Autonomous control method and system for chemical pipe gallery inspection robot based on artificial intelligence

Abstract

The invention provides a chemical pipe gallery inspection robot autonomous control method and system based on artificial intelligence, and relates to the technical field of program control machines. Environmental parameters are monitored in real time, and the power output proportion, the electrode voltage and the running speed of electronic elements in an inspection robot are dynamically optimized; the accuracy and initiative of heat dissipation management of the robot are remarkably improved, and the thermal runaway risk of local components is effectively avoided. According to the method, the dynamic balance between the heat dissipation efficiency and the inspection efficiency is realized, the component loss caused by temperature rise is reduced, the overall service life of equipment is prolonged, and the safety, stability and intelligent level of inspection task execution are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of program-controlled machines, and in particular to an autonomous control method and system for a pipeline corridor inspection robot. Background Art

[0002] Chemical pipeline corridor inspection robots are becoming a hot topic of industry attention and research. Robotic inspection solutions that have emerged in recent years often utilize integrated perception systems based on visual sensors, infrared thermal imaging, and multiple gas sensors to monitor and provide early warning of pipeline corridor conditions. These robots can partially reduce manual inspection costs, improve inspection efficiency, and mitigate personnel safety risks, becoming a crucial technical tool for chemical park inspections.

[0003] In the prior art, the publication number is CN116890342A, and the name is a control method and system for a chemical pipeline corridor inspection robot. By obtaining the operating data of the pipeline corridor inspection robot to be detected, the data is analyzed for abnormalities using a method based on the robot operation abnormality analysis network to generate corresponding abnormal distribution vectors. The abnormality analysis network uses combined knowledge learning, uses a template robot operation data sequence for training, and uses the target abnormality decision service combined with the abnormal distribution vector of the pipeline corridor inspection robot operation data to determine the abnormal decision result of the robot operation data. It can realize abnormal analysis and decision-making of the pipeline corridor inspection robot operation data, thereby accurately judging the abnormal operation of the robot and providing solutions for repair. This can improve the reliability and efficiency of the pipeline corridor inspection robot, reduce the impact of operational failures on inspection tasks, and improve the overall effect of pipeline corridor inspection.

[0004] However, the inspection robots currently on the market generally have problems such as single heat dissipation control and insufficient adaptability:

[0005] 1. During the inspection process, the continuous operation of the robot's internal components, especially high-power electronic components, can easily lead to overheating, seriously affecting the long-term stability and safety of the inspection robot. In addition, existing technologies for internal thermal management of robots mainly use fixed heat dissipation or passive air cooling, lacking dynamic heat dissipation management technologies that actively respond to changes in the local thermal environment. Especially in local areas within the pipeline corridor where the thermal environment fluctuates drastically, traditional robot control solutions are unable to effectively adjust the heat dissipation strategy in real time, which can easily cause local thermal runaway of components, thereby affecting the overall performance stability of the robot.

[0006] 2. At the same time, the reduced inspection speed and unstable power output caused by insufficient heat dissipation further reduce the efficiency of the robot's inspection tasks; therefore, it is urgent to develop an intelligent inspection robot autonomous control method that can actively respond to environmental thermal changes and optimize the heat dissipation of internal electronic components and robot power distribution in real time to ensure the long-term stable, safe and efficient operation of the chemical pipeline corridor robot.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0008] In view of the deficiencies in the prior art, the present invention provides an autonomous control method for a chemical pipeline corridor inspection robot based on artificial intelligence to solve the problems raised in the above background technology.

[0009] The purpose of the present invention is to achieve the following: an autonomous control method for a chemical pipeline corridor inspection robot based on artificial intelligence, the specific steps of which include:

[0010] Step S1: When the inspection robot moves along the preset inspection route, it measures the air ion concentration, electrostatic field strength, and combustible gas concentration at its current location in real time. At the same time, it collects local thermal radiation distribution data at the preset collection point adjacent to and closest to the route.

[0011] Analyze the local thermal radiation distribution data at the preset collection points to obtain the corresponding local thermal radiation coefficient;

[0012] Step S2: Establish an active ionization control system for the inspection robot surface, including an ion generator and an electrode drive circuit. The electrode drive circuit has a built-in low-power current-limiting safety barrier for stabilizing the output and regulating the high voltage. The generated electrode voltage is applied to the electrode tip of the ion generator to drive the ionization of the surrounding air and form an ion wind.

