Advanced Control for Applications最新文献

Industrial robot is a and multi-output complex system with strong coupling and high nonlinearity. The motion control accuracy of the system is affected by many factors. To solve the difficulty in establishing the input and output characteristics of robot dynamics modeling, the robot motion model is established through the Lagrangian energy function. At the same time, the nonlinear relationship between angular velocity, angular acceleration, and robot torque is accurately expressed through improved cascaded neural network. In addition, the optimal time planning of the robot's trajectory in joint space is studied using multinomial interpolation method and the particle swarm optimization (PSO). In the simulation experiment, the effect of the proposed dynamic model fitting was outstanding. Under the mixed multinomial difference calculation planning, the angular position trajectories of the three joints changed very smoothly. In the data set application test, the average error of the PSO algorithm was 0.4061 mm and the average task time was 9.101 s, which were lower than other planning algorithms. Experiments showed that the Lagrangian dynamic model analysis based on genetic algorithm cascaded neural network and PSO trajectory scheduling method under mixed multinomial difference had better trajectory planning performance in handling tasks.

The flow field of the environment plays a crucial role in cigarette combustion cone fallout propensity test, with air velocity exhibiting a positive correlation with combustion volume. In order to minimize the impact of the environmental flow field on the test results, it is necessary to control the air speed within the range of 200 ± 30 mm/s in the test area of each tobacco test channel. To address this concern, which used the Realizable k-ε model to develop a mathematical model of the testing environment. The uniformity of air speed in each channel and its relationship with structural parameters were then analyzed. Based on these findings, the key structural parameters of the ventilation hood are optimized. After restimulated the optimized model, the results demonstrate a higher level of uniformity in the environmental flow field of the optimized section. To validate the accuracy of the simulation results, measurements indicated that the maximum air speed value at all points is 225.6 mm/s, while the minimum value is 178.44 mm/s. These values fall within the specified range of 200 ± 30 mm/s, thus meeting the design requirements. This study ensures that the cigarette can burn in a steady state during the cigarette combustion fallout propensity test and improves the stability of the cigarette combustion cone drop tendency test results.

With the development of social resources, people's consumption of energy is huge, so renewable energy, such as wind energy, has been widely concerned and developed. Although there has been sufficient development of wind power generation, its output has some problems such as uncertainty, which leads to insufficient utilization of wind energy resources and uneven power output quality level, which brings great challenges to the grid connection. To solve this problem, a short-term wind power prediction model combining firefly algorithm and long term memory network is proposed. The main motivation of the research is to improve the accuracy of wind power prediction and thus improve the utilization of wind energy resources. Compared with the existing methods, the innovation of FA-LSTM model lies in the integration of the two algorithms, making full use of the advantages of FA in global search optimization and LSTM in time series data processing, and improving the accuracy and stability of prediction. During the experiment, we used different wind farm data to train and test the model. The results show that the FA-LSTM model can improve the optimal fitness by more than 50% compared with other algorithms, and the iterative prediction error is smaller. Standard root mean square error (RMSE) and mean absolute error (MAE) were used to evaluate the model. The accuracy of RMSE and MAE reached over 97% and 98% respectively. When the test data is highly volatile, the data accuracy of FA-LSTM model reaches 92% and 94%, and the FA-LSTM model drops to the stable value faster. FA-LSTM model has the best fitting degree with the true value curve, and the fitting degree reaches more than 90%. Comparing the actual power and predicted power of different units, the actual power of Unit 1 is 34.875, and the predicted power obtained by FA-LSTM model is 34.935, with an error of only 0.06. The key finding of this study is that the prediction model combining FA and LSTM has high accuracy and stability in wind power prediction, and can effectively deal with the uncertainty and volatility of wind energy resource utilization. FA-LSTM model provides an effective solution for wind power prediction, which is helpful to improve the utilization rate of wind energy resources.

The power system (PS) has the problem of grid connection of energy storage (ES) system. When the ES of the communication base station (BS) is associated with the power grid, relevant control strategies are formulated to schedule the base station energy storage (BSES). The total cost required during the scheduling period is determined using the lease income model. In the dispatching process, the BSES is applied to the peak load shifting (PLS) dispatching and economic dispatching of the PS. It is optimized by particle swarm optimization (PSO) algorithm and improved bare bone particle swarm optimization (BBPSO) algorithm. The constructed rental income model is used to calculate the total cost required during the scheduling period. In the dispatching, the BSES is applied to the PLS dispatching and economic dispatching of the PS. This model is optimized by PSO algorithm and improved BBPSO algorithm. The findings indicate that the BSES has good PLS capability. The larger the BS is, the more obvious the charging and discharging situation is. When the time is 4 h, the output load of 150,000 BSES is 486.67 MW, 341.14 MW more than that of 100,000 BSs. The discharge depth affects the lease cost, and the best discharge depth is 0.4. At this discharge depth, the larger the BS scale is, the greater the costs. In improving the performance of BBPSO algorithm, the model has the minimum convergence iteration of 15, with the best convergence effect. In the economic dispatching of PS, the total cost of accessing 200,000 BSs to store energy is 846.4658 million per year, which saves 367.4591 million. The suggested approach can effectively lower PS costs and increase stability.

