Intelligent control system and control method for active safety stabilization rudder of ship

Abstract

The invention discloses an intelligent control system and method for a ship active safety stabilization rudder. The intelligent control system is composed of a ship motion sensing module, a ship model module, an intelligent decision-making module and a multi-mode stabilization control module. The ship model module carries out online identification on a response characteristic model by using a recursive Fourier transform or model reference adaptive method, and updates model parameters to adapt to changes of ship loading, navigational speed and sea conditions; the multi-mode stabilization control module adjusts controller parameters in real time according to the model updating result, and the stability and effectiveness of the control effect are guaranteed; and the intelligent decision-making module uses a neural network to continuously learn and optimize the fuzzy control rule, so that the accuracy and adaptability of decision making are improved. According to the intelligent control system and control method for the active safety stabilization rudder of the ship, the problem of dual uncertainty of rudder stabilization is effectively solved, the safety of the ship under the severe sea condition is remarkably improved, and the intelligent control system and control method are suitable for ships with vehicle rudders such as container ships and unmanned ships.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ship navigation safety control, and particularly relates to an intelligent control system and control method for a ship active safety stabilizer. BACKGROUND

[0002] As a main transportation carrier, ships are widely used in the development, utilization, protection and control of the ocean, and are an important support for marine transportation and ocean economy. When sailing on the sea full of uncertainties, marine accidents occur frequently, among which the most common cause is excessive rolling in adverse sea conditions, which poses a safety hazard and is unpredictable.

[0003] The current traditional stabilizer control has double uncertainties. On the one hand, the superposition of the initial inboard roll, the outboard roll of the steering and the external disturbance induced roll may induce excessive roll problems, especially in the face of cross-waves harmonic roll, parametric roll and riding wave lateral swing, which may make the stabilizer become a stabilizer, and there is a safety uncertainty in stabilizing. On the other hand, the model perturbation caused by the change of sailing conditions, the random disturbance of wind and waves, and the constraints of the nonlinearity, rapidity and loss of the rudder, affect the robustness and adaptability of the control algorithm, and restrict the effect of the ship rudder stabilizing control, and there is a serious performance uncertainty problem. The safety uncertainty and performance uncertainty of the traditional stabilizing control hinder its popularization and application.

[0004] Ship rudder stabilizing control is a typical multi-objective optimization control problem, and the traditional optimization method has limitations. Although intelligent optimization algorithms have been gradually applied in ship motion control, such as using the fast non-dominated sorting genetic algorithm with elite strategy to solve the optimal Pareto solution set, better track tracking accuracy and stabilizing effect can be achieved, but ship motion control is extremely complex, and existing intelligent algorithms are still not enough. At present, various methods such as model-free adaptive control are used to ensure the robust control algorithm of intelligent ship safety, but in order to achieve more efficient and safe ship motion control, an intelligent decision and optimization mechanism based on human-computer integration is needed, which combines the advantages of human experience and intelligent algorithms to achieve more efficient and safe ship motion control. SUMMARY

[0005] The purpose of the present application is to provide an intelligent control system and control method for a ship active safety stabilizer, to solve the safety problems of stability loss, ship structure damage and cargo binding failure caused by accidental excessive roll of the ship in adverse sea conditions, and to improve the safety of ship navigation in adverse sea conditions.

[0006] To achieve the above purpose, the present application provides an intelligent control method for a ship active safety stabilizer, comprising the following steps:

[0007] Step S1: Predict and warn of occasional excessive rolling motion;

[0008] Step S11: Based on ship motion sensor data and ship motion adaptive response characteristic model, establish a ship navigation safety perception system;

[0009] Step S12: Process the collected data using amplitude limiting filtering and nonlinear Kalman filtering algorithms, select an appropriate response model based on loading status, speed and sea state, and establish a prediction model for occasional excessive rolling motion.

[0010] Step S13: Based on the IMO ship stability criteria, study the safety standards for excessive rolling and its risk identification principles, and establish an active safety early warning mechanism for cross wave harmonic rolling and parametric rolling stability failure modes.