[0013] Step S3: The real-time collected air ion concentration, electrostatic field strength, and electrode voltage output by the electrode drive circuit are integrated and analyzed to calculate the active ion release enhancement coefficient; based on the active ion release enhancement coefficient, the heat dissipation efficiency coefficient of each test point on the surface of the inspection robot is calculated;

[0014] Step S4: Using the real-time calculated heat dissipation efficiency coefficient and local thermal radiation coefficient of each test point as input, a multivariate correlation method is used to construct an autonomous control adjustment model. The autonomous control adjustment model is used to:

[0015] Dynamically optimize the power output ratio of the internal electronic components corresponding to the test point j on the surface of the inspection robot to reduce the surface temperature of the electronic components;

[0016] Automatically adjust the electrode voltage output by the electrode drive circuit to cooperate with the ion wind to enhance heat dissipation;

[0017] Adjust the inspection robot's travel speed to balance heat dissipation requirements and inspection efficiency.

[0018] Furthermore, the vehicle travels along the preset inspection route and moves to the preset collection point closest to the current route node each time. When the infrared thermal radiation sensor is started to scan the local radiation intensity, the original thermal radiation data is obtained. ;

[0019] The original thermal radiation data obtained Take the maximum value of the region With minimum value , and normalized to the dimensionless local thermal radiation coefficient ,and ; i is the representation of “normalization”, the same below;

[0020] The original values measured by multiple ion concentration sensors are averaged and the averaged results are normalized to dimensionless air ion concentration. ,and ;

[0021] Normalize the electrostatic field strength sensor measurement value to dimensionless electrostatic field strength ,and ;

[0022] Real-time monitoring of the raw values measured by multiple combustible gas concentration sensors , the original values measured by multiple combustible gas concentration sensors Perform averaging and normalize the averaging results to dimensionless combustible gas concentration ,and ; Set the combustible gas concentration Safety threshold .

[0023] Furthermore, multiple conical stainless steel ion generator electrodes are arranged around the inspection robot housing; each ion generator electrode is led to the high-voltage driver circuit board in the cabin through the same shielded wire harness;

[0024] The high-voltage driver circuit board consists of a DC-DC boost module and a microcontroller unit (MCU). The MCU performs closed-loop regulation on the boost module output through PWM signals.

[0025] Feedback voltage of the boost module read by the MCU Normalized processing is performed to obtain the electrode voltage ,and ;

[0026] The low-power current-limiting safety barrier includes an RC current-limiting network consisting of a high-voltage current-limiting resistor and a ceramic capacitor; an avalanche diode is added to clamp overshoot, ultimately limiting the overall discharge current and discharge energy to a preset safety range;

[0027] Receive normalized combustible gas concentration ; If a safety lock condition is detected during any measurement cycle When the output PWM duty cycle is set to 0%, , and then the normalized electrode voltage ; To prohibit ionizing discharge;

[0028] When high voltage is applied to the tip of the ion generator electrode, a local electric field strength is generated, causing the surrounding air molecules to ionize, forming positive and negative ions; the positive and negative ions are accelerated under the action of the high voltage field and ejected radially along the tip, forming a perceptible "ion wind" airflow.

[0029] Furthermore, the air ion concentration parameters with unified dimensions are obtained in real time , electrostatic field strength and electrode voltage , active ion release enhancement coefficient is calculated by linear weighted fusion ,and ;

[0030] Based on preset collection points The local thermal radiation coefficient calculated at The heat dissipation efficiency coefficient of each test point j on the surface of the inspection robot is calculated by the classification function. Perform graded calculations and set ;and , M1 is the total number of points to be tested;

[0031] when The closer it is to 0, the less heat dissipation capacity of the inspection robot surface at the test point j is, and the greater the active ion release intensity that needs to be improved;

[0032] when The closer it is to 1, the closer the heat dissipation efficiency is to the maximum state, the stronger the active heat dissipation capability is, and the more necessary it is to ensure the stability and long-term working performance of the internal electronic components corresponding to the test point j on the surface of the inspection robot.

