118 results about "Expert analysis" patented technology

A depolarization waveform classifier based on the Modified lifting line wavelet Transform is described. Overcomes problems in existing rate-based event classifiers. A task for pacemaker/defibrillators is the accurate identification of rhythm categories so correct electrotherapy can be administered. Because some rhythms cause rapid dangerous drop in cardiac output, it's desirable to categorize depolarization waveforms on a beat-to-beat basis to accomplish rhythm classification as rapidly as possible. Although rate based methods of event categorization have served well in implanted devices, these methods suffer in sensitivity and specificity when atrial/ventricular rates are similar. Human experts differentiate rhythms by morphological features of strip chart electrocardiograms. The wavelet transform approximates human expert analysis function because it correlates distinct morphological features at multiple scales. The accuracy of implanted rhythm determination can then be improved by using human-appreciable time domain features enhanced by time scale decomposition of depolarization waveforms.

A security identification system and method for identifying and/or verifying subjects includes analyzing primary biometric data of a subject and comparing it to known biometric data in a database. Primary biometric analysis includes determining whether a match exists with respect to the primary biometric data and, if a match exists, whether the match is a strong match. If the primary match is not a strong match, secondary biometric data is input for the subject. Secondary biometric analysis includes determining whether a match exists with respect to the secondary biometric data and whether the match is a strong match. An indication of whether the subject is cleared is provided based on the primary biometric data and, if collected, the secondary biometric analysis. In further aspects, expert analysis and automatic feedback may also be provided.

The invention provides a system and a method for predicting the coal and gas outburst risk of a mine in real time, which relate to a system and a method for judging mine natural disaster of coal and gas outburst risk degree through combination of artificial intelligence and expert analysis. The system uses a microseismic signal for reflecting the ground stress intensity and the gas outburst quantity for reflecting the gas change as analysis parameters to be combined with the expert experience, and can improve the predicting accuracy of the coal and gas outburst risk to high than 90 percent. The system and the method are characterized in that the system mainly consists of a data collection module, a data transmission module, a real-time data tracking and analysis center and an integrated early warning module, wherein after the data collection module collects underground data, the data is transmitted to the real-time data tracking and analysis center through the data transmission modulefor calculation, analysis and reasoning, and the integrated early warning module gives the early warning when a reasoning result shows that the risk occurs. The invention is applicable to similar mines with the coal and gas outburst risk.

The invention provides an automobile fault diagnosis system based on an Android platform. The automobile fault diagnosis system comprises an ECU and a CAN bus, and further comprises a data conversion module, an automobile fault decoding module and an automobile fault expert analysis module, wherein one end of the data conversion module is connected with the CAN bus, the other end of the data conversion module is connected with a Bluetooth module in a wireless mode, the Bluetooth module is connected with the automobile fault decoding module, and the automobile fault decoding module is connected with the automobile fault expert analysis module. The automobile fault diagnosis system lowers automobile fault diagnosis cost, enables a diagnosis process to be more convenient, and improves automobile maintenance efficiency.

A comprehensive monitoring system for electric power system transformers comprises an IEC61850-based unified modularized CPU (central processing unit) hardware platform, a sensor, a system terminal, at least one of nine monitoring logical devices, and further comprises an expert analysis system, including a thermal management mathematical model and an oil and gas analysis mathematical model, wherein by configuring and starting software, a function for monitoring corresponding LDs (logical device) which are independent of one another is achieved; and by performing independent effective data acquisition on the transformers respectively, and integrating and processing the data by the CPU, the electric power system transformers are comprehensively monitored in a configurable way. The comprehensive monitoring system for the electric power system transformers is convenient and flexible in application; current situations of repeated data acquisition, and shortage of data integration, data processing, information exchange and information sharing are changed; conversion from the conventional mechanism-based timed maintenance to the state-based preventative maintenance is facilitated; the maintenance cost is obviously saved; service lives of the transformers are prolonged; and a customer can obviously reduce the purchase cost and the management cost.

The invention discloses an on-line failure diagnosis, prediction and feedback control method of a small/medium size gas turbine and a device thereof, being used for carrying out on-line analysis on parameters representing running states of the gas turbine. The method comprises the following steps: adopting an artificial neural network (ANN) to analyze the operating characteristics of all working conditions of a gas turbine set; constructing an expert analysis database; adopting a fuzzy logic analysis block and combining a Kalman filtering module for failure isolation; constructing a multi-parameter analysis module to carry out on-line detection on the thermal performance and the running state of the gas turbine set; and finally, outputting the setting values of related control parameter by the on-line analysis on the parameters representing the running states of the gas turbine. A dynamic data processor (DSP) is adopted to cure the analysis means into a chip, and the invention can realize accurate evaluation of the states of parts in the gas turbine, improves the availability of equipment, prolongs time between overhaul, enhances the capability of preventing sudden failures and improves the operation level of the gas turbine on the basis of analysis technologies such as failure category, advanced failure analysis methods, failure experts and the like.

