99results about "Detecting faulty hardware using neural networks" patented technology

The invention relates to a fault diagnosis method for a rolling bearing under variable working conditions, and the method solves a problem that the universality of a deep learning model becomes poor because of the complex and variable working conditions of mechanical equipment through combining with a transfer learning algorithm on the basis of employing a convolutional neural network learning model. The method comprises the steps that firstly, data collected under different working conditions is cut to divide samples, the samples are preprocessed through FFT, then low-level features of the samples are extracted through improved ResNet-50, and then a multi-scale feature extractor analyzes the low-level features from different angles to obtain high-level features to serve as input of a classifier; in the training process, high-level features of a training sample and a test sample are extracted at the same time, the conditional distribution distance between the training sample and the test sample is calculated and serves as one part of back propagation of a target function to achieve intra-class self-adaption, the influence of domain drift is reduced, and a deep learning model can bebetter qualified for a fault diagnosis task under the variable working condition.

A method for analyzing the use of a work machine is disclosed. In one embodiment, the method may include providing a computer with a neural network on the work machine. Further, the method may include inputting data to the computer, at least a portion of the data associated with a load experienced by one of the components of the work machine. The neural network, when executed by the computer may then classify a current operation of the work machine into one of a plurality of types of operations.

Methods for system failure prediction include clustering log files according to structural log patterns. Feature representations of the log files are determined based on the log clusters. A likelihood of a system failure is determined based on the feature representations using a neural network. An automatic system control action is performed if the likelihood of system failure exceeds a threshold.

A storage device includes a nonvolatile memory device including a plurality of memory blocks, each including a plurality of memory cells connected to a plurality of word lines, and a controller configured to perform a first read operation on memory cells connected to a selected word line included in a selected memory block based on a request of an external host device. The controller is further configured to perform a check read operation that checks a reliability of the memory cells of the selected memory block after performing the first read operation. In the check read operation, the controller is further configured to select and perform one of an actual check and a machine learning-based check.

A method or apparatus for monitoring a system by detecting misbehaving components in the system is presented. A computing device receives historical data points based on a set of monitored signals of a system. The system has components that are monitored through the set of monitored signals. For each monitored component, the computing device performs unsupervised machine learning based on the historical data points to identify expected states and state transitions for the component. The computing device identifies one or more steady components based on the identified states of the monitored components. The computing device also receives real-time data points based on monitoring the set of signals from the system. For each identified steady component, the computing device examines the received real-time data points for deviation from the expected state and state transitions of the steady component. The computing device reports anomaly in the system based on the detected deviations.

The invention discloses a complex analog circuit fault identification and estimation method and system, and belongs to the field of power electronic circuit fault prediction, and the method comprisesthe steps: building a degradation simulation model of a to-be-diagnosed analog circuit, and carrying out parameter aging simulation experiment of different devices; extracting a series of time domainfeatures of the output signal by using a time sequence transformation method, and establishing health indices of the devices based on the angular similarity; whether the circuit is degraded and a degradation starting point are identified in combination with a time sliding window and a convolutional neural network; reusing a part of hidden layers in the previous identification network and the long-short-term memory cycle network to perform health state estimation on an analog circuit in degradation; and evaluating prediction accuracy. The health state of the analog circuit can be effectively estimated while the fault state starting point of the analog circuit is accurately recognized, and the invention has the advantages of being high in operation efficiency and accurate in recognition.