Abstract: A method for classifying a response signal of acceleration data of a structure includes obtaining at least one signal feature of a response signal, inputting the at least one signal feature into an artificial neural network, and classifying, using the artificial neural network, the response signal as an impact event or a non-impact event. One or more signal features may be used, including a response length feature, a number of peaks feature, a spectral energy feature, a dominant frequency feature, a maximum response feature, a center of mass feature, a slope feature, an average peak power feature, a response symmetry feature, or combinations thereof. One or more artificial neural networks may be used. The artificial neural networks may be trained using different combinations of signal features.

Abstract: A method for classifying accelerometer data of a structure includes obtaining acceleration data from an accelerometer positioned to monitor a structure and receive vibrations from the structure. The acceleration data includes a plurality of measurements. The method includes selecting a subset of the plurality of measurements as an event signal. The subset of the plurality of measurements have a magnitude that exceeds a noise floor and includes a first measurement, a second measurement, and a plurality of intermediate measurements between the first measurement and the second measurement. The plurality of intermediate measurements exceed an event threshold. The event threshold is greater than the noise floor. The method includes comparing the event signal to a set of historical events and classifying the event signal as an event type.

Abstract: A system for monitoring integrity of a structure includes at least one sensor module and a gateway. The gateway receives data packets from the sensor module(s) and periodically pushes the data packets to an offsite system without receiving a request from the offsite system. Additional data packets may be transmitted on request. The system may include a solar power supply. The system may include a communication module to transmit data packets over a communications link. The communication module may have a dynamic IP address. The communication module may remain in a standby state until additional information is received from the gateway. A method for monitoring integrity of a structure includes determining a power failure and pushing a packet to the offsite system indicating the power failure. A method for monitoring integrity of a structure includes determining an event and transmitting a data packet corresponding to the event.

Abstract: A method for classifying a response signal of acceleration data of a structure includes obtaining at least one signal feature of a response signal, inputting the at least one signal feature into an artificial neural network, and classifying, using the artificial neural network, the response signal as an impact event or a non-impact event. One or more signal features may be used, including a response length feature, a number of peaks feature, a spectral energy feature, a dominant frequency feature, a maximum response feature, a center of mass feature, a slope feature, an average peak power feature, a response symmetry feature, or combinations thereof. One or more artificial neural networks may be used. The artificial neural networks may be trained using different combinations of signal features.

Abstract: A method and system for monitoring the integrity of a structure such as a building or a bridge includes taking accelerometer readings using an accelerometer and taking inclinometer readings using an inclinometer. The accelerometer and inclinometer each take readings in at least one axis, with one coincident axis between the two. The accelerometer readings are preferentially sampled at a higher rate than the inclinometer readings. Accelerometer readings verify inclinometer readings, and vice-versa. Using acceleration readings, it can be determined whether, when, and at what frequency inclination readings should be taken. The inclinometer can be powered down as long as accelerometer readings indicate that the environment would strain the inclinometer. Inclinometer readings can also be modified and corrected using inclinometer readings. Data accuracy and reliability are enhanced, and the overall integrity of a structure is dynamically monitored even as the structure and its environment change over time.