18results about How to "High-precision identification" patented technology

The invention discloses a multi-task electromagnetic model based on a hybrid expert network, and belongs to a wireless communication technology. The model comprises a preprocessing module, a feature extraction module, a task output module and a pre-training-fine tuning learning strategy. The preprocessing module carries out standardization processing on the multi-source electromagnetic signals; the feature extraction module is based on a Transform structure, introduces a hybrid expert network to replace part of a traditional feedforward neural network, and dynamically selects an expert sub-network through a task specific routing mechanism; the task output module configures a special structure according to different task targets; in the pre-training stage, a mask auto-encoder is used for pre-training large-scale label-free data, and a downstream task is subjected to full-amount fine adjustment through small-scale label data. According to the method, multi-task collaborative learning and differential expression are realized, and the recognition performance, robustness and processing efficiency of the model in a complex electromagnetic environment are improved.

The utility model discloses a flour conveying adjusting device which comprises a machine frame, a control unit, an auger conveying device and a material pipe, a sealing plate is arranged at the connecting position of the auger conveying device and the material pipe, and the sealing plate is connected with the end of the corresponding auger conveying device through an elastic reset assembly. A material level sensor is arranged in the end, corresponding to the material pipe, of the auger conveying device, and a displacement sensor is arranged on the outer side wall of the auger conveying device. And the accurate recognition capability of the blockage and the sensitivity of monitoring and early warning are improved.

The application belongs to the technical field of vehicle information anonymization detection, and particularly relates to a multi-type image anonymization annotation dataset construction and target coverage rate determination method. The method is based on a face and license plate image dataset with double annotation of theoretical anonymization region and anonymization features, introduces an anonymization feature extraction branch in an improved YOLOv5-L model and performs cross-modal feature fusion, combines a plurality of loss functions with theoretical anonymization region positioning loss as the core and a two-stage progressive training and difficult example mining mechanism, and realizes precise learning of the anonymization features. After normalizing the input anonymization image, the model inference obtains the theoretical anonymization region coordinates and maps them back to the original size, and through non-maximum suppression and matching of the IoU threshold, the region coverage rate is calculated to determine the positive detection, missed detection and statistical false detection rate. The application effectively overcomes the feature dependency failure and model robustness problem, and realizes high-precision, low-misjudgment anonymization detection and evaluation under various anonymization conditions.

The application discloses a method for identifying large-area fresh water and salt water lake types, which comprises the following steps: binarizing lakes according to the measured salt and fresh water types of the lakes; obtaining attribute data within a research area range; extracting time series values of attribute data of each lake basin within the research area range, and calculating the average value of each attribute data; counting the attribute differences between salt water and fresh water lakes, and selecting the attribute with significant difference as a key attribute; for each key attribute, searching for an optimal segmentation threshold of salt water and fresh water lakes within the value range of the key attribute; taking the optimal identification precision of each key attribute as a weight, and taking the salt and fresh water type identification result of each key attribute under the optimal segmentation threshold as a value to perform weighted average calculation, rounding off the weighted average calculation result, and identifying salt water and fresh water lakes according to the final calculation result. The application can realize high-precision identification of salt and fresh water lakes in a large area.

The invention discloses a subsynchronous harmonic compensation method and device of a power system. The method comprises the following steps: acquiring a real-time load current signal; based on a preset first window function, performing windowing processing on the real-time load current signal to obtain a first windowing current signal; carrying out peak detection on the first windowed current signal in a preset frequency range to obtain respective frequencies, amplitudes and phases of a plurality of subsynchronous harmonics; judging whether to maintain a first window function based on the frequencies and amplitudes of the plurality of subsynchronous harmonics; based on the respective frequencies, amplitudes and phases of the plurality of subsynchronous harmonics, sine wave signals corresponding to the plurality of subsynchronous harmonics are generated; and compensating the real-time load current signal through a unified power quality regulator based on the sine wave signals corresponding to the plurality of subsynchronous harmonics. According to the invention, the technical problems of low subsynchronous harmonic detection precision and weak separation capability of the existing unified power quality conditioner are solved.

The utility model provides a kind of jacking rotary code scanning device, it is related to battery production technical field.Jacking rotary code scanning device includes first driving part, mounting piece, transmission part and second driving part.The output end of first driving part is connected with mounting piece, for driving mounting piece to lift, the number of transmission part is multiple, multiple transmission parts are movably arranged in mounting piece and are sequentially transmission connection, the output end of second driving part is connected with any one transmission part, for driving multiple transmission parts to rotate, transmission part is used to drive battery to rotate, to this is conducive to identification mechanism accurate identification battery, and by driving battery to rotate can effectively avoid the problem that identification mechanism cannot be identified due to battery surface reflection light influence identification mechanism cannot be identified.Obviously, the jacking rotary code scanning device provided by the utility model embodiment is high in degree of automation, and significantly improves identification success rate and production efficiency.