[0033] Furthermore, the autonomous control adjustment model includes:

[0034] According to the heat dissipation efficiency coefficient The real-time change of the measured point j is introduced, and the maximum rated power output ratio of the electronic component is set. , and linearly multiply and The correlation result is used to represent the power output ratio of the electronic components corresponding to the test point j on the inspection robot. ;

[0035] when The closer it is to 0, the more the electronic component corresponding to the test point j needs to actively reduce power to prevent thermal runaway;

[0036] when The closer it is to 1, the closer the power output ratio of the electronic component corresponding to the measured point j is to .

[0037] Furthermore, according to the real-time local thermal radiation coefficient and heat dissipation efficiency coefficient , determine the heat dissipation efficiency coefficient of all test points j Minimum value of , dynamically adjust the electrode voltage , and obtain the normalized electrode voltage after real-time adjustment ;

[0038] Only when the local thermal radiation coefficient Increased heat dissipation efficiency coefficient Lower, that is The closer it is to 0, Increase, the electrode voltage increases to generate stronger ion wind to enhance heat dissipation;

[0039] When the local thermal radiation coefficient Reduce or heat dissipation efficiency coefficient Increase, that is The closer it is to 1, Reduce and save energy consumption;

[0040] When the local thermal radiation coefficient and heat dissipation efficiency coefficient When both remain unchanged, .

[0041] Furthermore, according to the heat dissipation efficiency coefficient of all test points Minimum value of and local thermal radiation coefficient , automatically adjust the real-time driving speed ratio of the inspection robot ;

[0042] When the minimum heat dissipation efficiency coefficient The closer it is to 0 and the local thermal radiation coefficient of the preset collection point in front When the value is closer to 1, the inspection robot automatically reduces the driving speed ratio. , ensuring safe heat dissipation;

[0043] When the minimum heat dissipation efficiency coefficient The closer it is to 1, the local thermal radiation coefficient of the preset collection point in front As the value approaches 0, the inspection robot automatically increases the driving speed ratio. , in order to improve inspection efficiency.

[0044] An artificial intelligence-based autonomous control system for a chemical pipeline corridor inspection robot, the system being used to execute an artificial intelligence-based autonomous control method for a chemical pipeline corridor inspection robot, comprising:

[0045] Data acquisition module: used to measure the air ion concentration, electrostatic field strength, and combustible gas concentration at the current location of the inspection robot in real time as it moves along the preset inspection route. At the same time, it collects local thermal radiation distribution data at the preset collection point adjacent to and closest to the route.

[0046] Analyze the local thermal radiation distribution data at the preset collection points to obtain the corresponding local thermal radiation coefficient;

[0047] Ion wind generation module: This module is used to establish an active ionization control system for the inspection robot's surface. It includes an ion generator and an electrode drive circuit. The electrode drive circuit has a built-in low-power current-limiting safety barrier for stabilizing the output and regulating the high voltage. The generated electrode voltage is applied to the electrode tip of the ion generator to drive the ionization of the surrounding air and form an ion wind.

[0048] Coefficient calculation module: used to integrate and analyze the real-time collected air ion concentration, electrostatic field strength and electrode voltage output by the electrode drive circuit to calculate the active ion release enhancement coefficient; based on the active ion release enhancement coefficient, the heat dissipation efficiency coefficient of each test point on the surface of the inspection robot is calculated;

[0049] Model building module: This module uses the real-time calculation of the heat dissipation efficiency coefficient and local thermal radiation coefficient of each test point as input, and uses a multivariable correlation method to build an autonomous control adjustment model. The autonomous control adjustment model is used to:

[0050] Dynamically optimize the power output ratio of the internal electronic components corresponding to the test point j on the surface of the inspection robot to reduce the surface temperature of the electronic components;

[0051] Automatically adjust the electrode voltage output by the electrode drive circuit to cooperate with the ion wind to enhance heat dissipation;

[0052] Adjust the inspection robot's travel speed to balance heat dissipation requirements and inspection efficiency.