[0011] Step S14: When the ship's rolling state is detected to be close to or exceed the safety standard, issue an early warning signal in a timely manner;

[0012] Step S2: Establish rudder roll reduction control to resist accidental excessive roll;

[0013] Step S21: Based on the decoupling of yaw and roll, study the dual-mode control mechanism of heading control and rudder roll reduction;

[0014] Active safety rudder roll reduction control is implemented from three aspects: wave encounter angle selection, extreme roll amplitude reduction, and extreme roll acceleration reduction. The optimal wave encounter angle is selected according to sea conditions and ship motion state to reduce roll amplitude and acceleration. By controlling the rudder angle and rudder speed, the roll amplitude and acceleration are limited to a safe range.

[0015] Step S22: Simultaneously, study the superposition mechanism of initial inward tilt, outward tilt and roll caused by external disturbances. Analyze the superposition mechanism and decoupling mechanism of roll amplitude under sudden rudder movement and abnormal wave conditions in the frequency domain. Based on the motion prediction model and risk warning mechanism of occasional excessive roll, implement feedforward decoupling control of the rudder roll reduction loop to solve the problem of occasional excessive roll in maneuverability.

[0016] Step S3: Achieve intelligent decision-making and optimization for the active safety steering;

[0017] Step S31: Adaptively adjust system parameters through online identification of response feature models, online prediction of disturbance motion, and multi-objective intelligent optimization strategies;

[0018] Step S32: Identify the response model parameters online using recursive Fourier transform or model reference adaptive method, obtain the transient ship motion mathematical model, and update the controller parameters in real time to achieve the best transient control performance;

[0019] Step S33: Using NSGA-II and PSO multi-objective intelligent optimization algorithms, solve the mutual constraints between control performance such as heading control, active safety roll reduction and rudder wear, optimize the control strategy of active safety rudder, and improve the overall system performance.

[0020] An intelligent control system for active safety roll reduction rudder of a ship is provided to execute the aforementioned intelligent control method for active safety roll reduction rudder of a ship. The control system consists of a ship motion sensing module, a ship model module, an intelligent decision-making module, and a multi-mode roll reduction control module.

[0021] Preferably, the ship motion sensing module collects ship motion data, sea state data, and ship status data through multiple sensors; the collected data is processed by capacitive Kalman filtering, multi-source heterogeneous information fusion, and iterative intelligent filtering algorithms, and used as input data for the ship intelligent sensing system to provide accurate data support for subsequent decision-making and control.

[0022] Preferably, the ship motion data includes roll, bow roll, sway, and pitch data; sea state data, including wind speed, wave height, and wave direction; ship's own status data, including loading status and speed; and sensor types, including accelerometers, gyroscopes, wind speed sensors, and wave sensors.

[0023] Preferably, the ship model module is used to construct adaptive response characteristic models of ship motion under all working conditions and all sea states; through qualitative and quantitative analysis of the perturbation range of ship motion model parameters under different loading, speed and sea state conditions, ship motion response models under different loading, speed and sea state conditions are established respectively.

[0024] Preferably, by utilizing neural network deep learning, fuzzy synthesis, and multi-model switching methods, ship motion response models under different loading, speed, and sea state conditions are integrated to construct an adaptive response feature model, providing accurate model support for ship motion forecasting and risk warning.

[0025] Preferably, the intelligent decision-making module is used to integrate common navigation practices, the experience of senior navigation experts, and ship expertise to create fuzzy control rules using fuzzy comprehensive reasoning.

[0026] Preferably, the fuzzy control rules and neural network in the intelligent decision-making module are initialized; the initial fuzzy control rules are set according to navigation experience and ship expertise; the neural network is randomly initialized or pre-trained based on existing experience data to lay the foundation for subsequent self-learning and optimization; the fuzzy inference rules are adjusted by the neural network according to the system operation records to form an expert control system based on a dynamic fuzzy neural network with self-learning characteristics.

[0027] Preferably, the intelligent decision-making module receives data from the ship motion perception module, combines the established fuzzy control rules and the results of neural network self-learning, and performs fuzzy comprehensive reasoning; based on the roll risk identification results, it generates an active safety rudder roll reduction strategy, including selecting appropriate operating modes and control parameters, and transmits the decision results to the multi-mode roll reduction control module.