The invention discloses an overhead line intelligent fault positioning processing system and a method thereof. The system mainly comprises a fault indicator, a gatherer, a voltage transformer and a monitoring management platform. An ad-hoc network is formed through the monitoring management platform, the gatherer, the voltage transformer and the fault indicator for data communication and transmission. Through a wireless ad-hoc networking technology, the use of a wireless network of a service provider is unnecessary, and restrictions of a service provider network are eliminated, such that the operation cost is saved, and data security is ensured; at the same time, faults such as single-phase grounding and the like are determined through combination with an expert analysis unit, system functions are enriched, and the accuracy in determining a single-phase grounding fault is substantially improved; and besides, the fault indicator as a major part employs an induction power-drawing technology, the problem of depletion of electric energy does not have to be considered, installation is finished in one step, replacement is unnecessary, the practicality is enhanced, at the same time, since an energy consumption problem is solved, the system provided by the invention can fully exhibit more effects, and the functions are increased.

An investment and financing risk assessment method includes the following steps of step 1, collecting information of a user who applies for investment and financing; step 2, utilizing a risk assessment system to analyze the information of the user who applies for investment and financing and obtaining a preliminary analysis result; step 3, distributing the information to an expert evaluation system according to the preliminary analysis result and proceeding to an expert review to obtain an expert analysis result; step 4, generating a risk assessment report according to the expert analysis result and grading the user who applies for investment and financing to a plurality of grades; and step 5, subjecting the user who meets grade requirements to investment and financing information matching according to the risk assessment report. The investment and financing risk assessment method has the advantages of achieving the further processing of the investment and financing information, encoding the information in a standardization mode, quantifying the critical data such as the integrity risk, subjecting the investment and financing information to the intelligent matchmaking trading through the establishment of certain mathematical models, improving the efficiency of the investment and financing transaction greatly, and reducing the cost of the investment and financing transaction.

The invention discloses an online power cable partial discharge monitoring system based on electromagnetic waves and a high-frequency current transformer (CT). The online power cable partial discharge monitoring system comprises broad frequency band Rogowski coil current mutual inductors which are distributed at respective monitoring positions of a cable, wherein the broad frequency band Rogowski coil current mutual inductors are connected with corresponding signal amplifying modules; the signal amplifying modules are connected with a data acquisition card through transmission optical fibers; and the data acquisition card is connected with a computer with a background expert analysis system. An insulation condition of a power cable is judged in real time and accurately by the combination of an optical fiber communication system and an expert recognition system, so that the effectiveness of the online power distribution cable partial discharge monitoring system is checked; therefore, the safety of a power supply network is improved, accidents of network lines are avoided, the using cost of the network lines is reduced, and the online power cable partial discharge monitoring system is an ideal online partial discharge monitoring device special for monitoring partial discharge of the power cable.

The invention discloses an Ethernet-based power quality on-line monitoring device comprising a power grid 1, a data acquisition sub module 2, a DSP analysis sub module 3, a basic electrical parameter coprocessor 4, an industrial personal computer secondary storage and control sub module 5, and a power quality management platform 6. The DSP analysis sub module 3 mathematically analyzes power grid voltage and current waveform data acquired by the data acquisition sub module 2 to obtain power quality index data, and the DSP analysis sub module 3 reads high-precision basic electrical parameter data obtained by the basic electrical parameter coprocessor 4 and transmits the high-precision basic electrical parameter data and the power quality index data to the industrial personal computer secondary storage and control sub module 5 in real time. The power quality management platform 6 calls data from the industrial personal computer secondary storage and control sub module 5 regularly, periodically or artificially. The power quality management platform 6 mainly completes statistical and expert analysis of harmonics and inter-harmonics, voltage fluctuation and flickering, amplitude-frequency deviation, transient disturbance and other indexes. By adopting the device, power quality can be monitored and analyzed in a real-time and comprehensive manner, especially, harmonics, inter-harmonics, transient disturbance and flickering can be monitored, the accuracy and real-time performance are improved, and the frequency resolution is improved.

The invention belongs to the technical field of hydroelectric power generation equipment, in particular to an on-line monitoring data analysis and evaluation method of a hydroelectric unit. The analysis and evaluation method comprises the following steps: S1, establishing a unit operation characteristic database; S2, establishing the unit state database; S3,performing characteristic parameter dataanalysis; S4, performing characteristic parameter evaluation and diagnosis; S5, performing Fault Matching and Troubleshooting Suggestions. The invention has the advantages of real-time grasping the health state of the unit, and providing powerful technical support for safe operation, optimized scheduling and maintenance guidance. It can also focus on analyzing and evaluating the monitoring information of each unit, and can carry out real-time physical examination on the units in operation state, which is easy to analyze and compare the operating characteristics and rules of different units, to promote the optimal operation of units in time, and to give full play to the role of analysis and diagnosis of experts in the field.

