A tool management system of a machine tool capable of determining an appropriate time to replace a tool used by a machine tool is provided. The tool management system includes: at least one detection unit among: a vibration detection unit attached to a spindle that supports a tool of a machine tool to detect vibration; a sound detection unit provided in the vicinity of the spindle to detect acoustic waves produced during operation of the machine tool; and a servo motor current value detection unit that detects a current value of a servo motor of a driving device of the machine tool; a tool replacement determination unit that determines the necessity to replace the tool on the basis of information related to a detection value of at least one of the vibration, the acoustic waves, and the current value detected during operation of the machine tool; and a detection start/end command setting unit that adds commands for a detection start point and a detection end point of at least one of the vibration, the acoustic waves, and the current value of the servo motor to a machining program.

A tool wear monitoring and predicting method is provided, and uses a hybrid dynamic neural network (HDNN) to build a tool wear prediction model. The tool wear prediction model adopts actual machining (cutting) conductions, sensing data detected at the current tool run of operation and the predicted tool wear value at the previous tool run of operation to predict a predicted tool wear value at the current tool run. A cyber physical agent (CPA) is adopted for simultaneously monitoring and predicting tool wear values of plural machines of the same machine type.

A cutting apparatus having a cutting blade for cutting a workpiece held on a chuck table is disclosed. The cutting apparatus includes an elastic wave detecting sensor for detecting an elastic wave due to the rotation of the cutting blade, a reference data storing section configured to store reference data as a set of reference processing elastic wave data and reference idling elastic wave data, a threshold value storing section, a ratio calculating section, and a determining section.

A machine tool includes an input interface configured to receive an instruction, an actuator configured to actuate, control circuitry configured to control an actuation of the actuator based on the instruction, a component having a physical state to be affected by the actuation, a sensor configured to detect the physical state, and a computer connected to the control circuitry via an external communication interface. The computer is configured to receive a signal from the sensor, generate, based on the signal, rough state-description data relevant to an occurrence of an abnormality in the component, transmit the rough state-description data to the control circuitry, generate detailed state-description data based on the signal, the detailed state-description data being more informative than the rough state-description data such that the detailed state-description data facilitates identifying an abnormal part in the component, and transmit the detailed state-description data to a monitoring computer via a communication network.

An automated constructing method of cloud manufacturing service is provided for a distributed system including a virtual machine and a service manager. The method includes: obtaining a library package which is locally built, analyzing the library package to obtain key information, and generating a library information file; automatically generating a project source code file according to the library information file, and generating a web service package according to the project source code file; and deploying, by the service manager, the web service package on the virtual machine.

A method and system of a predictive maintenance IoT system comprises receiving a plurality of sensor data over a communications network and determining one or more clusters from the sensor data based on a pre-determined rule set. Further, the sensor data is classified through a machine learning engine and the sensor data is further base-lined through a combination of database architecture, data training architecture, and a base-lining algorithm. Intensity or degree of fault state is mapped to a fuel gauge to be depicted on a user interface and a predictive maintenance state is predicted through a regression model and appropriate alarm is raised for user action.

An air tool monitoring apparatus includes a housing having a hollow chamber formed therein, and also having an inlet and an outlet formed therein, each of the inlet and an outlet in communication with the chamber. The apparatus also includes first and second sensors for sensing condition indicative of tool usage and wear, a battery disposed in the housing, a generator for recharging the battery, and a microprocessor operatively connected to the housing and including a timer, a memory storage module, and a unique identifier. The apparatus may include a baffle for guiding air past the generator. The apparatus further includes a switch for starting and stopping the timer, and a communication device for sending data from the microprocessor to a data collection device. Methods of using the apparatus, along with systems for monitoring and reporting on usage of multiple air tools equipped with the apparatus, are also described.

A spindle with intelligent auto-detection system may comprise a spindle, a shell configured for covering the spindle, a first conducting ring, a second conducting ring and at least a sensor. The spindle has a connecting section and a working section, and the connecting section is configured for connecting a power unit of a processing machine. Moreover, a tool is secured on the working section, and the sensor is positioned in an inner tube of the spindle. The first conducting ring and the second conducting ring in a recess of the shell are respectively electrically connected to the sensor and an analytical instrument. When the spindle is spinning, the sensor is adapted to measure various data of statuses of the spindle and the processing machine, and the obtained data is configured to be sent to the analytical instrument, thereby achieving monitoring effect.

A system and method for monitoring and predicting wear of a cutting tool used for machining a workpiece is disclosed. The system includes a cutting tool having a shank and a cutting head. The system also includes a split, modular and wireless wear detection system including one or more sensors mounted to the cutting tool for providing a data signal representative of a physical condition of the system, and a data recording and data transmitting device for recording the data signal from the one or more sensors and for generating and transmitting a data signal to a processor. The processor applies a machine learning data processing technique in real time to monitor and/or predict a condition of various components and/or parameters of the system during a metal cutting operation.

The present disclosure relates to a method for online monitoring defect of a milling tool, comprising the steps of: 1) installing a vibration sensor module on a machine tool spindle; 2) acquiring initial sample data; 3) setting a threshold value ?S.sub.0 with a time interval of T; 4) measuring vibration signals of n blades in x, y and z directions in each period T.sub.0; 5) shaping to obtain n strong vibration cutting wave data respectively formed by n blades in x and y directions in each period T.sub.0; 6) analyzing and processing the strong vibration cutting wave data to obtain the difference ?S.sub.0.sup./ between the cutting strong vibration wave areas formed by each blade in each period T.sub.0; 7) outputting a blade wear or defect signal to a display alarm module according to the constraint conditions by a data comparing and analyzing module, and giving an alarm by a display alarm module.