18results about How to "Low real-time" patented technology

The invention relates to the field of numerical control machining and computer-aided manufacturing software, and particularly discloses a honeycomb core six-axis ultrasonic cutting track digital control and interpolation optimization system which comprises a track preprocessing module, a parameterized spline interpolation module, a six-axis linkage inverse solution module, a dynamic feed-forward compensation module, an ultrasonic energy adaptive control module and a multi-source information fusion and decision module. By the adoption of the technical scheme, smooth and efficient interpolation of a track, dynamic feed-forward compensation of motion errors and self-adaptive adjustment of cutting energy can be achieved, and therefore the machining precision, the surface quality and the system stability are improved. According to the invention, ultrasonic energy control is originally incorporated into an overall trajectory control closed loop, and real-time accurate regulation and control of cutting energy are realized through the ultrasonic energy adaptive control module. The module is based on force, amplitude, temperature and other multi-sensor information, adopts fuzzy reasoning to intelligently decide output power, and ensures that cutting energy is constant and optimal under different processing conditions.

The invention discloses an underwater target detection method based on differential attention. The method comprises the following steps: acquiring an underwater image to be detected; based on the underwater image data set, constructing a lightweight underwater target detection network model based on a differential attention mechanism; constructing a joint loss function, and performing end-to-end training on the lightweight underwater target detection network model to obtain a trained lightweight underwater target detection network model; performing mathematical equivalence fusion on the lightweight underwater target detection network model to generate a lightweight reasoning model; and inputting the obtained underwater image to be detected into the lightweight reasoning model to realize target detection of the underwater image. According to the method, a differential attention feature interaction mechanism is introduced, common-mode noise is stripped through differential calculation, and the detection precision and real-time performance of an underwater fuzzy scene and a tiny target are remarkably improved in combination with a feature pyramid network integrating dynamic scale perception and semantic gating.

The application discloses a kind of multi-obstacle prediction navigation obstacle avoidance methods based on single-line laser radar, first, the obstacle point cloud data detected by single-line laser radar is collected, the data is filtered and classified, and the obstacle point cloud array is obtained;Shape fitting is carried out on the classified obstacle point cloud array to realize the detection of obstacles;Data correlation is carried out on the obstacles detected in the adjacent two frames of obstacle point cloud arrays, the current motion state of each obstacle is obtained, and its historical trajectory is recorded to realize the tracking of obstacles;The trajectories of multiple obstacles in the future are predicted, the results of global path planner are read and segmented into multiple local paths;In each local path, map-free end-to-end strategy navigation is realized;The method of the application is applied to floor cleaning robots, service robots and AGVs and other mobile robots, improves the safety of robot obstacle avoidance, and has the characteristics of real-time and low cost.

This invention relates to the field of machining and intelligent control technology, and discloses a multi-process collaborative control system for machining equipment based on multi-source data. The system includes a spatial modeling module, a multi-source sensing and feature mapping subsystem, a reference calibration module, and a collaborative execution module. The spatial modeling module constructs a hierarchical partitioned spatial mesh model enveloping the workpiece and drives dynamic node growth. The multi-source sensing and feature mapping subsystem synchronously acquires operating status data, converts it into spatial attribute values, and stores them in voxel units. After the workpiece is transferred to a new process, the reference calibration module constructs a cross-process coordinate transformation matrix and performs pose transformation on the spatial attribute values ​​stored in the model. The collaborative execution module generates machining compensation increments based on the transformed spatial attribute values ​​and injects them into the CNC system. This invention solves the problem of physical feature discontinuity in multi-process flow, realizing spatial mapping and adaptive compensation from previous physical states to the current process.

The application discloses a kind of MIMO mobile phone antenna adaptive tuning methods based on reinforcement learning, comprising the following steps: acquisition operating parameter;Operating parameter set is fused and encoded, and the characteristic vector containing historical state and time series information is generated;According to operating parameter set, the action range boundary is calculated, and the out-of-bound detection rule and rollback trigger condition are generated;Characteristic vector and action range boundary are input into improved diffusion strategy generation model, and tuning action is generated using hierarchical policy network;According to the out-of-bound detection rule, detection is carried out and rollback is triggered when out-of-bound, to obtain stable execution state;Stability index is calculated and diversity-stability collaborative reward function is constructed, and hierarchical policy network is updated;Scene label is generated, key-value pair index is formed and stored, and lightweight strategy is constructed and solidified through network distillation method.The application realizes the adaptive tuning of MIMO mobile phone antenna.

This invention provides a method and system for compressing power messages, relating to the field of power system control technology. The method includes: acquiring power messages via a first FPGA; timestamping the acquired power messages; caching the timestamped messages in a first shared memory; extracting messages from the first shared memory; parsing the messages according to their type and classifying and storing them in a second shared memory; extracting messages from the second shared memory by control block using a second FPGA; compressing the compressed packages corresponding to the control blocks; storing the compressed packages in a third shared memory; packaging and secondary compression according to a set time period; generating a total compressed package for that time period; and storing it on an SSD for dual-disk storage. This invention effectively reduces the storage space requirements for historical messages, improves the storage time of historical messages, and solves the problem of frequent failures in storing historical messages for post-event analysis of power systems.