A novel strategy using a chaotic gravitational search algorithm (CGSA) based nonlinear PID control scheme, which is validated through a laboratory helicopter model called the twin rotor system, is presented in this paper. In this work, CGSA is used as a stochastic based global optimization algorithm for controller design in the twin rotor system adopted. The fine chaotic search process used in CGSA obtains the optimal solution in the iterative process based on the current best solution. The goal of the controller design in this paper is to stabilize the twin rotor system with considerable cross couplings to reach the selected position and follow the desired trajectory effectively. The addition of nonlinear functions to the PID controller structure initiates better error tracking and facilitates smooth output under changing input conditions. The design objective is to implement a nonlinear PID control scheme for the angular displacements of the twin rotor system with minimization of the integral square error (ISE) as the fitness function in the algorithm. The statistical performance of the controller is analyzed by considering the best, worst, mean, and standard deviations of ISE. In this work, simultaneous control of pitch and yaw angles is considered to get rid of the coupling effect between the two rotors. From the simulation results it is observed that the proposed work shows better performance than the other evolutionary computation techniques. The results also indicate the advantage of the proposed CGSA based tuning for the two degree of freedom MIMO control with standard reference trajectories as per the TRMS330-10 model.

Short-term electricity load forecasts (STELF) is an essential part of power system and operation, capable of balancing electricity demand and is vital to the safety and efficient operation of the power system. The research improves the Long short-term memory (LSTM), combines it with Bidirectional recurrent neural network (BIRNN), and obtains the improved Bidirectional Long Short-Term Memory Network (BiLSTM) forecasting model. The Sparse Search Algorithm (SSA) can provide a new solution to more difficult global optimization problems and has been improved due to the shortcomings of the search and detection mechanisms. and a simplex mechanism is introduced to obtain an improved Search Mechanism Sparse Search Algorithm (SMSSA) optimized pathfinding algorithm. And constructs the SMSSA-based optimized BiLSTM for STELF model. By choosing actual data, the model's prediction behavior is confirmed. The results showed that, in descending order, BiLSTM, LSTM, and Recurrent Neural Network (RNN) had the best fitting effects between the predicted and actual values. BiLSTM also had the highest prediction accuracy, with error values of 95.7059 for Root Mean Square Error (RMSE), 79.1575 for Mean Absolute Error (MAE), and 2.1260% for Mean Absolute Percent Error (MAPE). After SMSSA optimized the parameters, SMSSA-BiLSTM had the best fit and had errors that were much lower than those of the other two models. According to the three error judgment metrics of RMSE, MAE, and MAPE, the errors were 82.6298, 71.9029, and 2.0952%, respectively. This showed that SMSSA-BiLSTM performed well in short-term power load forecasting, offering security for the power system's safe operation.

Beer is one of the popular drinks, the temperature control in the process of beer fermentation plays a crucial role. The current temperature control method mainly uses the traditional PID control, but its control adjustment time is long, the overshoot is large, the control effect still needs to be improved. A beer fermentation and brewing temperature monitoring system based on immune fuzzy PID controller was designed in this experiment. Immune fuzzy PID controller is a nonlinear controller, which combines the advantages of traditional PID controller and fuzzy controller and refers to the regulatory mechanism of biological immune system, and obtains good suitable characteristics by controlling the parameter values of the system. PID converts the rule information into fuzzy information by fuzzy basic theory and stores it in computer database. By referring to the actual situation of PID, the computer uses fuzzy reasoning to adjust the PID parameters. The beer fermentation temperature monitoring system based on the traditional PID controller is compared with the proposed system. Under the control of the designed temperature monitoring system, the temperature has a certain effect on the fermentation speed of beer. The fermentation time of high temperature fermentation (16°C) is 3 days shorter than that of normal temperature fermentation (10°C). The robustness and applicability of the system are verified.

From 2013 to now, Beijing-Tianjin-Hebei (Hereinafter referred to as “the region”) has carried out comprehensive air pollution governance, which has promoted the sustained and rapid development of the regional economy while significantly improving regional air quality. However, the spatial and seasonal differences in atmospheric quality are obvious, and the regional and structural problems are still prominent. There is a long way to go for new challenges of cooperate governance of PM_2.5 and O₃. Therefore, first, we should further deepen the joint prevention and control mechanism based on regional collaborative governance. Second, we should rely on technological innovation to impetus the upgrading of energy and industrial structure. Third, we should adjust the transportation structure and create a new pattern of transportation network. Fourth, we should improve the ecological compensation mechanism and give full play to the functions of ecological conservation areas. Fifth, we should think highly of the self-purification capacity of the ecosystem and build urban forest parks. At last, we should Strengthen publicity and mobilization, and participate in joint governance through nationwide action.

The quadruple tank (QT) system consists of four interacting tanks and can switch between the minimum and non-minimum phase behavior with changes in the positions of pump valves and is considered a benchmark control problem. In the present study, long-short term memory (LSTM), a type of recurrent neural networks (RNN) is designed for the benchmark QT system based on the model-based control framework. Random input–output sequences are generated from the white box model of the QT system to train an LSTM network model. The LSTM network is tuned by adjusting its hyperparameters such as the number of hidden layers, hidden units, and epochs to minimize the prediction error on the test data. The trained model is cross validated both during and after training to avoid overfitting. Once a reasonably reliable model is obtained, another LSTM network is trained for use as a controller. The network architecture is constantly modified till the controller is able to track the test setpoints with minimum error. This procedure is repeated with a gated recurrent unit (GRU) network and the servo and regulatory response of both the network models and controller are evaluated in terms of standard performance measure namely root mean square error (RMSE), integral square error (ISE), and control effort (CE). It is observed that the controller designed based on RNN performs better than a conventional centralized controller.