Reducing costs is an important part in todays buisness. Therefore manufacturers try to reduce unnecessary work processes and storage costs. Machine maintenance is a big, complex, regular process. In addition, the spare parts required for this must be kept in stock until a machine fails. In order to avoid a production breakdown in the event of an unexpected failure, more and more manufacturers rely on predictive maintenance for their machines. This enables more precise planning of necessary maintenance and repair work, as well as a precise ordering of the spare parts required for this. A large amount of past as well as current information is required to create such a predictive forecast about machines. With the classification of motors based on vibration, this paper deals with the implementation of predictive maintenance for thermal systems. There is an overview of suitable sensors and data processing methods, as well as various classification algorithms. In the end, the best sensor-algorithm combinations are shown.
plants, an intelligent solution is required in order to be able to ofer individual maintenance strategies depending on the state of the plant. For this reason, the project uses machine learning (ML) methods.
The essential steps of an intelligent PMA strategy are the digital acquisition of (sensor) data, their evaluation, the analysis of the acquired data and the prediction of probable events.
First, possible component defect combinations (CDC) of the industrial plant were analyzed
using standard technical risk analysis methods (FMEA, risk graph, fault tree analysis) [
The core of this work is the evaluation of a combination of detection measures for data processing methods and ML algorithms. The optimal combination of these is a prerequisite for an eficient PMA strategy that can be used for the respective industrial plant.
A study by Bearingpoint [
A basic approach is to use the already implemented sensors of the plant for process
monitoring. This passive method is particularly suitable for systems that are already in operation.
Another passive approach is to introduce dedicated sensors into the system. The additional
sensors are introduced to monitor defined wear components and to detect potential defects.
In the third approach, a test signal is actively fed into the system. The degree of wear of the
components to be monitored can be deduced from the feedback. An example of this is Time
Domain Reflectometry (TDR) [
When buying industrial sensors, you often have to commit to a sensor resolution. This requires that you have a basic understanding of what accelerations occur on the component. For this purpose, the efects were previously considered in an experiment when an accelerometer with an insuficient resolution is used. In this case, the sensor generates vibrations that exceed the sensor resolution. A CDC of the fan motor is that the fan wheel has an imbalance. This fault situation was simulated by attaching an unbalance to the fan blade.
The result of this simulation is shown in figure 1 (a). There are shown the measured
accelleration values in x- and y- axis of an accelleration sensor with a maximum resolution of ±2 . The
red values show the vibrations of the motor without an imbalance and the blue values show
the vibrations which occurs with an imbalance. It can be clearly seen that the vibrations on the
motor increased due to the imbalance. It can also be seen that vibrations that go beyond the
set sensor resolution of ±2 were not recorded correctly. They are in line with the maximum
acceleration of ±2 . The measured values that did not exceed the maximum resolution were
not afected by this. The experiment shows that the CDC "imbalance" can cause very strong
vibrations. The vibrations are so strong that they exceed a sensor resolution of ±2 . If a sensor
is used that can only record values up to a resolution/acceleration of ±2 , these are recorded
incorrectly. The values that exceed the maximum resolution are then incorrectly saved in the
data record [
The requirement for a condition-based PMA is a structured data collection of sensor values. The following sensors were used to obtain status data: • Three-axis acceleration sensors (Accelerometer):
– LIS 3DH, MMA 8451, ADXL 343, ADXL 345 • Three-axis acceleration sensors with three-axis yaw rate sensor (gyroskope) – MPU 60.50 – MLX 90393 • Three-axis magnetic field sensor (magnetometer) • Multi sensors with three-axis acceleration, three-axis yaw rate and three-axis magnetic ifeld measurement
– MPU 92.65, BNO 055, GY 250, GY 521
These recorded the acceleration, the rotation rate and the surrounding magnetic field of the
fan motor R3G180-AJ11-XF from ebm-papst Mulfingen GmbH & Co. KG used in the thermal
system. Figure 2 shows the measurement set-up with the selected three-axis acceleration
sensors [
The fan motor was operated at fixed speeds, which were divided into 7 classes. This classification was based on the specific values 0%, 50%, 60%, 70%, 80%, 90% and 100% of the maximum engine speed. During the operation of the fan motor the vibration of the crankcase was sensed and recorded by the sensors. More than 980,000 structured sensor data sets per measurement series and sensor type were recorded. A total of more than 2.6 million data sets have thus been recorded for all sensor types. A section of a full data set is shown in Table 1.
