A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.

A transducer includes a conductive sheet installed on a sheath of a cable, an insulative sheet installed on the conductive sheet, holes being formed in predetermined positions of the insulative sheet, and a conductive sheet installed on the insulative sheet, holes being formed in predetermined positions of the conductive sheet. The transducer has structure in which, when the cable is tightened by the screw from the top of the conductive sheet and fixed, the distal end of the screw comes into contact with the conductive sheet passing through the holes formed in the insulative sheet and the conductive sheet, and the conductive sheet and the conductive sheet are electrically connected.

The error diagnosis device has: an input unit that receives a downstream pressure value and an upstream pressure value, said downstream pressure value being detected on the downstream side of a fuel pump and said upstream pressure value being detected on the upstream side of the fuel pump; and a determination unit that, if the downstream pressure value is less than a preset first threshold value, determines whether or not the upstream pressure value is less than a preset second threshold value. The determination unit determines that an error has occurred further upstream than the fuel pump if the upstream pressure value is less than the second threshold value and determines that an error has occurred in the fuel pump if the upstream pressure value is at least the second threshold value.

The present disclosure relates to a fault diagnosis method of a reciprocating machinery based on a keyphasor-free complete-cycle signal. The method includes the following steps: 1) building a complete-cycle vibration signal image library; 2) training an image recognition model; 3) acquiring a complete-cycle data on a keyphasor-free basis; 4) building an automatic feature extraction model; and 5) inputting a hidden layer feature of an autoencoder into a support vector machine (SVM) classifier to obtain a diagnosis result. By using a deep cascade convolutional neural network (CNN), the present disclosure achieves the goal of complete-cycle data acquisition on a keyphasor-free basis, solves the problems that traditional intelligent fault diagnosis relies on a keyphasor signal and real-time diagnosis fails due to insufficient installation space. In addition, by using an autoencoder for automatic feature extraction, the present disclosure avoids manual feature selection, reduces labor costs.

The present disclosure relates to a fault diagnosis method of a reciprocating machinery based on a keyphasor-free complete-cycle signal. The method includes the following steps: 1) building a complete-cycle vibration signal image library; 2) training an image recognition model; 3) acquiring a complete-cycle data on a keyphasor-free basis; 4) building an automatic feature extraction model; and 5) inputting a hidden layer feature of an autoencoder into a support vector machine (SVM) classifier to obtain a diagnosis result. By using a deep cascade convolutional neural network (CNN), the present disclosure achieves the goal of complete-cycle data acquisition on a keyphasor-free basis, solves the problems that traditional intelligent fault diagnosis relies on a keyphasor signal and real-time diagnosis fails due to insufficient installation space. In addition, by using an autoencoder for automatic feature extraction, the present disclosure avoids manual feature selection, reduces labor costs.

A tool abnormality determination system is provided. The tool abnormality determination system includes: a tool that machines a workpiece; a control device that includes a storage portion in which a monitoring range is stored and an arithmetic portion for comparing the monitoring range to a load of the tool during machining; and an interface device that can notify, when the load of the tool exceeds the monitoring range, an operator of a question regarding whether or not the tool is in an abnormal condition other than abrasion.

A selector lever with redundant detent pins and detent plates and a method for using the selector lever to test for a failure of one or more detent pins. The selector lever includes at least two slides for independently moving the detent pins within the detent plates. The independent slides allow one detent pin to remain engaged. With only one detent pin engaged, the operator may test the ability to move the shaft and conclude whether or not the detent pin has failed.

An inspection system for assessing and visualizing structural damage to a structural platform comprises sensors operatively coupled to the structural platform that assess structural damage to or failure of the structural platform. A structural health monitoring processor operatively coupled to the sensors determines structural damage in response to the sensors. At least one RF transponder and associated reader determines the position of the structural platform relative to a user augmented reality viewing device. The user augmented reality viewing device includes a camera that captures images of the structural platform. The user augmented reality viewing device displays real world images of the structural platform and virtual indications of determined structural damage that are dependent on the position and orientation of the user augmented reality viewing device relative to the structural platform.

A method includes capturing multivariate time-series data comprising two or more data sets from a system captured over a past time period and a present time period, applying at least two sliding time windows to the multivariate time-series data in determining respective data matrices, computing an orthonormal matrix for each of the data matrices, wherein the orthonormal matrix is a signature of fluctuation patterns of a respective data matrix, computing a difference between at least two of the data sets in the past and the present time periods through the orthonormal matrices, and detecting a fault in at least one of the systems by comparing the difference to a threshold.

A planar motor rotor displacement measuring device and its measuring method are provided. The motor is a moving-coil type planar motor. The device comprises probes, two sets of sine sensors, two sets of cosine sensors, a signal lead wire and a signal processing circuit. The method is arranging two sets of magnetic flux density sensors within a magnetic field pitch τ along two vertical movement directions in the rotor located in the sine magnetic field area. Sampled signals of the four sets of sensors are respectively processed with a frequency multiplication operation, four subdivision signals are obtained, the zero-crossing points of the four subdivision signals are detected, and then two sets of orthogonal pulse signals are generated. The pulse number of the orthogonal pulse signals is counted, and phase difference of the two sets of orthogonal pulse signals is respectively detected.