2.1. Real-Time Measurements
Figure 1 shows a general diagram of the system consisting of four inertial measurement units (IMUs) with MEMS technology. Each IMU incorporates an accelerometer, gyroscope, and magnetometer. The digital-output triple-axis accelerometer has a full-scale programmable range of ±2 g, ±4 g, ±8 g, and ±16 g with integrated 16 bit ADC.
The digital-output triple-axis gyroscope has a full-scale range until ±2000°/s and integrated 16 bit ADC. The triple-axis silicon monolithic Hall-effect magnetic sensor has an output data resolution of 14 bit (0.6 μT/LSB) or 16 bit (15 μT/LSB) and a full-scale measurement range of ±4800 μT.
Figure 1a shows a schematic of the four sensors installed on each of the walls of the rectangular building. Each sensor includes an IMU, a wireless communication module with the IEEE 802.15.4 protocol (WIFI-Xbee) to create a fast point-to-multipoint network and a rechargeable battery.
A local computer acquires the sensor signals through a router, as shown in
Figure 1b,c. The system uses a client–server architecture (TCP/IP protocol) to monitor one or several buildings in a control room from any geographical location (
Figure 1d).
The sensors’ location reference considers the front of the building. This work calculates the inclination angle, assuming no vertical and horizontal wall deformations exist. According to the expert knowledge of structure and architecture specialists, the recommendation for this project stage was to place the sensors as high as possible on each wall. Likewise, the suggestion was applied to the small-scale physical model for laboratory tests.
Although outside the scope of this work, for measurements related to vertical and horizontal wall deformations, more than one sensor should be used per wall. The sensor network and software were designed considering possible project growth.
Cities in lacustrine and seismic zones can have many buildings with diverse damage, including biaxial inclinations. They are still habitable but require frequent inspections, which must be carried out in medium periods. The situation is even more critical after a seismic event. Therefore, each vulnerable building must have a diagnosis and inventory of its main damages, which still do not put its habitability at risk but require periodic supervision. The biaxial inclination is typical in buildings on soil with differential settlements. For this case, the experts evaluate them periodically using manual high-precision inclinometers.
On the basis of IMU measurements, the calculated inclination for this work ranged from 0° to 1.5°, with a resolution of 0.1°. The proposed method allows a resolution of <0.1° depending on the used sensors.
The model uses angles based on relative variables (deviation variables) concerning an initial inclination that could exist when the measurements and monitoring begin; there may be zero or nonzero initial slope in each of the four walls. This initial tilt information must be obtained by expert inspection before the real-time monitoring system begins to operate.
Additionally, accelerometer signals contain electrical noise, and the system can detect temporary vibrations. For such reasons, the selected sampling frequency is 50 samples per second (S/s) to apply digital filters with a cutoff frequency of up to 25 Hz. Furthermore, a quaternion-based orientation filter [
40] for inertial sensors effectively separates static and dynamic accelerations. The time series of the measured inclinations is treated with a proposed algorithm of successive repetitions, which eliminates other disturbances still present.
Section 2.2 describes the combination of these methods, which significantly improves the final results. Building inclinations evolve over long periods (months or years). This work verified different patterns and their evolution with computationally generated values and a small-scale physical model for laboratory tests, as described in
Section 3.
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 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.
2.3. Tilt Patterns
Eighteen basic patterns were proposed, representing the shapes of frequent inclinations in buildings, mainly considering the differential settlements [
7,
8,
9]. Several buildings are leaning (off-kilter), from Big Ben at just 0.26° to the Sturluson church tower in Germany at 5.19° [
42]. In general, construction regulations establish the maximum limits of the average inclination of the building through formulas based on its height, specified in percentages [
43]. For example, the maximum slope allowed for a building 18 m high is 0.65% or 0.37°; for 36 m height, it is 0.48% or 0.28°. However, quite a few buildings have slopes greater than 1° and are still inhabited, although they are under supervision, as shown in
Figure A1 (
Appendix A) for the Mexico City Press Clinic and
Figure A2 for the Palace of Fine Arts.
This work uses sexagesimal degrees; the tilt resolution is 0.1°, and the severity or range is from −1.5° to 1.5°. The tilt patterns and neural models developed can be applied to smaller resolutions, i.e., hundredths of a degree. Likewise, a conversion can be made to a percentage concerning the height of the building. The base patterns can be illustrated graphically by considering the inclinations’ general shapes. The tilt resolution of this project was 0.1°.
Figure 5a presents the sensors’ initial reference system (when installed on the walls). Two axes are used to measure the building’s tilt. The Y–Z plane represents the biaxial tilt, allowing the IMUs to be easily powered regardless of their location on the building walls. A generic building illustration is presented regarding the walls’ inclination.
Figure 5b illustrates pattern 0, where all four walls tilt to the right.
Figure 5c shows the rotation of the axes Y and Z, regardless of their location on the building walls.
