Artificial Intelligence (AI) is transforming industries, particularly through Industry 4.0, by integrating technologies such as the Internet of Things (IoT) to optimize production processes and resource management. It addresses challenges such as reducing environmental impact while fulfilling consumer demands. Innovative sensors enable real-time data collection for environmental monitoring. Adopting advanced technologies such as energy cells, particularly lithium-ion batteries, is crucial for sustainable mobility and reducing environmental impact in the automotive industry. It is vital to understand the key parameters of energy cells, including range, energy density, and durability, and implement them while embracing the principles of Second Life efectively. For example, machine learning (ML) algorithms are utilized in industrial contexts to identify air and water pollutants and estimate the State of Charge (SoC) for automotive applications. These methodologies improve eficiency, sustainability, and innovation in various industrial sectors.
terpret sensor data ofers numerous benefits. By utilizing sophisticated algorithms and predictive models, it is Artificial Intelligence (AI) is revolutionizing various sec- possible to identify pollutants accurately, continuously tors including healthcare, finance, education, transporta- monitor air and water quality, and optimize industrial tion, and notably, industry. Its capacity to analyze vast processes to reduce environmental impacts. However, data sets in real-time and generate precise predictive the applications of artificial intelligence in industry are insights is reshaping production processes, enhancing not limited to the environmental sphere. Nowadays, the resource allocation, and boosting operational eficiency automotive industry is facing one of the most significant in industries worldwide. Industry 4.0 [1] represents a challenges in its history: to provide sustainable mobility crucial turning point in the evolution of the industrial and reduce the environmental footprint of transportation landscape, characterized by the integration of advanced on a global scale. One of the key pillars of this transtechnologies and widespread digitization of production formation is the energy cell[7]. Energy cells, notably processes. Inspired by the notion of the "smart factory," lithium-ion batteries, are crucial in revolutionizing vehiit emphasizes the interconnection of machines, systems, cle energy usage towards zero-emission transportation, and people via IoT, AI, big data, cloud computing, and combating air pollution, and mitigating climate change. advanced robotics[2, 3, 4]. The concept of Industry 4.0 is However, to fully realize it is essential to have a precise based on the idea of automated and connected production, comprehension of key parameters like range, energy denwhere machines and systems communicate with each sity, charging time, and durability. Accurate estimation other in real-time to optimize processes and decision- of these parameters is critical for developing large-scale making. In this context, innovative sensors [5, 6] play a zero-emission vehicles and ensuring proper disposal and crucial role by enabling the collection of detailed, real- reuse, aligning with Second Life principles[8]. time data on various environmental and operational pa- The following sections highlight the application of Marameters. Using artificial intelligence to analyze and in- chine Learning (ML) in industrial challenges, focusing on the detection of pollutants in air (2) and water (3), and on State of Charge estimation in automotive applications (4).
issues[9], prompting the development of a more acces- DATA ACQUISITION sible solution. Challenges like low sensitivity and se- SHoarftdwwaarree::SMECNUSIaPnLdU/oSrAHPoIst lectivity in miniaturized, low-cost smart solutions are addressed, with comparisons made to CEN (European Committee for Standardization) reference instruments, PREPROCESSING noting lower accuracy and stability but highlighting their nSoorfmtwaalizrea:tioEnMA filtering and value in data aggregation[10]. Spatial analysis techniques Hardware: MCU and/or Host aid in evaluating pollutant sources, while the limitations of chemical micro-sensors are extensively discussed in the literature, along with methodologies to improve their CLASSIFICATION performance. SHoarftdwwaarree::MMLCPU,CoNrNHoosrtLSTM
At the core of our proposed system is a sensor array including aluminum oxide for broad-spectrum volatile Figure 2: The proposed integrated system. SDM stands for organic compound detection, a commercial capacitive SENSIPLUS Deep Machine. humidity sensor, and graphene-functionalized sensor for pollutant sensitivity. These selections aim for versatility and sensitivity across contaminant types. Integration This includes phases of baseline air exposure, controlled with the SENSIPLUS platform facilitates precise electrical introduction of contaminants, and subsequent recovery, impedance measurements, crucial for accurate air quality designed to capture the dynamic nature of indoor air assessment. The proposed integrated system is shown quality. This methodological approach is crucial for proin Figure 1 and is mainly composed of the following: (1) ducing comprehensive sensor data that reflects the comSENSIPLUS Chip (henceforth SPC): a microelectronic plexities of real-world indoor environments. measurement device with on-chip sensing capabilities, For the analytical component of our study, we imjointly developed by Sensichips s.r.l.[11] and the Depart- plemented several machine learning models, including ment of Information Engineering at the University of Multi-Layer Perceptrons (MLP), Convolutional Neural Pisa. Equipped with a versatile analog front end and Networks (CNN), and Long Short-Term Memory (LSTM) various internal and external ports, it enables electrical networks. These models were trained on datasets colimpedance measurements on both internal and exter- lected from our sensor array, to achieve high accuracy in nal sensors. It has already been adopted in other works, classifying diferent air contaminants. The contaminants as in [12, 13, 14]. (2) SENSIPLUS Deep Machine (SDM): included in our study encompass a range of substances a hardware/software module designed for data acqui- commonly found in indoor settings, such as acetone, alsition, processing, and analysis. The block diagram in cohol, ammonia, bleach, and various volatile organic Figure 2 illustrates the logical flow of operations, high- compounds (VOCs), along with controls like water vapor lighting the software and hardware components utilized and clean air to facilitate accurate classification between for each task. Data acquisition is enabled by the SPC API, polluted and unpolluted conditions. a software library in C or Java, operating respectively Our findings indicate that the system can classify air on Micro Controller Units (MCUs) and multiple hosts contaminants with an average accuracy surpassing 75%, like Linux/Windows/Android, depending on application showcasing its potential efectiveness in indoor air qualneeds. Classification tasks utilize ML techniques like ity assessment. However, classification accuracy varied MLP, CNN, or LSTM, adaptable to run on MCU or more among diferent contaminants, with notable challenges powerful devices like PCs, depending on computational in distinguishing similar substances like acetone and alrequirements. cohol. This variation underscores the complexities of air quality monitoring and identifies avenues for future enhancement.
