Starting from the fact that in sensorless control systems of Permanent Magnet Synchronous Motor (PMSM) the load torque can have short and significant variations, this paper presents the sensorless control of a PMSM based on a Linear Adaptive Disturbance Rejection Controller (LADRC) type controller. Essentially, the successful operation of the LADRC controller to achieve PMSM rotor speed control performance depends on a good estimation of the disturbances acting on the system. Traditionally, an Extended State Observer (ESO) is used to make such an estimate. In this paper, it is proposed to use a Disturbance Observer (DO) to estimate the external disturbances, and after their rejection, the LADRC controller ensures an equivalent global behavior of the control system with an ideal double integrator, and thus increased ease in achieving the desired control performance. Control structures and Matlab/Simulink implementation of the sensorless PMSM control system based on LADRC controller with ESO/DO type observer are presented, as well as its use in tandem with a Reinforcement Learning Twin-Delayed Deep Deterministic Policy Gradient (RL-TD3) specially trained agent that provides correction signals for more accurate estimation of external disturbances and hence improved control performance. Qualitatively superior performance is achieved by using LADRC with the RL-TD3 agent control structure in terms of parametric robustness, response time, and steady-state error. Also, by calculating the fractal dimension (DF) of the controlled signal and the PMSM rotor speed, it is found that the higher the DF, the better the performance of the control system. The validation of the superiority of the proposed control structures is carried out by means of numerical simulations in the Matlab/Simulink environment.

The dynamic global automotive sector is characterized by an ever-evolving demand for high-quality vehicles and accessible prices. This research tackles the issue of scrap reduction in electric motor manufacturing for the automotive industry, specifically in a Chinese company, by employing the PDCA methodology. The paper delves into the company's background and current landscape, while pinpointing the problem: specific production lines segments experiencing hi-pot issues are the primary source of scrap. The overarching goal is to design and implement a strategy that, leveraging the PDCA approach, reduces scrap generated during the eight-months subassembly (armature) manufacturing process, from its current average of 2.92% to 0.7%, ultimately enabling the company to eliminate hi-pot defects.

Over the last ten years, the integrated pond aquaculture (IPA) has been developing rapidly as a new aquaculture mode, and mechanical power oxygenator is a common oxygenation device in this aquaculture mode. However, with the gradual expansion of the application range of this aquaculture mode, the problems of low efficiency, poor oxygenation uniformity, and low applicability of mechanical power oxygenators, which can produce water reflux and suction pollution accumulation, have gradually emerged. Therefore, we designed a new type of push-water aerator device (NPWAD) applicable to the integrated recirculating water aquaculture mode of ponds. Mainly, the specific parameters of the key components were clarified through the selection calculation and structural design, and the experiments were carried out in the self-constructed pond integrated aquaculture system at the experimental base. The experiments were carried out on the water in the tank for grass carp culture, and the oxygenation and water pushing effects of the type of push-water aerator device under 15 groups of different operating parameters were carried out by using multiple types of high-precision water quality monitoring sensors, with the rotational speed of the device, the operating time (0-30 min) and the height of the water (0.5-1.5 m) as the independent variables, and the oxygenation amount R, the oxygenation power efficiency E_s and the surface layer of the water as the evaluation indexes, average flow velocity V_f were used as its evaluation indexes of oxygenation and water pushing. The results show that the optimal parameters of the NPWAD are impeller water lifting component speed n_1=1000r/min, small-hole aeration component speed n_2=2280r/min. At this time, the average oxygen increase of this device is R=1.96mg/L, the average oxygenation power efficiency is E_s=3.8 kg·(h·kW)-1, the DO uniformity of the water M_1=95.3%, and the average flow velocity V_f=190.8mm/s, which can effectively promote the water directional flow and achieve the water circulation and layer exchange, and it is in line with the preferred swimming speed of grass carp at various growth stages. The new type of push-water aerator device is able to enhance the DO concentration of the water faster, but also to achieve the purpose of promoting the directional flow of the water and renewing the water in the tank, as well as in a short period of time to improve the uniformity of the DO of the water faster, for the improvement of the pond aquaculture production efficiency has practical significance.