[0028] Preferably, the ship model module uses recursive Fourier transform or model reference adaptive method to identify the response feature model online based on the real-time collected data, and updates the model parameters to adapt to changes in ship loading, speed and sea state.

[0029] The multi-mode anti-roll control module adjusts the controller parameters in real time based on the model update results to ensure the stability and effectiveness of the control effect;

[0030] The intelligent decision-making module uses neural networks to continuously learn and optimize fuzzy control rules, thereby improving the accuracy and adaptability of decision-making.

[0031] Therefore, the present invention employs the above-mentioned intelligent control system and control method for active safety roll reduction rudder of a ship, and the beneficial effects are as follows:

[0032] (1) Improve navigation safety: This invention establishes a prediction and early warning model for occasional excessive rolling motion, which can detect the risk of rolling in advance and take proactive safety measures to reduce rolling in a timely manner. This effectively avoids accidents such as loss of stability, damage to the hull structure and failure of cargo lashing caused by excessive rolling, and significantly improves the navigation safety of ships in adverse sea conditions.

[0033] (2) Innovative control method: The multi-mode roll reduction control method proposed in this invention combines heading control and rudder roll reduction. It comprehensively considers factors such as the influence of sea waves on roll, the law of loss of ship stability, the mechanism of damage to ship strength and cargo lashing safety, and roll reduction control from multiple aspects. It has stronger pertinence and effectiveness and can better adapt to complex sea conditions compared with traditional control methods.

[0034] (4) Intelligent Decision-Making and Optimization: The intelligent decision-making and optimization mechanism for active safety rudders constructed in this invention deeply integrates human-machine intelligence and active safety theory. It solves the safety uncertainty problem of traditional rudder roll reduction control through intelligent decision-making models, and solves the uncertainty problem of ship motion control by using intelligent multi-objective optimization, thereby improving the system's adaptability and robustness and realizing intelligent control of the ship's active safety roll reduction rudder.

[0035] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0036] Figure 1This is a schematic diagram of a module of an intelligent control system for active safety roll reduction rudder of a ship according to the present invention;

[0037] Figure 2 This invention relates to the research concept of an intelligent control system for active safety roll reduction rudders on ships.

[0038] Figure 3 This invention constructs an adaptive response characteristic model of ship motion under all working conditions and all sea states.

[0039] Figure 4 This invention is based on an active safety rudder roll reduction decision model using human-machine integrated intelligence. Detailed Implementation

[0040] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0041] like Figures 1-2 As shown, the present invention discloses an intelligent control system for active safety roll reduction rudder of a ship, which consists of a ship motion sensing module, a ship model module, an intelligent decision-making module, and a multi-mode roll reduction control module.

[0042] The ship motion sensing module collects ship motion data, sea state data, and ship status data through various sensors. The collected data is processed using algorithms such as capacitive Kalman filtering, multi-source heterogeneous information fusion, and iterative intelligent filtering, serving as input data for the ship's intelligent sensing system and providing accurate data support for subsequent decision-making and control.

[0043] Various sensors for ship motion sensing modules are installed on the vessel, ensuring reasonable installation locations and accurate data collection on ship motion, sea conditions, and its own status. The sensors are connected to the data processing unit for sensor calibration and data transmission testing to guarantee the accuracy and stability of data acquisition.

[0044] The ship's motion data includes: roll, bow roll, sway, and pitch data. Sea state data includes: wind speed, wave height, and wave direction. Ship's own status data includes: loading status and speed. Sensor types include: accelerometers, gyroscopes, wind speed sensors, and wave sensors.

[0045] Using real-ship test data, the adaptive response feature model of ship motion in the ship model module was initialized and trained. By collecting ship motion data under different loads, speeds, and sea states, algorithms such as nonlinear GA, least squares method, support vector machine, and empirical parameter identification were used to determine the model parameters and construct the initial adaptive response feature model.

[0046] The ship model module is used to construct adaptive response feature models of ship motion under all operating conditions and sea states. Through qualitative and quantitative analysis of the perturbation range of ship motion model parameters under different loading, speed, and sea states, ship motion response models are established for different loading states (empty, half-loaded, full-loaded), speed states (full speed, half speed, slow speed, low speed), and sea state states (calm, light waves, moderate waves, large waves). Utilizing methods such as neural network deep learning, fuzzy synthesis, and multi-model switching, these models are fused to construct an adaptive response feature model, providing accurate model support for ship motion forecasting and risk warning. Figure 3 As shown.

