Neural computing-based pilot safety risk analysis method and system

Abstract

The invention discloses a pilot safety risk analysis method and system based on neural computing. The method comprises the following steps: identifying safety risk factors; establishing a mapping relation between the safety risk factors and the unsafe behaviors of the pilot; establishing a structure model of a cortex-basal nucleus-thalamus nerve circuit; the method comprises the following steps: respectively establishing AMPA and GABA nerve synapse calculation models based on a double-exponential synapse theory and an alpha-beta synapse theory; establishing a calculation model of a cortex-basal nucleus-hill nerve circuit; calculating thalamus discharge rates under the influence of different safety risk factors, and simulating a regulation mechanism of dopamine and acetylcholine in a safety risk formation process. According to the method, safety analysis is carried out from the perspective of pilot neurodynamics, and key physiological basis and theoretical support are provided for improving a risk analysis model and optimizing system design by analyzing a neural regulation mechanism of acetylcholine and dopamine in a safety risk forming process.

Description

Technical Field

[0001] The present invention belongs to the field of aviation, relates to pilot safety risk analysis, and specifically relates to a pilot safety risk analysis method and system based on neural computing. Background Art

[0002] The widespread application of intelligent interaction technology in cockpits has improved the efficiency of human-machine systems and brought new challenges to safety risk analysis. Existing research on safety risks of human-machine intelligent interaction mainly focuses on the analysis of the human-machine intelligent interaction process in the cockpit, the modeling of pilots' situational awareness and cognitive processes, and the analysis of the oscillation rhythm of pilots' neural signals. These methods can describe the formation process of human-machine intelligent interaction safety risks from a macro perspective. However, the neurodynamic mechanism of pilots in the process of safety risk formation is still unclear. Microscopic neural activities such as brain neuron discharge patterns, changes in neurotransmitter levels, and synaptic plasticity during the operation process have a direct impact on their cognitive ability, decision-making judgment, and behavioral response. Revealing the influence mechanism of pilots' microscopic neural dynamics in the process of human-machine intelligent interaction safety risk formation can analyze the pilots' operational behaviors that drive or inhibit potential risks in different situations, and provide key physiological basis and theoretical support for improving risk analysis models and optimizing system design. Summary of the invention

[0003] Purpose of the invention: In order to overcome the deficiencies in the prior art, a method and system for pilot safety risk analysis based on neural computing is provided to solve the problem that traditional safety risk analysis models only focus on macro factors such as behavior and environment, and lack analysis of the individual neurophysiological state of pilots.

[0004] Technical solution: To achieve the above purpose, the present invention provides a pilot safety risk analysis method based on neural computing, comprising the following steps:

[0005] S1: Identify safety risk factors;

[0006] S2: Establish a mapping relationship between safety risk factors and unsafe behaviors of pilots, and abstract vision, hearing, touch and vestibular senses into electrical stimulation of the cortex;

[0007] S3: Establish a structural model of the cortical-basal ganglia-thalamus neural circuit;

[0008] S4: Based on the double exponential synapse theory and α-β synapse theory, AMPA (α-amino-3-hydroxy-5-methyl-4-isoxazolepropionic acid) and GABA (γ-aminobutyric acid) synapse computational models were established respectively;

[0009] S5: Combine the structural model of the cortex-basal ganglia-thalamus neural circuit, the AMPA neural synapse computational model and the GABA neural synapse computational model to establish a computational model of the cortex-basal ganglia-thalamus neural circuit;

[0010] S6: Through the computational model of the cortex-basal ganglia-thalamus neural circuit, the thalamic discharge rate under the influence of different safety risk factors is calculated to simulate the regulatory mechanism of dopamine and acetylcholine in the process of safety risk formation.

[0011] Furthermore, the safety risk factors in step S1 include air traffic control, airborne systems, and environment;

[0012] Air traffic control safety risk factors include information transmission errors, read-back-hear-back errors, failure to acknowledge or respond to instructions, and non-standard terminology;

[0013] Information transmission error: Transmission error refers to the situation where information transmission is interrupted or lost during the communication between pilots and air traffic controllers. This error may be caused by technical problems such as signal instability, noise interference, frequency mismatch, etc.

