16 results about "Fuzzy identification" patented technology

The invention relates to the technical field of defect detection, in particular to a mold defect detection method and system based on an image recognition technology. The method comprises the following steps: acquiring a parting surface image of a target mold; performing region segmentation on the parting surface image to generate parting surface contour data; identifying a mold closing gap of the parting surface contour data, and generating a parting surface gap distribution diagram; an ejection mechanism of the mold is positioned based on the parting surface gap distribution diagram, and position coordinates of the ejection mechanism are obtained; controlling an image acquisition device to shoot a local area of the ejection mechanism according to the position coordinates of the ejection mechanism to obtain a local high-definition image of the ejection mechanism; performing ejector pin assembly segmentation on the local high-definition image of the ejection mechanism, identifying the contour of an ejector pin positioning plate and extracting coordinates of a mounting hole; according to the method, high-precision identification and cause analysis of mold defects are realized through precise positioning, refined defect classification and process simulation, and the defects of inaccurate positioning, fuzzy identification and lack of dynamic adaptation in traditional detection are overcome.

The invention is suitable for the technical field of intelligent traffic driving behavior analysis, and provides a driving style identification method, device and equipment, and the method comprises the steps: obtaining the current driving data and current scene information of a current vehicle; according to the current scene information, a first driving style rule base in the driving style fuzzy recognition system is adjusted to obtain a second driving style rule base, and the first driving style rule base is obtained by simplifying a pre-constructed initial driving style rule base; the second driving style rule base comprises a plurality of second driving style rules, carrying out matching calculation on the current driving data and each second driving style rule to obtain the matching rule strength of each second driving style rule, and according to the matching rule strength of all the second driving style rules and the current vehicle, determining the current driving style of the vehicle. And determining the current driving style of the driver. According to the invention, the technical problems of low identification accuracy and insufficient dynamic adaptability of the driving style of the driver in the prior art can be solved.

The application relates to a robot control method and device, a storage medium, a computer program product and a substation operation auxiliary robot. The method comprises the following steps: in response to a user's information input operation, a target control signal is acquired; the target control signal is input to an instruction fuzzy identification model to obtain the membership degree of the target control signal relative to each candidate instruction fuzzy category; the candidate instruction fuzzy category corresponding to the maximum membership degree is taken as a target instruction category corresponding to the target control signal; and an operation matched with a target instruction signal corresponding to the target instruction category is executed. The method can improve the intelligence of human-computer interaction in the robot inspection process.

The present application relates to the technical field of robot navigation, and more particularly to an intelligent navigation method for a robot, in which the image of an obstacle in the running track of the robot is acquired in real time, the image is preprocessed, the motion feature is extracted and the motion type is classified, the problem of fuzzy identification of irregular obstacles in the traditional method is solved, and the error decision caused by misjudgment of the obstacle type is avoided, the application adopts differentiated judgment logic for different motion type obstacles: for regular motion obstacles, the passing mode is determined by comprehensively considering the relative motion distance and the difficulty of detouring, so as to avoid excessive conservatism, on the other hand, for irregular motion obstacles, the running uncertainty representation value is introduced to quantify the motion confusion degree, and the real-time relative distance judgment is combined to ensure the safety of detouring, so as to prevent the efficiency from being reduced due to excessive avoidance of low-risk obstacles, and also avoid collision caused by forcibly detouring high-risk obstacles.

The invention relates to the technical field of intelligent adjustment of audio equipment, and discloses a system for automatically adjusting loudspeaker volume and sound effect according to wind sound volume, which comprises a wind noise acquisition module, an audio processing module, a main control module and a loudspeaker module, and is characterized in that the modules are sequentially in signal transmission connection. The loudspeaker volume and the sound effect type are dynamically adjusted according to the wind noise level, the wind noise is not counteracted to retain environment sound perception, and the problems that an existing noise reduction scheme is not real, influences safety and is not adaptive to the wind noise adjustment sound effect are solved. According to the invention, the wind noise acquisition module adopts a loudspeaker periphery distributed microphone layout, and captures a wind noise and environmental noise mixed signal near a loudspeaker at 360 degrees, thereby avoiding irrelevant noise interference; the audio processing module separates and recognizes the wind noise through a special DSP algorithm, and accurately judges the wind noise level by combining with the comparison of a wind noise feature database, thereby providing a reliable basis for adjustment, and overcoming the defects of inaccurate collection and fuzzy recognition of traditional equipment.

