtained by the GIS map information sub-system; 3) after determining the disaster type, class and affected geographic position, using an affected area judgment sub-system to mark an evacuation site as the evacuation terminal point of all persons; 4) according to the obtained GIS map information, personnel real-time distribution information and disaster area judgment information, calculating a personnel evacuation route and an evacuation scheme of all persons by using an evacuation simulation sub-system. The population dynamic distribution point is obtained by a mobile phone communication data mining method. The method is combined with the city evacuation simulation for obtaining the population situation of whole city before the evacuation. The scientificity and accuracy of the city evacuation simulation are ensured, and the effective basis is provided for the following evacuation scheme.

The invention discloses environment-friendly straw feed manufacturing equipment. The equipment comprises a feeding pipe, a box body, an electric telescopic rod, a camera, a stir-frying knife, a pressing plate, an air blower, a crushing box, a heater, a drying box and a rotary conical roller, wherein the feeding pipe is arranged on the top of the box body, the electric telescopic rod is arranged on the top of the box body, and the pressing plate is arranged at the bottom of the electric telescopic rod; a cutter is arranged on the lower surface of the pressing plate, a rotating shaft is arranged in the box body, and the stir-frying knife is arranged at the bottom of the rotating shaft; a pressure bearing plate is arranged in the box body, a cam is arranged at the bottom of the pressure bearing plate, and a timer is arranged on the outer wall of the box body; the top of the box body is communicated with the air blower, an inclined guide plate is arranged below the pressure bearing plate, and the crushing box is arranged at the outlet end of the inclined guide plate; the bottom of the crushing box is connected with the drying box, and a discharging pipe is arranged at the bottom of the drying box. The equipment guarantees reasonable utilization of straw, straw feed particles can be conveniently stored, the breeding feed cost is reduced, and the equipment is simple in structure, convenient to use and easy to popularize.

The invention provides an emotion monitoring method and system. The method comprises steps as follows: acquiring ECG (electrocardiogram) data, psychological scale data and motion data of a user; monitoring emotions of the user by the aid of an emotion judging model according to the acquired ECG data, psychological scale data and motion data to generate monitoring results of the emotions of the user. The emotion monitoring method and system solve the problem that existing psychological health related products using mobile client terminals are not accurate enough in emotion judgment.

The invention discloses high-tear strength silicone rubber which comprises the following raw materials: 100 parts of methylvinyl crude rubber, 30-60 parts of white carbon black, 4-6 parts of vinyl silicone oil, 0.5-2 parts of hydroxyl silicone oil, 0.5-1 part of vinyltrimethoxy silane and 0.1-0.4 part of demoulding auxiliary. The invention also discloses a preparation method of the high-strength silicone rubber, which comprises the following steps: (1) putting the methylvinyl crude rubber, hydroxyl silicone oil, vinyltrimethoxy silane and a demoulding auxiliary into a kneading machine for kneading; (2) adding the white carbon black in 3-5 batches, mixing into agglomerate, heating and vacuumizing; and (3) cooling to 60-80 DEG C, adding the vinyl silicone oil in 3-5 batches, mixing into agglomerate and discharging and packaging to obtain the high-strength silicone rubber. In the invention, by adding the vinyl silicone oil into the raw materials of the high-strength silicone rubber, the tear strength of silicone rubber is remarkably improved while guaranteeing the hardness, elasticity, heat resistance and tensile strength of the silicone rubber; and the preparation method is simple in process, and the production efficiency is high.

The invention relates to the field of electric power system analysis and control, and particularly discloses an automatic evaluation platform and an automatic evaluation method for power grid equipment status. The automatic evaluation method includes: extracting monitoring data in real time on line; retrieving data which changes; finding out an equipment classification which power grid equipment which changes belongs to according to the data which changes; invoking an evaluation model for evaluating; and grading evaluation results, and proposing an overhaul proposal. The automatic evaluation platform and the automatic evaluation method for the power grid equipment status can comprehensively diagnose equipment insulation status according to various testing information and equipment operation status, provides decision support for fault locating and equipment overhauls, and can efficiently and accurately evaluate the power grid equipment status in real time.