[0014] Read-back-hear-back errors: Read-back-hear-back errors occur when pilots misinterpret instructions read back to air traffic controllers, or when controllers fail to detect errors when they hear back pilot confirmations. Such errors may result from pilot distraction, fatigue, or the effects of ambient noise.

[0015] Failure to confirm or respond to instructions: Failure to confirm or respond to instructions means that the pilot fails to confirm the instructions of the air traffic controller as required, or the air traffic controller fails to receive the confirmation within the specified time. This may make it impossible for the controller to determine whether the pilot has received and understood the instructions, and thus be unable to effectively carry out subsequent air traffic management.

[0016] Non-standard terminology: Non-standard terminology refers to the use of terms or expressions that do not conform to aviation communication standards during communication. This may be due to the language habits of pilots or air traffic controllers, cultural differences, or temporary expressions in emergency situations.

[0017] Airborne systems refer to the various subsystems on the aircraft. The pilot sends instructions to the various subsystems of the aircraft through the cockpit human-machine interface to further control the flight parameters and heading to achieve safe flight. Airborne system safety risk factors include design defects, technical system failures and human-machine mutual trust;

[0018] Design defects: Design defects mainly refer to the unreasonable interface design, information presentation method and operation logic design of the cockpit human-machine system, mainly including the unintuitive and inconsistent interface, complex operation of the automation system, etc., which may easily cause confusion or misoperation of pilots during operation.

[0019] Technical system failure: This type of risk covers the failure or erroneous triggering of technical systems such as autonomous driving systems, avionics systems, and communication systems.

[0020] Trust between humans and machines: Trust between humans and machines is mainly reflected in the following two aspects: Automation dependence: pilots over-rely on automation / intelligent systems; Distrust of automation: some pilots are skeptical of automation / intelligent systems, resulting in excessive monitoring or frequent intervention in the system.

[0021] Starting from the pilot's main sensory system, environmental safety risk factors include visual load, auditory load, tactile perception and vestibular perception.

[0022] Visual load: Visual load refers to the situation where pilots need to process a large amount of information in a complex visual environment.

[0023] Auditory load: Auditory load involves the pilot's ability to process auditory information in the presence of noise or multiple audio signals.

[0024] Tactile perception: Tactile perception is the pilot's perception of the response of the control equipment through tactile feedback.

[0025] Vestibular perception: Vestibular perception involves the pilot's sense of balance and spatial awareness.

[0026] Furthermore, the structural model of the cortex-basal ganglia-thalamus neural circuit in step S3 includes direct pathway, indirect pathway and hyperdirect pathway structures;

[0027] The route structure of the direct pathway is cortex → striatum → medial globus pallidus → thalamus → cortex. Dopamine binds to the dopamine D1 receptor on the striatum, activating the Gs-type G protein of the G protein-coupled receptor, thereby enhancing the activity of adenylate cyclase, increasing the synthesis of cyclic adenosine monophosphate, and activating protein kinase A. Protein kinase A increases the activity of GABAergic neurons in the striatum by regulating ion channels and other downstream effectors, inhibits the activity of the medial globus pallidus, reduces its inhibitory effect on the thalamus, and promotes the transmission of motor signals from the thalamus to the cortex;

[0028] The route structure of the indirect pathway is cortex → striatum → lateral globus pallidus → subthalamic nucleus → medial globus pallidus → thalamus → cortex. Dopamine binds to the dopamine D2 receptor on the striatum, activates the Gi-type G protein of the G protein-coupled receptor, inhibits adenylate cyclase, reduces the level of cyclic adenosine monophosphate, and reduces the activity of protein kinase A. This action weakens the inhibitory effect of GABAergic neurons in the striatum, thereby enhancing the activity of the lateral globus pallidus. The lateral globus pallidus sends glutamatergic signals through the subthalamic nucleus (subthalamic nucleus), excites the medial globus pallidus, and further inhibits the thalamus from transmitting motor signals to the cortex through its GABAergic neurons;

