1. Introduction
The digitalization of manufacturing is being driven forward by the decreasing costs of information and communication technology. Cyber-physical systems (CPS), or in the manufacturing context Cyber-Physical Production Systems (CPPS), are an important technological element in the realization of the 4th industrial revolution [
1]. CPPS and their applicability in industrial environments are of increasing interest in current research and industry. A CPPS is clustered into subsystems: the physical world and the cyber world. These subsystems interact with each other through data acquisition and decision-making support and control functionalities, respectively [
2].
In 2018, the World’s energy consumption has increased by almost 40% compared to the consumption in 1990 [
3]. The industrial share of total final consumption (TFC) stayed at the ~30% [
4]. Although the absolute consumption increased to ~57% compared to the consumption of industrial sector in 1990 [
5]. In times of increasing energy demand and decreasing energy resources, a further optimization and revaluation in industrial sector is imperative.
The Heating Ventilating and Air-Conditioning (HVAC) system is responsible for a large part of the energy consumption in industry. According to internal Volkswagen data [
6], it accounts on average for about 40% of the total energy consumption in industrial buildings. Automobile production can be classified into press shop, assembly, paint shop and body shop. Body shop is responsible for almost one-quarter of the total energy consumption, preceded only by the paint shop [
6]. Within the case study of a body shop, the HVAC system has the highest energy demand, succeeding the other infrastructure consumption: the hall lighting and workplace lighting. In the body shop, the HVAC consumption exceeds 60% of the total energy demand, succeeding the consumption from the production itself [
6].
The main function of an HVAC system is to satisfy and maintain the requirements with respect to air and building environment in general, for example, thermal comfort, air pollution control and the hygienic aspect, which is achieved by conditioning outdoor air to the desired levels in occupied buildings or for product processing and transporting the air in the room through an exhaust duct. It controls and maintains temperature, humidity, air movement, air cleanliness and pressure differential within a defined space. Wang [
7] classified HVAC systems into comfort HVAC systems and process HVAC systems depending on the application. Comfort HVAC systems provide occupants with a comfortable and healthy indoor climate and process HVAC systems provide and maintain the necessary air conditioning for production, storage or other defined processes [
7,
8].
In order to guarantee that the indoor climate in the body shop is up to the user requirements, the production’s emissions need to be transported out of the conditioned space using the HVAC system, this is done using the technical exhaust air vent. One of the main emissions in a body shop is fine dust, which is a byproduct of the welding process. In the geographical location of this study, Wrzesnia, Poland, to be precise, an occupational exposure limit is regulated under TRGS 900 [
9]. The limit values are 1.25 mg/m
for PM2.5 and 10 mg/m
for PM10; this is then taken up again in Chapter 2 and elaborated on in more detail.
Fine dust can be measured using specific measuring technology, specifically using an optical sensor that measures and monitors fine dust concentrations with preconditioned air. Within the study, the fine dust is measured by this optical scattered light measurement [
10]. However, this method is highly cost-intensive [
11].
Digital technologies, such as the Internet of Things (IoT), offer a wide number of applications in various sectors [
12]. One of the examples is to use cost-effective smart sensors, which enable users to measure ambient conditions and upload them to the cloud [
13]. This enables users to experiment or use a more modern control concept, for example, machine learning algorithms. Li [
14] presented a hybrid model based on long short-term memory (LSTM) network and attention mechanism (LSTM-attention) applied to the prediction of Total Suspended Particulate Matter (TSP) concentration. Li [
14] showed that the model approach can be applied to the prediction of dust concentrations in open-pit mines, thus helping in decision support on when to carry out dust suppression work.
The main scope of this paper is to study different model approaches using data measured in an industrial welding area of an automobile body shop.
The paper starts with a literature review concerning fine dust or particulate matter and the national regulations and technical rules concerning Particulate Matter (PM) and industrial welding. It then explains the methodology and approach used in this paper. This is followed by the factory data collection setup, data analysis and data correlations. Subsequently, the created data models or algorithms are presented with the results and the statistical comparisons. Finally, the conclusion and future scope or applicability of the paper are outlined. The project shows the possibilities of using an alternative data model correlation from more common and less expensive parameters, such as air velocity, air temperature, relative humidity, the CO content around the perimeter and the electric current of the welder. By using machine learning algorithms, we show that by using commonly available sensors in a production hall, it is possible to correlate fine dust data cost-effectively.
