20 results about "Characteristic response" patented technology

The invention discloses a turbine fault characteristic collaborative verification method and system, and belongs to the technical field of turbine fault diagnos.The turbine fault characteristic collaborative verification method comprises the steps that structural component parameters, operation boundary conditions and historical operation data of a target area of a turbine are collected, and a heat-stress-vibration coupled simulation model is established; a working condition disturbance factor is introduced to simulate an unsteady-state operation condition; a simulation model is driven through a typical operation event, a response set is extracted, and an abnormal response mapping domain is constructed; actual measurement monitoring data are collected and reconstructed, and feature response vectors are generated; projecting the simulation response to a feature response space, and constructing a response fusion error tensor; generating a verification weight field, extracting highly-correlated simulation sub-responses, and forming a dynamic weighted matching group; identifying an optimal influence path chain through path backtracking, and outputting a fault judgment result and a collaborative verification index; according to the method, traceable modeling, quantitative verification and response mechanism analysis of fault identification are realized, and the method has high precision, high interpretability and engineering practicability.

The invention provides an engineering mechanical equipment remote monitoring system and method based on the Internet of Things, and relates to the technical field of equipment operation monitoring, and the method comprises the steps: carrying out the cross-scale feature response of a dynamic impact signal of engineering mechanical equipment through an intelligent calculation node, and obtaining a frequency domain migration feature and an energy attenuation feature; carrying out gradient operation on the operation thermal field data of the engineering mechanical equipment to obtain heat flow evolution characteristics; utilizing a coupling analysis model dynamics interaction map; performing space-time resonance convolution prediction on node states and edge relations of the dynamic interaction atlas based on the displacement track to obtain a state prediction curve of the engineering mechanical equipment; and according to the state prediction curve and a preset scheduling instruction, an adaptive feedback network is constructed at an edge computing node of the Internet of Things, and then remote monitoring scheduling is performed on the engineering mechanical equipment based on the adaptive feedback network, so that operation state prediction and scheduling closed-loop control of the engineering mechanical equipment can be realized; therefore, the remote monitoring stability of the engineering mechanical equipment is improved.

The invention discloses an AI-based power distribution equipment partial discharge online diagnosis and positioning method, which relates to the technical field of equipment detection, and comprises the following steps: acquiring high-frequency signals in power distribution equipment in real time, sequentially calculating a topological inconsistency index, an echoing characteristic response abnormal index and a burst pulse ring chaos index, and calculating a false index based on the three results, so as to realize the partial discharge online diagnosis and positioning of the power distribution equipment. The method is used for judging whether the signal is a real signal generated by partial discharge of equipment. And if the false index is lower than a threshold value, determining that the discharge signal is a real discharge signal, and performing type identification and accurate positioning through a preset AI model. According to the method, non-discharge interference signals can be effectively identified, the fault judgment accuracy is improved, the false alarm rate is reduced, the trust of operation and maintenance personnel on a system diagnosis result is enhanced, the manual inspection pressure is relieved, and the maintenance cost is reduced.

The application provides a PI controller parameter setting method and device, relates to the technical field of automation control, is applied to a PI control system, the PI control system comprises a PI controller and a controlled object, and the method comprises the following steps: acquiring a characteristic response curve corresponding to the controlled object; acquiring a first-order inertia delay model by using a square difference integral minimum processing method according to the characteristic response curve; and determining target parameters corresponding to the PI controller according to a first formula acquired in advance through the first-order inertia delay model, so that the dynamic performance of a closed-loop response curve reaches an optimal state. The application finds optimal parameters by using the distribution of root loci on the real axis, realizes the optimal dynamic performance of the closed-loop response curve, and endows controller parameter setting and design with clear physical meanings.

The invention relates to the field of industrial intelligent nondestructive testing, in particular to a complex stress environment-oriented forging fatigue failure precursor signal intelligent identification method, which comprises the following steps of: firstly, constructing physical space mapping, extracting a streamline vector field based on forging finite element simulation data, and calculating a sensor path coupling factor; quantifying anisotropic constraint of the complex stress structure on signal propagation; dynamically setting a signal decomposition algorithm penalty factor according to a streamline geometric curvature, constructing a reference signal in combination with a load spectrum and a coupling factor, and extracting a feature response from stress environment monitoring data; then calculating the real-time signal-to-noise ratio, constructing an adaptive index, and combining the coupling factor and the directional transfer entropy to obtain a blocking index; and finally, setting double statistical windows based on a load period, completing failure precursor signal identification and judgment according to statistical characteristics of the double statistical windows, and remarkably improving the accuracy and timeliness of fatigue failure early warning through streamline field physical constraint and signal-to-noise ratio self-adaptive modulation.