[0029] The route structure of the hyperdirect pathway is cortex → subthalamic nucleus → medial globus pallidus → thalamus → cortex. The Glu neurons of the cerebral cortex directly project to the subthalamic nucleus, and form a hyperdirect pathway through the extensive connection between the subthalamic nucleus and the medial globus pallidus. The GABA neurons of the medial globus pallidus directly regulate the thalamic nuclei, and the thalamus is connected to the cerebral cortex through Glu nerve fibers. This connection triggers the dynamic changes of "inhibition-enhancement-inhibition" in the electrical activity of cerebral cortical neurons. It can be seen that the changes in the activity of GABA neurons in the medial globus pallidus, the output nucleus of the basal ganglia, will directly cause changes in the final outgoing information of the basal ganglia, thereby accurately realizing the initiation and cessation of motor plans, while inhibiting the generation of unnecessary actions.

[0030] Furthermore, the construction of the AMPA and GABA synapse computational model in step S4 includes:

[0031] Neurons form a signal transmission pathway through synaptic connections. The action potential of the presynaptic neuron is transmitted to the postsynaptic neuron after a certain delay. Therefore, the synaptic current is calculated as:

[0032] I syn =g max s(ν-E syn )

[0033] Among them, I syn is the postsynaptic current, g max and E syn denote the maximum synaptic conductance and synaptic back potential, respectively, and s denotes the synaptic variable;

[0034] AMPA synaptic channels are simulated by double exponential synapses:

[0035]

[0036] Among them, τ r and τ d The rise time and decay time are respectively, is the normalization factor

[0037] GABA synaptic channels are mimicked by alpha-beta type synapses:

[0038]

[0039] Where s is the synaptic variable, α is the synaptic activation rate constant, β is the deactivation rate constant, and [T] is the concentration of transmitter released by the presynaptic neuron. When the synapse is triggered, [T] is usually a fixed constant.

[0040] The dopamine coefficient is a multiplier of the maximum synaptic conductance of all synaptic models on the direct pathway, and the acetylcholine coefficient is a multiplier of the maximum synaptic conductance of all synaptic models on the indirect pathway. Both are test coefficients.

[0041] Furthermore, the Hodgkin-Huxley equation in step S5 describes the membrane potential change of each neuron, and the AMPA and GABA models describe how neurons interact through excitatory and inhibitory synapses, thereby achieving complex communication between neurons.

[0042] The neuron model of the cortex-basal ganglia-thalamus neural circuit computational model is expressed as follows:

[0043] The Hodgkin-Huxley model is described by the following differential equation:

[0044]

[0045] Where V is the membrane potential, C is the membrane capacitance, and g leak are the maximum conductivities of the sodium ion channel, potassium ion channel, and leak channel, respectively, and E Na 、E K and E leak are the reversal potentials of the corresponding channels, and I(t) is the external input current;

[0046] The dynamic behavior of ion channels is represented by the following system of equations:

[0047]

[0048] Among them, m, h and n represent the gating variables of sodium ion channel and potassium ion channel respectively, α x and β x is a rate constant that depends on the membrane potential and has the following form:

[0049]

[0050]

[0051] Furthermore, the method for calculating the average thalamic discharge rate in step S6 includes the following steps:

[0052] A1: Calculate the instantaneous discharge rate

[0053]

[0054] Among them, t i represents the i-th discharge moment of the neuron, δ is the Dirac function, which is used to capture the discharge event at a specific moment;

[0055] A2: Calculate the average discharge rate

[0056]

[0057] Where t0 is the start time of the time window and T is the duration of the window.

[0058] The present invention provides a pilot safety risk analysis system based on neural computing, comprising:

[0059] Safety risk analysis module, used to analyze the correspondence between the pilot's unsafe behaviors and safety risks during flight;

[0060] A model building module, used to build a neural computing model based on the direct pathway, indirect pathway and hyperdirect pathway of the cortex-basal ganglia-thalamus neural circuit; the neural computing model includes the Hodgkin-Huxley model, AMPA and GABA synaptic models;

[0061] The analysis module is used to calculate the average discharge rate of the thalamus under stimulation of different cortical currents and different acetylcholine and dopamine coefficients, and to analyze the regulatory mechanism of acetylcholine and dopamine during the formation of safety risks.