The invention discloses a micro integrated household hospital service platform. The micro integrated household hospital service platform is characterized by comprising a household hospital check platform, a mobile control platform, an information service platform and a logistics dispensing platform. Task requests are initiated by patients through the mobile control platform, body multi-index check is accomplished through the household hospital check platform, the check results are uploaded to the information service platform, through intelligent or online expert analysis, instructions are acquired, and the instructions are fed back to the mobile control platform in real time, through a mobile control platform payment module, renting expensive equipment matched with the platforms, purchasing reagents, purchasing medicines and online expert service charge payment can be realized, and the logistics dispensing platform is used for realizing corresponding dispensing service. The micro integrated household hospital service platform is advantaged in that basic medical check projects can be accomplished in a household mode, deep intervention of doctors and medical equipment of the Internet + Medical is realized, the medicines, the reagents and apparatuses are made to realize convenient circulation, high-quality medical resources are utilized household in a household hospital mode, and integrated household hospital service is provided.

The invention belongs to the technical field of information detection and identification, and particularly relates to a radiation source individual identification method based on multi-domain featurefusion. The radiation source individual identification method can solve the problems of poor classifier generalization ability, strong expert analysis subjectivity, low radiation source individual recognition rate and the like in the existing radiation source individual identification methods, multi-domain features such as a time domain, a time-frequency domain, a high-order domain and the like are fused, and a multi-layer neural network model is designed as a classifier so as to achieve radiation source individual recognition. The multi-domain features are fused to solve the problem that feature information is not comprehensive, a neural network model is adopted for recognition and classification, and the problems that prior information such as a radiation source signal modulation mode isrelied on during recognition, and subjectivity of an expert system is high are solved. Meanwhile, the neural network model improves the generalization capability of the system, and obtains a better radiation source individual recognition effect.

The invention discloses a monitoring defect intelligent auxiliary disposal system based on a big data analysis technology, which comprises a monitoring defect information detection and identificationmodule, a monitoring defect intelligent judgment module, a typical defect signal expert analysis knowledge base, a monitoring defect auxiliary disposal module and a defect disposal situation automatictracking module; wherein the monitoring defect information detection and identification module and the typical defect signal expert analysis knowledge base are connected with the monitoring defect intelligent judgment module, the monitoring defect information detection and identification module transmit defects detection information to the monitoring defect intelligent judgment module, the typical defect signal expert analysis knowledge base exchanges information with the monitoring defect intelligent judgement module, the monitoring defect auxiliary disposal module is connected with the monitoring defect intelligent judgement module, and the defect disposal status automatic tracking module is connected with the monitoring defect auxiliary disposal module. The invention timely finds out and eliminates the unsafe factors affecting the stable operation of the electric power system, eliminates the defects in the budding state, and ensures the safe operation of the electric network.

The invention discloses a lightning activity expert analysis system on the basis of a GIS (geographic information system) technology. The lightning activity expert analysis system comprises a lightning data importing module, a data recalculation module, a lightning parameter statistics module and a display and output module. The lightning data importing module reads lightning sample data from lightning databases; the lightning parameter analysis module analyzes and calculates the verified lightning sample data; analysis results are displayed or outputted by the display and output module. The lightning activity expert analysis system has the advantages that the lightning activity expert analysis system on the basis of the GIS technology is researched and created by the aid of the GIS spatial analysis technology, so that spatial distribution of lightning information can be displayed and analyzed, lightning parameters can be conveniently and quickly analyzed, a full-set scheme can be provided for analyzing statistics samples of the measured data of lightning positioning systems, counting complete regional lightning parameters and counting corridor lightning parameters of power transmission lines, lightning protection design and evaluation platforms are provided for power grids, and powerful decision support can be provided for lightning protection work of the power grids.

The invention discloses an environment interference filtering system based on prison isolation net vibration monitoring and a method thereof. The environment interference filtering system comprises an expert analysis module, a data processing module and vibration monitoring terminals. The vibration monitoring terminals are installed on a prison isolation net at equal intervals and used for collecting vibration data of the isolation net, and then the data is uploaded to the data processing module. The data processing module is used for receiving the data uploaded by the vibration monitoring terminals and calculating the vibration information to practical values, and then the practical values are stored in a database and forwarded to the expert analysis module. According to the invention, the vibration of the isolation net is detected, statistics and analysis are carried out on the monitored vibration data, environment interference is eliminated, and the false alarm rate is lowered.

The method of recognizing fingerprints comprises an analysis step (21) in which an expert analyses characteristic points of a fingerprint image so as to be able to differentiate the fingerprint whose image is presented to him. The method comprises a modification step (19) in which the said print image available with various levels from a grey scale is modified into a second image in which at least one grey range of the first image is parameterized so as to be represented with various levels from a colour scale. The modification makes it possible to identify the characteristic points on an unknown fingerprint image more accurately and also to compare the said image to other known fingerprint images more easily.