This invention relates to the field of spectral analysis and identification of genuine and counterfeit Chinese medicinal materials, and discloses a method for identifying counterfeit Cordyceps sinensis based on multispectral fusion. This method first collects multispectral image data of samples under standard conditions; eliminates equipment and environmental noise through standardized preprocessing to establish a reliable data foundation; then, it fuses extracted spectral derivative features and spatial texture features to construct a lightweight neural network identification model. Its core innovation lies in introducing a physical interference stripping model, which can actively correct spectral distortion caused by moisture and mold, obtaining intrinsic spectra to improve model robustness; and through dynamic verification and incremental learning mechanisms, the model can continuously evolve, effectively identifying new counterfeiting methods. Finally, the entire model is integrated into a multispectral portable terminal, achieving rapid screening within seconds and outputting a complete report including authenticity determination, type inference, and confidence level. Ultimately, this solves the industry problems of low efficiency, reliance on experience, and inability to be applied on-site by traditional methods.

The application provides a method for secondary inspection of an agricultural tillage vehicle when avoiding obstacles, and belongs to the technical field of agricultural intelligent equipment. The method comprises a core control and decision system, an environment perception system, an execution system, a power system, a communication and monitoring system, and a safety and self-checking system. The core control and decision system is used for overall planning of the collaborative operation of various systems. The safety and self-checking system is used for ensuring operation safety and equipment stability. The safety and self-checking system performs secondary inspection based on a multi-modal sensing fusion system to ensure operation safety and equipment stability of the tillage vehicle. The multi-modal sensing fusion system realizes secondary inspection through data preprocessing and trust degree mobilization, key parameter checking and trust degree improvement, redundant data elimination, and conflict analysis and result integration. The application realizes secondary inspection of obstacles and controls the obstacles within 30 ms, effectively improves the accurate identification of obstacles by the agricultural tillage vehicle, and improves the tillage efficiency of the agricultural tillage vehicle.

The invention discloses a vehicle active splash-proof control method and device and a vehicle, and relates to the technical field of vehicle control. The method comprises the steps of obtaining road information of a first road section and information of traffic participants through multi-sensor fusion and cloud collaboration, determining a road ponding type according to the road information, determining a vehicle target control quantity according to the distance and the relative speed between a vehicle and the traffic participants based on different conditions of small-range ponding or large-range ponding, and determining a vehicle target control quantity according to the vehicle target control quantity. And finally, the suspension height and the vehicle speed of the vehicle are controlled according to the target control quantity, the driving experience is guaranteed, meanwhile, water is actively prevented from being splashed to pedestrians, and the accuracy of avoiding pedestrians or non-motor vehicles is improved.

The present invention provides: an input section that inputs scene information indicating a state of a prescribed scene in a container that stores objects; a processing section that sorts objects present in the container by size based on the scene information input by the input section, and performs processing that detects objects of a size that is not permitted to be stored in the container based on the number of objects of each size that are sorted; and an output section that outputs a result of the processing performed by the processing section.

The application relates to the technical field of construction inspection, and discloses a highway construction inspection optimization method based on artificial intelligence, which comprises the following steps: a boundary identification model is used to identify pit boundary pixels in a construction ground image, the pit boundary pixels are mapped to a highway construction site, and an area surrounded by the mapping positions of the pit boundary pixels is regarded as a pit; disparity information of the pit is calculated based on a left view and a right view of the pit, a stereo matching algorithm is used to estimate the depth and width of the pit, and the depth and width of the pit are obtained; a safety risk value of a discrete grid is generated based on pit information of the pit in the discrete grid, and secondary inspection is carried out on the discrete grid with a safety risk value higher than an allowable risk. The pit depth, width and area are obtained through the stereo matching algorithm, the safety risk value of the discrete grid is generated in combination with the pit information, precise secondary inspection of the high-risk discrete grid is realized, and fine safety management of the highway construction is realized.

The invention discloses a Boost converter physical information identification method, and belongs to the crossing field of power electronics and artificial intelligence. Aiming at the problems of discontinuous current, differential coupling and parasitic parameter identification caused by non-minimum phase characteristics of a Boost converter, the invention provides a physical information neural network architecture fusing a switch modulation impedance network and a time sequence adaptive mask. A nonlinear state space model is constructed, and a coupling relation between a capacitor equivalent series resistor and a load is embedded by adopting an algebraic method, so that differential item nesting is eliminated, and the numerical stability is improved; meanwhile, a time sequence index mask layer is designed, automatic decoupling and joint identification of global inherent parameters and multi-section local load parameters are achieved in single training, and multi-working-condition online parameter updating is supported. According to the method, a whole set of circuit parameters including parasitic resistance can be identified from sparse sampling data with high precision, and support is provided for predictive maintenance of a power electronic system.

