Buildings' Biaxial Tilt Assessment Using Inertial Wireless Sensors and a Parallel Training Model

Abstract

Applications of MEMS-based sensing technology are beneficial and versatile. If these electronic sensors integrate efficient processing methods, and if supervisory control and data acquisition (SCADA) software is also required, then mass networked real-time monitoring will be limited by cost, revealing a research gap related to the specific processing of signals. Static and dynamic accelerations are very noisy, and small variations of correctly processed static accelerations can be used as measurements and patterns of the biaxial inclination of many structures. This paper presents a biaxial tilt assessment for buildings based on a parallel training model and real-time measurements using inertial sensors, Wi-Fi Xbee, and Internet connectivity. The specific structural inclinations of the four exterior walls and their severity of rectangular buildings in urban areas with differential soil settlements can be supervised simultaneously in a control center. Two algorithms, combined with a new procedure using successive numeric repetitions designed especially for this work, process the gravitational acceleration signals, improving the final result remarkably. Subsequently, the inclination patterns based on biaxial angles are generated computationally, considering differential settlements and seismic events. The two neural models recognize 18 inclination patterns and their severity using an approach in cascade with a parallel training model for the severity classification. Lastly, the algorithms are integrated into monitoring software with 0.1° resolution, and their performance is verified on a small-scale physical model for laboratory tests. The classifiers had a precision, recall, F1-score, and accuracy greater than 95%.

Keywords: biaxial tilt angle; building applications; inclination severity; real-time measurement; signal processing; structural health monitoring; time-series algorithms.

Figure 1

System overview. Sensor including IMU + the wireless communication module with the IEEE 802.15.4 protocol and a rechargeable battery. (a) Schematic of the four sensors installed on each of the walls of the rectangular building. (b) Local computer acquiring the sensors’ signals through a router. (c) Client–server architecture (TCP/IP protocol) of the system. (d) Monitoring of one or several buildings in a control room from any geographical location.

Figure 4

Algorithm block diagram of successive repetitions for a sampling instant and each of the eight biaxial tilt angles. The explanation of (a–d) may be read in the paragraph before Figure 4.

Figure 6

The possible evolution of the tilt angles. (a) The wall is perpendicular to its base, and there are no tilts. (b) The wall has tilted over time; the Y-axis is tilted clockwise and is represented by a positive sign.

Figure 7

A simplified scheme of the 18 base patterns proposed in this work.

Figure 10

Confusion matrix to evaluate NN_1. The Y-axis represents the accurate classification assigned to the patterns (true label), while the X-axis indicates the classification given by the network (predicted label). The diagonal values show the correctly labeled patterns; the neural network classified them as the same pattern to which they belong. Table 2 shows the performance metrics of the multiclass classifier using macro-average, with values truncated to two decimal places.

Figure 12

Parallel recognition model training.

Figure 15

A small-scale physical model for laboratory tests in rectangular buildings.

Figure 16

(a) IMU installation schematics. (b) Screws for tilt simulation. (c) Digital inclinometer.

Figure A1

Clinic Prensa, which is a leaning building and is under supervision.

Figure A2

The Palace of Fine Arts in Mexico City.

Figure A3

(a) The main screen of the user interface. (b) A pop-up alarm screen.

Figure 2

An orientation of frame B relative to frame A can be attained through a rotation of the angle θ around an axis $A_{\widehat{r}}$ defined in frame A.

Figure 3

Quaternion rotation method to obtain gravity acceleration.

Figure 5

(a) Reference system for the sensors. (b) Example of pattern 0. (c) Angle rotation.

Figure 8

General diagram of the classification model. (a,b) Show the four sensors and the four biaxial tilts, respectively. (c) The classifier of base patterns. (d) The computer model for the pattern severity classification.

Figure 9

General schema of the classifier of base biaxial tilt patterns ($\mathit{N}{\mathit{N}}_{\mathbf{1}}$).

Figure 11

Multilayer perceptron neural network (NN₂) topology to classify biaxial tilt severity.

Figure 13

The classifier of the base biaxial tilt pattern and parallel recognition model implementation to classify the tilt severity. (a) The input of the four biaxial tilts, illustrated initially in Figure 8b. (b) The classifier of base biaxial tilt patterns of Figure 8c. (c) This output allows the choice of a set of weights and biases (see Figure 12c). (d) The classifier of the tilt severity (see Figure 11).

Figure 14

Most representative confusion matrix of NN₂.