8 results about "Vibration signal analysis" patented technology

The present application relates to a kind of powder packaging machine transmission component fault pre-diagnosis method based on vibration signal analysis, the present application is accurate to collect multiple source vibration signals, standardization processing of time-frequency characteristics, generate fault semantic anchor point library in combination with prior knowledge of dynamics and under the training method of multiple loss constraint convolutional neural network, realize the adaptive alignment of vibration signal hidden space feature and physical fault mechanism.The present application outputs the joint attribution time-frequency graph of specific fault type, and the coincidence degree of model attention area and theoretical fault frequency label is based on physical consistency check, significantly improve diagnostic accuracy and explainability, effectively assist equipment operation decision, the present application is by constructing the fault semantic anchor point library based on physical mechanism, and it is embedded in the hidden space optimization process of convolutional neural network in differentiable way, effectively overcome the problem that traditional data-driven model is generally present in powder packaging machine transmission chain fault diagnosis.

The present application belongs to the technical field of fault diagnosis, and particularly relates to a belt conveyor bearing fault diagnosis method and system based on temperature and vibration signal analysis. The method comprises the following steps: removing outliers and correcting baseline drift of the collected temperature and vibration signals respectively; using kurtosis and envelope entropy to optimize variational mode decomposition to extract fault components and generate time-frequency diagrams, and using temperature change rate to map weighting coefficients for reconstruction and high-frequency gain compensation; splicing the weighted time-frequency diagram and the two-dimensional temperature diagram into a three-dimensional tensor, inputting the residual network of the band coordinate attention and the deformable convolution branch, and using the temperature energy proportion to adjust the joint loss output to output the diagnosis result. The present application effectively enhances the multi-modal feature expression capability of the model under complex variable working conditions by establishing the physical correlation between temperature change and high-frequency vibration, and significantly improves the diagnosis accuracy and generalization performance.

The application relates to the technical field of circuit breaker fault diagnosis, and discloses a circuit breaker internal defect online detection method based on vibration signal analysis. According to a standard sequence of circuit breaker vibration acceleration, opening and closing coil current and time data, and in combination with a vibration characteristic analysis platform, time domain, frequency domain and time-frequency domain characteristic data of a circuit breaker operating parameter are classified and accurately extracted, so that the mechanical operating state of a circuit breaker internal structure is deeply mined in multiple dimensions based on time domain, frequency domain and time-frequency domain of circuit breaker vibration signals. According to circuit breaker vibration time domain data, circuit breaker vibration frequency domain data and circuit breaker vibration time-frequency domain data, and in combination with an artificial intelligence algorithm and different structure fault standard vibration signal characteristic data of a circuit breaker established based on big data, comprehensive intelligent diagnosis of a circuit breaker internal structure fault is carried out, so that intelligent and accurate diagnosis of a circuit breaker internal structure fault based on circuit breaker vibration signal characteristics is realized.

The present application relates to the engine detection technical field, specifically to a kind of engine knock fault detection method based on vibration signal analysis.Method includes: obtaining the voltage vibration signal and pulse square wave signal of engine and pretreatment, obtain vibration digital sequence and pulse timestamp set;From pulse timestamp set, the difference of adjacent timestamp is extracted as time span, combined with physical mechanical angle interval, rigid body dynamics equation is constructed, instantaneous angular acceleration is calculated, then vibration digital sequence is mapped to crankshaft rotation space, and equal-angle vibration sequence is obtained;Equal-angle vibration sequence is converted in frequency domain and filtered out mechanical noise, and knock residual signal is obtained, the knock characteristic energy in monitoring window is calculated, when exceeding preset safety threshold, control adjustment instruction is issued.The present application restores the mechanical running state under transient variable load, effectively suppresses order ambiguity defect, reduces underlying operation load and response delay.

The present application relates to the technical fields of machine state diagnosis and vibration signal analysis, and discloses a motor mechanical fault frequency detection and determination method, device, equipment and medium, comprising: acquiring motor operating parameter signal detection periodic fluctuation, collecting vibration acceleration signal when the periodic fluctuation remains unchanged after control parameter adjustment, analyzing time domain characteristics to detect periodic impact related to rotating speed, performing frequency domain analysis to detect mechanical fault frequency, filtering vibration acceleration signal to detect rotating frequency multiplication component, and determining that the motor has a feedback component position fixed type fault when there is periodic impact and no mechanical fault frequency and rotating frequency multiplication is detected. The present application accurately identifies the feedback component position fixed type fault caused by grating pollution by combining operating parameter and vibration signal analysis, utilizing comprehensive judgment of control parameter response, frequency domain characteristics and frequency multiplication detection, and improving the accuracy and reliability of fault positioning.

The application discloses a kind of based on adaptive enhanced EEMD's mixed-flow water turbine vibration signal processing method, it is related to vibration signal analysis and processing technical field.Mixed-flow water turbine vibration signal is collected, and wavelet denoising is carried out;Adaptive band weighted noise is injected to the signal after denoising, and the signal after adding noise is obtained;The signal after adding noise is decomposed by EMD, and the stop condition is modified to double-constraint mode stop criterion in the EMD decomposition process, using the double constraint of extreme point quantity and residual energy change rate, obtain IMF component set and residual;IMF is effectively screened based on fault sensitivity index IMF component, and compensation term is introduced in residual, to obtain the final decomposition result, as vibration signal processing result.Through band weighted noise injection, background noise is effectively suppressed, and through double-constraint stop criterion and fault sensitivity screening, modal aliasing is effectively suppressed, so that fault characteristics can be more accurately separated and signal-to-noise ratio is improved.

A system for continuously monitoring at least one machine including at least one magnetic sensor sensing magnetic fields emitted by at least one machine, at least one vibration sensor synchronously sensing vibrations emitted by the at least one machine, a signal analyzer receiving at least a portion of the magnetic field emission signals and vibration signals and performing analysis thereof, the signal analyzer providing an output based on the analysis, the output including at least an indication of a condition of the at least one machine, and a control module initiating at least one of a repair event on the at least one machine, an adjustment to a maintenance schedule of the at least one machine and an adjustment to an operating parameter of the at least one machine based on the indication, whereby efficacy of the at least one machine is improved.