The invention discloses a personal-credit evaluation method of intelligent combination and a system. The method is suitable for use in the system. The system includes a sample data acquisition module,a sample data processing module, a data feature training module, a scoring model construction module and a scoring model test module. The method includes the steps of: S1, acquiring sample data of model training by the sample data acquisition module; S2, dividing samples into a training set I, a training set II and a test set; S3, carrying out feature grouping on the sample data of the training set I, the training set II and the test set; S4, carrying out training on each set of data features, and generating a corresponding trained sub-model by each set of data features; S5, carrying out prediction on the trained sub-models; and S6, testing a finally constructed credit scoring model on the test set by the scoring model test module to evaluate model test effect.

The invention discloses a multi-center medical data structure standardization system based on a general data model. The system comprises a source database, a cache database, a target database, a dataconnection management module, a data structure scanning module, a mapping construction unit, a mapping execution unit, an incremental updating unit and a quality control unit. The source database is adatabase for executing a medical business process by each medical data center. The cache database and the target database are deployed in an exclusive front server of each medical data center. The target database of each medical data center is connected with the cloud server to realize collaborative analysis among the multi-center medical data. The medical data structure mapping relation design process is improved, cooperation between information technicians and medical staff is facilitated, and the working efficiency is improved. An incremental updating mechanism is provided, and the systemoperation efficiency is improved.

The invention discloses an intelligent scheduling decision-making method for flood and drought control based on extreme climate conditions. The intelligent scheduling decision-making method is used inriverside areas and comprises the steps of: step 1) acquiring and collecting various kinds of original data; step 2) preliminarily establishing a virtual reservoir model; step 3) optimizing the virtual reservoir model; step 4) and utilizing a final data model obtained in the step 3) to output various kinds of data to sub-functional modules, thereby achieving the intelligent scheduling decision-making purpose for flood and drought control in the riverside areas under extreme climate conditions. The intelligent scheduling decision-making method can ensure scientificity, precision and reliability of the data, achieves the effects expert early-warning support and decision scheme analysis, can timely respond to the sudden rainstorm process, and immediately starts up a pumping station drainage,not only reduces the water accumulating volume, but also greatly reduce the full-load working process of the pumping station, saves energy and reduces emission, effectively improves the early-warningand handling capacity of flood and drought control in the riverside areas, promotes the improvement of integral level of water resource scheduling management, and has extremely high practicability.

The invention relates to an automatic group optimization system for power battery boxes in EV battery swap stations and an operating method thereof. The system comprises a power battery information real-time processing module, a grouping strategy library configuration module, a battery group information database, and a power battery box group auto-optimization scheduling module, wherein the power battery information real-time processing module is used for acquiring information of a battery box swapped from an EV in real time and transmitting, analyzing and storing the acquired information, the grouping strategy library configuration module is used for providing the power battery box group auto-optimization scheduling module with a grouping strategy configuration entry, the battery group information database is used for receiving query of the power battery box group auto-optimization scheduling module and changes to the power battery group information, and the power battery box group auto-optimization scheduling module is used for receiving a swap command, acquiring a grouping strategy and a calculation priority, and changing existing group information that dissatisfies the grouping strategy according to the demand of the grouping strategy. The system has the advantages that the battery box grouping strategies are reasonably configured, the group information of battery boxes is dynamically adjusted, the problem that a whole battery group stops due to changes of individual performances is solved, and power batteries are more available.