An example of a recorded data set is shown in figure 3. It shows the measured acceleration from the housing vibration in the spatial x- and z- orientation. The individual classes are highlighted in color to make a distinction possible. Due to the highest spatial coverage, it can be seen that the measurement results for class 80% can be assigned to the resonance range of the fan motor, since the acceleration values in the x- and z- alignment are at their maximum values here.
In order to be able to better diferentiate the individual classes, it is in some cases advantageous if the data records are processed before classification. The methods used for data conditioning are presented here:
One possibility to process the data sets consists of the diferencing and absolute value formation of subsequent values according to equation 1.
= | − +1| calculated.
and +1 are the successive sensor values. Another processing method is the integration of the data according to equation 2. Here the area under two successive values and +1 is ⎧ ⎪ ⎪ ⎪ ⎪⎩ ⎪⎪ + 0.5 ⋅ ( +1 − ) = ⎨ − 0.5 ⋅ ( − +1) if < +1 if > +1 if = +1
In both the processing methods, an additional smoothing can be carried out by calculating the moving average according to equation 3.
The parameter specifies the degree of smoothing. The parameter is the diference between the indices between the instantaneous value and the maximum value ± specified by =
⋅ ∑ 1 + − the degree of smoothing. Thus depends on the degree of smoothing and can be determined according to equation 4.
=
With the degree of smoothing , first optimizations regarding the classification of the
measured sensor data can be carried out [
Figure 4 (a) shows the acquired raw data of an acceleration sensor in the x-orientation. It can be seen that a delimitation regarding the classes is not clear. For example, the acceleration in the direction of the x-axis at −8 / 2 is not unique and can in principle be assigned to any class. In Figure 4 (b) the classes are more delimited after the diferencing and smoothing and thus a class assignment is clearer. For example, the value 0.7 can be clearly assigned to the class shown in gray.
Figure 5 (a) shows the raw data from the measurements in x- and y-orientation. A classiifcation is clearly not possible due to the overlapping point clouds. Figure 5 (b), on the other hand, shows the data prepared after the diferencing. It can be seen that the point clouds are now clearly distinguishable, making visual and algorithmic class assignment easier.
The evaluation of the ML algorithms with regard to the respective sensors and the data
processing was divided into a training and a test phase. In the training phase, the data records
were divided evenly by feeding every tenth data value of the respective training method to the
ML algorithm. As a result, the respective ML algorithm was trained with 10% of the data. The
complete data set was then evaluated in the test phase. Several ML algorithms were
considered for the recorded data sets. These included decision trees [
Figure 6 shows two confusion matrices [13] for the focus cluster algorithm, which show the distribution between the actual class and the class determined by the algorithm. The numbers on the axes correspond to the seven defined classes in which the data records have been categorized. The darker an area, the more often the ML algorithm has assigned data records to a class. A correct assignment is obtained if the assigned class corresponds to the actual class. Ideally, you would get a black diagonal from top left to bottom right.
Figure 6 (b) shows the result for the data sets prepared after diferencing and smoothing. It can be seen that the majority of the data records were assigned to the actual classes, the hit rate here was over 98%. On the other hand, it can be seen in Figure 6 (a) that a significantly lower hit rate has been achieved for the unprepared data sets.
The preceding test were performed by measuring the vibration of a stand-alone motor on a workbench, which was not build into a working machine. Therefore this data cannot be used to make a prediction for maintenance, but the feasibility of categorizing a motor by its vibration and magnetic field was studied. To get a better picture of the real working conditions of such a motor a larger data set was collected by mounting three multifunction sensors (GY 521, BNO 055, MPU 92.65) on a thermal system which is used in day to day operations. These data sets were then used to build a statistical model based on auto regression and moving average (ARMA [14], [15]) of the vibration. The statistical models were created for every sensor orientation separately to get an optimal result for each time series. As the metric to compare the diferent models was chosen the maximum relative deviation (MRD) according to equation 5. = max | −
| predicted by the model at this time-step.
In equation 5 are the measured sensor values used to build the model and are the values (5)
To compare the results of the ML algorithms for the respective sensors, a matrix with the relevant properties was created for each combination of ML algorithm and sensor: • Classification accuracy (performance) of the algorithms • Computing time for the training and testing phase of the algorithms • Smoothing factor G of the multifunction sensor GY 521 and the gradient boost method.