Figure 6 illustrates an example of the wall’s possible tilts from its front view. The positive Y-axis is to the right, and the positive Z-axis goes into the page (to the sensor). In
Figure 6a, the wall is perpendicular to its base, and there are no tilts. In
Figure 6b, the wall has tilted over time; the Y-axis is tilted clockwise and is represented by a positive sign.
Figure 7 shows a simplified scheme of the 18 base patterns proposed in this work. Considering the expert knowledge of structure and architecture specialists, the 18 base patterns can cover the building tilt forms in practice and even more. These patterns contemplate each wall as a single entity; however, each wall tilt has a close relationship throughout the structure. Furthermore, if the classifier does not recognize a predominant pattern, the biaxial inclination of each wall is recorded independently by the real-time monitoring system. Likewise, the possible future redesign of the system may include new tilt types with classifier retraining and some changes to the model or includes more sensors per wall.
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 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 7.
A simplified scheme of the 18 base patterns proposed in this work.
The biaxial tilt measured by the sensors is determined as shown in Equation (4), e.g., when the Z-axis has not changed.
where
represents the biaxial inclination of the wall
w of the building.
The ordered pair (
) represents the relative angles in the Y- and
Z-axes, respectively, for the wall
w | w = 0 … 3. For example, for pattern 0, considering the resolution of 0.1°, Equation (5) is obtained for a wall 0.
Equation (6) represents the building’s biaxial tilt patterns mathematically for its four walls.
where
is the set of base tilt patterns,
is the base pattern,
are the tilt angles of walls 0, 1, 2, and 3, respectively, and
represent the relative angles in the Y- and Z-axes, respectively, for the wall
w | w = 0 … 3.
The 18 base patterns were created using Equations (4) and (5). Equations (7)–(10) show examples for patterns 6 and 14 from
Figure 7. Pattern 6 has inclinations in walls 2 and 3, as shown in Equation (7), with the rotation directions of
Figure 5c.
The values are substituted into Equation (7) considering the system resolution of 0.1°, resulting in Equation (8).
Pattern 14 presents tilt in wall 0, as shown in Equation (9). The values are substituted in Equation (10).
Table 1 shows examples of patterns 0–3 of the four walls based on Equations (4)–(6).
So far, the example patterns have been for the minimum inclination of 0.1°. For the computer model’s training, variations of the patterns were made. For example, the pattern 0 for wall 0 illustrated with Equation (5), based on increments of 0.1°, can go up to ; the same applies for walls 1, 2, and 3. However, there may be differences in the inclination between the walls, which would result in a distorted pattern 0, but the computer system indicates the angles in each wall so that an expert has additional information on the base pattern recognized. Similar behavior can be presented for other patterns.
2.5. Classifier of Base Biaxial Tilt Patterns () of Figure 8c
A multilayer perceptron neural network was used to classify the base tilt patterns. Parameters that are not directly learned within the neural network training were adjusted on the basis of exhaustive search-generated candidates from a grid of parameters (
grid-search) [
44,
45]. This grid consisted of different values for each parameter, such as epochs, learning rate, and loss function. For fitting the model to the data, the possible combinations of the grid were evaluated, and the best combination was chosen according to a specific metric (in this case, accuracy).
After applying the grid-search method, the chosen hyperparameters during the training phase were the mean squared error (MSE) as the loss function, learning rate , and training for 2000 epochs. The hidden layer and the output layer used a hyperbolic tangent activation function.
A stratified cross-validation of the 18 features (base patterns) was implemented to obtain the training and a test subset (with a ratio of 70:27, respectively). The validation uses 3% of the dataset. Afterward, the neural network training was conducted using only the training subset, leaving the test subset out of the training phase.
To have more certainty that the neural network
architecture had learned adequately, the test subset was used as input for the neural network
in the test or evaluation phase of the classifier. The metric
MSE was used to compare the trained neural network
performance. The coefficient of determination
did not add different information. Through many tests, the topology shown in
Figure 9 was selected.
had eight input neurons, where ( represent the four ordered pairs of inclinations in the Y- and Z-axes for the four building walls. It had two hidden layers (96 and 58 neurons, respectively) and a layer of 18 output neurons to classify the 18 base patterns. According to a set of tests and the range of inclinations to be monitored for this work (−1.5° to 1.5°), the hyperbolic tangent activation function () was used to process each of the outputs () with m = 0, …, 17.
For the neural network supervised training, a target output vector was related to each input vector, as shown in Equation (11).
where
is the training dataset consisting of the base tilt pattern
and their respective target vectors
. For the simulation, a computational algorithm generated
, varying the inclinations
0.1° up to
1.5°, according to the corresponding base pattern (0…17). A total of 12,900 patterns were used (approximately 715 patterns for each base pattern): 70% for training the network, 3% for validation, and 27% for testing, with which the best results were obtained using the library of Python neural networks.
