Precision farming technologies refer to a set of cutting-edge tools and strategies implemented to optimize the management of the plantation. Smart meter devices, IoT technologies, and Wireless Sensor Networks are only a few examples of the innovative systems increasingly employed from an Agriculture 4.0 point of view. Recent literature has paid close attention to the role of Artificial Intelligence (AI) and Deep Learning (DL) algorithms in helping farmers and improving soil productivity. In this regard, this paper presents the design of a Wireless Sensor Network based on low-cost, low-power PV-supplied sensor nodes able to acquire data regarding environmental conditions and soil parameters. Among all the implemented sensors, the most critical is the soil moisture sensors because of many issues related to cost, installation, reliability, and calibration. Thus, this paper proposes a deep learning approach based on Long Short-Term Memory (LSTM) networks to provide a virtual soil moisture sensor using only the data acquired by the other transducer installed on the node. Performances estimation of the virtual sensors and an in-depth comparison with other learning-based approaches have been presented in this paper to validate the effectiveness of the proposed soft sensing approach.

The recent development of highly automated machinery and intelligent industrial plants has increasingly enabled the continuous monitoring of their efficiency and condition, with the aim of maintaining high production efficiency and minimal malfunctions. Typical condition monitoring and fault detection applications are often achieved using acoustic and vibrational techniques, but the availability of distributed electrical measurements opens new opportunities for industrial fault detection with minimal impact on electrical systems. Even if artificial intelligence-based approaches can be used to model industrial equipment by means of measures made on electrical systems to which they are connected, machine learning algorithms have been demonstrated to be particularly adequate for this purpose due to the huge amount of data produced by interconnected sensors and devices. In this context, the aim of this work is to propose a new unsupervised analysis methodology for detecting anomalies in industrial machinery using electrical current values and other parameters measured on the power grid. The proposed framework is aimed at incorporating the advantages of Machine Learning algorithms and those of traditional analysis, optimizing their operation to improve performance and execution time; this also incorporates a methodology for analyzing the temporal dynamics of the anomaly based on Short-time Fourier transform to strengthen the performance of the detection. The results obtained showed excellent performance, both compared to the evaluations of a technical expert and to other methodologies used in the literature, with zero false positives detected in all datasets tested and a negligible number of undetected outlier events, less than 4% of the total in the datasets.

Wireless Sensor Networks are subjected to some design constraints (e.g., processing capability, storage memory, energy consumption, fixed deployment, etc.) and to outdoor harsh conditions that deeply affect the network reliability. The aim of this work is to provide a deeper understanding about the way redundancy and node deployment affect the network reliability. In more detail, the paper analyzes the design and implementation of a wireless sensor network for low-power and low-cost applications and calculates its reliability considering the real environmental conditions and the real arrangement of the nodes deployed in the field. The reliability of the system has been evaluated by looking for both hardware failures and communication errors. A reliability prediction based on different handbooks has been carried out to estimate the failure rate of the nodes self-designed and self-developed to be used under harsh environments. Then, using the Fault Tree Analysis the real deployment of the nodes is taken into account considering the Wi-Fi coverage area and the possible communication link between nearby nodes. The findings show how different node arrangements provide significantly different reliability. The positioning is therefore essential in order to obtain maximum performance from a Wireless sensor network.

Power Quality Disturbances (PQD) have affected many people due to the growing number of electronic nonlinear loads and because of the significant increase of renewable sources connected to the grid. Previous works have shown the development of algorithms to detect and classify these disturbances. A thorough review of PQD detector algorithms pointed out the use of machine learning and deep learning algorithms as the most used, accurate and up-to-date approaches to deal with this problem. Up until now, these algorithms were used in a sliding window manner that often fail to identify more than one disturbance in a single window frame. In this work, an innovative architecture called Single Shot Power Quality Disturbance Detection (SSPQDD) has been developed to solve this problem. Several experiments were conducted using a simulation dataset in order to validate the performances of the proposed SSPQDD in comparison with other algorithms available in literature in terms of computational resources, accuracy of identification and number of layers. Furthermore, an experimental testbench has been carried out to test the performances of SSPQDD using real measurement data in case of multiple disturbances in a single window frame. The overall accuracy obtained using the proposed SSPQDD was 96.55% in PQD detection.

The problem of Power Quality analysis is becoming crucial to ensuring the proper functioning of complex systems and big plants. In this regard, it is essential to rapidly detect anomalies in voltage and current signals to ensure a prompt response and maximize the system’s availability with the minimum maintenance cost. In this paper, anomaly detection algorithms based on machine learning, such as One Class Support Vector Machine (OCSVM), Isolation Forest (IF), and Angle-Based Outlier Detection (ABOD), are used as a first tool for rapid and effective clustering of the measured voltage and current signals directly on-line on the sensing unit. If the proposed anomaly detection algorithm detects an anomaly, further investigations using suitable classification algorithms are required. The main advantage of the proposed solution is the ability to rapidly and efficiently detect different types of anomalies with low computational complexity, allowing the implementation of the algorithm directly on the sensor node used for signal acquisition. A suitable experimental platform has been established to evaluate the advantages of the proposed method. All the different models were tested using a consistent set of hyperparameters and an output dataset generated from the principal component analysis technique. The best results achieved included models reaching 100% recall and a 92% F1 score.

In several applications (e.g. industrial plants, energy production systems, pipelines, offshore plants, wind turbines, etc) the DC-DC converter must endure harsh environmental and operating conditions. Stress as temperature, humidity, mechanical shocks and vibrations deeply affect the converter from both performance and reliability points of view. However, recent literature misses to consider a characterization of the DC-DC convert performances in presence of harsh operating environment with considerable stress levels. Trying to solve these needs, this paper presents a customized Reliability Stress Screening (RSS) test plan that includes high temperature, low temperature, high humidity and wideband vibration to characterize the electrical performances of an innovative DC-DC converter used in diagnostic systems for condition monitoring of industrial plants. The converter presented in this work has been driven using the Pulse Skipping Modulation (PSM) in spite of the well-known Pulse Width Modulation (PWM) in order to increase the conversion efficiency and the autonomy of the node. The test plan has been performed on a set of eight customized DC-DC converters to ensure significant and reliable results. The aim of this characterization under harsh environments is to propose a robust and reliable DC-DC converter that could be installed in different operating environments ensuring its proper expected performances. The measurement results highlight the stability of the proposed converter in terms of efficiency, input ripple, output ripple, step response and reliability. One of the most striking results highlighted in the manuscript is that the benefits of PSM with respect to the PWM in case of light load conditions are even more remarkable in presence of harsh environment.