29 results about "Position domain" patented technology

The invention relates to a multi-modal sensor data adaptive alignment method and system based on deep learning, and belongs to the technical field of multi-modal data processing, and the method comprises the following steps: S1, obtaining respective spatial point location data from a plurality of heterogeneous sensors, and obtaining a multi-modal sensor data set; s2, constructing a multi-path feature extraction network model to extract spatial convolution feature representations of different modal sensor data; s3, calculating the cross-modal correlation between different modal features by adopting a position vector feature sequence dimension regularity mode, and dynamically adjusting the alignment offset of the multi-modal features in the spatial position dimension based on the cross-modal correlation; s4, performing continuous position domain transformation on the multi-modal data by utilizing a micro position offset alignment technology so as to realize fine-grained alignment of the multi-modal data; the method has the beneficial effects that the alignment offset of the multi-modal feature in the spatial position dimension is dynamically adjusted, so that the alignment operation can adapt to the dynamic change of data in real time.

According to the intelligent locomotive and non-locomotive mode train vehicle electronic and electrical architecture method and system, a domain centralized control electronic and electrical architecture is formed through modularization and fusion distributed functions; or the functional controller in the region is integrated into the region controller and is further fused in a cross-domain manner to form an electronic and electrical architecture consisting of the central processing unit and the region controller; cab position domain controllers at the two ends can be arranged according to the characteristics of a locomotive, walking part position domain controllers are arranged at the positions of all walking parts, one or two or more vehicle body position domain controllers and the like are arranged in a mechanical room, and the walking part position domain controllers, the vehicle body position domain controllers and the like can be arranged according to the characteristics of a railway vehicle. A more complex cross-domain fusion algorithm is supported, expansion of intelligent driving, multi-energy collaboration and reconnection control is convenient to access, vehicle data sharing and inter-function collaboration control are achieved, evolution to electrification, electronization and intellectualization is easy, and a cloud and fog management and control-oriented platform can be further achieved.

The present invention discloses a method for robust complex coefficient repetitive control of a permanent magnet synchronous motor based on a position domain internal model, which relates to the technical field of permanent magnet synchronous motor control. First, the time domain periodic characteristics of the spindle speed are used to construct an improved time domain complex coefficient repetitive controller. Second, based on the position domain periodic characteristics of the cutting force, a position domain repetitive extended state observer is constructed to online estimate non-periodic disturbances such as parameter perturbations and position domain periodic disturbances caused by the cutting force. Finally, the separation design principle and the small gain theorem are applied to derive the system stability conditions, and an optimization algorithm is used to synchronously optimize the controller parameters. The system design method based on time domain complex coefficient repetitive control and position domain repetitive extended state observer of the present invention designs an improved complex coefficient repetitive control system based on the position domain repetitive extended state observer to achieve feedforward compensation for position domain periodic disturbances and non-periodic disturbances and fast and high-precision tracking of time domain periodic reference speed signals.

The invention discloses a driving corridor generation method, a trajectory planning method and a related device. The trajectory planning method comprises the following steps: obtaining a reachable set at a (k + 1) th moment through Minkowski and a reachable set of a vehicle at a kth moment; projecting the reachable set at the (k + 1) th moment in the position domain to obtain a drivable area at the (k + 1) th moment; generating a driving corridor of the vehicle according to the drivable areas at all moments; determining a first distance from the own vehicle to the boundary of the driving corridor and a second distance between the own vehicle and the other vehicle; predicting a robbing driving intention probability and a yielding driving intention probability of other vehicles; establishing a trajectory planning model according to kinematics constraints, state quantity and control quantity constraints, collision constraints of the two vehicles, planning initial time period constraints, a robbing driving intention probability, a yielding driving intention probability, a self-vehicle optimization objective function and an other-vehicle optimization objective function; and calling the first distance and the second distance to solve the trajectory planning model, and taking the optimal solution of the own vehicle as a target planning trajectory of the own vehicle.