The application discloses a dynamic human body falling detection method based on future human body time sequence posture prediction, and the method comprises the following steps: automatically calibrating the ground in a monitoring scene to obtain ground plane parameters; detecting, cropping and tracking the human body target in a video image to obtain a human body image sequence; performing single-person 3D posture estimation on the human body image sequence frame by frame to obtain a historical 3D skeleton sequence; constructing a skeleton motion flow feature according to the historical 3D skeleton sequence, and extracting a current human body state feature by using a time sequence feature coding model; predicting a future H-frame human body 3D skeleton sequence based on the current human body state feature; determining whether the human body has a risk of falling soon according to the included angle between the human body trunk vector in the future 3D skeleton and the ground plane normal vector, and combining the distance information of the skeleton key point to the ground plane; and outputting a warning signal when a preset condition is met, and the method is suitable for security monitoring, old-age care, public safety and the like.

The application provides a driver output current detection method, which comprises the following steps: recording data and calculating average value and waveform sinusoidal degree according to the above method after the system reaches steady state; if the difference between the calculation result of the measured driver output current and the reference data of the detection equipment is within a reasonable range, the test is qualified, otherwise the test is unqualified. The application adopts a phase-locked loop method to determine the current zero-crossing point, and adopts an equivalent approximate method to measure the harmonic distortion rate and compare the transient error of the reference waveform to judge the waveform sinusoidal degree, so that the calculation efficiency and accuracy are improved from the above aspects.

The application belongs to the technical field of nonlinear system control, and discloses a method and system for introducing composite learning into nonlinear system output feedback adaptive control. The application directly reuses the existing K-filter in standard output feedback backstepping control to construct an extended prediction error, and does not need to establish an additional observer or a state estimation model (such as a series-parallel estimation model, a fuzzy observer, etc.) in parallel with the K-filter. This functional reuse design eliminates the calculation overhead of the additional dynamic system, reduces the storage requirement and real-time calculation burden of the controller, and significantly reduces the hardware implementation cost and system debugging complexity. Meanwhile, through the composite driving of the tracking error and the extended prediction error, the cumulative information is continuously introduced by using the historical memory of the regression quantity, so that the adaptive and self-learning ability of the control system is significantly enhanced, and the parameter estimation convergence and the system response performance are improved.

The application provides an event camera-based pulse neural network tracking method and system. Multi-time step event data and low-resolution grayscale images output by an event camera are acquired, and the event data are combined with time sequence and polarity to form a multi-channel event tensor; dynamic event features in the event tensor and static image features in the grayscale images are extracted respectively, and feature fusion is performed through channel splicing and convolution operation; the fused features are input into a super-resolution decoder, up-sampling of the images is realized through transposed convolution operation, and a high-resolution moving target image is generated; the high-resolution image is input into a pulse neural network feature extraction module based on LIF neurons, features of a target template and a search area are extracted, and a target position is determined through cross-correlation operation to realize tracking. The application can effectively improve the spatial resolution of the event camera output image and the target positioning accuracy, and realizes robust target tracking in a complex dynamic environment on a low-power edge device.

The application provides a wharf vehicle predicted driving time measurement method and device, and relates to the technical field of path planning, which comprises the following steps: in a road network constructed based on an Actor model, when a specified departure or arrival time is given, a road segment is deduced along a forward direction or a reverse direction from a path endpoint; a density of each road segment is obtained based on an entering / leaving time statistical distribution, a driving time statistical distribution is obtained by querying a historical record according to the density, after smoothing and normalization processing, the statistical distribution of a next road segment is deduced by combining and deducing through probability multiplication, and the iteration is performed until the other endpoint of the path, and the most possible time point is obtained from the final distribution and the total time is calculated. The application can improve the efficiency by using multi-thread parallel computing, the initial measurement accuracy is significantly improved, the subsequent scheduling adjustment is reduced, and the stability and efficiency of large-scale calculation are ensured.

The application relates to an asynchronous preloading frequency hopping method, system and device under limited hardware resources and belongs to the technical field of wireless communication. The method comprises the following steps: pre-generating a frequency hopping configuration set; loading initial configurations in the frequency hopping configuration set to a hardware configuration unit of a radio frequency chip, establishing and initializing a mapping relationship between the hardware configuration unit and the frequency hopping configuration; starting a hardware frequency hopping time sequence and an interrupt triggering mechanism; reading a current frequency hopping state when the frequency hopping time slot is interrupted, determining a current hardware configuration unit, and calculating a target frequency hopping configuration to be used after a predetermined number of hops in the future according to the current frequency hopping state; judging whether the current hardware configuration unit matches the target frequency hopping configuration based on the mapping relationship; if the current hardware configuration unit does not match the target frequency hopping configuration, triggering an asynchronous loading process, loading the target frequency hopping configuration to the current hardware configuration unit, and updating the mapping relationship. The application avoids the blocking of the interrupt real-time performance caused by the serial peripheral interface operation, and ensures the microsecond-level precision of the frequency hopping time sequence.