This invention relates to the field of industrial intelligent nondestructive testing, and more specifically, to an intelligent identification method for fatigue failure precursor signals of forgings under complex stress environments. The method includes: first, constructing a physical space mapping; extracting streamline vector fields based on finite element simulation data of the forging; calculating sensor path coupling factors; and quantifying the anisotropic constraints of complex stress structures on signal propagation. Next, dynamically setting the signal decomposition algorithm penalty factor according to the streamline geometric curvature; constructing a reference signal by combining the load spectrum and coupling factors; and extracting characteristic responses from stress environment monitoring data. Subsequently, calculating the real-time signal-to-noise ratio (SNR), constructing an adaptive index, and obtaining a blocking index by combining the coupling factor and directional transfer entropy. Finally, setting a dual statistical window based on the load period; and completing the identification and judgment of failure precursor signals according to their statistical characteristics. Through streamline field physical constraints and adaptive SNR modulation, the accuracy and timeliness of fatigue failure early warning are significantly improved.

The invention discloses a dynamic feature regulation and control target detection method and system based on image quality perception, and relates to the field of computer vision and artificial intelligence, and the method comprises the steps: extracting multi-scale features of an input image; acquiring a global quality score and a local quality distribution diagram of the encoded image features; the quality-guided dynamic regulation and control are carried out on channel and space dimensions, the characteristic response preference can be adaptively adjusted, and the adaptability to the dimensions such as the structure or the texture is enhanced; performing fusion coding on the multi-scale features; and analyzing the regulated and controlled features, and outputting a target detection result. The method is suitable for various detection architectures, and the target detection accuracy and robustness of the model in a low-quality image scene can be improved.

The present application relates to touch human-computer interaction technical field, especially touch data processing method, system and touch screen. The method comprises the following steps: collecting the capacitance signal of touch surface, extracting the pressure value and contact area parameter of touch point, constructing the touch feature chain with time sequence association, and storing the touch feature chain as user operation data; identifying the pressing action sequence in the touch feature chain, extracting the force variation feature of pressing process, calculating the pressure change rate based on the force variation feature, identifying the force inflection point and the force inflection point, distinguishing physiological fluctuation and random noise, and generating pressure behavior feature; calculating the ratio of pressure change rate and area change rate to form pressure-area response function, determining key pressure interval, calculating function eigenvalue in each interval, and forming tool characteristic response data. The present application greatly improves the accuracy, naturalness and tool modeling ability of touch interaction through touch human-computer interaction technology.

The invention relates to the technical field of big data analysis, in particular to a big data management method and system for high-speed rail case maintenance, and the method specifically comprises the steps: obtaining contact impedance basic data and physical connection attribute data of a case according to time-frequency image analysis; importing the physical connection attribute data of the case into a micro-damage residual stress calculation strategy to calculate a structural stress evolution difference value and an auxiliary damage factor in real time; extracting contact impedance basic data of the case and airflow characteristic response distribution of an operation environment, and calculating the operation reliability probability of the case system according to the data; synchronously estimating and evaluating precise maintenance regulation and control requirements of each case state evolution monitoring unit in a time period; dynamically monitoring the operation reliability probability and precise maintenance regulation and control requirements of each case state evolution monitoring unit in a time period, and executing a corresponding maintenance strategy; according to the invention, the problem of low big data decision precision of preventive maintenance of the high-speed rail system in the prior art is solved.

The invention discloses a single-chip microcomputer intelligent environment monitoring system based on multi-sensor fusion, which belongs to the field of gas measurement, and comprises an array construction module used for constructing a sensor array, the response curves of the sensors to different gases are non-linearly different in a specific concentration interval through at least one physical adjustment or chemical adjustment, and the response curves of the sensors to the different gases are non-linearly different in the specific concentration interval; forming a response asymmetry matrix; the dynamic adjustment module is used for establishing a physical rule mapping mechanism according to the response asymmetry matrix and mapping the response of each sensor to a nonlinear parameter coordinate system, and each axis of the nonlinear parameter coordinate system corresponds to the characteristic response of different gases; and the dynamic displacement module is used for adjusting working parameters of the sensor according to the environment variables. Multi-sensor response can be converted into differentiated feature dimensions, the problem of cross sensitivity of low-cost sensors is effectively solved, interference signals are eliminated layer by layer through a logic decision link, target signals in mixed gas are accurately separated, and the distortion rate and the false alarm rate of detection results are reduced.

