Agriculture sector is an important pillar of the global economy. The cotton crop is considered one of the prominent agricultural resources. It is widely cultivated in India, China, Pakistan, USA, Brazil, and other countries of the world. The worldwide cotton crop production is severely affected by numerous diseases such as cotton leaf curl virus (CLCV/CLCuV), bacterial blight, and ball rot. Image processing techniques together with machine learning algorithms are successfully employed in numerous fields and have also used for crop disease detection. In this study, we present a deep learning-based method for classifying diseases of the cotton crop, including bacterial blight and cotton leaf curl virus (CLCV). The dataset of cotton leaves showing disease symptoms is collected from various locations in Sindh, Pakistan. We employ the Inception v4 architecture as a convolutional neural network to identify diseased plant leaves in particular bacterial blight and CLCV. The accuracy of the designed model is 98.26% which shows prominent improvement compared to the existing models and systems.
Design of a potentially robust autopilot to control lateral motion of a jet aircraft for maintaining the balance, turbulence rejection, handling asymmetric wind pressure, linearization and constraints on the inputs imposes technological and computational challenges for certain control algorithms. Especially, when the multiple states and inputs are strongly coupled to each other, it is imperative to evaluate the performance of most efficient control schemes which not only provide stable and error free response but also fulfill the system requirements with minimum computational cost. This paper demonstrates lateral motion control of a jet aircraft using state feedback controllers, proportional integral derivative controller and model predictive controller to evaluate and compare the control objectives. In a block diagram framework as a function of elementary tuning parameters, all strategies are implemented on a linearized state space model which is furnished by the set of fundamental equations of motion. The effects of disturbance, input and output constraints, sampling time and different controller gains are studied for the underlying multiple input multiple output system. State feedback algorithms provide minimum flexibility to achieve the control objectives in restraining the output within constraint boundaries. Proportional integral derivative controller is more flexible, yet not able to impose the limitation on both the input/output pair. Finally, model predictive controller presents the most efficient features by virtue of response time, robustness, stability, cost and constraints fulfillment with minimal computation and input cost.
Decentralized power generation efficaciously merges technological advances in a rapidly changing face of power networks introducing new power system components, advanced control, renewable sources, elegant communication, and web technology paving the way for the so called smart grids. Distributed generation technology lies at the intersection point of power systems, power electronics, control engineering, renewable energy, and communication systems which are not mutually exclusive subjects. Key features of renewable integration in a distribution network include loss minimization, voltage stability, power quality improvement, and low-cost consumption resulting from abundant natural resources such as solar or wind energy. In this research work, a case study has been carried out at a 132 kV grid station of Layyah, Pakistan, which has active losses, reactive losses, low power factor, low voltage on the demand side, and overloaded transformers and distribution lines. As a result, power outage issue is frequent on the consumer side. To overcome this issue, a simulation of load flow of this system is performed using the Newton-Raphson method due to its less computational time, fewer iterations, fast convergence, and independence from slack bus selection. It finds the harsh condition in which there were 23 overloaded transformers, 38 overloaded distribution lines, poor voltage profile, and low power factor at the demand side. There is a deficit of 24 MW in the whole system along with 4.58 MW active and 12.30 MVAR reactive power losses. To remove power deficiency, distributed generation using solar plants is introduced to an 11 kV distribution system with a total of 24 units with each unit having a capacity of 1 MW. Consequently, active and reactive power losses are reduced to 0.548 MW and 0.834 MVAR, respectively. Furthermore, the voltage profile improves, the power factor enhances, and the line losses reduce to a great extent. Finally, overloaded transformers and distribution lines also return to normal working conditions.
Measurement of composition of mixtures at high pressures is important in many applications such as supercritical drying of aerogels, high-pressure sterilization and synthesis of nanostructured materials. The frequency response of uncoated microcantilevers immersed in ethanol-CO2 mixtures with compositions ranging from 0.85 to 4 weight % of ethanol in ethanol-CO2 were measured at a temperature of 318 K and pressure range of 10 MPa to 22 MPa. The resonant frequencies and Q-factors were found to decrease with the increasing weight % of ethanol in the mixture. The data indicate that the composition of a mixture can be measured by measuring the resonant frequency of the cantilever in the mixture after obtaining a calibration curve by measuring resonant frequencies of mixtures with known composition. The sensitivity of the technique which is defined as the ratio of resonant frequency shift to the change in fluid mixture was investigated. An analytical expression for sensitivity was derived using Sader's model. The sensitivity was found to be a complex function of density and viscosity of the mixture as well as the length, density and width of the cantilever. Using the density and viscosity data in the literature for ethanol-CO2 mixtures with various compositions, the sensitivity of the cantilevers were calculated at each pressure and temperature. The results indicate that the minimum composition that can be measured with the current setup is between 480 ppm and 980 in the pressure range of 10 MPa to 22 MPa by using a 150 µm long cantilever and between 600 and 1450 ppm by using 200 µm long cantilever. Acknowledgment: - This project has received funding from the European Union´s Horizon 2020 research and innovation programme under grant agreement No 685648.
This paper presents a novel supervised machine learning-based electric theft detection approach using the feature engineered-CatBoost algorithm in conjunction with the SMOTETomek algorithm. Contrary to the previous literature, where the missing observations in data are either ignored or imputed with average values, this work utilizes k-Nearest neighbor technique for missing data imputation; thus, an accurate and realistic estimation of the missing data is achieved. To mitigate the biasness to the majority data class, the proposed model utilizes the SMOTETomek algorithm, which neutralizes the mentioned effect by managing a proper balance between over-sampling and under-sampling techniques. Feature Extraction and Scalable Hypothesis (FRESH) algorithm is utilized at the later stage of the proposed NTL detection framework to extract and select the most relevant data features from the provided dataset. Afterward, the model is trained using the CatBoost algorithm to classify the consumers into two distinct categories, i.e., genuine and theft. Finally, to interpret the model’s decision for the corresponding predictions, the tree-SHAP algorithm is utilized. To validate the efficacy of the proposed ML based theft detection approach, its performance is compared with that of the traditional gradient boosting ML algorithms such as XGBoost, lightGBM, Ensemble bagging, boosting ML models, and other conventional ML models using five of the most widely used performance metrics, i.e., precision, accuracy, F1score Kappa and MCC. The proposed technique achieved an accuracy of 93% and a detection rate of 92%, which is significantly higher than all the considered competing algorithms under identical dataset and hyperparameters.