[0053] Compared with the existing technology, the beneficial effects of the present invention are: the present invention significantly improves the accuracy and initiative of the robot's heat dissipation management by real-time monitoring of environmental parameters and dynamically optimizing the power output ratio, electrode voltage and driving speed of the electronic components inside the inspection robot, and effectively avoids the risk of thermal runaway of local components; this method achieves a dynamic balance between heat dissipation efficiency and inspection efficiency, reduces component loss caused by temperature increase, extends the overall life of the equipment, and improves the safety, stability and intelligence level of inspection task execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0055] Figure 1 Schematic diagram of the overall method of the present invention.

[0056] Figure 2 This is a block diagram of the system modules of the present invention.

[0057] Figure 3 This is a schematic diagram of the inspection robot and its ion wind generation according to the present invention. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0059] Example 1:

[0060] See also Figure 1 and Figure 3 , the present invention provides a technical solution:

[0061] In the extreme environment of high temperature and flammable gases, the chemical pipeline inspection robot achieves temperature control and power optimization by measuring and actively adjusting the secondary ion wind field within the pipeline corridor. At the same time, it automatically shuts off active ionization when a flammable gas leak is detected to ensure the safety of the system in flammable and explosive environments. The "secondary ion wind field" is a weak air flow field generated by the interaction between existing electric charges and gas molecules in the chemical pipeline corridor. It comes from:

[0062] Static electricity accumulation and natural discharge in pipeline corridors: Static electricity will accumulate on the insulating surface of the pipeline due to fluid flow, friction or high-voltage lines near power transmission equipment. When the local electric field strength exceeds the threshold, a small amount of "static electricity jet" (also known as "ion wind") will appear.

[0063] Corona discharge from high-voltage equipment: The presence of high-voltage cables or induction heating devices in the tunnel can also generate corona discharge, forming a "secondary ion wind field" around the tip electrode. These ion wind fields can be measured in real time using sophisticated electrostatic ion sensors.

[0064] The autonomous control method of the chemical pipeline corridor inspection robot based on artificial intelligence includes the following specific steps:

[0065] Step S1: When the inspection robot moves along the preset inspection route, it measures the air ion concentration, electrostatic field strength, and combustible gas concentration at its current location in real time. At the same time, it collects local thermal radiation distribution data at the preset collection point adjacent to and closest to the route.

[0066] Analyze the local thermal radiation distribution data at the preset collection points to obtain the corresponding local thermal radiation coefficient;

[0067] Further explanation: The vehicle will travel along the preset inspection route and will reach the preset collection point closest to the current route node each time. When the infrared thermal radiation sensor is started to scan the local radiation intensity, the original thermal radiation data is obtained. ;Unit W / m²; Where, The index of the nearest preset collection point;

[0068] The original thermal radiation data obtained Take the maximum value of the region With minimum value , and normalized to the dimensionless local thermal radiation coefficient ,and . The specific characteristics are ;

[0069] It should be noted that the preset inspection path is the sequence of the centerline coordinates of the pipe gallery. Each point represents a path node. Indicates the Nth path node; the preset collection point is Select between adjacent path nodes; The i in is a representation of “normalization” and will not be described in detail later;

[0070] This embodiment presets the collection point The distance from the inspection robot's current position is ≤ 0.5m;

[0071] Multiple ion concentration sensors are evenly spaced around the inspection robot housing, forming a circular array at 45° intervals; ion concentration sensor model: AIC-100, range 0ions / cm³–10 6 ions / cm³; in this embodiment, the number of ion concentration sensors is set to 8;

[0072] Read the original output value of each ion concentration sensor every 100ms , the original values measured by multiple ion concentration sensors are averaged and the averaged results are normalized to dimensionless air ion concentration ,and ; This embodiment The specific characteristics are ;in: ; ;

[0073] An electrostatic field strength sensor is installed at the center of the top of the robot. The electrostatic field strength sensor in this embodiment is model: EFS-50, with a range of 0kV / m–50kV / m.

