14results about How to "Guaranteed time consistency" patented technology

The invention discloses a hospital-oriented software and hardware collaborative medical data hierarchical processing method and device. According to the method, in a hospital intranet, statistics is carried out on the flow of medical data flow based on a source IP and a target IP two-tuple through a hardware side, a large flow and a small flow of the medical data flow are distinguished according to a dynamic threshold value, and an identifier is added to the large flow. The hardware flow table module carries out short-period quintuple statistics on the identified large-flow medical data message and reports a result with a timestamp; and the software flow table module performs long-period statistics on the small-flow medical data messages, synchronously fuses results of the two parties through timestamps, generates a full-amount medical network flow table, and further optimizes a dynamic threshold value and a processing strategy. According to the invention, through layered flow establishment and double-cycle cooperation, high performance of hardware processing and flexible large capacity of software processing are both considered, the utilization rate of hospital network resources and the consistency of flow data are effectively improved, and accurate support can be provided for hospital intranet monitoring, service awareness, safety protection and strategy automation.

The invention relates to the technical field of equipment monitoring and control, and discloses a power take-off wheel real-time energy consumption monitoring method and system and a storage medium. The method comprises the following steps: synchronously acquiring a torque value and a rotating speed value to construct a sampling data record; torque fluctuation gradient setting sampling frequency is calculated, and whether the sampling frequency is switched or not is judged based on the fluctuation gradient change rate and the hysteresis band; calculating instantaneous power and accumulated energy consumption, establishing a power baseline, and generating an energy consumption abnormal event when the deviation degree exceeds a preset number of times; and according to the deviation degree and the duration, determining an alarm level and executing corresponding alarm. According to the invention, the real-time performance of energy consumption monitoring and the utilization efficiency of edge computing resources are improved.

The invention relates to a learning state monitoring method, system and device based on artificial intelligence and a medium. The method comprises the following steps: collecting signals such as physiological and behavior images of a target object through a multi-source heterogeneous sensor, and performing normalization processing on aligned features to generate a standardized feature vector; calculating a comprehensive cognitive state score of the feature vector by adopting a dynamic weighted fusion algorithm, and judging and outputting a soft label according to a preset threshold value; applying constraint random disturbance based on statistical distribution characteristics of the feature vectors to generate synthetic data, and associating the synthetic data with the soft labels to construct a soft label data set; by taking the feature vector of the data set as input and the soft label as a supervision signal, iteratively calculating loss through a preset loss formula, updating model network parameters to convergence, and obtaining an optimized neural network model; during real-time monitoring, processed sensor signals are input into the model, and quantitative learning state scores are output through end-to-end reasoning. The method can break through the limitation that traditional monitoring is high in subjectivity and insufficient in real-time performance.

The application relates to the technical field of image processing, and particularly discloses a bullet rapid measurement method and system based on high-speed video key frame retrieval. The original video frames are uniformly formatted, and frame events carrying influence weights are generated, so that the time sequence consistency of playback, screen projection and target reporting is ensured. Whether to generate a key section summary is dynamically judged through time sequence accumulation of the weights, and the content of the key section summary is matched according to operation requirements, so that the network transmission burden and recovery delay are reduced, and the terminal full playback and decoding calculation burden are reduced. Four-level differentiated key section summaries and incremental frame playback are adopted, so that the recovery complexity of the key section is reduced, the terminal can quickly and directionally retrieve effective event segments through the key section summary, the retrieval and measurement time consumption is shortened, and the balance between real-time performance, transmission efficiency and resource cost is ensured. Through event interval division, asynchronous sampling and adaptive transmission regulation and control, the number of image collections in invalid intervals and the uplink transmission load are reduced.

The invention discloses a hydrogen damage test device and a detection method thereof.The hydrogen damage test device comprises an electrolyte container, an electrochemical workstation, an acoustic emission probe, an acoustic emission detector and a computer, and a metal sample, an auxiliary electrode and electrolyte are arranged in the electrolyte container; the metal sample and the auxiliary electrode are soaked in the electrolyte and are both connected with the electrochemical workstation, the non-hydrogen-filling surface of the metal sample is provided with the acoustic emission probe, the other surfaces of the metal sample except the hydrogen filling surface are sealed through resin, the acoustic emission probe is connected with the acoustic emission detector, and the electrochemical workstation and the acoustic emission detector are both connected with the computer. According to the method, acoustic emission signals are collected in real time in the electrochemical hydrogen charging process, synchronous analysis is conducted in combination with parameters of the hydrogen charging process, elastic wave signals generated by a local damage event can be captured at the moment of hydrogen-induced microcrack initiation, and therefore real-time recognition of the hydrogen crack initiation moment is achieved; and the accuracy and reliability of hydrogen damage early recognition are improved.