The invention belongs to the technical field of sensors, and discloses a seat self-adaptive system sensor which is characterized in that when an upper-layer film semi-finished product or a lower-layer film semi-finished product generates elastic deformation, output end wires corresponding to the upper-layer film semi-finished product and the lower-layer film semi-finished product are in a loop state; the upper-layer film semi-finished product and the lower-layer film semi-finished product respectively have quantitative resistance values which are reduced along with the increase of the mutual contact area of the upper-layer film semi-finished product and the lower-layer film semi-finished product, and data are transmitted to an external controller. The induction contacts are relatively independent, the creep phenomenon of continuous resistance change under constant external force can be eliminated through the exhaust hole layer, and accurate data can be rapidly and stably output; a flexible circuit structure is adopted and is flexibly laid in each area according to the shape of the seat. The problems of fuzzy recognition, coverage limitation, crosstalk, serious creep and the like of existing similar sensors can be effectively solved, and the use experience with higher science and technology and comfort is brought to users.

The present invention discloses a method, system, and storage medium for controlling an amphibious vehicle to escape from distress. The method is applied to the technical field of amphibious equipment and can improve the amphibious vehicle's ability to pass through when its tires are stuck, thereby enabling the amphibious vehicle to escape from distress smoothly and quickly. The method comprises: obtaining first motion data of the amphibious vehicle; calculating wheel slip based on the first motion data, and fuzzifying the slip fuzzy data to obtain slip fuzzy data; obtaining second motion data of the amphibious vehicle; calculating wheel vertical load based on the second motion data; calculating load deviation based on the wheel vertical load, and fuzzifying the load deviation fuzzy data; obtaining wheel suspension rate of the amphibious vehicle, and fuzzifying the load deviation fuzzy data to obtain suspension rate fuzzy data; determining the wheel stuck state through fuzzy identification based on the slip fuzzy data, the load deviation fuzzy data, and the suspension rate fuzzy data; and performing preset control and adjustment on the amphibious vehicle according to the wheel stuck state using preset fuzzy control rules.

The invention provides a method for identifying a hail storm through radar data, and the method comprises the following steps: S1, identifying a storm monomer: employing a storm unit identification algorithm, and identifying the storm monomer from radar base data through a preset threshold value; s2, parameter characteristics are calculated, wherein multiple parameters of the storm monomers are calculated; s3, performing probability density statistics: performing probability density statistics on the multiple parameters obtained through calculation; and S4, fuzzy recognition: according to the probability density of the multiple parameters, performing fuzzy judgment by adopting a fuzzy recognition method. The method is convenient to realize through a high-level computer language algorithm, can effectively reduce the labor intensity of front-line business personnel for analysis, improves the timeliness, avoids the interference of subjective factors of the personnel, and improves the accuracy.

This application provides a method for generating household robot actions based on ChatGPT interaction and ontology knowledge. It uses ChatGPT's natural language processing capabilities to infer the task target state. Through the provided hybrid reasoning and verification mechanism, the household robot can still quickly complete accurate target instance reasoning in complex household scenarios, solving the problem of target instance inability to identify or fuzzy identification in traditional methods; and can independently construct a small and high-precision ontology knowledge base to guide task planning and execution based on the task to be performed. It improves the efficiency of household robots in utilizing prior knowledge and the intelligence level of the robot itself. This application also provides a household robot action generation system based on ChatGPT interaction and ontology knowledge.

The application discloses a kind of weak stratum receding type section grouting intelligent fuzzy identification and control method and system, comprising the following steps: in the process of grouting, real-time acquisition grouting pressure, grouting flow and pull tube displacement data;According to fixed section length, the grouting process is divided, and the grouting parameters of each section are calculated;With grouting parameters as features, a three-level fuzzy inference system is used to identify weak strata;According to the identification result, the grouting parameters are adjusted adaptively, and the grouting is continued until the standard condition is reached;After grouting is completed, a three-level grouting effect evaluation system of point, line and body is constructed to evaluate the grouting effect.The application realizes real-time acquisition of grouting parameters, combined with hierarchical fuzzy judgment, to identify the weak characteristics of strata and the grouting state in real time, and uses the identification result as a closed-loop control decision, to adaptively optimize the section grouting parameters during construction, and to ensure stable and reliable reinforcement effect.Through the evaluation system, the improvement effect of single point, single tube and overall strata is graded.

This invention provides a method and system for fusion of ore and rock attributes in implicit modeling of polymetallic ore bodies. The method includes: collecting multi-source heterogeneous data of complex polymetallic associated ore deposits and preprocessing the multi-source heterogeneous data; constructing an ore and rock type classification model based on a random forest algorithm; inputting the preprocessed multi-source heterogeneous data into the pre-trained ore and rock type classification model; calculating the Gini importance index of each attribute data in the multi-source heterogeneous data; identifying attribute data with a Gini importance index greater than a first threshold as core attribute data; inputting the core attribute data into a pre-trained fusion network to obtain a comprehensive ore and rock evaluation index; using a fuzzy C-means clustering algorithm to perform three-dimensional spatial clustering of the comprehensive ore and rock evaluation index, outputting spatial confidence scores, and determining ore and rock transition zones based on the spatial confidence scores. This invention enables high-precision fusion of multi-source heterogeneous data and fuzzy identification and confidence quantification of ore and rock transition zones.