[0074] Read the raw intensity value every 100ms , unit kV / m, normalizes the electrostatic field strength sensor measurement value to dimensionless electrostatic field strength ,and ; The specific characteristics are ;in, ; ;

[0075] Multiple combustible gas concentration sensors are arranged in a ring at the bottom of the inspection robot to monitor the original value in real time. , the unit is %LEL;

[0076] It should be noted that: there are 4 combustible gas concentration sensors; model: GCM-200, range 0%LEL–100%LEL;

[0077] The raw values measured by multiple combustible gas concentration sensors Perform averaging and normalize the averaging results to dimensionless combustible gas concentration ,and ; The specific characteristics are ;in, ; ;

[0078] Set safety threshold ; corresponds to 20%LEL; and ; If a safety lock condition is detected during any measurement cycle When the electrode voltage in the active ionization control system is immediately , enter safety lock and prohibit ionization discharge.

[0079] Step S2: Establish an active ionization control system for the inspection robot surface, including an ion generator and an electrode drive circuit. The electrode drive circuit has a built-in low-power current-limiting safety barrier for stabilizing the output and regulating the high voltage. The generated electrode voltage is applied to the electrode tip of the ion generator to drive the ionization of the surrounding air and form an ion wind.

[0080] In chemical pipeline corridors, due to the confined space and dense pipelines, static electricity easily accumulates and air flow is restricted. Active ionization on the inspection robot's surface generates ionized wind, which neutralizes static electricity, aids air flow, and reduces the risk of partial discharge. This embodiment uses a ring-shaped conical electrode ion generator and an integrated high-voltage drive circuit due to their small size, fast response, and ease of packaging within the inspection robot's housing.

[0081] A plurality of conical stainless steel ion generator electrodes are arranged around the inspection robot housing; the tip radius of the conical stainless steel ion generator electrode in this embodiment is 50 μm;

[0082] Lead each ion generator electrode to the high-voltage driver circuit board in the cabin through the same shielded wire harness;

[0083] The high-voltage driver circuit board consists of a DC-DC boost module and a microcontroller unit (MCU). The MCU performs closed-loop regulation on the boost module output through PWM signals.

[0084] Feedback voltage of the boost module read by the MCU Normalized processing is performed to obtain the electrode voltage ,and ; This embodiment ;in, ; ;

[0085] The low-power current-limiting safety barrier includes an RC current-limiting network consisting of a high-voltage current-limiting resistor and a ceramic capacitor; an avalanche diode is added to clamp overshoot, ultimately limiting the overall discharge current and discharge energy to a preset safety range;

[0086] In this embodiment, the preset safety range for discharge current is ≤1mA, and the preset safety range for single discharge energy is ≤0.1mJ; the inspection robot housing adopts an IP6X explosion-proof structure; and in this embodiment, "the electrode drive circuit has a built-in low-power current-limiting safety barrier, which can adopt the R.-STAHL-9004 series INTRINSPAK single-channel Zener barrier or the Pepperl+Fuchs-HiC2031 intelligent current driver, and an RC current-limiting network consisting of its own high-voltage current-limiting resistor and ceramic capacitor, as well as an avalanche diode clamp, is connected in series at its output to ensure that the final discharge current is ≤1mA and the discharge energy is ≤0.1mJ."

[0087] Specifically, a 100MΩ high-voltage current-limiting resistor and a 1nF ceramic capacitor are connected in series at the output end of the drive circuit to form an RC current-limiting network.

[0088] Receive normalized combustible gas concentration If detected , the output PWM duty cycle is set to 0%, so that , and then the normalized electrode voltage ; It corresponds linearly to the PWM duty cycle, and the PWM duty cycle corresponds from 0% to 100% From 0kV to 10kV;

[0089] It's important to note that PWM stands for "Pulse-Width-Modulation." It's a control method that adjusts the average output voltage or power by varying the duration of a digital signal's "high level" within each cycle (i.e., the duty cycle). When a safety lockout condition is detected, the PWM signal's duty cycle is forcibly set to 0%, completely shutting down the output and quickly severing the device's drive power supply to ensure safety.

[0090] After normalization and Linear positive correlation; under the state of safety lock condition, Zeroed in a single direction;

[0091] This solution uses a DAC / PWM controlled DC-DC boost module and a single-stage RC current limiting network. Compared with multi-stage current limiting or software current limiting solutions, it has the advantages of fast hardware response, low energy loss, small size, and easy overall packaging in the inspection robot housing. The current limiting safety barrier design with integrated avalanche diode can quickly clamp at high voltage peak times, meeting the explosion-proof and low energy consumption requirements of chemical pipeline corridor inspections.

