144 results about "Fuzzy recognition" patented technology

A copper strip surface defect detection system based on multi-feature fuzzy recognition comprises an encoder module, an image acquisition module, an image processing module, wherein the encoder module is used for obtaining the speed information of the operation of a copper strip and generating a frequency signal; the image acquisition module is used for acquiring the surface color image of the copper strip; and the image processing module is used for carrying out defect detection on the surface color image of the copper strip, wherein the defect detection of the image processing module specifically comprises the following processes of: applying a pre-judgment algorithm, if a defect is included, performing defected image division by a Canny algorithm, extracting the width-length ratio, circularity, squareness and invariant moment characteristics of the defected image and then inputting the extracted characteristic vectors into a multi-feature fuzzy recognition classifier, thereby identifying the type of the defect. By using the system, the identification rate and recognition accuracy of the type of the surface defect of the copper strip are improved, the requirements of enterprises for detecting and storing the surface defect information of the copper strip are met; and simultaneously, the system can be applied to the surface quality detection of other materials.

The invention provides an electrocardiosignal quality evaluation method and device based on high-dimensional fuzzy recognition. The electrocardiosignal quality evaluation method and device can obtain high-dimensional pattern characteristic sets that describe the electrocardiosignal quality from different angles, the high-dimensional pattern characteristic sets comprise a time-domain characteristic subset, a frequency domain characteristic subset, a multi-scale domain characteristic subset and a nonlinear analysis characteristic subset, each subset comprises a plurality of different quantification indexes, and then electrocardiosignals that are described by the high-dimensional pattern characteristic sets are mapped into different characteristic zones through a competing network with fuzzyclustering features, so that the classification of the electrocardiosignal quality level is obtained.

A chatting robot system based on a fuzzy neural network comprises a speech acquisition terminal, a characteristic extracting module, a matching searching module, a fuzzy neural network analysis module, a speech postprocessing module and a speech broadcasting module, wherein the characteristic extracting module is connected with the speech acquisition terminal, the matching searching module is provided with a sound model data base and connected with the characteristic extracting module, the fuzzy neural network analysis module is connected with the matching searching module, the speech broadcasting module is connected with the matching searching module, the speech broadcasting module is connected with the speech postprocessing module, and the fuzzy neural network analysis module is provided with a fuzzy neural network training data base and a knowledge data base. According to the chatting robot system based on the fuzzy neural network and a chatting method, the technologies of fuzzy recognition, pattern matching searching, a artificial neural network and the like are utilized, the fuzzy reasoning process of thinking and speeches of the human brain is simulated, a reply can be made according to contexts and emotion characteristics, and the system has the self-learning ability in different scenarios.

The invention discloses a wireless transmission recording pen and a recording system with application scene recognition control; the wireless transmission recording pen, through detecting a self motion state and surrounding noise environment, and combing with a fuzzy recognition method, can intelligently judge the current application environment of the recording pen, thereby adaptively regulating a self working mode of the wireless transmission recording pen according to the current application environment and parameters such as electric quantity, memory and the like of the recording pen. The wireless transmission recording pen establishes a wireless transmission communication connection with an intelligent mobile terminal, and the intelligent mobile terminal establishes the wireless communication connection with a cloud server, thereby forming the recording system which can transmit audio data recorded by the recording pen to the intelligent mobile terminal and the cloud server in real time or in non-real time. The wireless transmission recording pen and the recording system disclosed by the invention support control command interaction among the wireless transmission recording pen, the intelligent mobile terminal and the cloud server, and further can realize the control on other devices except the recording system by recognizing a voice command; the functions of the traditional recording system can be expanded, the experience of a user is improved, and great convenience is brought to the user.

The invention discloses a combustion monitoring and diagnosis method based on feature extraction and fuzzy C-means cluster, comprising steps of utilizing time-frequency domain analysis and comentropy analysis technology to extract a flame characteristic value reflecting the combustion condition in flame detection signals, utilizing the fuzzy C-means cluster algorithm to perform FCM cluster analysis on the flame characteristic value and calculating a fuzzy combustion index through the fuzzy recognition. The invention can obtain a quantitative value of a combustion state through the fuzzy mode recognition and calculation of the combustion index, can classify the combustion states to realize quantitative monitoring of the combustion state, can promptly and accurately reflect boiler operation performance attributes, can provide new thoughts and methods for optimizing the performance and monitoring the state of the boiler, and can provide a reference model to the advanced modules of the power plant monitoring information system (boiler operation optimization, state monitoring and fault diagnosis).

The invention provides a smart home voice control system based on voice fuzzy recognition technology. The smart home voice control system comprises a sample acquisition module for acquiring a user voice instruction; a sample training module for binding the user voice instruction to a control function; a sample generating module for uploading, to a host system, the control function to be analyzed, saved and recorded, and generating a voice instruction sample set with a calibrated control function; a voice input module for inputting an original voice signal and compressing the original voice signal to generate a voice signal to be uploaded to the host system; and a voice comparison module for comparing the voice signal with the voice instruction sample set and outputting a corresponding control function instruction. A smart home voice control method is also provided. The smart home voice control system and method realize a user voice self-learning control function of a smart home system, realize voice control without prescribing a language and an accent, enable the smart home system to recognize the user, and prevent the voice instruction of invalid user.