[0047] The intelligent decision-making module integrates common maritime practices, the experience of senior maritime experts, and ship-specific knowledge to create fuzzy control rules using fuzzy comprehensive reasoning. The fuzzy control rules and neural network within the intelligent decision-making module are initialized. Initial fuzzy control rules are set based on maritime experience and ship-specific knowledge; the neural network is randomly initialized or pre-trained based on existing experience data to lay the foundation for subsequent self-learning and optimization. Figure 4 As shown.

[0048] By adjusting the fuzzy inference rules based on system operation records using a neural network, an expert control system based on a dynamic fuzzy neural network with self-learning characteristics is formed. The intelligent decision-making module receives data from the ship motion perception module and performs fuzzy comprehensive inference by combining the established fuzzy control rules and the self-learning results of the neural network. Based on the roll risk identification results (residual stability risk, hull strength risk, cargo securing risk, etc.), an active safety rudder roll reduction strategy is generated, including selecting appropriate operating modes (roll reduction on, off, or adjusted) and control parameters (such as rudder angle, rudder speed, etc.), and the decision results are transmitted to the multi-mode roll reduction control module.

[0049] The multi-mode roll reduction control module, based on instructions from the intelligent decision-making module and a joint control mechanism of heading control and rudder roll reduction, controls the system from three aspects: wave encounter angle selection, extreme roll amplitude reduction, and extreme roll acceleration reduction. Under the premise of decoupling of bow and roll, the influence mechanism of ship speed, engine speed, and rudder speed on the rudder roll reduction effect under severe sea conditions is studied. Using H∞ theory, the backstepping algorithm, and the mirror mapping method, a simple and robust controller is designed for the ship's motion system. This controller adjusts the rudder angle and rudder speed in real time according to the ship's motion state and sea state, achieving effective control of the ship's heading and roll. Simultaneously, based on the superposition mechanism of initial inward heeling, outward heeling during yaw, and roll caused by external disturbances, feedforward decoupling control is implemented on the rudder roll reduction loop to avoid occasional excessive roll during maneuvering. The stability of the controller is proven using Lyapunov stability theory.

[0050] During ship operation, the ship model module uses real-time collected data and employs recursive Fourier transform or model reference adaptation methods to identify the response characteristic model online and update model parameters to adapt to changes in ship load, speed, and sea state. The multi-mode roll reduction control module adjusts controller parameters in real time based on the updated model results to ensure the stability and effectiveness of the control effect. The intelligent decision-making module uses neural networks to continuously learn and optimize fuzzy control rules, improving the accuracy and adaptability of decision-making.

[0051] This invention also proposes an intelligent control method for active safety roll reduction rudders of ships, applied to the aforementioned control system, comprising the following steps:

[0052] Step S1: Predict and warn of occasional excessive rolling motion.

[0053] Step S11: Based on ship motion sensor data and ship motion adaptive response characteristic model, establish a ship navigation safety perception system.

[0054] Step S12: Process the collected data using amplitude limiting filtering and nonlinear Kalman filtering algorithms, select an appropriate response model based on loading status, speed and sea state, and establish a prediction model for occasional excessive rolling motion.

[0055] Step S13: Based on the IMO ship stability criteria, study the safety standards for excessive rolling and the principles for risk identification, and establish an active safety early warning mechanism for stability failure modes such as transverse wave harmonic rolling and parametric rolling.

[0056] Step S14: When the ship's rolling state is detected to be close to or exceed the safety standard, issue an early warning signal in a timely manner.

[0057] Step S2: Establish rudder roll reduction control to resist accidental excessive roll.

[0058] Step S21: Based on the decoupling of yaw and roll, study the dual-mode control mechanism of heading control and rudder roll reduction.

[0059] Active safety rudder roll reduction control is implemented from three aspects: wave encounter angle selection, extreme roll amplitude reduction, and extreme roll acceleration reduction. For example, the optimal wave encounter angle is selected based on sea conditions and ship motion to reduce roll amplitude and acceleration; and roll amplitude and acceleration are limited to a safe range by controlling rudder angle and rudder speed.