[0092] The specific implementation of "applying the generated electrode voltage to the electrode tip of the ion generator to drive the ionization of the surrounding air and form ion wind" is explained as follows:

[0093] Figure 3 Description of the main modules:

[0094] DC-DC boost module: boosts the robot's onboard 24V DC voltage to an adjustable high-voltage output of 0kV-10kV.

[0095] 100MΩ current-limiting resistor: connected in series in the high-voltage output circuit to limit the output current to ≤1mA.

[0096] 1nF ceramic capacitor: connected in parallel with the current-limiting resistor to form an RC filter network to filter out spike noise and stabilize the voltage.

[0097] Avalanche diode: connected in parallel at the output end, it quickly clamps when the output voltage exceeds the rated value to protect the circuit safety.

[0098] IP6X explosion-proof sealed housing: All high-voltage components are encapsulated here to prevent external leakage and meet the explosion-proof requirements of chemical environments.

[0099] Output to the ion generator electrode tip: The high voltage after current limiting and clamping is sent to the ion generator electrode tip through the shielded wire.

[0100] The output end of the high-voltage module is processed by a low-power current-limiting safety barrier and then transmitted to the tip of the cone-shaped electrode located on the outer shell of the inspection robot through a dedicated high-voltage shielded cable (withstand voltage ≥ 12kV, outer braided copper mesh);

[0101] The shielded cable is grounded externally, with high voltage retained only at the tip to prevent leakage and interference with other electronic components of the entire machine.

[0102] The cone tip of the ion generator electrode is fixed to the metal flange through an insulating ceramic sleeve, and the flange and the inspection robot housing are grounded;

[0103] When high voltage is applied to the tip of the ion generator electrode, a local electric field strength is generated, causing the surrounding air molecules to ionize, forming positive and negative ions; the positive and negative ions are accelerated under the action of the high voltage field and ejected radially along the tip, forming a perceptible "ion wind" airflow.

[0104] Step S3: The real-time collected air ion concentration, electrostatic field strength, and electrode voltage output by the electrode drive circuit are integrated and analyzed to calculate the active ion release enhancement coefficient; based on the active ion release enhancement coefficient, the heat dissipation efficiency coefficient of each test point on the surface of the inspection robot is calculated;

[0105] Further explanation: This implementation achieves dynamic quantification and characterization of ion wind release intensity through real-time analysis of air ion concentration, electrostatic field strength, and electrode voltage, providing an accurate basis for further thermal management optimization;

[0106] 1.1) Obtain the air ion concentration parameters after unified dimension from step S1 in real time every 50ms , electrostatic field strength and electrode voltage , active ion release enhancement coefficient is calculated by linear weighted fusion ,and The calculation formula is ;in, is the active ion release enhancement coefficient, which is in the interval (0,1); and ; ; and ; , and is the weight coefficient of the corresponding parameter;

[0107] When the air ion concentration parameter , electrostatic field strength and electrode voltage When any parameter increases, The linear increase indicates that the active ionization release ability is enhanced;

[0108] When the three parameters approach the maximum value 1 at the same time, When it approaches 1, it indicates that the active ion release is at the highest level, the current ion wind is maximized, and the optimal auxiliary heat dissipation state is achieved;

[0109] When the three parameters approach 0 at the same time, When it approaches 0, it indicates that the active ion release has basically stopped, the ion wind effect is almost zero, the auxiliary heat dissipation effect disappears, and the surface heat dissipation efficiency decreases;

[0110] 1.2) Based on preset collection points The local thermal radiation coefficient calculated at The heat dissipation efficiency coefficient of each test point j on the surface of the inspection robot is calculated by the classification function. Perform graded calculations and set ;and , M1 is the total number of points to be tested; the specific steps are as follows:

[0111] Set multiple test points on the surface of the inspection robot. The test points are represented by j, and j∈{1,2,…,M1}, where M1 is the total number of test points.