The invention relates to the technical field of touch man-machine interaction, in particular to a touch data processing method and system and a touch screen. The method comprises the following steps: collecting a capacitance signal of a touch surface, extracting a pressure value and a contact area parameter of a touch point, constructing a touch feature chain with time sequence association, and storing the touch feature chain as user operation data; identifying a pressing action sequence in the touch characteristic chain, extracting a force change characteristic of a pressing process, calculating a pressure change rate based on the force change characteristic, identifying a force generating inflection point and a force receiving inflection point, distinguishing physiological fluctuation and random noise, and generating a pressure behavior characteristic; and calculating the ratio of the pressure change rate to the area change rate to form a pressure-area response function, determining key pressure intervals, calculating function characteristic values in the intervals, and forming tool characteristic response data. According to the invention, through a touch control man-machine interaction technology, the accuracy, naturalness and tool simulation capability of touch control interaction are greatly improved.

The invention provides a frequency converter dynamic response optimization method and system and a medium, and relates to the technical field of frequency converters, and the method comprises the steps: receiving a motor drive signal, driving a first signal processing threshold to carry out sparse representation, determining a time-varying transfer sequence, and carrying out the amplification processing of the time-varying transfer sequence based on local phase expansion; the second frequency modulation node identifies the time-varying transfer sequence so as to determine a frequency conversion signal based on a Markov decision of directional frequency modulation in the first state space and the second action space; and triggering a third pulse optimization node, performing pulse coding on the frequency conversion signal, determining an optimized frequency conversion signal through relative equilibrium optimization based on switching loss and harmonic suppression, and performing control driving on the frequency converter. According to the invention, the technical problem of unstable control performance caused by insufficient response to dynamic characteristics of the motor due to the fact that a frequency converter control method in the prior art generally depends on preset fixed control parameters and simple frequency adjustment is solved.

The application provides an engineering mechanical equipment remote monitoring system and method based on an Internet of Things, relates to the technical field of equipment operation monitoring, and obtains frequency domain migration characteristics and energy attenuation characteristics by performing cross-scale characteristic response on the dynamic impact signal of the engineering mechanical equipment through an intelligent computing node, performing gradient operation on the operation thermal field data of the engineering mechanical equipment, and then obtaining thermal flow evolution characteristics; the dynamic interaction atlas is obtained by using a coupling analysis model; the node state and edge relationship of the dynamic interaction atlas are predicted by using space-time resonance convolution based on displacement trajectories, and the state prediction curve of the engineering mechanical equipment is obtained; the adaptive feedback network is constructed at the edge computing node of the Internet of Things according to the state prediction curve and the preset scheduling instruction, and then the engineering mechanical equipment is remotely monitored and scheduled based on the adaptive feedback network, so that the operation state prediction and scheduling closed-loop control of the engineering mechanical equipment can be realized, and the stability of the remote monitoring of the engineering mechanical equipment is improved.

This application discloses a method and system for detecting low-altitude unmanned aerial vehicles (UAVs) based on event stream frequency enhancement, relating to the fields of computer vision and UAV monitoring technology. The method includes acquiring raw event stream data of a scene to be detected; reconstructing brightness signals and performing frequency analysis on the raw event stream data to extract frequency features characterizing the rotor rotation characteristics of the UAV in the scene to be detected, and mapping the frequency features to a frequency embedding vector; generating dynamic gating parameters based on the frequency embedding vector, and using the dynamic gating parameters to modulate and fuse the event features to obtain frequency-enhanced features; and outputting the detection result of the UAV in the scene to be detected based on the frequency-enhanced features, the detection result including the UAV's category and location information. This application can effectively suppress background noise that does not conform to the rotor frequency characteristics, while enhancing the feature response of the UAV target, significantly improving the robustness and accuracy of UAV detection.

The invention discloses a high-pressure pipeline system component dynamic test method based on hydraulic excitation, and relates to the technical field of system vibration source detection, and the method comprises the steps: S1, building a high-pressure pipeline system employing a modular architecture and a multi-sealing protection structure; s2, a pulsating pressure exciter is used for generating periodic flow channel switching to generate pulsating pressure waves, control over the excitation frequency and amplitude is achieved by adjusting the rotating speed of a rotor, and pulsating pressure excitation in a fixed-frequency or fixed-amplitude or sweep-frequency mode is applied to the tested component; s3, adopting a distributed control architecture to realize coordinated regulation and control of excitation parameters and a pipeline system state, and synchronously acquiring pressure response and vibration response data; and S4, analyzing dynamic response characteristics of the component based on the acquired data, identifying a characteristic response frequency, and evaluating dynamic stability and structural integrity. According to the invention, the technical bottleneck of high-frequency pulsating excitation under the high-voltage zero-leakage condition is broken through, and an effective test means is provided for evaluating the reliability or dynamic response characteristics of components.