Dissolved Oxygen (DO) concentration is a vital parameter that indicates water quality. DO short term forecasting using time series analysis on data collected from an aquaculture pond is presented here. This can provide data support for an early warning system for an improved management of the aquaculture farm. The conventional forecasting approaches are commonly characterized by low accuracy and poor generalization problems. In this article, we present a novel hybrid DO concentration forecasting method with ensemble empirical mode decomposition (EEMD) based LSTM (Long short-term memory) neural network (NN). With this method, first, the sensor data integrity is improved through linear interpolation and moving average filtering methods of data preprocessing. Next, the EEMD algorithm is applied to decompose the original sensor data into multiple intrinsic mode functions (IMFs). Finally, the feature selection is used to carefully select IMFs that are strongly correlated with the original sensor data and integrate both into inputs for the NN. The hybrid EEMD-based LSTM forecasting model is then constructed. Performance of this proposed model in training and validation sets was compared with the observed real sensor data. To obtain the exact evaluation accuracy of the forecasted results of the hybrid EEMD-based LSTM forecasting model, three statistical performance indices were adopted: MAE, MSE, and RMSE. Results presented for short term (12-hour period) and long term (1-month period) give a strong indication of suitability of this method for forecasting DO values.

The paper presents an analysis of the latest developments in the field of stereo vision in the low-cost segment, both for prototypes and for industrial designs. We described the theory of stereo vision and presented information about cameras and data transfer protocols and their compatibility with various devices. The theory in the field of image processing for stereo vision processes is considered and the calibration process is described in detail. Ultimately, we presented the developed stereo vision system and provided the main points that need to be considered when developing such systems. The final, we presented software for adjusting stereo vision parameters in real-time in the python language in the Windows operating system.

All humans will experience the process of birth, old age, illness, and death. However, when faced with life-sustaining decisions, the families of patients are often faced with medical decisions as surrogates. In recent years, the families of patients have started to value the importance of the right to palliative care, although this often requires lengthy discussions. Therefore, this study explored the predictability of factors that affect the feeling experienced by patients’ families when signing Do-Not-Resuscitate Consent. This study used a cross-sectional study and interviewed 90 family members using a structural questionnaire. The study hypotheses were tested using a t-test, one-way analysis of variance, product–moment correlation, and hierarchical regression analysis. Attribute variables of family members, such as gender and whether they live with the patient, are predictors that affect the family member’s feeling experience when signing Do-Not-Resuscitate Consent. The emotional support from medical professionals to family members helps the family member to express their negative feelings on signing Do-Not-Resuscitate Consent; more informational support information provided to family members by medical professionals can alleviate negative feelings felt by family members when signing Do-Not-Resuscitate Consent. This study identified that family members’ knowledge about Do-Not-Resuscitate acquired from medical professionals is relatively low. It is suggested that critical care units regularly conduct training on hospice palliative care, implement standard care procedures of hospice palliative care at critical care units, and provide detailed medical information about advanced decisions to family members so as to reduce their emotional stress. This will ensure that intensive care units can also achieve the goal of critically ill hospice palliative care.

Artificial intelligence systems are increasingly becoming a component of security-critical applications. The protection of such systems from various types of destructive influences is thus a relevant area of research. The vast majority of previously published works are aimed at reducing vulnerability to certain types of disturbances or implementing certain resilience properties. At the same time, the authors either do not consider the concept of resilience as such, or their understanding varies greatly. This work presents a formalized definition of resilience and its characteristics for artificial intelligence systems from a systemic point of view. It systematizes ideas and approaches to building resilience to various types of disturbances. Taxonomy of resilience of artificial intelligence systems to destructive disturbances is proposed. Approaches and technologies for complex protection of intelligent systems, issues of their resource efficiency and other open research issues are considered. Approaches of resilience assessment for artificial intelligence system are also analyzed and recommendations are provided for their implementation.