[0112] Each test point j clearly corresponds to the heat dissipation part of a specific electronic component inside the inspection robot, including but not limited to the heat dissipation parts of the following components:

[0113] Test point j=1: corresponds to the heat sink surface of the main control unit (MCU or CPU) inside the robot;

[0114] Test point j=2: corresponds to the heat sink surface of the power module (DC-DC converter or battery management module) inside the robot;

[0115] Test point j=3: corresponds to the heat sink surface of the power amplifier element (MOSFET or IGBT power tube) of the electrode high-voltage drive circuit inside the robot;

[0116] Test point j=4: corresponds to the heat dissipation part of the RF power amplifier chip of the robot's internal communication module (such as Wi-Fi or wireless communication module);

[0117] Test point j=5: corresponds to the surface of the power device heat sink of the robot's internal motion control module (such as the motor driver);

[0118] Test point j=6: corresponds to the heat dissipation part of the main processing chip (such as ADC or signal conditioning chip) of the sensor data processing circuit inside the robot;

[0119] Other test points : They correspond respectively to the heat dissipation parts of other auxiliary modules or special electronic devices inside the robot, such as the solenoid valve control unit, lidar control circuit, visual recognition module or infrared thermal imaging module and other key electronic components.

[0120] By clearly defining the correspondence between each test point and the heat dissipation part of a specific electronic component inside the inspection robot, accurate temperature monitoring and effective active heat dissipation control can be achieved, ensuring the safe operation of the inspection robot in a long-term high-reliability state.

[0121] The preset inspection path is the centerline coordinate sequence of the pipe gallery , select a preset collection point sequence between adjacent path nodes ,The inspection robot measures the distance between its current position and each path node in real time;

[0122] Every time the robot moves to the path node closest to the current position, it automatically identifies the nearest preset collection point ;

[0123] Real-time collection and calculation of preset collection points The local thermal radiation coefficient at ,and , and based on the local thermal radiation coefficient The numerical value is divided into low-level interval, medium-level interval and high-level interval;

[0124] Low-level range: , indicating that the thermal change ahead is small;

[0125] Intermediate range: , indicating moderate thermal changes ahead;

[0126] Advanced range: , indicating that the thermal changes ahead are large;

[0127] Based on the calculated active ion release enhancement coefficient , the following piecewise linear function is used to calculate the heat dissipation efficiency coefficient ; ;

[0128] in, is the heat dissipation efficiency coefficient of the jth test point, with a value range of (0,1); k1, k2 and k3 are corresponding sensitivity constants, and 0<k1<k2<k3<1;

[0129] When the active ion release enhancement factor When it approaches 1, it reflects the local thermal radiation coefficient Improvements require higher active heat dissipation capabilities;

[0130] When the active ion release enhancement factor As the value approaches 0, the heat dissipation efficiency at all levels approaches 0, indicating that active heat dissipation is becoming less effective. In this case, other measures must be taken in a timely manner to ensure the safety of electronic components.

[0131] Local thermal radiation coefficient An increase in the value indicates that the heat radiation of the collection point ahead of the preset path is enhanced. The system responds to environmental changes by increasing the heat dissipation efficiency coefficient calculation rate, reflecting the ability to dynamically adjust active heat dissipation requirements;

[0132] When the active ion release enhancement factor When it increases, the intensity of active ionization release increases. Linear increase ensures that the robot's active heat dissipation capability adapts to changes in environmental requirements;

[0133] when The closer it is to 0, the less heat dissipation capacity of the inspection robot's surface at the point j to be tested is, and the greater the active ion release intensity needs to be increased;

[0134] when The closer it is to 1, the closer the heat dissipation efficiency is to the maximum state, the stronger the active heat dissipation capability is, and the more necessary it is to ensure the stability and long-term working performance of the internal electronic components corresponding to the test point j on the surface of the inspection robot.

[0135] This embodiment dynamically adjusts the heat dissipation efficiency calculation method of each electronic component heat dissipation point on the surface of the inspection robot according to the local thermal radiation conditions of the front path collection point, which is significantly different from the traditional single heat dissipation efficiency calculation mode; through the thermal radiation coefficient grading and classification heat dissipation efficiency calculation method, the inspection robot's thermal management is effectively refined and differentiated, and can timely and effectively predict and respond to environmental thermal changes, improve the operating stability of the robot's electronic components, and reduce the risk of thermal runaway, thereby significantly improving the robot's reliability and service life in complex environments.