This invention relates to a deep learning-based adaptive alignment method and system for multimodal sensor data, belonging to the field of multimodal data processing technology. The method includes the following steps: Step S1. Acquire spatial location data from multiple heterogeneous sensors to obtain a multimodal sensor dataset; Step S2. Construct a multi-path feature extraction network model to extract spatial convolutional feature representations of different modal sensor data; Step S3. Calculate the cross-modal correlation between different modal features using a position vector feature sequence dimension normalization method, and dynamically adjust the alignment offset of multimodal features in the spatial location dimension based on the cross-modal correlation; Step S4. Utilize a small position offset alignment technique to transform the multimodal data in the continuous position domain to achieve fine-grained alignment of the multimodal data. The beneficial effect of this invention is that dynamically adjusting the alignment offset of multimodal features in the spatial location dimension allows the alignment operation to adapt to dynamic changes in the data in real time.

The application discloses a personnel positioning system based on a power plant, and relates to the technical field of safety production management of power plants. A positioning domain service module is used to independently generate a positioning assertion credential to assert the area where personnel are located, an identity domain service module is used to independently generate an identity attribute credential to assert the identity verification result of personnel, and a workflow domain service module is used to independently generate an operation permission credential to assert the operation permission authorized by a work ticket. A collaborative decision module is used to acquire the three types of credentials in real time. After a common personnel identity is extracted and matched and verified, a ternary safety assertion is formed. A short-time temporary operation token is dynamically issued according to the ternary safety assertion. An intelligent locking control module is used to perform triple verification of the signature, object and time limit of the temporary operation token, and then the conduction and locking of a device operation loop are controlled, so that independent management and dynamic on-demand combination of position, identity and permission are realized, and the flexibility and response efficiency of the power plant when facing dynamic work ticket approval, personnel replacement and area adjustment are improved.

The invention relates to the technical field of mining hydraulic support control, and provides a mining hydraulic support control method and system.The method comprises the steps that whether a sensor is connected to a sensor interface or not is detected; if detecting that the sensor is connected to the sensor interface, sending broadcast data to the sensor; first sensor data fed back by the sensor is received, and the first sensor data comprises type domain information and position domain information of the sensor; and determining the type of the sensor according to the first sensor data, and loading control information corresponding to the sensor. According to the application, the technology of automatically, accurately and reliably identifying the type of the sensor can be realized, so that the system installation and maintenance process is simplified, and the intellectualization and reliability of the system are improved.

The present disclosure relates to a train operation method and device based on the coupler state, equipment, storage medium and computer program, the method comprising: initializing all gear discrete points in the discrete position domain to obtain a discrete gear sequence set, calculating an expected speed sequence according to the discrete gear sequence set, calculating a train coupler state sequence according to the pre-acquired coupler critical displacement and the discrete position domain sequence, calculating a train coupler state change sequence according to the train coupler state sequence, calculating a coupler state change index sequence according to the train coupler state change sequence, calculating a stability index sequence according to the coupler state change index sequence, calculating a speed following index sequence according to the expected speed sequence and a preset target speed sequence, calculating a comprehensive evaluation index sequence according to the stability index sequence and the speed following index sequence, selecting an optimal gear sequence in the discrete gear sequence set according to the comprehensive evaluation index sequence, and controlling the train to run by using the optimal gear sequence.

This invention discloses a train position determination method and device to address the problem that existing positioning technologies cannot accurately calculate and distinguish the positions of multiple trains. The method includes: determining the position domains of the first train and the second train based on the historical positions of a first train located within the overhead contact line section of the traction power supply system and a second train newly entering the overhead contact line section; traversing the first and second train position domains to obtain at least one candidate position combination; determining the electrical operating parameters of the traction power supply system corresponding to each candidate position combination based on the first and second candidate positions in each candidate position combination; and determining the real-time positions of the first and second trains based on the first and second candidate positions corresponding to candidate position combinations whose electrical operating parameters meet preset target parameter conditions. This method significantly improves the accuracy and reliability of train position positioning.