[0060] Step S22: Simultaneously, study the superposition mechanism of initial inward tilt, outward tilt during rotation, and roll caused by external disturbances. Analyze the superposition mechanism and decoupling mechanism of roll amplitude under conditions such as sudden rudder movement and abnormal waves in the frequency domain. Based on the motion prediction model and risk warning mechanism for occasional excessive roll, implement feedforward decoupling control for the rudder roll reduction loop to solve the problem of maneuvering-related occasional excessive roll.

[0061] Step S3: Achieve intelligent decision-making and optimization for the active safety rudder.

[0062] Step S31: Adaptively adjust system parameters through online identification of response feature models, online prediction of disturbance motion, and multi-objective intelligent optimization strategies.

[0063] Step S32: Identify the response model parameters online using recursive Fourier transform or model reference adaptive method, obtain the transient ship motion mathematical model, and update the controller parameters in real time to achieve optimal transient control performance.

[0064] Step S33: Using multi-objective intelligent optimization algorithms such as NSGA-II and PSO, the mutual constraints between control performance such as heading control, active safety roll reduction and rudder wear are resolved, the control strategy of active safety rudder is optimized, and the overall system performance is improved.

[0065] Therefore, this invention employs the aforementioned intelligent control system and method for active safety roll reduction rudders. By establishing a prediction and early warning model for occasional excessive roll motion, it can detect roll risks in advance and take timely active safety roll reduction measures, effectively avoiding accidents such as loss of stability, hull structural damage, and cargo lashing failure caused by excessive roll, significantly improving the navigation safety of ships in adverse sea conditions. The multi-mode roll reduction control method proposed in this invention, which combines course control and rudder roll reduction, comprehensively considers factors such as the impact of waves on roll, the laws governing loss of ship stability, the mechanism of hull strength damage, and cargo lashing safety, providing roll reduction control from multiple aspects. It has stronger pertinence and effectiveness and can better adapt to complex sea conditions compared to traditional control methods. The intelligent decision-making and optimization mechanism for active safety rudders constructed in this invention deeply integrates human-machine intelligence and active safety theory. It solves the safety uncertainty problem of traditional rudder roll reduction control through intelligent decision-making models and addresses the uncertainty problem of ship motion control using intelligent multi-objective optimization, improving the system's adaptability and robustness, and realizing intelligent control of active safety roll reduction rudders.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent control method for active safety roll reduction rudder of a ship, characterized in that, Includes the following steps: Step S1: Predict and warn of occasional excessive rolling motion; Step S11: Based on ship motion sensor data and ship motion adaptive response characteristic model, establish a ship navigation safety perception system; Step S12: Process the collected data using amplitude limiting filtering and nonlinear Kalman filtering algorithms, select an appropriate response model based on loading status, speed and sea state, and establish a prediction model for occasional excessive rolling motion. Step S13: Based on the IMO ship stability criteria, study the safety standards for excessive rolling and its risk identification principles, and establish an active safety early warning mechanism for cross wave harmonic rolling and parametric rolling stability failure modes. Step S14: When the ship's rolling state is detected to be close to or exceed the safety standard, issue an early warning signal in a timely manner; Step S2: Establish rudder roll reduction control to resist accidental excessive roll; Step S21: Based on the decoupling of yaw and roll, study the dual-mode control mechanism of heading control and rudder roll reduction; Active safety rudder roll reduction control is implemented from three aspects: wave encounter angle selection, extreme roll amplitude reduction, and extreme roll acceleration reduction. The optimal wave encounter angle is selected according to sea conditions and ship motion state to reduce roll amplitude and acceleration. By controlling the rudder angle and rudder speed, the roll amplitude and acceleration are limited to a safe range. Step S22: Simultaneously, study the superposition mechanism of initial inward tilt, outward tilt and roll caused by external disturbances. Analyze the superposition mechanism and decoupling mechanism of roll amplitude under sudden rudder movement and abnormal wave conditions in the frequency domain. Based on the motion prediction model and risk warning mechanism of occasional excessive roll, implement feedforward decoupling control of the rudder roll reduction loop to solve the problem of occasional excessive roll in maneuverability. Step S3: Achieve intelligent decision-making and optimization for the active safety steering; Step S31: Adaptively adjust system parameters through online identification of response feature models, online prediction of disturbance motion, and multi-objective intelligent optimization strategies; Step S32: Identify the response model parameters online using recursive Fourier transform or model reference adaptive method, obtain the transient ship motion mathematical model, and update the controller parameters in real time to achieve the best transient control performance; Step S33: Using NSGA-II and PSO multi-objective intelligent optimization algorithms, solve the mutual constraints between control performance such as heading control, active safety roll reduction and rudder wear, optimize the control strategy of active safety rudder, and improve the overall system performance.