The invention discloses a three-dimensional model testing apparatus capable of simulating water outburst and mud outburst geological disasters. The apparatus comprises a lower supporting rack, an axial pressure loading device, a peripheral pressure loading device, and a model sample part; the peripheral pressure loading device is arranged on the top of the lower supporting rack and is capable of loading a peripheral pressure onto the model sample by filling high-pressure gas or water into the peripheral chamber through a pressure adjusting valve; the model sample part is arranged in the peripheral pressure loading device, an annular water tank is arranged in a movable pressing plate under the model sample part, a water pressure is loaded on the model sample through a water penetrating plate by filling water into the annular water tank; and the axial pressure loading device is arranged in the lower supporting rack, is connected to the sample model part by going through the bottom of the peripheral pressure loading device, and applies an axial pressure on the model sample through an oil cylinder arranged on the lower end of the axial pressure loading device. The provided apparatus has the advantages of simple whole machine structure, good stability, and convenience for carrying out tests, and can precisely simulate the initial environment of a sample and carry out excavate unloading tests. Through a pre-fabricated model sample, the test period is largely shortened, and the test efficiency is improved.

The invention discloses a method and system for evaluating power consumption condition performance of an electric power user. The method comprises the following steps: solving first level index weights subjective weights of second level indexes corresponding to first level indexes by using an improved G1 algorithm; calculating correction weights of the second level indexes by using a modified intuitionistic fuzzy entropy method and the subjective weights; calculating performance evaluation scores of the first level indexes according to the correction weights by using a TOPSIS method based on an intuitionistic fuzzy set; and calculating an estimated value of power consumption condition performance of the electric power user according to the performance evaluation scores and the first level index weights. According to the method, based on the hierarchical comprehensive assessment method, the first level index weights are solved by using the improved G1 algorithm, the second level index weights are calculated by using the modified intuitionistic fuzzy entropy method, twice weighting integration is carried out on the index values of the levels, thereby reducing the influence of single weighting to the performance evaluation result, and expert experience and objective data are combined to reflect the subjective and objective evaluation information, which ensures the validity and the rationality of the performance evaluation.

The invention discloses a planning network data system and a fast intelligent generating method thereof in the technical field of electric industrial application. According to the invention, the generation of a network data model is realized through a current status network data module, a transformer substation intelligent optimization planning module, a transformer substation automatic modeling functional module and a network frame optimization planning module; the working thoughts of power grid planning experts are simulated and a corresponding mathematical model is set up and supplemented by a plurality of advanced intelligent algorithms, so that the scientific property and the accuracy of the formed mathematical model are ensured. According to the fast intelligent generating method, network data can be fast and intelligently generated with seldom manual intervention and a corresponding network model can be automatically set up, so that the work load for planning a power grid is maximally reduced and the procedure for planning is simplified.

The invention relates to a sea cucumber culturing and automatic catching device, and relates to the field of sea cucumber culturing. The device comprises a culturing cage, a catching device, a sunshade device, a cleaner and a feeding device, the upper end of the culturing cage is provided with an opening, the catching device is provided with transverse and longitudinal movement mechanisms, the transverse movement mechanisms are installed symmetrically in the opening of the culturing cage, the longitudinal movement mechanism is fixedly mounted on the transverse movement mechanism, the sunshadedevice comprises a rotation mechanism and a contraction mechanism, the rotation mechanism is installed in the sidewall of the culturing cage, the contraction mechanism is arranged in the tail end of the rotation mechanism, the cleaner is arranged in a position, close to the bottom, in the culturing cage, the feeding device is fixedly mounted in the sidewall of the culturing cage, and the culturingcage is internally provided with attaching bases of semi-cylindrical structures. The sea cucumber culturing and automatic catching device can improve the survival rate of cultured sea cucumbers and can catch the sea cucumbers automatically.