[0062] Beneficial effects: Compared with the prior art, the present invention conducts safety analysis from the perspective of pilot neurodynamics, which solves the problem that traditional safety risk analysis models only focus on macro factors such as behavior and environment, but lack analysis of the individual neurophysiological state of pilots. By analyzing the neural regulation mechanism of acetylcholine and dopamine in the process of safety risk formation, it provides key physiological basis and theoretical support for improving risk analysis models and optimizing system design. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a schematic diagram of the process of the present invention;

[0064] Figure 2 This is a structural model diagram of the cortex-basal ganglia-thalamus neural circuit;

[0065] Figure 3 This is the experimental site map;

[0066] Figure 4 This is a curve of the average thalamic discharge rate that changes with the experimental groups. DETAILED DESCRIPTION

[0067] The present invention is further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention. After reading the present invention, various equivalent forms of modifications to the present invention by those skilled in the art all fall within the scope defined by the claims attached to this application.

[0068] like Figure 1 As shown, the present invention provides a pilot safety risk analysis method based on neural computing, comprising the following steps:

[0069] S1: Identify safety risk factors;

[0070] Safety risk factors include air traffic control, onboard systems, and the environment;

[0071] Air traffic control safety risk factors include information transmission errors, read-back-hear-back errors, failure to acknowledge or respond to instructions, and non-standard terminology;

[0072] Information transmission error: Transmission error refers to the situation where information transmission is interrupted or lost during the communication between pilots and air traffic controllers. This error may be caused by technical problems such as signal instability, noise interference, frequency mismatch, etc.

[0073] Read-back-hear-back errors: Read-back-hear-back errors occur when pilots misinterpret instructions read back to air traffic controllers, or when controllers fail to detect errors when they hear back pilot confirmations. Such errors may result from pilot distraction, fatigue, or the effects of ambient noise.

[0074] Failure to confirm or respond to instructions: Failure to confirm or respond to instructions means that the pilot fails to confirm the instructions of the air traffic controller as required, or the air traffic controller fails to receive the confirmation within the specified time. This may make it impossible for the controller to determine whether the pilot has received and understood the instructions, and thus be unable to effectively carry out subsequent air traffic management.

[0075] Non-standard terminology: Non-standard terminology refers to the use of terms or expressions that do not conform to aviation communication standards during communication. This may be due to the language habits of pilots or air traffic controllers, cultural differences, or temporary expressions in emergency situations.

[0076] Airborne systems refer to the various subsystems on the aircraft. The pilot sends instructions to the various subsystems of the aircraft through the cockpit human-machine interface to further control the flight parameters and heading to achieve safe flight. Airborne system safety risk factors include design defects, technical system failures and human-machine mutual trust;

[0077] Design defects: Design defects mainly refer to the unreasonable interface design, information presentation method and operation logic design of the cockpit human-machine system, mainly including the unintuitive and inconsistent interface, complex operation of the automation system, etc., which may easily cause confusion or misoperation of pilots during operation.

[0078] Technical system failure: This type of risk covers the failure or erroneous triggering of technical systems such as autonomous driving systems, avionics systems, and communication systems.

[0079] Trust between humans and machines: Trust between humans and machines is mainly reflected in the following two aspects: Automation dependence: pilots over-rely on automation / intelligent systems; Distrust of automation: some pilots are skeptical of automation / intelligent systems, resulting in excessive monitoring or frequent intervention in the system.

[0080] Starting from the pilot's main sensory system, environmental safety risk factors include visual load, auditory load, tactile perception and vestibular perception.

[0081] Visual load: Visual load refers to the situation where pilots need to process a large amount of information in a complex visual environment.

[0082] Auditory load: Auditory load involves the pilot's ability to process auditory information in the presence of noise or multiple audio signals.