The invention discloses an X-ray-based pickled kohlrabi defect detection method, which comprises the following steps of: firstly, constructing a three-dimensional database as a basic data support for attenuation compensation calculation; accurate gray value correction is performed on the collected X-ray original image, and the gray difference between the foreign matter and the vegetable body is highlighted; adaptive filtering, edge enhancement and threshold segmentation processing are sequentially carried out on the compensated image, 12-dimensional feature parameters of a target area are extracted, a convolutional neural network model is adopted, the 12-dimensional feature parameters serve as input, and accurate classification and recognition are carried out on internal defects through deep feature learning of a convolutional layer, a pooling layer and a full connection layer. Through cooperation of the X-ray source and the image acquisition module and combination of a salted vegetable body attenuation compensation algorithm, accurate identification of metal foreign matters, glass, plastics and other nonmetal foreign matters is improved, detection sensitivity is greatly improved, foreign matter and defect characteristics are clearly highlighted, and industrial high-precision detection requirements are met.

The invention belongs to the technical field of environment monitoring and the Internet of Things, and particularly relates to a multi-source water quality abnormity early warning and automatic sample reserving system and method based on the Internet of Things. The system comprises a multi-source water quality sensing array, an edge computing gateway, an intelligent sample reserving control unit, an Internet of Things communication module and a cloud platform. Through multi-source parameter fusion, a dynamic baseline adaptive threshold, correlation coupling judgment and a grading early warning mechanism, the false alarm and missing alarm rate is effectively reduced; when advanced early warning is triggered, the sample reserving device is synchronously driven to complete water sample collection and RFID information writing, and encrypted data is uploaded to a cloud platform. According to the invention, high-precision identification of abnormal water quality and immediate locking of polluted samples are realized, and the integrity and timeliness of an environment supervision evidence chain are guaranteed.

The present application relates to the technical field of fault diagnosis, in particular to an automobile fault intelligent diagnosis system, the system comprises: a collection sequence verification module, an intensity anomaly grouping module, a trend path reconstruction module, a frequency priority empowerment module and a reverse estimation judgment module.In the present application, the time label and the sampling point number sequence verification signal are checked in sequence and the intensity mutation condition, the collection time sequence disorder phenomenon is discriminated and clustered, the grouping identification of the jump abnormal signal is completed combined with the connection path sequence of the signal node in the wiring structure diagram, the signal evolution path is screened with the help of the trend consistency in the time sequence and is mapped with the running state, the triggering frequency of each path in different periods is searched and the increasing trend is determined, the signal source point is located reversely through the path space distribution, the accurate identification ability of the potential fault source point can be improved, and the problem that the diagnosis accuracy is easily decreased under the condition of fault node space-time dislocation is solved.

This invention belongs to the field of strip and plate production technology, specifically an automatic identification method for side bending of rolled pieces in the strip and plate production process. The method includes the following steps: S1: The rolled piece exits the furnace, and initial parameters are obtained, mainly including the rolled piece grade, inlet thickness, inlet width, and inlet temperature; S2: Production begins, after the rolled piece passes through the mill stand, the outlet thickness, outlet width, and rolling speed are obtained. The rolled piece moves along the rolling direction via the roller conveyor. This invention's automatic identification method for side bending eliminates the need for traditional manual inspection, reducing labor costs and increasing automation in the inspection process. Based on the relative distance signal from the rangefinders on the transmission and operation sides, the degree of side bending at the rolling centerline is obtained after processing. This solves the problem of relying on manual visual judgment of side bending on-site and provides accurate side bending data, improving the accuracy of side bending identification and providing guidance for subsequent supply and demand adjustments, thereby improving product quality.

This invention relates to a non-targeted identification method for mycotoxin metabolites in wine based on mass spectrometry coupled with chromatography, specifically for the detection and identification of ochratoxin A and its metabolites in wine. Through sample pretreatment, chromatographic separation, mass spectrometry detection, data screening, and fragment ion confirmation of wine samples, non-targeted detection of ochratoxin A and its metabolites can be achieved without relying on standards. In the sample pretreatment stage, the target analyte is extracted using acidified acetonitrile solution, and impurities are removed by salting out and centrifugation. Separation of ochratoxin A and its metabolites is achieved by coupling high-performance liquid chromatography with time-of-flight mass spectrometry using a reversed-phase C18 column for gradient elution. The mass spectrometry analysis uses full-scan mode and alternates between positive and negative ion modes to ensure high resolution and high sensitivity, making it suitable for the detection of mycotoxins in wine and other foods, meeting food safety regulatory requirements.

The invention discloses a notebook computer light sensing face recognition method. The method comprises the following steps: step 1, double-spectrum environment sensing; step 2, dynamic illumination compensation processing; step 3, extracting features in all directions; step 4, deep feature fusion; step 5, lightweight network identification; and step 6, event-driven energy efficiency management. According to the method, environmental limitation is broken through through dual-spectrum sensing and three-dimensional illumination modeling, and the recognition precision is improved by combining a dynamic compensation algorithm with harmonic analysis; the robustness of a complex scene is enhanced through deep feature fusion, the power consumption is reduced through cooperation of event-driven management and a lightweight network, the endurance is prolonged through collaborative optimization of software and hardware, the maintenance cost is reduced through modular design, and comprehensive upgrading of precision, energy efficiency and practicability is achieved.