3. Methodology and Approach
As methodological framework a Cyber-Physical Production Systems (CPPS) is used;
Figure 1 shows an adapted CPPS framework for this application.
The approach to integrate a CPPS in the body shop is driven by the goals of improving energy efficiency while maintaining air quality in the production environment and being cost efficient. The CPPS system provides a decision support by calculating the fine dust concentration in the production environment. This enables the HVAC operator in the physical world to use conservative sensors, such as temperature, relative humidity and CO to operate the HVAC system. Further, the CPPS enables a model-based control in the future.
With this cyber-physical HVAC system, energy efficiency, air quality and thermal conditions can be improved in the production environment by providing decision support, greater transparency and enabling model-predictive control in real-time. With the proposed approach, one can measure fine dust in the air without using expensive fine dust sensor in each welding area in a body shop. This can lead to a high cost savings when monitoring a large body shop hall in a factory. The low-cost IoT sensor technology combined with machine learning enables large-scale deployment with moderate costs compared to the high-precision fine dust sensors on factory scale.
3.1. Setup for Collecting Data in the Factory Hall
In order to find the correlation between the HVAC-System, air quality and production activity, it is necessary to collect and analyze the variables on site. An experiment within the scope of a collaboration project between TU Braunschweig and Volkswagen AG is thus commenced. To investigate seasonal influences, experiments were conducted in winter and summer at five consecutively working days, to be exact from 6th to 8th of August 2018 and from 26th to 30th of November 2018. This allowed us to measure the experiment under 5 different air exchange rates, which were set 8 h before the start of each measurement. For the first three days, the reductions were concentrated on the main exhaust air vents, the openings of which can be found directly under the ceiling of the production hall, this is detailed
Table 1. Moreover, for the last two days, we set to measure the effect on the reductions on the technical exhaust vents, which is directly responsible for exhausting the welding emission.
Figure 2 shows the difference on the positions of the two exhaust vents and the HVAC system used in the factory hall.
The reduction limit was set to 50% because the technical exhaust vents are the main way to exhaust the byproducts of the welding.
Table 1 lists the experimental parameters for the work days with the expected energy saving potential in compare to the reference day (monday), which is based on the assumption of constant fan efficiency. A change in volume flow rate affects the fan power requirement as follows [
8]:
for example, 10% less volume rate will lower power demand by 33%. The supply air fan has a nominal power of 40 kW, while the exhaust air fan and the technical exhaust fan operate at nominal power of 30 kW and 60 kW.
The samples were taken during welding corrections; welding of floor elements (galvanized steel) with the welding torch SKS Power Feeder PF5 (MAG method); coated with steel wire with copper with a diameter of 1.0 mm; Argon; and CO inert gas welding, sanding and cleaning of welding seams. An oscillating time of at least 6 h was taken into account, so that the air conditions in the welding area settle before the measurements were commenced.
3.2. Data Acquisition and Analysis
In order to ensure that the regulatory thresholds are well maintained, certified gravimetric measurements from the work safety department accompanied the experiment. This gravimetric measurements were executed according to PN EN 689:2018, a Polish version of EN 689 [
24].
Table 2 and
Table 3 show the result of the gravimetric measurements respectively in summer time between 6 and 8 August 2018 and winter time from 26 to 30 of November 2018, measured over the time period of 8 h. The gravimetric measurement devices were hung directly on the workers shown in
Figure 3. The results of the gravimetric measurements are shown in
Table 2 and
Table 3.