The invention discloses a receiving view field splicing method, system and device based on a distributed satellite navigation antenna and a medium, and relates to the technical field of satellite navigation, and the method comprises the steps: carrying out the splicing of a receiving view field based on carrier attitude information, carrier position information and the spatial geometric position of the distributed satellite navigation antenna and a virtual target measurement point; constructing a geometric deviation correction model for mapping from the position domain to the observation domain; uniformly and geometrically reducing the observed quantity of the distributed satellite navigation antenna to a virtual target measurement point based on the geometric deviation correction model to obtain the combined observed quantity of the distributed satellite navigation antenna; on the basis of the combined observed quantity of the distributed satellite navigation antenna, constructing an online estimation model for the time delay deviation between the receivers, and estimating the time delay deviation between the receivers; and correcting the clocks of the receivers based on the time delay deviation between the receivers. According to the invention, the optimal full-view-field satellite geometric distribution can be realized, so that the problem of poor PDOP caused by installation limitation of the GNSS is improved.

The invention discloses a ship traffic transportation safety supervision method and system based on AI and big data, particularly relates to the field of ship traffic supervision, and is used for solving the problems that hidden ship positions and supervision blind areas are difficult to dynamically identify and the traffic risk early warning capability is insufficient in the existing ship traffic supervision process. AIS ship dynamic data is collected through a base station to generate a real-time traffic state set, a hidden suspected ship is marked after ship AIS signal loss is detected, steering avoidance behaviors of surrounding ships are analyzed, a hidden probability position domain is inferred through reverse cross positioning, space-time correlation verification is performed on a hidden target, a motion parameter range of the hidden target is reversely deduced, and a real-time traffic state is obtained. And meanwhile, a monitoring blind area migration path and a monitoring blind area range are identified based on a continuous monitoring period, a dynamic monitoring risk area is generated in the electronic chart, and traffic monitoring early warning is carried out on ships entering the area, so that dynamic identification and traffic safety monitoring of hidden ship activities are realized.

The application discloses a kind of underground ultra-wideband system integrity threshold calculation method based on Gaussian mixture model, it is applicable to the new integrity evaluation system of underground large space.This method uses the hyperframe of Gaussian mixture model GMM to process the ultra-wideband ranging error sample based on TOA positioning, reflects the superiority of flexible Gaussian mixture model processing bimodal distribution, and fully considers the correlation between ranging error and distance under the environment of underground large space, introduces distance factor when establishing error model, clearly deduces the method for calculating protection level PL in position domain, continuously convolves double-component hyper GMM, obtains multi-component GMM, and the hyper nature still holds after convolution.This application solves the contradiction between traditional Gaussian hyper model and non-gaussian characteristic error under complex environment, tightens PL with small calculation cost, and improves system availability.

The invention discloses a position domain iterative learning independent pitch control method under sparse sampling, and mainly relates to the technical field of wind power generation load control. The method comprises the following steps: establishing a position domain state space model of the wind driven generator, and converting a frequency conversion periodic load into fixed space frequency interference; designing an iterative learning observer (ILO) to realize high-precision estimation of periodic interference; an iterative learning independent variable pitch controller (ILC-IPC) is designed, a PD type iterative learning control law is constructed in combination with the interference estimation value, and the load suppression precision is improved; and a linear matrix inequality (LMI) optimization problem about the sampling step length is constructed and solved, the maximum allowable sampling step length for ensuring the system stability is determined, and the balance of the control performance and the cost under sparse sampling is realized. Through position domain modeling, an iterative learning mechanism and sparse sampling optimization, the periodic load of the wind driven generator is effectively inhibited, the hardware and calculation requirements of a control system are reduced, and the operation efficiency and economical efficiency of the system are improved.