[0083] Tactile perception: Tactile perception is the pilot's perception of the response of the control equipment through tactile feedback.

[0084] Vestibular perception: Vestibular perception involves the pilot's sense of balance and spatial awareness.

[0085] S2: Establish a mapping relationship between safety risk factors and unsafe behaviors of pilots, and abstract vision, hearing, touch and vestibular senses into electrical stimulation of the cortex;

[0086] The mapping relationship between safety risk factors and pilot unsafe behaviors is shown in Table 1;

[0087] Table 1 Mapping relationship between safety risk factors and pilot unsafe behaviors

[0088]

[0089] S3: Establish a structural model of the cortical-basal ganglia-thalamus neural circuit;

[0090] like Figure 2 As shown, the structural model of the cortical-basal ganglia-thalamus neural circuit includes direct pathway, indirect pathway and hyperdirect pathway structures;

[0091] The route structure of the direct pathway is cortex → striatum → medial globus pallidus → thalamus → cortex. Dopamine binds to the dopamine D1 receptor on the striatum, activating the Gs-type G protein of the G protein-coupled receptor, thereby enhancing the activity of adenylate cyclase, increasing the synthesis of cyclic adenosine monophosphate, and activating protein kinase A. Protein kinase A increases the activity of GABAergic neurons in the striatum by regulating ion channels and other downstream effectors, inhibits the activity of the medial globus pallidus, reduces its inhibitory effect on the thalamus, and promotes the transmission of motor signals from the thalamus to the cortex;

[0092] The route structure of the indirect pathway is cortex → striatum → lateral globus pallidus → subthalamic nucleus → medial globus pallidus → thalamus → cortex. Dopamine binds to the dopamine D2 receptor on the striatum, activates the Gi-type G protein of the G protein-coupled receptor, inhibits adenylate cyclase, reduces the level of cyclic adenosine monophosphate, and reduces the activity of protein kinase A. This action weakens the inhibitory effect of GABAergic neurons in the striatum, thereby enhancing the activity of the lateral globus pallidus. The lateral globus pallidus sends glutamatergic signals through the subthalamic nucleus (subthalamic nucleus), excites the medial globus pallidus, and further inhibits the thalamus from transmitting motor signals to the cortex through its GABAergic neurons;

[0093] The route structure of the hyperdirect pathway is cortex → subthalamic nucleus → medial globus pallidus → thalamus → cortex. The Glu neurons of the cerebral cortex directly project to the subthalamic nucleus, and form a hyperdirect pathway through the extensive connection between the subthalamic nucleus and the medial globus pallidus. The GABA neurons of the medial globus pallidus directly regulate the thalamic nuclei, and the thalamus is connected to the cerebral cortex through Glu nerve fibers. This connection triggers the dynamic changes of "inhibition-enhancement-inhibition" in the electrical activity of cerebral cortical neurons. It can be seen that the changes in the activity of GABA neurons in the medial globus pallidus, the output nucleus of the basal ganglia, will directly cause changes in the final outgoing information of the basal ganglia, thereby accurately realizing the initiation and cessation of motor plans, while inhibiting the generation of unnecessary actions.

[0094] S4: Based on the double exponential synapse theory and α-β synapse theory, AMPA (α-amino-3-hydroxy-5-methyl-4-isoxazolepropionic acid) and GABA (γ-aminobutyric acid) synapse computational models were established respectively;

[0095] Neurons form a signal transmission pathway through synaptic connections. The action potential of the presynaptic neuron is transmitted to the postsynaptic neuron after a certain delay. Therefore, the synaptic current is calculated as:

[0096] I syn =g max s(ν-E syn )

[0097] Among them, I syn is the postsynaptic current, g max and E syn denote the maximum synaptic conductance and synaptic back potential, respectively, and s denotes the synaptic variable;

[0098] AMPA synaptic channels are simulated by double exponential synapses:

[0099]

[0100] Among them, τ r and τ d The rise time and decay time are respectively, is the normalization factor

[0101] GABA synaptic channels are mimicked by alpha-beta type synapses:

[0102]

[0103] Where s is the synaptic variable, α is the synaptic activation rate constant, β is the deactivation rate constant, and [T] is the concentration of transmitter released by the presynaptic neuron. When the synapse is triggered, [T] is usually a fixed constant.