In evaluating the system’s operational eficiency, we prioritized minimizing data acquisition times and energy consumption, optimizing for low-power operations ideal for IoT applications. This focus ensures the efectiveness and practicality of our solution for real-world deployment, highlighting the importance of eficiency in Figure 1: The proposed integrated system. SDM stands for environmental monitoring technologies. SENSIPLUS Deep Machine. Looking forward, we anticipate several potential enhancements to our system. These include integrating
Our methodology involves a structured measurement additional sensor types to expand the range of detectable protocol to simulate various indoor air quality conditions. contaminants, exploring advanced machine learning models to enhance classification accuracy, and developing expanded real-time monitoring capabilities. These eforts aim to further improve the comprehensiveness and usability of our indoor air quality monitoring system.
In conclusion, our work contributes to environmental monitoring eforts by demonstrating the feasibility of a sensor-based and machine-learning-integrated system for indoor air quality assessment. While promising, our results also highlight the challenges in air quality monitoring and the necessity for continued innovation in this ifeld. Our study represents a step toward achieving more accessible, eficient, and accurate air quality monitoring solutions.
public health and security. An End-to-End IoT-ready node is proposed for sensing, processing, and transmitting wastewater pollutant data. Utilizing Smart Cable Water with SENSIPLUS chip sensors, the system employs impedance spectroscopy to distinguish pollutants from other substances. Data processing, on a low-cost Micro Control Unit, involves anomaly detection, classification, and false positive reduction through machine learning algorithms.
SENSIPLUS [15]. The system’s objective is to detect substances in wastewater. However, direct measurements from sewage drains are impractical due to unreliable conditions and health risks. To address this challenge, Synthetic WasteWater (SWW) is created to simulate sewage composition. The recipe used to create SWW is inspired by previous work, and pH adjustments are made to replicate real wastewater conditions. Fourteen substances have been spilled in the SWW background: (1) Acetic Acid; (2) Acetone; (3) Ethanol; (4) Ammonia; (5) Formic Acid; (6) Phosphoric Acid; (7) Sulphuric Acid; (8) Hydrogen Peroxide; (9) Synthetic Waste Water; (10) Sodium Hypochlorite; (11) Sodium Chloride; (12) Dish Wash Detergent; (13) Wash Machine Detergent; (14) Nelsen. These substances are divided into two categories: substances to be identified (group 1) and outlier samples (group 2) to be excluded by the system. This method guarantees a safe environment for dataset creation without any biological risks.
and the RedOx dynamics, the six IDEs of the SCW were coated with six diferent metals: Gold (M1), Copper (M2), Silver (M3), Nickel (M4), Palladium (M5), and Platinum (M6). From the resulting sensors, we recorded the resistance measured at a frequency of 78 kHz for the Gold and Platinum IDEs, while Resistance and Capacitance were measured at a frequency of 200 Hz for Gold, Platinum, Silver, and Nickel. This yielded a feature vector comprising ten values: six resistance and four capacitance measurements. Notably, the experimental campaign did not involve the use of Palladium and Copper IDEs.
Preprocessing and Classification. In the Data Preprocessing phase, raw sensor data is normalized before being sorted and evaluated by a Finite State Machine (FSM) shown in Figure 5. This process determines whether the data should proceed to the Classification phase.
The Data Preprocessing phase involves normalizing the raw data from sensors, establishing a robust baseline signal, and determining whether the normalized sample should proceed to the anomaly detector or be directly classified using the FSM.
of interest and others in the sewerage network is crucial. The primary aim is to determine if the substance being investigated is of interest, minimizing subjective evaluations unless specified.