This application provides a structural optimization method for a three-coil inductive abrasive particle detection sensor. Applied to the field of sensor technology, this method constructs a sensor structural parameter set based on the geometric and turn count parameters of the sensor coils, sensor installation constraints, and wire diameter specifications. It calculates the axial magnetic field distribution of the coil using the precise integral of the magnetic induction intensity along the central axis of the thick coil. It obtains the equivalent magnetic moment by combining a particle response model and calculates the induced voltage corresponding to each axial position based on reciprocity. It samples the induced voltage along the axial position to construct a position domain event waveform and extracts the main peak feature within a preset search interval. Based on the extracted main peak feature, it constructs a target evaluation index and performs multi-objective optimization to obtain a non-dominated candidate solution set. It then performs truth value verification and qualification screening on the candidate solution set to obtain the optimal structural parameter solution set, achieving efficient, stable, and interpretable optimization design of the three-coil sensor structure.

A method 800 for making molecular computations comprises: i) providing a mixture 100 comprising a scaffold 110 comprising N scaffold positions 120; ii) designing a set of computing tiles to drive a desired computation, the set of computing tiles comprising at least N different computing tile types, wherein the computing tile types are selected to be used for the computation, in such a way that a target output has a higher probability of being reached than the probability for any other potential output, wherein for each computing tile 140, a bottom position domain 160 is arranged to bind directly to a matching scaffold position 120 with a first binding strength, and to the compute domains 150 of other computing tiles 140 with a set of second binding strengths, which are each weaker than the first binding strength; iii) adding the designed set of computing tiles to the mixture 100; iv) allowing computing tiles 140 to bind to scaffold positions 120 until all scaffold positions 120 required for the computation have been filled; v) allowing replacement of all mismatched computing tiles 140, based on correct compute domain bindings being enthalpically favoured over incorrect compute domain bindings; and vi) reaching an output configuration.

The invention discloses a receiver integrity monitoring method and system based on cloud integrated positioning, and relates to satellite positioning. The method comprises the following steps: constructing a GNSS double-difference observation equation according to differential data; constructing an ionized layer constraint equation; according to the GNSS double-difference observation equation and the ionosphere constraint equation, posterior state estimation of receiver position parameters is obtained through Kalman filtering; calculating a filtering information vector according to the posterior state estimation and the observed value of the current epoch; recognizing a fault satellite according to the filtering information vector; constructing a three-stage filter of the visible satellite; and the position parameters of the receiver are monitored by using a three-stage filter. In view of large errors caused by the fact that the deviation of a measurement domain needs to be converted to a position domain through the maximum slope in traditional RAIM detection, the fault detection is directly carried out in the position domain by constructing a three-stage filter system, and the errors are reduced.

The application discloses a dead zone compensation method and device of a current loop, a motor control system and a storage medium, and the method comprises the following steps: based on a rotor electrical angle of a current axis, an array of the current axis is constructed, the current axis is a d-axis or a q-axis; the array of the current axis contains N elements, the rotor electrical angle of the current axis is divided into N equal parts, and each element is used for storing accumulated current error of a corresponding rotor electrical angle history period of the current axis, and N is a positive integer; based on the array of the current axis, a position domain repetitive control based on the rotor electrical angle of the current axis is adopted to perform dead zone compensation on a current loop of the current axis. According to the scheme, the position domain repetitive control based on the rotor electrical angle is added to the d-q axis current loop, so that the dead zone compensation can be realized, and the compensation effect is relatively ideal.

The invention discloses a position confirmation method of a leakage sensor and a storage medium. The position confirmation method of the leakage sensor comprises the following steps: firstly, counting all possible leakage points and all predicted installation positions of the leakage sensor; the installation position factor priority of each predicted installation position relative to each possible leakage point is obtained; the concentration factor priority of the predicted installation position relative to each leakage point is obtained through operation of analogue simulation equipment; obtaining the priority of each predicted installation position based on the installation position factor priority and the concentration factor priority; data with the priority smaller than or equal to a threshold value is removed, and statistics is conducted on the priority of each possible leakage point at each predicted installation position; and determining a final installation position by judging that at least several predicted installation positions are required to contain position domains of all possible leakage points. Scientific confirmation of the position of the leakage sensor is realized.