It can be seen that the highest performance is achieved when using the raw data. In the training and test phases the integrated and the diferenced data are slightly faster. A comparison was made for each sensor and ML algorithm combination. The best performing data processing method was then selected for each combination. The comparison tables of the sensors which have achieved the best results of the sensor types examined are listed in Tables 3 to 5. These were the ADXL 345 (accelerometer), the MPU 60.50 (gyroscope) and the GY 521 (accelerometer, gyroscope and magnetic field). The processing method with the highest performance for the respective algorithm is shown for each of the sensors.
= 0
The result of the examinations according to Table 3 was that all acceleration sensors achieved the greatest performance with smoothing ( = 99) and data prepared by diferencing. The focus cluster algorithm achieved the highest performance.
The result according to Table 4 is that the highest performance was achieved with unprocessed and unsmoothed data with the gyroscopes. The gradient boost process achieved the highest performance.
In the case of the multifunction sensors with acceleration, magnetic field sensors and gyroscope, it can be seen from Table 5 that the highest performance was achieved with smoothing ( = 99) and diferenced data using the cluster cluster algorithm.
Table 6 shows the lowest MRDs for each separate sensor orientation with their number of auto regressive (p) and moving average (q) terms.
These results show a maximum deviation up 28.3% with the gyroscope values in z orientation. The lowest deviation was reached with acceleration in z orientation and the magnetic ifeld in x orientation with only 10.1% and 10.6% respectively. The diference in accuracy of the models is rather high and therefore an ARMA model can only be used to model two of the nine time series measured. For the remaining seven there should be used other means of modeling.
It has been found that the processing of the raw data in the form of smoothing and diferencing in combination with the focus cluster algorithm gave the best results for acceleration sensors. The gyroscopes examined showed that the unprocessed raw data without smoothing in combination with the gradient boost method achieved the highest classifiability. The multisensors examined gave the best results when using the focus cluster algorithm in combination with smoothed and diferenced data. In addition it was found, that an ARMA model could be used to predict the acceleration in z orientation and the magnetic field in x orientation.
Based on these results, the combination of detection measure, data processing method and ML algorithm can in the next step be used for a PMA strategy. For a complete PMA, further detection measures have to be examined. For that purpose, this procedure is continued with further sensor types in order to find an optimal combination for all necessary detection measures. In the future, a prediction model is to be developed on the basis of these results, with which predictions can be made about the degree of wear of system components of a thermal system under automation. Formal aging and error models of the respective system components must also be created in order to map the aging process of components. These models can then be used to make probabilistic statements about the failure probabilities of the individual assemblies. Such models could be based on Dynamic Bayesian Networks (DBN) [16], auto regresssion and moving average (ARMA) [17] or, as the focus cluster algorithm has yielded such an high performance, a multi dimensional focus trajectory. In addition to that, the statistical models used to predict the motor vibration in day to day operations could be extended to auto regression, integrated, moving average to get a better result for all sensor orientations. [11] A. Géron, Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques for Building Intelligent Systems, 1st ed., O’Reilly Media, Boston, 2017. [12] T. Rashid, Make Your Own Neural Network, 1st ed., CreateSpace Independent Publishing
Platform, North Charleston, SC, USA, 2016. [13] M. Füllsack, A (partially) interactive introduction to Systems Sciences, 2013. URL: http: //systems-sciences.uni-graz.at/etextbook/bigdata/confusionmatrix.html. [14] C. Lin, Y. Hsieh, F. Cheng, H. Huang, M. Adnan, Time series prediction algorithm for intelligent predictive maintenance, IEEE Robotics and Automation Letters 4 (2019) 2807– 2814. doi:10.1109/LRA.2019.2918684. [15] H. Akaike, Maximum likelihood identification of gaussian autoregressive moving average models, Biometrika 60 (1973) 255–265. URL: http://www.jstor.org/stable/2334537. [16] P. Dagum, A. Galper, E. Horvitz, Dynamic network models for forecasting, in: D. Dubois, M. P. Wellman, B. D’Ambrosio, P. Smets (Eds.), Uncertainty in Artificial Intelligence, Morgan Kaufmann, 1992, pp. 41–48. URL: https: //www.sciencedirect.com/science/article/pii/B9781483282879500104. doi:https://doi. org/10.1016/B978-1-4832-8287-9.50010-4. [17] J. Wang, Y. Liang, Y. Zheng, R. X. Gao, F. Zhang, An integrated fault diagnosis and prognosis approach for predictive maintenance of wind turbine bearing with limited samples, Renewable Energy 145 (2020) 642–650. URL: https://www.sciencedirect.com/science/article/ pii/S0960148119309371. doi:https://doi.org/10.1016/j.renene.2019.06.103.