The invention discloses an energy-saving optimization control method and system of an air compression station building, a medium and a product, and belongs to the field of air compression station building energy-saving control, and the method comprises the steps: collecting multi-source operation data of the air compression station building in a current sampling period; based on the multi-source operation data, the real gas consumption of the user in the current sampling period is calculated through the mass conservation relation among the gas supply amount, the gas storage variable amount and the gas consumption; inputting the real gas consumption of the user into a preset gas consumption prediction model, outputting gas consumption prediction data in future preset time, and solving to obtain gas supply distribution of each air compressor based on the gas consumption prediction data and a preset power-gas supply relation model of each air compressor; and on the basis of all the air supply distributions, an operation instruction is generated, all the air compressors are controlled to operate, and energy-saving optimization control is completed. By implementing the method, the problem that in the prior art, due to the fact that the outlet flow of the air compressor is directly adopted as the user gas consumption, gas consumption requirement recognition is not accurate can be solved.

The embodiment of the application provides a real-time acquisition method and system of welding heat input, the method comprises the following steps: perceiving displacement movement of a welding torch or a welding wire through a diffuse reflection photoelectric switch array installed on the surface of a pipeline, and generating a corresponding pulse trigger signal; perceiving current data and voltage data of a welding circuit through a Hall sensor system, and generating a corresponding analog electric signal; synchronously acquiring the pulse trigger signal and the analog electric signal through a multi-channel data acquisition device, and converting the analog electric signal into a digital signal with a time stamp; calculating real-time welding speed data according to the time sequence of the pulse trigger signal and the preset spatial geometric relationship of a plurality of diffuse reflection photoelectric switches; performing multi-stage filtering processing on the current data and the voltage data; determining a unified time stamp, and performing time sequence matching on the filtered current data, the voltage data and the welding speed data based on the unified time stamp; and calculating a welding heat input value.

The invention provides an air gun control system. The air gun control system comprises a host, manifold pressure, a network switch, a deck interface unit, a deck power supply unit, a time controller and a subarray, the host is in pressure connection with a manifold through a serial port line and is also connected with the network switch through a network cable, the deck interface unit is connected with the network switch and the deck power supply unit through cables, the time controller is a time receiving and control device, is connected with the network switch and is connected to the host, and the subarrays are connected with the deck interface unit through seismic cables. Each subarray is designed to be an independent module and is located below the water surface, and data interaction between underwater equipment and deck equipment is achieved. The air gun control system provided by the invention has a modular design and a simple structure, and can effectively reduce the system cost and improve the operation convenience.

The invention relates to the technical field of traffic control, in particular to a second-hand car market mixed flow traffic control method and system based on multi-target recognition. The method comprises the following steps: in response to an activation signal of a barrier gate triggering device, collecting multi-dimensional identification original data of vehicles passing through a barrier gate of a second-hand vehicle market through a multi-source identification device; performing cross-device data calibration processing on the multi-dimensional recognition original data, performing feature matching, and generating a vehicle identity recognition result and an identity confidence coefficient parameter; according to the vehicle identity recognition result and the identity confidence coefficient parameter, a dynamic passing strategy engine is called to generate a vehicle passing permission evaluation result and a strategy adaptation coefficient; and generating vehicle passing state record data according to the passing authority evaluation result and the strategy adaptation coefficient, performing classification analysis, generating an intervention processing work order, and feeding back the intervention processing work order to the system optimization module for iteratively updating the identification model and the passing strategy. The barrier gate passing efficiency of the second-hand car market can be greatly improved.