The application provides a communication configuration method, a federated learning method, a device, an electronic device and a medium, wherein the communication configuration method comprises: determining a task identifier of a federated learning task and a positioning domain name of each party participating in the federated learning task; determining a communication domain name of the each party based on the task identifier and the positioning domain name of the each party; determining a communication certificate between the each party based on the positioning domain name of the each party; and configuring the communication domain name of the each party and the communication certificate between the each party to the each party, so that the each party establishes a communication connection and performs the federated learning task based on the communication connection. The communication configuration method, the federated learning method, the device, the electronic device and the medium provided by the application can realize automatic configuration of the communication connection of the each party, greatly simplify the configuration process of the federated learning cluster under the premise of ensuring the communication security and reliability.

The present invention proposes a GNSS slow-varying fault detection method that combines the observation domain, the position domain, and the time domain, which relates to the field of satellite positioning technology. The method includes: based on the concept of solution separation in the position domain, regarding the difference between the complete set solution and the subset solution as a fault test quantity and storing it in a smoothing window; at the same time, using the residual information in the observation domain to design a consistency check factor to accurately obtain the end time of the slow-varying fault and avoid the false alarm risk caused by abnormal information; in addition, based on the fault test quantity stored in the smoothing window in the time domain, reconstructing and obtaining a new fault test quantity to quickly detect the slow-varying fault; finally, by comparing the size of the fault test quantity with the detection threshold, the detection of the slow-varying fault is completed. This method not only supports the fast and accurate detection of slow-varying faults, but also is applicable to complex dynamic scenarios, providing new ideas for GNSS data quality control.

This invention discloses a method for generating and evaluating Doppler simulation data for low-Earth orbit (LEO) satellites. By employing source-end discrete-time gating, the system is forced to directly block output when the time deviation exceeds 1 ms, fundamentally severing the error coupling path and ensuring the purity of the output data. In the inertial frame velocity synthesis, an explicit Earth rotation-related velocity correction term is introduced, enabling even stationary receivers to accurately reflect their motion in inertial space. An elevation-angle-weighted noise model is used to accurately simulate the physical phenomenon of sharp link deterioration in LEO satellites at low elevation angles, realistically reflecting the tracking and loss-of-lock behavior of receivers in complex geometric environments. Terminal physical consistency verification is introduced. By comparing the distance change rate calculated in the velocity domain with the distance rate of the position domain derivative in real time, a rigorous closed-loop feedback mechanism is constructed, which can automatically identify and eliminate abnormal data caused by ephemeris jumps or numerical divergences, significantly improving the engineering confidence of the simulation data.

The invention provides a coreless linear motor multi-working-condition self-evolution intelligent control method and system, and relates to the technical field of linear motor control, and the method comprises the steps: collecting operation parameters, dividing working condition sub-regions, calculating a projection residual error, determining a current working condition, and generating a feedback control quantity; meanwhile, extracting position domain frequency spectrum characteristics of unmodeled disturbance force to construct a compensation function, and generating a feed-forward compensation amount; and automatically updating the spectrum characteristic quantity and adjusting the boundary of the working condition sub-region according to the control performance index, and generating a new working condition sub-region if necessary. The method can adapt to various working condition changes, control precision is improved, and self-evolution control is achieved.

Embodiments of the present application relate to the field of medical equipment, and disclose an intelligent planning system of electrode array, an electronic device and a storage medium.The system comprises: a probabilistic ablation effect prediction module which utilizes a pre-trained Gaussian process regression model describing the probability of any point in a target region being ablated, takes maximizing the expected ablation coverage volume of the target region and minimizing the uncertainty of the prediction result as the target, and predicts an initial electrode array configuration; a model self-adaptation module which acquires actual pose information of a current electrode during electrode placement into the target region based on a current electrode array configuration; and a constraint-aware dynamic optimization module which determines target pose information of a next electrode in an effective position domain satisfying a preset geometric constraint based on the current electrode array configuration and the actual pose information of the current electrode placed into the target region, so as to place the next electrode into the target region based on the target pose information. The problem of dynamically planning an electrode array is solved.