Only one of the 18 output neurons is triggered when pattern recognition is excellent. In other cases, more than one is activated, but a predominant value indicates the pattern with the most remarkable similarity. This behavior, regarding the most notable similarity, is essential for future work improvements. In that sense, if a building presents a different tilt pattern than the 18 proposed in this work or one that is the combination of two or more base patterns or their distortions, then specialists can analyze the inclination angles returned by the measurement system for each wall. We propose a buildings’ biaxial tilt classification assessment with a computer expert system that can be progressively enriched with new scientific and technological contributions and the experience derived from its application in real buildings in each geographical area. For example, Mexico City has land with very particular characteristics.
Figure 10 presents the confusion matrix generated by the base pattern classification of
.
Figure 10.
Confusion matrix to evaluate
NN1. 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 10.
Confusion matrix to evaluate
NN1. 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.
Table 2.
Performance scores of .
Table 2.
Performance scores of .
Metrics | Evaluation |
---|
Precision | 0.95 |
Recall | 0.94 |
F1 | 0.95 |
Accuracy | 0.95 |
The precision [
46] is the ratio shown in Equation (12).
where
is the number of true positives, and
is the number of false positives. The precision is intuitively the ability of the classifier not to label as positive a sample that is negative. The worst value is zero, and the best is one.
The recall [
46] is defined in Equation (13).
where
is the number of true positives, and
is the number of false negatives. Recall is intuitively the ability of the classifier to find all the positive patterns.
The
score is interpreted as a weighted average of precision and recall, where an F1 score reaches its best value at one and worst score at zero. The relative contribution of precision and recall to the
score is equal. The formula for the
score is shown in Equation (14).
In the multiclass and multilabel case, this was the average of the score of each class with weighting depending on the average parameter.
Considering that some of the 18 base biaxial tilt patterns proposed can be infrequent in buildings, the classifier of base biaxial tilt patterns (
) is very recommendable since the performance scores were higher than 94%.
Section 3 presents examples of tilt pattern classification on a small-scale physical model for laboratory tests.
2.6. Tilt Severity Classification
Each pattern (vector of eight angles) was labeled with an algorithm assigning the tilt severity according to Equation (15).
where
S is the tilt severity,
represents a relative angle in any Y- or Z-axis for a wall (see Equation (6)), and
is the set of base biaxial tilt patterns.
The eight tilt angles can frequently have similar magnitudes because each wall has a close relationship throughout the structure; this is considered in the training patterns. In this way, when the severity labeling algorithm detects an angle within exceeding some limit of the four intervals presented in Equation (15), the severity pattern is labeled with the upper level.
Experimental work began with various topologies of a multilayer perceptron neural network to evaluate its performance as a classifier of the tilt severity or to consider other options.
Figure 11 shows the selected topology with eight inputs (
); two hidden layers (100 and 98 neurons, respectively) and an output layer for the severity classification. A hyperbolic tangent function was used as the activation function (
), to process the outputs (
).
Table 3 shows how the neurons will be activated.
The first option for training the model to classify tilt severity used a single dataset from the 18 base biaxial tilt patterns; however, the differences in the complexities between the base patterns produced significant distortions. A model named parallel was implemented.
2.6.1. Parallel Recognition Model to Classify the Tilt Severity
This model was specialized for recognizing each base pattern severity.
Figure 12 presents the schema of the parallel recognition model training. It was trained with 18 datasets, each one formed by the severity patterns of a single base pattern.
The network was trained with 18 datasets, as shown in Equation (16).
where
is a set with the number
j of severity variations based on the pattern
x.
Depending on its complexity, the number
j must be different for each base pattern; more complex base patterns (different tilt angles on each wall) will have greater variations. The parallel recognition model training of
Figure 12 allows such differences in the number of variations in tilt severity between base patterns without implications on possible training data imbalances.
Figure 12a illustrates that severity samples for patterns 0–17 can generally be different. Depending on the complexity of the base pattern, 569–3884 samples were used for each training set (18 sets): 70% for training, 3% for validation, and 27% for testing.
Figure 12.
Parallel recognition model training.
Figure 12.
Parallel recognition model training.
Figure 13 presents the base biaxial tilt pattern classifier and parallel recognition model implementation to classify the tilt severity.
Figure 13a is the input of the four biaxial tilts, illustrated initially in
Figure 8b.
Figure 13b is the classifier of base biaxial tilt patterns of
Figure 8c, which outputs a base pattern
. This output allows the selection (
Figure 13c) of the set
with the weights and biases of the trained
NN2 indicated in
Figure 12c. Lastly,
Figure 13d is the classifier of the tilt severity (see
Figure 11), which has an output
, corresponding to reduced risk, high risk, serious risk, or critical risk, respectively.
Figure 14 presents the most representative confusion matrix generated by the parallel recognition model to classify the tilt severity.
Table 4 shows its metrics. The tests were performed with the severity samples of each of the 18 base tilt patterns. The classifier metrics were between 0.94 and 0.98, depending on the complexity of the base tilt pattern. The specialization based on the training of each neural network is illustrated in
Figure 12, and the implementation is shown in
Figure 13. The performance was high, eliminating possible ambiguities between different patterns. The neural network was specialized to recognize the specific severity of each base pattern.