The exposition limits (PM2.5 = 1.25 mg/m
and PM10 = 10 mg/m
) were held under the regulatory threshold during the experiments, except for the PM2.5 on Tuesday 7 August 2018. This outlier, however, was not backed by the PM10 result on the same day, which stayed far below the limit of 10 mg/m
. The measurements with the same air exchange rate settings were also repeated in winter and shown in the
Table 3. The measurement results are more dependent on workers behavior, movements and routines, rather than the reduction in air exchange rate shown in
Table 1, which might explain the spike and the nonlinear results.
3.3. Correlation Study between Fine Dust and Other Parameters
In order to be able to design a system which can predict the amount of values of PM10 and PM2.5 with the combination of other sensors, reference data sets are measured and collected.
Figure 3 shows a representative schematic of the measurements setup in the hand welding area on-site. The places chosen for the sensor installations represent the spots where workers operate manually using a hand welder during the productions, which means the resulting air velocity, Temperature, Relative Humidity and CO
depend greatly on workers actions and activities. The fine dust PM2.5 and PM 10 are measured using optical sensors as well providing a dataset for the purpose of validating the designed algorithm. The sensor used was fine dust FDS 15 from Dr. Födisch Umweltmesstechnik AG which has accuracy of ±5
g/m
and a measuring range from 2
g/m
to 3.000
g/m
[
10].
Table 4 shows the results of the measurements data in winter time on 8-h average, the data of PM2.5 and PM10 were measured using optical sensors FDS 15. With the proper use of the data from these sensors combined with an algorithm, the amount of PM10 and PM2.5 in the air can be predicted to a certain extent. Which variables are to be selected for input can be decided based on the correlation analysis. The best combination of the inputs, that gives the lowest error in the prediction, can be chosen as input variables for the model. This selection is known as feature selection [
25].
From the correlation analysis, the dependency of PM10 and PM2.5 on other available variables is noticeable.
Figure 4 and
Figure 5 show the calculated linear coefficients for each variable using Pearson and Spearman’s Rho Correlation. The correlation between and input variables and target variable provides the basis for the feature extraction. Strong correlation means that the changes in chosen features (variables) causes higher changes in the target variable. Pearson coefficient suggests how two variables are correlated linearly. On the other hand, Spearman’s Rho coefficient shows the nonlinear monotonic relation between two variables. The formula for the Spearman rank correlation coefficient is [
26]
where
is the difference between two ranks of each observation and
n is the number of observations.
Table 5 shows exemplary
as the difference between ranks of each observation of PM2.5 and relative humidity (RH), where
n defined the total number of observations, which means total number of samples, in the case of this study approximately 350,000.
Each variable has correlation a coefficient of 1 to itself. Because both substances are categorized as fine dust, PM10 and PM2.5 have a strong positive linear correlation to each other. Both substances have negative intermediate correlations with relative humidity (RH) and positive intermediate correlations with CO. The electricity current (CT) shows a weak positive correlation to both PM10 and PM2.5. These variables were chosen, as those are the potential quantities which might affect the amount of PM2.5 and PM10 in the welding area.
3.4. Data Model
Spearman’s rho coefficient test is used to show the monotonic behavior of the variables to each other. PM10 and PM2.5 show a strong increasing monotonic relation with each other and also have sufficient monotonic relation with the current (CT), CO and relative humidity (RH). This result also shows that PM10 and PM2.5 have decreasing monotonic behavior with Air Velocity (V). The combination of Pearson and Spearman’s coefficients show that the Current (CT), CO, Relative Humidity (RH) and Air Velocity (V) are more suitable to serve as input variables for the model. The aim is to exclude PM2.5 as an input and make a model which would give better prediction for PM10.
In order to select the best fit model, different machine learning models were designed, trained and tested using the available data. These includes linear regression and feedforward neural networks for regression and classification (Probabilistic Neural Network), which contain the whole interval of possible values separated in high number of intervals. This is a particular case of application of classification. Aside from that, the design of the models use supervised learning, which means the output target variable is already available for the training. Different features and respectively variables were considered for the models and the performances were compared. Current (CT), CO
, Relative Humidity (RH) and Air Velocity (V) Features are the variables chosen as inputs for the model. The splitting of the measured data is set at random, accordingly, the ratio of the training and test data sets was set manually.