This invention relates to the field of low-voltage electrical control technology, and discloses a control method and system for a low-voltage intelligent control cabinet based on parameter adaptation. The method includes: performing deviation quantization mapping on the initial state parameter set of the low-voltage intelligent control cabinet to obtain a deviation vector; performing symbolic deconstruction on the deviation vector to obtain a sequence of symbolic changes; using a priori disturbance characteristic spectrum, weighting the symbolic change sequence based on characteristic responses to obtain disturbance decoupling weights for the deviation vector; performing disturbance recovery on the deviation vector based on the disturbance decoupling weights to obtain the true deviation amplitude of the deviation vector; performing transient compensation on the current control output value of the low-voltage intelligent control cabinet according to the true deviation amplitude to obtain a control correction amount for the current control output value; and performing fusion limiting encoding on the control correction amount and the current control output value to obtain the control command for the low-voltage intelligent control cabinet. This invention can improve the efficiency of a low-voltage intelligent control cabinet control based on parameter adaptation.

The application provides a variable frequency converter dynamic response optimization method, system and medium, and relates to the technical field of variable frequency converters. The method comprises the following steps: receiving a motor driving signal, driving a first signal processing threshold to perform sparse representation, determining a time-varying transfer sequence, and the time-varying transfer sequence exists amplification processing based on local phase expansion; a second frequency modulation node identifies the time-varying transfer sequence to determine a variable frequency signal based on a first state space and a second action space, and a directional frequency modulation Markov decision; a third pulse optimization node is triggered to perform pulse coding on the variable frequency signal, and the optimized variable frequency signal is determined through relative balance optimization based on switching loss and harmonic suppression, and the variable frequency converter is controlled and driven. The application solves the technical problem that the variable frequency converter control method in the prior art usually depends on preset fixed control parameters and simple frequency adjustment, the dynamic characteristic response of the motor is insufficient, and the control performance is unstable.

The invention provides a bearing residual life prediction method based on a gated convolutional neural network. The bearing residual life prediction method comprises the following steps: step 1, collecting bearing related data as input of a prediction network; step 2, carrying out compression fusion on the data features; step 3, re-checking the characteristic response; 4, constructing a position vector; 5, predicting the RUL of the bearing through a Relu activation function; and step 6, training the prediction network, reserving optimal training parameters, and outputting a prediction result. According to the method, expansion causal convolution is adopted, the receptive field is flexibly widened, the network is helped to memorize past information, position coding is adopted to a mechanical RUL prediction modeling task, position information is fused into features, and the information distinguishability of the prediction network is enhanced.

The invention provides a micro-damage non-linear Lamb wave nondestructive measurement detection and imaging method, which comprises the following steps of: exciting a non-linear Lamb wave to generate non-linear interaction with micro-damage in a tested sample by adopting a composite signal containing two different frequency components, and generating a non-linear characteristic response; synchronously acquiring a time domain signal and a frequency domain signal through a hybrid sensing array; respectively carrying out feature extraction, and then carrying out weighted fusion to obtain an enhanced micro-damage nonlinear feature vector; constructing a quantitative model fusing physical information, inputting the micro-damage nonlinear feature vector and the material physical parameters of the tested sample into the model, and outputting a quantitative measurement result of the micro-damage geometric parameters; executing a dynamic adaptive imaging algorithm based on the quantitative measurement result and the multi-modal signal, and generating a micro-damage two-dimensional imaging result; and feeding back a two-dimensional imaging result to a control unit of the hybrid sensing array, and adjusting spatial layout parameters of the sensing array so as to optimize the micro-damage detection precision of a subsequent detection period.

This invention discloses a low-power electronic nose system and control method based on a spiking neural network, belonging to the field of electronic noses and intelligent sensing systems. The system uses a spiking neural network as the algorithm module for the electronic nose. A low-power management module establishes bidirectional signal connections with both the sensor array module and the algorithm module. It reads the pulse sequence output by the algorithm module and the characteristic response signal of the sensor array module, generates a mode control signal, and feeds it back to the algorithm module to control the operating mode of the electronic nose system. Simultaneously, it outputs a rotation control signal to the sensor array module to control the sensors to work in rotation, forming a closed-loop control. This invention can effectively reduce the power consumption of the electronic nose and plays an important role in scenarios with inconvenient power supply, such as portable testing equipment and remote industrial sites.