The present application relates to the field of automatic driving sensor calibration, and discloses a sensor fusion calibration method for an unmanned sightseeing vehicle, which comprises the following steps: constructing a micro-displacement model by synchronously collecting a wheel speed meter and IMU data, and calculating an inter-frame pose change quantity in a vehicle coordinate system; filtering dynamic objects in a laser radar point cloud, eliminating dynamic interference in combination with motion prediction of the wheel speed meter and the IMU, and extracting static geometric features; performing motion compensation on the static point cloud based on the pose change quantity, and generating a time-aligned enhanced point cloud map; and minimizing errors between the enhanced point cloud map and a calibration reference, and optimizing an external parameter matrix of the wheel speed meter, the IMU and the laser radar. The algorithm is particularly suitable for a multi-sensor online calibration scene of a low-speed unmanned sightseeing vehicle, effectively solves the problems of tire slip and dynamic interference in a low-speed scene, and significantly improves the perception robustness and positioning accuracy of the unmanned sightseeing vehicle in a complex environment.

This invention relates to the field of fault diagnosis technology and discloses a device fault diagnosis method based on causal residual learning and invariant risk minimization. This method acquires multi-channel vibration signals of the target mechanical equipment during operation. Based on causal structure discovery and backdoor adjustment criteria, the vibration signals are decontaminated to eliminate interference components caused by changes in operating conditions, constructing a causal residual sequence that only characterizes the physical mechanism of the equipment fault. The sequence is input into a multi-timescale, multi-channel attention network to achieve recalibration of the causal residual sequence; hierarchical temporal features at different time resolutions are extracted and dynamically weighted and fused using a time-scale attention mechanism to obtain fault feature representations. These fault feature representations are input into a pre-trained fault classifier to output the final fault diagnosis result for the target mechanical equipment. This invention improves the model's cross-domain generalization performance and diagnostic accuracy under unknown operating conditions.

This invention discloses an online deviation calibration method and system for electricity meters, relating to the field of electricity detection technology, including the following steps: S1: Constructing a hierarchical topology measurement relationship for the distribution area and collecting metering data from the main meter and user electricity meters in the distribution area, while simultaneously collecting hierarchical node data from the meter box metering module and the branch box metering module, triggering control for the collection of frozen electricity, and completing meter synchronization before collecting frozen electricity, recording the clock deviation during the synchronization process and forming a unified time reference; S2: Performing time series information compression and anomaly detection based on the multi-dimensional dynamic and static data distribution changes of the distribution area and electricity meters. Based on the energy conservation of hierarchical topology measurement and time-frozen electricity, this invention introduces a decodeable calibration watermark beacon excitation and, through related decoding inversion path loss constraints, combines non-convex sparse multi-objective solution with uncertainty threshold constraints to achieve quantitative calibration output of online deviation of electricity meters.

The invention discloses a fault diagnosis method and system driven by flight parameters of a long-endurance unmanned aerial vehicle, and relates to the technical field of unmanned aerial vehicles, and the method comprises the steps: receiving multi-source flight data remotely transmitted by the unmanned aerial vehicle, and uniformly mapping the multi-source flight data to a global reference time axis for sampling continuity analysis, so as to recognize a missing section; for a continuous missing section, inputting a continuous flight parameter sequence before and after construction into a bidirectional time sequence estimation model, performing dynamic length prediction compensation to obtain a continuous flight parameter sequence, and performing flight state backtracking reconstruction based on a state space model to obtain a backtracking flight state sequence; extracting a multi-dimensional state feature vector from the backtracking flight state sequence, generating a fault diagnosis result by using a fault diagnosis model, constructing a fault evolution path and determining a fault cause by combining flight parameter abnormal trend analysis, parameter correlation analysis and environmental parameter auxiliary analysis, and realizing remote backtracking of the flight parameters of the long-endurance unmanned aerial vehicle. And the reliability of fault diagnosis is improved.

The utility model discloses a comprehensive perception fusion system, relates to the technical field of sensor data fusion, and solves the problems of insufficient clock synchronization precision and lack of fault tolerance and redundancy mechanisms in the prior art. Comprising a multi-sensor module, a distributed clock synchronization module, a data processing and fusion module, a fault-tolerant and redundancy management module and a power management module, the multi-sensor module realizes data acquisition and timestamp addition through a sensor interface unit, a local clock unit and a timestamp generation unit; the distributed clock synchronization module adopts a high-precision clock source and redundancy design, and the synchronization precision is improved through a clock distribution circuit and a clock synchronization detection circuit; the fault-tolerant and redundancy management module realizes rapid switching and recovery of the system through a fault detection unit, a switching control unit and a state recovery unit; according to the invention, the clock synchronization precision and the system fault-tolerant capability are greatly improved.