[0104] The dopamine coefficient is a multiplier of the maximum synaptic conductance of all synaptic models on the direct pathway, and the acetylcholine coefficient is a multiplier of the maximum synaptic conductance of all synaptic models on the indirect pathway. Both are test coefficients.

[0105] S5: The Hodgkin-Huxley equation describes the membrane potential changes of each neuron, and the AMPA and GABA models describe how neurons interact through excitatory and inhibitory synapses to achieve complex communication between neurons. Combining the structural model of the cortex-basal ganglia-thalamus neural circuit, the AMPA neural synapse computational model, and the GABA neural synapse computational model, a computational model of the cortex-basal ganglia-thalamus neural circuit is established, which is expressed as follows:

[0106] The Hodgkin-Huxley model is described by the following differential equation:

[0107]

[0108] Where V is the membrane potential, C is the membrane capacitance, and g leak are the maximum conductivities of the sodium ion channel, potassium ion channel, and leak channel, respectively, and E Na 、E K and E leak are the reversal potentials of the corresponding channels, and I(t) is the external input current;

[0109] The dynamic behavior of ion channels is represented by the following system of equations:

[0110]

[0111] Among them, m, h and n represent the gating variables of sodium ion channel and potassium ion channel respectively, α x and β x is a rate constant that depends on the membrane potential and has the following form:

[0112]

[0113]

[0114] The number of neuron groups and synaptic connection parameter settings of the cortical-basal ganglia-thalamus neural circuit computational model are shown in Tables 2 and 3;

[0115] Table 2 Number of neurons in each population

[0116]

[0117] Table 3 Parameter settings for AMPA and GABA synaptic connections

[0118]

[0119] S6: Through the computational model of the cortex-basal ganglia-thalamus neural circuit, the thalamic discharge rate under the influence of different safety risk factors is calculated to simulate the regulatory mechanism of dopamine and acetylcholine in the process of safety risk formation.

[0120] The method for calculating the average thalamic discharge rate includes the following steps:

[0121] A1: Calculate the instantaneous discharge rate

[0122]

[0123] Among them, t i represents the i-th discharge moment of the neuron, δ is the Dirac function, which is used to capture the discharge event at a specific moment;

[0124] A2: Calculate the average discharge rate

[0125]

[0126] Where t0 is the start time of the time window and T is the duration of the window.

[0127] In order to implement the above method, the present invention also provides a pilot safety risk analysis system based on neural computing, comprising:

[0128] Safety risk analysis module, used to analyze the correspondence between the pilot's unsafe behaviors and safety risks during flight;

[0129] A model building module, used to build a neural computing model based on the direct pathway, indirect pathway and hyperdirect pathway of the cortex-basal ganglia-thalamus neural circuit; the neural computing model includes the Hodgkin-Huxley model, AMPA and GABA synaptic models;

[0130] The analysis module is used to calculate the average discharge rate of the thalamus under stimulation of different cortical currents and different acetylcholine and dopamine coefficients, and to analyze the regulatory mechanism of acetylcholine and dopamine during the formation of safety risks.

[0131] The dopamine coefficient is a multiplier of the maximum synaptic conductance of all synaptic models on the direct pathway, and the acetylcholine coefficient is a multiplier of the maximum synaptic conductance of all synaptic models on the indirect pathway. Both are test coefficients.

[0132] In order to verify the effectiveness and real effect of the solution of the present invention, experiments are performed in this embodiment, as follows:

[0133] In this embodiment, the intelligent interaction scene of the civil aircraft cockpit is selected as the test object, and two types of safety risk factors, technical system failure and human-machine mutual trust, are designed and presented through the automatic flight control system. The experiment adopts the experimental paradigm of double-factor repeated measurement within-group design, and the treatment factors are system reliability and operation proficiency. The experimental site is as follows Figure 3 As shown, a total of 21 males participated in the experiment, and the ECG and EMG parameter sensors worn by the subjects recorded their bioelectric characteristic data throughout the whole process. The effectiveness of the present invention was verified by analyzing the correlation between the average thalamic discharge rate output by the cortex-basal ganglia-thalamus neural circuit calculation model and the physiological data observed in the experiment.