The invention discloses method for intelligently recognizing washing clothes and a washing machine. The method includes: using an image intelligent fuzzy recognition device arranged on the washing machine to acquire image information of clothes; acquiring LBP grain data of the clothes according to the image information; and acquiring clothes information according to the LBP grain data of the clothes. The method for intelligently recognizing the washing clothes and the washing machine can directly recognize materials of the clothes through surfaces of the clothes, can use the image intelligentfuzzy recognition device arranged on the washing machine to acquire image information of the clothes and clothes identification information, can acquire the clothes information through multiple ways,can reduce the cost of acquisition of the clothes information, and can improve the accuracy of the acquired clothes information.

The invention discloses a Chinese speech recognition system which comprises a speech data reception unit, a digital to analog conversion unit, a speech data recognition unit and a business flow control unit in sequence, wherein, the speech data recognition unit comprises a speech database, a similar sound recognition module, and a fuzzy recognition module; the business flow control unit is used for controlling business flow according to the received speech information from the speech data recognition unit. The system effectively improves Chinese speech recognition rate by the development of speech recognition technology, such as 'key word recognition system', 'nickname, synonym and parasynonyms recognition', and 'fuzzy recognition', etc.

The invention relates to a high-efficient voice instruction recognition method based on a fuzzy theory and an expert system, which mainly comprises the following steps of: A. establishing a flight knowledge base and an instruction library; B. performing fuzzy voice recognition; and C. performing reasoning judgment on voice by using a voice recognition expert system to obtain instructions. Proved by practices, by the application of the high-efficient voice instruction recognition method based on the fuzzy theory and the expert system disclosed in the invention, ten voice instructions which are mostly close to a training template are recognized through fuzzy recognition, and then the expert system is used for reasoning and judging the ten instructions one by one from the instruction mostly close to the training template to exclude unreasonable voice instructions and finally find out the instruction mostly suitable to the practice, and thus the voice recognition rate reaches more than 99 percent. Moreover, the system real-time property can be realized; the requirements of flight simulation training are met; and good training effect is achieved.

The invention relates to a CMS object-oriented artificial intelligence information secrecy system. A corresponding accurate secrecy relationship between information and an access object is established to eliminate defects of ''rigid uniformity and one lock'' of a conventional secrecy method. The system performs fuzzy recognition and automatic judgment in three aspects of the information, the access object and the secrecy relationship. Functions of automatic sensing, information acquisition, information recognition, object recognition, signal conditioning, characteristic extraction, fuzzy recognition function definition, membership degree definition, threshold definition, learning training, genetic correction, new person recognition learning, new information recognition, secrecy relationship editing, result processing and the like are set in AI access object recognition, AI information recognition and AI secrecy relationship recognition. The system is suitable for personal privacy protection, is especially suitable for application to VR/AR/MR (Virtual Reality/Augmented Reality/Mix reality) and mobile phones, and is suitable for security mobile storage and instant messaging products.

The invention relates to a fault diagnosis method and system for a speed change gearbox of a wind turbine. The method includes determining a fault mode corresponding to an abnormal state of a speed change gearbox to be identified that is acquired based on a pre-established multivariate fuzzy recognition model; wherein the pre-established multivariate fuzzy recognition model includes a wind turbinespeed change gearbox failure mode set, a fault symptom feature value library and a standard multivariate fuzzy symptom set. According to the fault diagnosis method and system, a vibration mechanism of each component of a speed change gearbox system is fully considered, multiple monitoring parameters are fused, and the multivariate fuzzy recognition model is established to achieve accurate diagnosis of the wind turbine speed change gearbox.

The invention discloses a driving style layered fuzzy recognition system based on a recognition coefficient. The driving style layered fuzzy recognition system comprises a data obtaining module, a recognition coefficient solving module and a recognition module; the data obtaining module obtains vehicle real-time traveling data, in the recognition coefficient solving module, a vehicle impact function is defined through the vehicle speed, and then the driving style recognition coefficient is defined through standard difference of a vehicle impact degree and a power demand coefficient; and in the recognition module, first layer of fuzzy control takes an acceleration pedal change rate mean value and a braking pedal change rate mean value as input variables and takes the fuzz impact degree as an output variable, second layer of fuzzy control takes the impact degree difference and the driving style recognition coefficient as an input variable and takes stability, radical degree and the caution degree as an output variable, and thus the driving style is classified and recognized. According to the driving style layered fuzzy recognition system, the power demand is considered when the driving style recognition coefficient is defined, the concept of the impact degree difference is introduced to establish a double-layer fuzzy control rule, and the driving style recognition precision is improved.