The present invention discloses a method and system for ship transportation safety supervision based on AI and big data, specifically related to the field of ship traffic supervision, and is used to solve the problems of identifying the position of hidden ships, difficult to dynamically identify blind spots in supervision, and insufficient traffic risk warning ability in the existing ship traffic supervision process; collecting AIS ship dynamic data through base stations to generate a real-time traffic state set, marking suspected hidden ships after detecting the loss of ship AIS signals, analyzing the steering and avoidance behaviors of surrounding ships, inferring the hidden probability position domain through reverse cross-positioning, performing spatio-temporal correlation verification on hidden targets and inferring the range of their motion parameters, and at the same time identifying the migration path and range of blind spots in supervision based on continuous monitoring periods, generating a dynamic supervision risk area in the electronic nautical chart and implementing traffic supervision warnings for ships entering the area, so as to realize the dynamic identification of hidden ship activities and traffic safety supervision.

A device of calculating indoor / outdoor seamless positioning on the basis of a common message format according to an embodiment may include a domain provided with a sensor for detecting a moving subject and configured to generate sensing data, a positioning domain configured to receive the sensing data from the domain and perform data fusion or sensor fusion. A method of calculating indoor / outdoor seamless positioning on the basis of the common message format according to an embodiment may include entering, by a moving subject, a detection range of a sensor provided in a domain, generating, by the sensor, sensing data necessary to calculate positioning of the moving subject, transmitting the sensing data to a positioning domain that performs data fusion or sensor fusion of the sensing data, and generating, by the positioning domain, a common message format of the sensing data for seamless positioning of the moving subject.

The invention relates to the technical field, in particular to an electromagnetic suppression equipment digital twinning technology, which comprises the steps of selecting n electromagnetic suppression equipment, constructing a digital model containing radiation characteristics such as transmitting power and bandwidth, generating a collaborative suppression pre-deployment scheme by adopting a potential game algorithm according to a scene radio wave propagation model, and further constructing a collaborative suppression pre-deployment scheme by taking minimization of accidental injury as a constraint. And using a genetic algorithm to optimize cooperative working parameters of the computing device in a multi-dimensional domain, and generating a pre-deployment optimal scheme based on a use scene. According to the method, a high-fidelity model containing an operation state is constructed to determine virtual-real accurate mapping so as to improve the deduction confidence coefficient, a potential game algorithm is applied to construct a utility function considering suppression and accidental injury, a Nash equilibrium point is automatically solved so as to realize scientific planning of a position domain, multi-dimensional optimization is carried out in a power domain in combination with a genetic algorithm, and minimum accidental injury hard constraint is set. White list interference is strictly limited while suppressing is guaranteed to reach the standard, and the efficiency and safety precision balance is achieved.

The embodiment of the invention relates to the field of medical equipment, and discloses an intelligent planning system for an electrode array, electronic equipment and a storage medium, and the system comprises a probabilistic ablation effect prediction module which uses a pre-trained Gaussian process regression model for describing the ablation probability of any point in a target area, predicting an initial electrode array configuration by taking the maximization of the expected ablation coverage volume of the target region and the minimization of the uncertainty of a prediction result as targets; the model self-adaption module obtains the actual pose information of the current electrode in the process of placing the electrode into the target region based on the current electrode array configuration; and the constraint perception dynamic optimization module determines target pose information of a next electrode in an effective position domain meeting preset geometric constraints based on the current electrode array configuration and actual pose information of the current electrode placed in the target region, so that the next electrode is placed in the target region based on the target pose information. The problem of dynamically planning the electrode array is solved.