The identification phase involves anomaly detection and multiclass classification for precise substance identification. Anomaly detection excludes common substances, focusing on outliers, while classification employs optimized KNN models trained solely on samples of interest. Grid search methods enhance the accuracy of both anomaly detection and multiclass classification models.
The study combined anomaly detection with a multi- YES class classifier for the final test, as illustrated in Figure 6.
However, the multiclass classifier incorrectly identified some outlier substances, leading to false positive alarms. Feature Selection To mitigate this, the anomaly detection system was integrated before the multiclass classifier. Consequently, Selected Frequencies most outlier samples were accurately classified as ’UNKNOWN,’ achieving an accuracy rate of 79.4%. Notably, Figure 7: The proposed method workflow. 20.6% of outlier samples, primarily sodium hypochlorite, were frequently misclassified as hydrogen peroxide.
Constrains Definition Characterization of batteries under test Is the classifier fixed?
NO Classifier selection
for tasks like battery life estimation and temperature control. Existing techniques like Coulomb counting and Open Circuit Voltage (OCV) face challenges such as measurement errors and the flat relationship between voltage and SoC in certain battery types like Lithium Iron Phosphate (LFP). Electrochemical Impedance Spectroscopy (EIS) emerges as a promising alternative but sufers from long measurement times. This work proposes a method to minimize measurement time while ensuring accurate SoC estimation, particularly with EIS and knowledgebased SoC classes.
The proposed approach follows the framework shown in Figure 1. It starts with the identifying design parameters and constraints, which include: (1) Resolution of SoC performance estimation, (2) Target measurement time, (3) Target Accuracy, (4) Battery type, and (5) Classifier. The second step is to characterize the device under test, focusing on achieving the most stringent parameters possible. Then the appropriate classifier from the previous dataset is evaluated. The chosen classifier, demonstrating better accuracy, is then integrated into the feature selection algorithm. The final stage involves feature selection using search algorithms, aimed at minimizing measurement time while preserving accuracy above the specified target.
problem was addressed using 10-class classification models where each class represents a 10% interval of the SoC.
The initial dataset comprises all available features, including 28 impedances (real and imaginary parts) measured at various frequencies, totaling 56 features collected from 7 diferent cells. These features represent the Nyquist plots of battery impedances at diferent SoCs, as illustrated in Figure 8. Performance evaluation metrics used are described by Grandini et al[16]. The experiments consistently followed the k-fold method, ensuring opti- Figure 9: Obtained confusion matrix of the Support Vector mal dataset utilization by rotating the batteries used. As Machine model, with mean value (top) and standard deviation a result, six trained models were obtained. Evaluation (bottom) for each class. metrics confirm that the Support Vector Machine (SVM) model outperforms others, with a mean accuracy of 0.83 and a standard deviation of 0.04. The resulting confusion imum Accuracy achieved over 50 runs, correlating with matrix shown in Figure 9 illustrates the performance of the weight coeficient, while considering measurement the SVM model. These preliminary classification tests time. The blue star indicates the solution with the highest identify SVM as the most efective ML model among Accuracy. The band represents SoC estimation Accuracy those considered. considering all features with the SVM classifier,showing
The problem of identifying the optimal set of frequen- a trade-of between accuracy and measurement time opticies for impedance measurement via EIS for battery SoC mization, where higher values prioritize accuracy over estimation has been addressed using optimization algo- time. rithms as search strategies, specifically Particle Swarm Ompentitme dizbaatisoend o(PnSaOs)u[p1e7r]v.isAedfitlneeasrsnifnugncmtioodnelis1,iami mplien-g 01..9050 AMcacxuimraucmyfAocrcmuirnaicmyum measuremet time MMienaimsuurmemmeenatstiumreemfoerttthimeemaximumAccurac1y.0 ittdsioimcibtneiavo.leanTrnshsce(eeClpyPaac)rrceatuolmarttaeoecttdeyarltio2nprrmSeeodpeCiarcestesuiseortnneimtmssa(etTthniPoet)nd,rawuatnrihaoditloiemofpnecaa.orsMraurmereecaemtstueperrrnee3t-- rccycuaA000...684000 Accuracy with al features 000...684 iilttrszuaeeenedeammm ment time () is computed as the sum of selected 0.20 0.2 roNm feature durations, with related to the use of all features. Parameters and range from 0 to 1, with 0.00 0.0 0.2 0.4weight coef cie0n.t6 0.8 1.0 0.0 serving as a weight coeficient between accuracy and time contributions.
The EU partially supported this work in the NextGenerationEU plan through MUR Decree n. 1051 23.06.2022 4.2. Results "PNRR Missione 4 Componente 2 Investimento 1.5" CUP H33C22000420001, partially through Horizon EuThis case study establishes a target accuracy of 0.95, re- rope RHE-MEDiation with (GA 101113045). gardless of measurement time. Figure 10 shows the max