The face of state administered utility grid is suffering from a severe stress due to the rapidly growing urban communities, population, luxurious lifestyle of residents and eventually their electricity needs. This trend being accelerated at a higher pace during the past decade calls for the incorporation of alternative power sources using renewables in grid-tied or islanding mode of operation so-called microgrid. This paper addresses the technical issues associated with a 132 kV grid dedicated to Qadirpur Ran, a rural district of Pakistan located adjacent to the city of Multan. The existing electrical architecture of the district is simulated using power flow solver which illustrates that the components of the grid undergo high losses, poor voltage profile and low power factor. In addition, the simulation study identifies 20 overloaded transformers and 20 overloaded distributed lines in the existing system. Without altering the network configuration, a solar plant and a biogas plant of 10 MW capacity each along with three additional biogas plants of 5 MW (2 MW, 2 MW, 1 MW) rating which serve as emergency backup during night time are proposed for the district. As a result, the district is isolated from the national grid eliminating complexities associated with grid integration and serving as an electrically autonomous enclave. The updated hybrid system announces appealing features in a broad spectrum of electrical power framework compared to the existing quantities providing exquisite solutions to the prevailing issues. Furthermore, the cost of all-renewable powered off-grid system is calculated taking into account contributed supplementary components to estimate the total payback period of 9.75 years.
This paper presents a novel data-oriented unsupervised machine learning-based theft detection approach for efficiently identifying the fraudster consumers. It accomplishes the above-mentioned objective by exploiting the intelligence of the robust principal component analysis (ROBPCA) algorithm in conjunction with the outlier removal clustering (ORC) algorithm. To avoid the irregularities in acquired consumers' data from a power utility, the statistical features are extracted from each consumer's consumption patterns using an anomalous time series extension. Based on the extracted features, the consumers with most similar features are initially grouped into two categories using the ROBPCA algorithm. In order to evade any overlapping between the two newly formed groups, the ORC algorithm is utilized to categorize the consumers distinctly as "suspicious" and "non-suspicious". Finally, a very selective onsite inspection is proposed, thus, saving the considerable time, resources, and overall cost of the utilities. The effectiveness of the proposed theft detection method is validated by comparing its performance with nine most widely used outlier detection methods on the basis of seven of the most prominent performance metrics. The accuracy and detection rate of the proposed technique are found as 94.34% and 92.52%, respectively, which is significantly higher than that of other studied conventional methods.
Doublefed induction generator(DFIG) has shown tremendous success inwind turbines due to its flexibility and ability to regulate the active andreactive power. However, the presence of brushes and slip rings affects itsreliability, stability, and power quality. Furthermore, itdoes not providepromising outcomes in case of faults even in presence of the crowbar circuit.In contrast, thebrushless doubly fed induction generator(BDFIG) is a morereliable option for wind turbines than its mentioned counterpart due to theabsence of the brushes and slip rings. This research work as such attempts toimprove the dynamic performance of thevector control(VC)oriented powerwinding (PW) stator flux-based BDFIG by optimally selecting theproportional-integral(PI) gains throughinternalmodel control(IMC)approach. The proposed control scheme is utilized to regulate the speed,torque, and reactive power of the considered BDFIG independently. Contraryto the previous literature where the “trial and error method” is generallyutilized, the current research work uses the IMC for selecting the mostsuitable PI parameters, thus reduces the complexity, time consumption, anduncertainty in optimal selection. The considered BDFIG based wind turbinewith the proposed control scheme provides a better BDFIG control designwith an enhanced dynamic response as compared to that of the same withDFIG under identical operating conditions and system configurations.
'/%3e%3cpath fill='%23fff' d='m8.751-17.959 10.11 11.373L3.997-9.844l13.94-6.1-7.692 13.129z'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='translate(0 -400)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -600)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -800)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1000)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1200)'/%3e%3cpath d='M0 0h1400v800H0z' style='fill:%23010066'/%3e%3cpath d='M576 100c-166.146 0-301 134.406-301 300s134.854 300 301 300c60.027 0 115.955-17.564 162.927-47.783-27.353 9.44-56.71 14.602-87.271 14.602-147.327 0-266.897-119.172-266.897-266.01 0-146.837 119.57-266.01 266.897-266.01 32.558 0 63.746 5.815 92.602 16.468C696.217 118.91 638.305 100 576 100z' style='fill:%23fc0'/%3e%3cpath d='m914.286 471.429-99.538-53.25 29.43 108.982-66.575-91.165-20.77 110.96-20.428-111.024-66.857 90.96L699.314 418l-99.701 52.943 74.065-85.192-112.8 4.441 103.694-44.62-103.555-44.94L673.8 305.42 600 220l99.538 53.25-29.43-108.982 66.575 91.165 20.77-110.96 20.428 111.023 66.857-90.959L814.97 273.43l99.702-52.944-74.065 85.193 112.8-4.441-103.694 44.62 103.555 44.94-112.785-4.79z' style='fill:%23fc0' transform='matrix(1.2738 0 0 1.2423 -89.443 -29.478)'/%3e%3c/svg%3e)