Figure 6 shows the schematic of the Feedforward Neural Network (FFNN) Model for regression using Current (CT), CO
, Relative Humidity (RH) and Air Velocity (V) as Inputs, feeding 2 Hidden Layers with each 10 Nodes and PM10 as output.
The schematic of the Feedforward Neural Network Model for classification (Probabilistic Neural Network) using the same inputs, two pattern (hidden) layers and PM10 as output is shown in
Figure 7. The number of nodes in the pattern layers are equal to the number of training points in the dataset. In the first pattern layer, the training data set uses 40% of the data, while the second layer utilizes 28% of the data set.
Last, Long Short-Term Memory (LSTM), a deep learning algorithm, is used in this study, the data from the aforementioned parameters are used as input variables, 1 dense layer with 25 LSTM Blocks and the particulate matter PM10 as output variables.
Figure 8 shows the schematic of the LSTM model for this study.
The models were trained with different amount of data starting from 20% to 80%. The models did not overfit until 40%, as the results continue to get better with the increase in the amount of training data. Models showed little betterment with increase in training data above 40%. The computational time increases drastically with the increase in training data above 40% for LSTM and FFNN, so 40% training data was the ideal choice to compare the models.
After building and training the model with the defined amount of data, the rest of the measured data was used for validating (testing) the model. The model is tested with different kinds of statistical methods such as R criteria for best fit, Minimum Absolute Error (MAE), Minimum Square Error (MSE) and Root Mean Square Error (RMSE). Visualization as well as statistical evaluation have been carried out to compare the actual data and the predicted data. By comparing different models with statistical as well as visual criteria, the best model for the application is chosen.
3.4.1. Model Result of Linear Regression, Feedforward Neural Network and Probabilistic Neural Network
From the correlation study, it was sufficient to say that a linear relationship exists up to some extent between the input variables and desired output. Building a linear regression model using the chosen variables from the correlation study seems to be a logical way to go. After training the parameters by using the training data, which consist of 40% of the data set, the model was tested using the rest of the data set.
Figure 9 shows a direct comparison of the prediction from the linear regression model and the test data from the measured data set. An evident discrepancy exist can be seen from the comparison. Visually,
Figure 10 shows a more satisfying result, which means the feedforward neural network model is a better fit of a model compared to linear regression. However, both results are not sufficient to use because of their inaccuracy. Both models use regression methods, in which the output layer consists of only one neuron and it gives a continuous output value.
Supervised learning classification methods also serve as alternative; they are used in building the model using probabilistic Neural Network. The result, thus the comparison to the test data is shown in the
Figure 11, which displays a more satisfying result in compare to
Figure 9 and
Figure 10. However, merely relying on visual analysis, a scientific analysis would not be valid.
For example, the results shown in
Figure 12, which show the visual representation of LSTM model output with the actual measured data, cannot show the difference or benefit of LSTM model compared to PNN model in
Figure 11. Therefore, one needs to compare the results using statistical methods as well.
3.4.2. Statistical Analysis of the Models
In order to do statistical checks, the models are tested using different kinds of methods, such as R-criteria for best fit, Minimum Absolute Error (MAE), Minimum Square Error (MSE) and Root Mean Square Error (RMSE) and using their results the best fit model can be chosen.
Table 6 shows that the LSTM Model has the lowest error in all error checks and the best squared correlation. In contrast to the linear regression model that shows a poor fit on the R
-Corellation and the lowest performance on the error tests, the LSTM Model shows good results, which is well matched with the visual comparison of
Figure 4 and
Figure 5, and thus supports the proof that LSTM is capable to be the best fit model for this study.
In order to get a better result, one could use a cumulative training method. A cumulative learning method uses aggregation of data as it grows with time. Consequently, it uses knowledge acquired on prior training to improve learning performance on subsequent training. On the contrary, a static training method uses discrete data, which means for each new training time period the algorithms are reset and fed with new data. Fixed training data are applied to a machine learning algorithm, and it does not use any knowledge from prior training. Therefore, cumulative method reuses learned knowledge to constrain new training, whereas static method depends entirely upon new training data as external inputs [
27]. Thor [
28] gave further description and definition of cumulative learning in the context of machine learning in detail.