The invention discloses a double normalization recognition method for directly forecasting and recognizing a transformer winding fault type, and relates to a novel method for directly forecasting and recognizing the transformer winding fault type based on a hidden markov model and fuzzy recognition. The method comprises the following steps of: step 1, establishing a databank about various mechanical types of transformer windings; step 2, establishing a fuzzy recognition bank, and providing membership degrees and recognition accuracy of each type of fault; step 3, establishing a hidden markov model recognition bank, providing a similar probability and recognition accuracy of each fault recognition; step 4, obtaining a weighting parameter through a hidden markov model recognition probability value; step 5, determining a weighting parameter of the hidden markov model and fuzzy recognition; step 6, obtaining a double normalization recognition index for recognizing the transformer winding fault; and step 7, directly recognizing the state and type of the transformer winding fault through the calculated dg recognition index. The method cannot be influenced by anthropic factors, is strong in environment interference resistance and has no errors caused by obtained conversion.

The invention discloses a nondestructive detection archaeology method, which comprises gathering geographic information data and geophysical prospecting property value of archaeological sites through a plurality of nondestructive detection technologies, dividing the geophysical prospecting property value of detection points into different data range segments to mark different colors, generating a drawing layer by interpolation, creating corresponding drawing layers with different detection methods in order, preserving the created drawing layers to a database, analyzing detection points in a same drawing layer, and a detection point whose property value exceeds the reservation normal range is an abnormal point, stacking the selected drawing layers and then outputting according to the selection of a user, getting the geographical position and the contour of the archaeological site by the image processing and the fuzzy recognition. By analyzing and replicating the gathered data of a plurality of archaeology methods, the method generates an intuitive chart, which can realize delineation and the definition of abnormality of cultural relics accurately through the comparing and analyzing of the detection data, and can represent the burying situation of the underground cultural relics without disinterring the archaeological sites, thereby establishing a base for the restoration of the archaeological sites and the protection of the cultural relic.

The invention relates to a number analysis method and system with a fuzzy recognition function. A number multi-way tree supporting wildcard characters is utilized. The method includes initializing every parameter to be an invalid value; matching every digit of a number string to be analyzed with every sub-layer of the number multi-way tree sequentially; returning to the previous sub-layer with the wildcard characters when encountering a node which is unable to be matched with and changing into the wildcard characters for re-matching; and analyzing the matched numbers until the leaf node or the last digit and subjecting the numbers to subsequent processing according to matching results. The number analysis method with the fuzzy recognition function solves the technical problem of the analysis of fuzzy numbers with uncertain start digit positions or middle digit positions, and the practicability of the number analysis method is improved.

The invention discloses an encoding system and method as well as a decoding system and method of an intelligent graph recognition two-dimension code. The intelligent graph code generated by the encoding system is identical with the color of a picture to form a color matrix which is merged to one edge, two edges or more edges of the picture, and fuzzy recognition can be carried out to form an intelligent graph recognition two-dimension code system which can be recognized through a pattern manner. According to the encoding/decoding systems and methods of the intelligent graph recognition two-dimension code, different colors (such as two colors, three colors and 8 colors) can be combined, and can be combined with patterns or presented in a graph manner; the data amount represented by the two-dimension code can be improved in a same area; a color setting area is set, the color amount and the color mode used during the encoding can be recognized through recognizing the data of the color setting area, and recognition is carried out through the color mode, so that the efficiency and correctness of the decoding of the two-dimension code can be improved.

The present invention discloses a voice controllable song-on-demand system and an operating process thereof. The voice controllable song-on-demand system comprises a client server and a remote server, wherein the remote server comprises a voice recognition module, a voice command database, and a song database, the client server has a fuzzy recognition module and external processing modules such as a TV module, a smart phone, a flat computer. When a user powers on a voice command function of the voice controllable song-on-demand system, the user only needs to input cognizable characters or character codes in a voice way in cooperation with displayed song-on-demand frame information, step process for requesting a song can be carried out easily, in addition, the song-on-demand frame is concise and clear, and the command is easily understood, thus the user can request the song without memorizing the command to be input, leaving the seat or borrowing a massive song requesting book, thereby raising convenience during song requesting.

The invention belongs to the field of combustion flame image processing technology and particularly relates to a combustion stability discrimination method based on a combustion mixing coefficient and fuzzy recognition. According to the method, first, a combustion flame image is subjected to feature extraction, the combustion mixing coefficient, combustion mixing coefficient fluctuation parameters, black dragon length and black dragon length fluctuation parameters are calculated, the combustion mixing coefficient, the combustion mixing coefficient fluctuation parameters, the black dragon length and the black dragon length fluctuation parameters serve as feature indexes, the close degree between a to-be-detected fuzzy set and a stable fuzzy set and the close degree between the to-be-detected fuzzy set and an instable fuzzy set are calculated by selecting a subordinating degree function corresponding to the feature indexes, combustion stability is discriminated according to the principle of closeness optimization, and accordingly the combustion stability discrimination method based on fuzzy recognition is established. Through the method, the influence of the combustion mixing coefficient on combustion stability is fully considered, good flame combustion stability recognition capability is achieved, combustion stability and instability can be correctly distinguished, and accuracy is high.