The present invention discloses a method, system and device for secure transmission of fingerprint identification data, which relate to the technical field of data transmission. The method comprises analyzing real-time fingerprint identification data to obtain a key identification area and a fuzzy identification area; then encrypting the fingerprint identification data, and setting an encryption code based on the key identification area and the fuzzy identification area; finally, transmitting the fingerprint identification data based on the encryption code, and setting an interference code during the data transmission process. The present invention is used to solve the problem in the existing improvements for secure transmission of fingerprint identification data, in which the encryption method is relatively traditional, resulting in that the encryption by only obtaining a dynamic password through a random number is easy to be cracked, thereby causing a security risk in the transmission of fingerprint identification data.

The application discloses a multi-channel drug fuzzy identification method and system based on surface-enhanced Raman spectroscopy. The method comprises the following steps: acquiring surface-enhanced Raman spectroscopy sequences of N sampling points of a sample to be measured; inputting the N surface-enhanced Raman spectroscopy sequences into N independent channel input ends of a trained CNN-GRU deep learning model respectively, and inputting the N surface-enhanced Raman spectroscopy sequences into a centralized channel input end of the trained CNN-GRU deep learning model; and the CNN-GRU deep learning model outputs a drug category or a drug category and a drug concentration grade. The CNN-GRU deep learning model introduces CNN and GRU into the analysis of Raman spectroscopy data features, so as to completely extract the detailed features and spatial correlation in the spectrum and be used for judging the drug type, can realize the rapid, simultaneous and high-accuracy identification of multiple drug types, and can also accurately quantitatively identify the concentration of the drug.

The application discloses a tower crane bolt axial force intelligent ultrasonic detection method and system based on multi-modal data fusion. First, a multi-level influence factor system is constructed based on fuzzy hierarchy comprehensive evaluation theory, and a high-risk area identification model is established. Based on the model, the regional risk value is calculated, and the monitoring distribution scheme is determined. In the selected area, a heterogeneous network composed of fiber Bragg grating strain sensors and ultrasonic sensors is arranged, and strain and ultrasonic data are synchronously collected. The multi-modal data are input into a deep belief network for feature fusion, and dynamic evaluation of the health state is realized through a fuzzy recognition model. Based on the dynamic grading evaluation result, an improved rain flow counting method and cumulative damage theory are used for fatigue life prediction. Finally, data fusion display and intelligent early warning are realized through a remote monitoring platform. The application realizes intelligent health management of the whole chain from risk identification, real-time monitoring to life prediction.

The invention relates to the technical field of printed circuit boards, in particular to an AI statistical method, device and equipment for printed circuit board assembly process parameters, and the method comprises the steps: converting a received original bill of materials into a target format text with semantic information reserved by using a document conversion service; identifying metadata in the target format text by using an AI semantic understanding and reasoning model, positioning the position of effective data corresponding to the metadata, obtaining the effective data based on position identification, and storing the effective data to a structured standard file based on semantic mapping; on the basis of the structured standard file and the pin calculation rule template, performing fuzzy recognition by using an AI semantic understanding and reasoning model, and calculating to obtain welding pin data; and calculating mounting point data based on the welding pin data and the mounting process rule base. Therefore, the problems that in the prior art, a technological parameter calculation method is low in applicability, BOM file content recognition accuracy is low, and parameter calculation accuracy is low can be effectively solved.

The invention discloses an excavator complete machine control system based on machine vision and an excavator, the excavator complete machine control system comprises an AI camera and a vehicle control unit, and the AI camera and the vehicle control unit interact through a CAN bus; the AI camera is used for acquiring an operation image, the operation image is identified through an image processor embedded in the AI camera to obtain a working condition and an action, and the AI camera sends the obtained working condition and action to the vehicle control unit through a CAN bus; and matching data are pre-stored in the vehicle control unit, and the matching data are called according to the received current working condition and action and parameter adjustment is carried out. Compared with traditional pump pressure recognition, the method has the advantages that action response delay can be reduced, secondary operation caused by weak excavation is avoided, similar actions can be effectively distinguished through fuzzy recognition, the parameter matching rate is increased, and oil consumption waste or action abnormity is avoided.