Abstract: A machine diagnostic system is provided which includes a host computer for determining a health state of a machine. The host computer is operatively coupled to a network backbone. The system also includes a machine diagnostic module adapted to be integrally mounted to a machine, the machine diagnostic module being operatively coupled to the network backbone. The machine diagnostic module collects data relating to operation of the machine and preprocesses the data, and the host computer analyzes the preprocessed data in determining the health state of the machine. The machine diagnostic system includes a system architecture which facilitates the machine diagnosis. The system architecture includes several software layers which provide for collecting and preprocessing machine data, transmitting the collected and/or preprocessed data over a network and analyzing such for machine diagnosis and process diagnosis.

Abstract: A micro-viscosity sensor for measuring the viscosity of a lubricant. The micro-viscosity sensor including at least one finger-like element or an array of finger-like elements vertically extending from the surface of a semiconductor base, the at least one finger-like element being oscillated at a desired frequency. The power required to oscillate the at least one-finger-like element is monitored because the power required is a function of the viscosity of the lubricant. The sensor also includes a temperature detector, wherein the thermal conductivity of the temperature detector varies in correspondence with the temperature of the lubricant. A first set of electrical contacts provides for electrical connection to the at least one finger-like element; and a second set of electrical contacts provides for electrical connection to the temperature detector.

Abstract: A system for training a neural network to synthesize vibration data relating to the operation of a machine. The system includes a first sensor operatively coupleable to the machine, the first sensor adapted to obtain at least one vibration signal relating to the operation of the machine. The system further includes a second sensor operatively coupleable to a power lead of the machine, the second sensor adapted to obtain at least one current signal relating to the operation of a machine. Additionally, the system includes a neural network operatively coupleable to the second sensor, the neural network being trainable to generate at least one synthesized vibration signal from the current signal, wherein the synthesized vibration signal is substantially equivalent to the vibration signal obtained from the first sensor.

Abstract: A method and apparatus for real-time electric motor diagnostics and condition monitoring. While the motor is energized, dynamic operating parameters are determined and a notification signed is generated if predetermined criterion are satisfied. The diagnostic apparatus is integrated with the motor and includes a set of sensors, a processing unit, a memory and an output interface for communicating alarms, warnings and calculated operating parameter values or the like to a display device and to an external supervisor having wireless paging capability to alert a remote operator or maintenance personnel. In a normal operating mode, the processing unit calculates a general class of derived motor operating parameters such as over-temperature, over-voltage, over-current, excessive vibration, and phase imbalance.

Abstract: An opto-mechanical torque sensing device suitable for use with rotary machinery integrates a photoelastic polymer detector, a light source, a photoelastic image sensor and an artificial intelligence neural network and algorithm. The photoelastic polymer is formed into a hollow cylinder and bonded to metal collars located at each end of the cylinder. The collars serve to readily place the cylinder detector over a machine shaft and affix it to the shaft using a keyway, setscrew, or spring pin. Alternatively, split collars and a split sleeve can also be used to clamp the detector to the shaft. In the presence of polarized light, the photoelastic polymer detector generates an optical fringe pattern that varies as a function of torque applied to the shaft or other machine part on which the detector is mounted. The artificial intelligence neural network learns the mapping relationship between the observed optical fringe pattern and the applied torque using a training procedure.