The invention discloses a timing synchronization system and method of a low-orbit satellite baseband, computer equipment and a medium, the timing synchronization system communicates with a digital signal processor and a baseband processing unit, and the timing synchronization system comprises a timer configured to receive timing configuration data sent by the digital signal processor, starting counting according to the timing configuration data so as to synchronize with the time of the digital signal processor; the instruction cache module receives and stores the timing instruction sets sent by the digital signal processor in sequence; the instruction analysis and execution module is connected with the instruction cache module and the timer, and is used for reading the timing instruction to be executed in the instruction cache module and timing data of the timer, analyzing instruction execution time of the timing instruction to be executed, and executing the timing instruction to be executed on time according to the timing data and the instruction execution time; therefore, data interaction between the digital signal processor and the baseband processing unit is completed. According to the invention, high precision, low power consumption and high real-time performance can be considered, and the flexibility of a timing system is improved.

The application provides a multi-view human motion capture method, device, system, medium and terminal, comprising: acquiring multi-view video signals of a to-be-captured object and audio signals corresponding to each video signal; eliminating the time difference of the multi-view video signals based on the audio signals to acquire multi-view synchronous video signals; extracting corresponding multi-view 2D human key points from the multi-view synchronous video signals; acquiring the correlation information between each view of the 2D human key points; and performing optimization calculation based on the correlation information to acquire 3D human posture information. The application can capture only by using an ordinary RGB camera; the self-occlusion problem is alleviated, and the capture accuracy is higher; compared with using an inertial sensor for motion capture, the application has better real-time performance, a lower use threshold and a larger recognition range, and is not limited by the number of people; the wearable device is reduced, the use experience of the user is improved, and the activity freedom is higher.

The application discloses a video image data intelligent gathering and full life cycle management method, relates to the technical field of video monitoring and intelligent security and protection, and discloses the following technical scheme: low light and shielding state are explicitized through working condition information, a degeneration area mask and a reliability weight graph are generated, video degeneration is converted from uncontrollable input into available control quantity, subsequent processing can adopt differentiated treatment on the degeneration area and the non-degeneration area, the interference of the degeneration area on detection output is reduced, and effective detail information of the non-degeneration area is reserved; the reliability weight is introduced into a detection model inference link, intermediate features are gate weighted, confidence penalty is applied to candidate frames falling into the degeneration area, a result reliability mark and an alarm linkage rule are generated, low reliability results are stored in a database, real-time alarm is inhibited or delayed triggering, alarm noise is reduced, and review resources are focused on high reliability events.

This application relates to a wireless signal optimization method for tire pressure information data transmission, comprising the following steps: a sensor node initiates a relay transmission mode based on link quality judgment, selects a relay node through a micro-routing protocol, and forwards data packets to a distributed slot antenna formed by coupling through vehicle body gaps via neighboring nodes; a central signal aggregator fuses the data received from multiple paths to reconstruct the complete tire pressure data stream. This application achieves reliable and continuous transmission of tire pressure signals under extreme obstruction environments, while also meeting the requirements of low power consumption and real-time performance.

Embodiments of the present application provide a method for NPU-based streaming speech synthesis vocoder and related products. The method includes obtaining input features to be processed for the streaming speech, wherein the input features to be processed are of fixed length; processing the input features of fixed length based on a vocoder model deployed on the NPU to output audio information; and determining a synthesis result for the streaming speech based on the audio information. By deploying the vocoder model on the NPU to perform synthesis of the streaming speech, the high performance of the NPU (especially the advantages in neural network inference, etc.) is combined to ensure high-quality speech synthesis while effectively reducing latency and real-time rate to meet actual market demand. In addition, the present application also provides a device and a computer-readable storage medium.

The application discloses a kind of multi-source heterogeneous sensor adaptive data fusion methods for dynamic target.First, the azimuth angle, elevation angle and distance data collected by multi-source heterogeneous sensor are preprocessed, forming uniform time sequence three-dimensional observation vector;Then extract angular velocity, angular acceleration and other motion characteristics and compare with preset threshold, distinguish target is in stable or strong maneuvering motion state;According to the discrimination result, the fusion scheme is switched using the asymmetric hysteresis comparison strategy, the Kalman filter based on the second-order exponential moving average is enabled in stable state, and the long short-term memory network with double attention mechanism is enabled in strong maneuvering state, and the optimal state estimation of target is output.The application realizes double-mode adaptive switching, noise covariance online estimation and hardware acceleration, and realizes real-time and high precision on embedded platform, improves the adaptability of dynamic target tracking in complex scene.