2. An intelligent control system for active safety roll reduction rudder of a ship, characterized in that: The intelligent control method for implementing the active safety roll reduction rudder of a ship as described in claim 1 comprises a ship motion sensing module, a ship model module, an intelligent decision-making module, and a multi-mode roll reduction control module.

3. The intelligent control system for active safety roll reduction rudder of a ship according to claim 2, characterized in that: The ship motion perception module collects ship motion data, sea state data, and ship status data through various sensors. The collected data is processed by capacitive Kalman filtering, multi-source heterogeneous information fusion, and iterative intelligent filtering algorithms, and used as input data for the ship intelligent perception system to provide accurate data support for subsequent decision-making and control.

4. The intelligent control system for active safety roll reduction rudder of a ship according to claim 3, characterized in that: Ship motion data includes roll, bow roll, sway, and pitch data; sea state data, including wind speed, wave height, and wave direction; ship's own status data, including loading status and speed; and sensor types, including accelerometers, gyroscopes, wind speed sensors, and wave sensors.

5. The intelligent control system for active safety roll reduction rudder of a ship according to claim 2, characterized in that: The ship model module is used to construct adaptive response characteristic models of ship motion under all working conditions and all sea states. Through qualitative and quantitative analysis of the perturbation range of ship motion model parameters under different loading, speed and sea states, ship motion response models under different loading, speed and sea state states are established respectively.

6. The intelligent control system for active safety roll reduction rudder of a ship according to claim 5, characterized in that: By utilizing neural network deep learning, fuzzy synthesis, and multi-model switching methods, we integrate ship motion response models under different loading, speed, and sea state conditions to construct an adaptive response feature model, providing accurate model support for ship motion forecasting and risk warning.

7. The intelligent control system for active safety roll reduction rudder of a ship according to claim 2, characterized in that: The intelligent decision-making module integrates common maritime practices, the experience of senior maritime experts, and ship expertise to create fuzzy control rules using fuzzy comprehensive reasoning.

8. The intelligent control system for active safety roll reduction rudder of a ship according to claim 7, characterized in that: The fuzzy control rules and neural network in the intelligent decision-making module are initialized; the initial fuzzy control rules are set based on navigation experience and ship expertise; the neural network is randomly initialized or pre-trained based on existing experience data to lay the foundation for subsequent self-learning and optimization; the fuzzy inference rules are adjusted by the neural network according to the system operation records to form an expert control system based on a dynamic fuzzy neural network with self-learning characteristics.

9. The intelligent control system for active safety roll reduction rudder of a ship according to claim 8, characterized in that: The intelligent decision-making module receives data from the ship's motion perception module, combines the established fuzzy control rules and the results of neural network self-learning, and performs fuzzy comprehensive reasoning. Based on the roll risk identification results, it generates an active safety rudder roll reduction strategy, including selecting appropriate operating modes and control parameters, and transmits the decision results to the multi-mode roll reduction control module.

10. The intelligent control system for active safety roll reduction rudder of a ship according to claim 2, characterized in that: Based on real-time collected data, the ship model module uses recursive Fourier transform or model reference adaptive method to identify the response feature model online and update the model parameters to adapt to changes in ship loading, speed and sea state. The multi-mode anti-roll control module adjusts the controller parameters in real time based on the model update results to ensure the stability and effectiveness of the control effect; The intelligent decision-making module uses neural networks to continuously learn and optimize fuzzy control rules, thereby improving the accuracy and adaptability of decision-making.

Images