Figure 13 shows the comparison of static and cumulative training methods and the statistic result from this study according to R
criteria. In the static training, the algorithm was trained for five days each month with new data. On the other hand, cumulative training uses aggregated data of the current and previous months. The cumulative training method showed a gradually increasing R
score reaching 0.81 R
, while the static method does not show a constant behavior and staying under 0.78 R
. This shows, that in training the LSTM Model, the cumulative training method is preferred.
4. Conclusions and Future Scope
This paper studied proof of concept for the Heating, Ventilation and Air-Conditioning (HVAC) system for a welding area. The proof of concept was modeled using four different machine learning algorithms and their performances were compared. The algorithms implemented were linear regression, feedforward neural network for regression, probabilistic neural network (Bayesian neural networks) for classification and Long Short-Term Memory (deep learning algorithm). Long Short-Term Memory showed the best result and potential for the control system.
A complete cyber-physical HVAC system in a body shop use case for the substitution of cost-intensive fine dust sensors was presented. The CPPS is then applied and validated in a real-world environment in one of the welding areas of Volkswagen’s production hall in Wrzesnia, Poland. A setup was configured and established based on the regulatory threshold to collect experimental data during production hours, in order to have a solid validation ground. The data were collected in 2 phases (in summer and winter), each extended through 5 production days. The concerned data set consist of air temperature,; relative humidity; air velocity; electric current used for welding; carbon dioxide; inhalable coarse particles; PM10, which are dust particles with a diameter of 10 micrometers (10 m) or less and fine particles; and PM2.5, which has a diameter of 2.5 m or less.
These were measured in the welding area during manual welding corrections, welding of floor elements (galvanized steel) with the welding torch (MAG method), sanding and cleaning of welded seam. As a double-proofing measure, 8-hour gravimetric measurements were taken, commissioned by the Volkswagen work safety department, in order to ensure that the reductions of air exchange rate kept the exposition thresholds under the regulated limits. Gravimetric measurement (respectively analysis) describes a method to quantify a substance or chemical constituent in a mixture based on its mass. In our case, the relevant substance is fine dust and the mixture is air. The gravimetric measurements were executed according to PN EN 689:2018. It showed that the reduction of air exchange rate does not have a linear correlation with the change in the amount of fine dust in the working area. The correlation study according to Spearman’s rho and Pearson showed that only four variables have direct correlation with the outputs (PM10 and PM2.5): relative humidity, CO Concentration, electric current and air velocity in the area. Because PM10 and PM2.5 show a strong increasing correlation with each other, PM2.5 could be excluded as an output variable. This will save a generous amount of computing time and cost. As supervised machine learning and deep learning algorithms are used in this study, the data from the aforementioned parameters are used as input variables and the particulate matter as output variables. The data were then split for training and testing of the models. The models are then tested statistically using different methods, such as R criteria for best fit, Minimum Absolute Error (MAE), Minimum Square Error (MSE) and Root Mean Square Error (RMSE). This shows that LSTM dominated the test with 0.821 discrepancy on R, 0.01020 on MAE, 0.00122 on MSE and 0.0257 on RMSE. As a comparison, the Linear Regression Model showed a poor result with 0.008 discrepancy on R, 0.03563 on MAE, 0.00377 on MSE and 0.05689 on RMSE. The results were also examined using graphical method. The LSTM or Long Short-Term Memory showed the best result and therefore is best suited for the HVAC control concept.
In the future it is possible to enhance the HVAC control using the LSTM model. It could be possible to install several micro controllers in the factory hall, that send the acquired data that is not expensive to measure data, such as relative humidity, CO, electricity current and air velocity. Data can then be used to train the LSTM model continuously. The output of the models can send computed fine dust values in real time to the HVAC system, which would be used as control parameter, besides typical control parameters, such as desired temperature, relative humidity and CO especially on factory scale, the cost savings would be significant and are very interesting for factory operators and planners.