[0134] Changing the cortical stimulation current size simulates the improvement of the subject's proficiency, reducing the dopamine coefficient and increasing the acetylcholine coefficient to simulate the impact of technical system failures and human-machine mutual trust on pilots under different system reliability. The parameters used to test the model are shown in Table 4. The average thalamic discharge rate of different experimental groups is as follows Figure 4 shown.

[0135] Table 4 Parameters of the test model

[0136]

[0137] The results of the F test of the within-group effect of the model simulation results are shown in Table 5. From the results of the variance analysis, it can be seen that there are significant differences in the average discharge rate of the thalamus in the main effects of system reliability and operation proficiency (p = 0.0009, p = 0.037), indicating that the established model can simulate the impact of different levels of safety risk factors on pilots.

[0138] Table 5 ANOVA results of the model

[0139] Experimental factors F-number P-value <![CDATA[Effect size η 2 > Power 1-β System reliability 62.16 0.000972 0.857330 0.99 Operation proficiency 8.344771 0.037378 0.115087 0.11

[0140] The results of the correlation calculation between the average thalamic discharge rate and the experimental data are shown in Table 6. From the correlation analysis results, it can be seen that the average thalamic discharge rate is significantly correlated with heart rate, muscle activation (biceps brachii) and system control time ratio; the correlation between the average thalamic discharge rate and the system control time ratio is high (Rho = -0.9667), indicating that as the system control time ratio decreases, the subjects need to continue to handle more complex operating procedures and decision-making tasks, causing an increase in the excitement of the thalamus.

[0141] Table 6 Correlation calculation results between thalamic average discharge rate and experimental data

[0142]

Claims

1. A pilot safety risk analysis method based on neural computing, characterized in that: The steps include: S1: Identify safety risk factors; S2: Establish a mapping relationship between safety risk factors and unsafe behaviors of pilots, and abstract vision, hearing, touch and vestibular senses into electrical stimulation of the cortex; S3: Establish a structural model of the cortical-basal ganglia-thalamus neural circuit; S4: Based on the double exponential synapse theory and α-β synapse theory, AMPA and GABA synapse computational models were established respectively; S5: Combine the structural model of the cortex-basal ganglia-thalamus neural circuit, the AMPA neural synapse computational model and the GABA neural synapse computational model to establish a computational model of the cortex-basal ganglia-thalamus neural circuit; S6: Through the computational model of the cortex-basal ganglia-thalamus neural circuit, the thalamic discharge rate under the influence of different safety risk factors is calculated to simulate the regulatory mechanism of dopamine and acetylcholine in the process of safety risk formation.

2. The pilot safety risk analysis method based on neural computing according to claim 1, characterized in that: The safety risk factors in step S1 include air traffic control, airborne systems, and environment; Air traffic control safety risk factors include information transmission errors, read-back-hear-back errors, failure to acknowledge or respond to instructions, and non-standard terminology; Airborne system safety risk factors include design flaws, technical system failures, and human-machine trust; Environmental safety risk factors include visual load, auditory load, tactile perception, and vestibular perception.