The invention discloses an automotive blower assembly noise test system. An elastic rope which is used for suspending an object to be tested and a bracket which is used for fixing the elastic rope are arranged above a position to be tested. A free-field microphone is arranged near the position to be tested. The free-field microphone outputs an acquired signal to a data acquisition and analyzing device. The data acquisition and analyzing device is connected with the object to be tested through a photoelectric tachometer. The object to be tested and the data acquisition and analyzing device are powered by a direct current voltage stabilizing power supply. The object to be tested is a blower assembly and / or blower motor assembly. According to the test system and a method, which are provided by the invention, under actual work conditions, sound pressure characteristics, time domain, frequency domain and auto-power spectrum characteristics of a specified test point of a blower / blower motor can be acquired; and the noise performance of the blower / blower motor assembly can be scientifically, repeatedly, objectively and comprehensively evaluated.

The invention relates to a method for quickly screening benzedrine drugs and morphine drugs in hair on the spot. The method sequentially comprises the following steps of step 1, placing the hair to be detected, and grinding media together in a grinding tube of a crusher, and performing grinding and pulverizing treatment for the first time in the grinding tube of the crusher; step 2, after the grinding is performed for the first time, adding a solvent to the grinding tube, dissolving the hair in the grinding tube, and performing grinding and pulverizing treatment for the second time in the grinding tube of the crusher; and step 3, taking liquid in the grinding tube after the grinding and pulverizing treatment is performed for the second time, performing detection on a corresponding colloidal gold plate, and displaying a screening result. Through the adoption of the method disclosed by the invention, the simple, convenient, quick and on-the-spot operation of screening the drugs in the hair can be realized; the method is high in specificity, high in selectivity, and high in sensitivity, and can be applied to screening the hair of actual drug addicts, and can be applied to the field of forensic toxicological analysis, and the screening and solving of relevant cases.

The invention relates to the field of meteorological application of electric power systems, in particular to a professional meteorological service application platform based on a power grid GIS. The platform includes a data acquisition and conversion module, a data storage module, a professional service adding module, a professional service module and a page display module; the ideas of modular design and object orientation are adopted, and according to the needs of business expansion, function modules can be flexibly added or modified without affecting original business, so that the system is good in function expansibility; when the current configuration of the system can not meet the function implementation need or the overall performance of the system is reduced, the expansibility can achieve smooth upgrading of the system by adjusting hardware configuration or increasing servers, so that the overall performance of the system is extended. The system can perform equipment model selection and flexible configuration according to the user quantity and the function implementation need and is scientific, rigorous and flexible.

The invention provides a liquor vintage identification method, which comprises the following steps: S1) measuring characteristic trace element contents of liquors with different brands and different storage times, and building a database; S2) taking the trace element contents in the database as characteristic values of training samples, training a vintage identification classifier through methods of machine learning and pattern recognition; S3) measuring the related trace element contents of the liquors to be measured, and building characteristic value vectors; and S4) substituting the characteristic value vectors obtained in the S3, which are subjected to dimension reduction, into the vintage identification classifier in the S2 for calculation, so as to ensure the vintage of the liquors to be measured. According to the invention, the method not only can guarantee scientificity and strictness, but also can improve the precision of the identification results and reduce the sample manufacturing complexity.

The invention provides a small- and medium-sized reservoir dam safety evaluating method based on GRA-BP (grey relational analysis and back propagation) neural network in order to overcome the defects of existing small- and medium-sized reservoir dam safety evaluating technology and method. The method comprises the steps of screening main factors influencing small- and medium-sized reservoir dam safety based on grey relational analysis method, and constructing a small- and medium-sized reservoir dam safety evaluation index system; generating a network training inspection sample; determining topological structure of the BP neural network; setting main training parameters of the BP neural network, initializing network connection weights and thresholds, and setting network training end conditions, error precision and training frequency; correcting the network by using L-M algorithm accumulative network global errors; entering the training and inspection samples to train and inspect the safety evaluating BP neural network, and finally constructing an intelligent dam safety evaluating model based on BP neural network. The method provides the functions such as comprehensive safety evaluation and hidden peril analysis, and is highly scientific, effective and practical.