3. The pilot safety risk analysis method based on neural computing according to claim 1 is characterized in that: The structural model of the cortex-basal ganglia-thalamus neural circuit in step S3 includes direct pathway, indirect pathway and hyperdirect pathway structures; The route structure of the direct pathway is cortex→striatum→medial globus pallidus→thalamus→cortex, dopamine binds to the dopamine D1 receptor on the striatum, activates the Gs-type G protein of the G protein-coupled receptor, thereby enhancing the activity of adenylate cyclase, increasing the synthesis of cyclic adenosine monophosphate, and activating protein kinase A; Protein kinase A increases the activity of GABAergic neurons in the striatum by regulating ion channels and other downstream effectors, inhibits the activity of the globus pallidus medialis, reduces its inhibitory effect on the thalamus, and promotes the transmission of motor signals from the thalamus to the cortex; The route structure of the indirect pathway is cortex→striatum→lateral globus pallidus→subthalamic nucleus→medial globus pallidus→thalamus→cortex. Dopamine binds to the dopamine D2 receptor on the striatum, activates the Gi-type G protein of the G protein-coupled receptor, inhibits adenylate cyclase, reduces the level of cyclic adenosine monophosphate, and reduces the activity of protein kinase A. The lateral globus pallidus sends glutamatergic signals through the subthalamic nucleus to excite the medial globus pallidus, and further inhibits the thalamus from transmitting motor signals to the cortex through its GABAergic neurons. The route structure of the hyperdirect pathway is cortex→subthalamic nucleus→internal globus pallidus→thalamus→cortex. The Glu neurons of the cerebral cortex directly project to the subthalamic nucleus, and form a hyperdirect pathway through the extensive connection between the subthalamic nucleus and the internal globus pallidus. The GABA neurons of the internal globus pallidus directly regulate the thalamic nuclei, and the thalamus is connected to the cerebral cortex through Glu nerve fibers.

4. The method for analyzing pilot safety risks based on neural computing according to claim 1, characterized in that: The construction of the AMPA and GABA synapse computational model in step S4 includes: Neurons form a signal transmission pathway through synaptic connections. The action potential of the presynaptic neuron is transmitted to the postsynaptic neuron after a time delay. Therefore, the synaptic current is calculated as: I syn =g max s(ν-E syn ) Among them, I syn is the postsynaptic current, g max and E syn denote the maximum synaptic conductance and synaptic back potential, respectively, and s denotes the synaptic variable; AMPA synaptic channels are simulated by double exponential synapses: Among them, τ r and τ d The rise time and decay time are respectively, is the normalization factor GABA synaptic channels are mimicked by alpha-beta type synapses: Where s is the synaptic variable, α is the synaptic activation rate constant, β is the deactivation rate constant, and [T] is the concentration of transmitter released by the presynaptic neuron. When the synapse is triggered, [T] is usually a fixed constant.

5. The pilot safety risk analysis method based on neural computing according to claim 1, characterized in that: The neuron model of the cortex-basal ganglia-thalamus neural circuit computational model in step S5 is expressed as follows: The Hodgkin-Huxley model is described by the following differential equation: Where V is the membrane potential, C is the membrane capacitance, and g leak are the maximum conductivities of the sodium ion channel, potassium ion channel, and leak channel, respectively, and E Na 、E K and E leak are the reversal potentials of the corresponding channels, and I(t) is the external input current; The dynamic behavior of ion channels is represented by the following system of equations: Among them, m, h and n represent the gating variables of sodium ion channel and potassium ion channel respectively, α x and β x is a rate constant that depends on the membrane potential and has the following form:

6. The method for analyzing pilot safety risks based on neural computing according to claim 1, characterized in that: The method for calculating the average discharge rate of the thalamus in step S6 comprises the following steps: A1: Calculate the instantaneous discharge rate Among them, t i represents the i-th discharge moment of the neuron, and δ is the Dirac function, which is used to capture the discharge event at a specific moment; A2: Calculate the average discharge rate Where t0 is the start time of the time window and T is the duration of the window.

7. A pilot safety risk analysis system based on neural computing, characterized in that: include: Safety risk analysis module, used to analyze the correspondence between the pilot's unsafe behaviors and safety risks during flight; A model building module, used to build a neural computational model based on the direct pathway, indirect pathway and hyperdirect pathway of the cortex-basal ganglia-thalamus neural circuit; The analysis module is used to calculate the average discharge rate of the thalamus under stimulation of different cortical currents and different acetylcholine and dopamine coefficients, and to analyze the regulatory mechanism of acetylcholine and dopamine during the formation of safety risks.

8. The pilot safety risk analysis system based on neural computing according to claim 7, characterized in that: The neural computational models include the Hodgkin-Huxley model, AMPA and GABA synaptic models.

Images