[0136] Step S4: Using the real-time calculated heat dissipation efficiency coefficient and local thermal radiation coefficient of each test point as input, a multivariate correlation method is used to construct an autonomous control adjustment model. The autonomous control adjustment model is used to:

[0137] Dynamically optimize the power output ratio of the internal electronic components corresponding to the test point j on the surface of the inspection robot to reduce the surface temperature of the electronic components;

[0138] Automatically adjust the electrode voltage output by the electrode drive circuit to cooperate with the ion wind to enhance heat dissipation;

[0139] Adjust the inspection robot's travel speed to balance heat dissipation requirements and inspection efficiency.

[0140] Further explanation: The autonomous control adjustment model includes:

[0141] 2.1) According to the heat dissipation efficiency coefficient The real-time change of the measured point j is introduced, and the maximum rated power output ratio of the electronic component is set. , and linearly multiply and The correlation result is used to represent the power output ratio of the electronic components corresponding to the test point j on the inspection robot. ;

[0142] In this embodiment, the power output ratio of the electronic components is The adjustment formula is defined as ;

[0143] in, Indicates the real-time power output ratio of the electronic component corresponding to the test point j, with a value of (0,1); The maximum rated power output ratio set for the electronic component corresponding to the test point j is normalized to 1;

[0144] When the heat dissipation efficiency coefficient When it decreases, it indicates that the heat dissipation capacity is insufficient, and the power output of the electronic components is automatically reduced to effectively prevent overheating of the components;

[0145] When the heat dissipation efficiency coefficient When improved, the electronic components allow for increased power output, better utilizing their performance;

[0146] when The closer it is to 0, the current technical target application state is that the electronic components actively reduce power. Specifically, the electronic components corresponding to the test point j need to actively reduce power to prevent thermal runaway.

[0147] when The closer it is to 1, the current technical target application state is that the component operates at maximum power to achieve maximum inspection efficiency and performance; specifically, the closer the power output ratio of the electronic component corresponding to the test point j is to .

[0148] 2.2) Based on the real-time local thermal radiation coefficient and heat dissipation efficiency coefficient , determine the heat dissipation efficiency coefficient of all test points Minimum value of , dynamically adjust the electrode voltage , and obtain the normalized electrode voltage after real-time adjustment ;

[0149] The autonomous electrode voltage regulation formula in this embodiment is defined as ;in, Represents the normalized electrode voltage control parameter after real-time adjustment, with a value range of (0,1); Indicates the heat dissipation efficiency coefficient of all test points The minimum value of

[0150] Only when the local thermal radiation coefficient Increased heat dissipation efficiency coefficient Lower, that is The closer it is to 0, Increase, the electrode voltage increases to produce a stronger ion wind to enhance heat dissipation; at this time, it is necessary to meet and ;correspond ;in is the adjustment coefficient term, used to control The output value range is limited to (0,1); Represents the local thermal radiation coefficient Compared with the previous sampling point, whether the state is increased or decreased; Indicates the heat dissipation efficiency coefficient of all test points The minimum value of is compared with the previous sampling point, indicating whether it increases or decreases;

[0151] It should be noted that the “previous sampling point” refers to the sampling time point closest to the current sampling moment when multiple consecutive data collections are performed at the same preset collection point.

[0152] When the local thermal radiation coefficient Reduce or heat dissipation efficiency coefficient Increase, that is The closer it is to 1, Reduce and save energy consumption; The output value range is limited to (0,1) to ensure that the regulation of electrode voltage is stable and effective; at this time, it is necessary to meet or ;correspond ; is the adjustment coefficient term, used to control The output value range is limited to (0,1);

[0153] When the local thermal radiation coefficient and heat dissipation efficiency coefficient When both remain unchanged, .

[0154] 2.3) Based on the heat dissipation efficiency coefficient of all test points Minimum value of and local thermal radiation coefficient , automatically adjust the real-time driving speed ratio of the inspection robot ;

[0155] In this embodiment, the real-time driving speed control formula is defined as ;in, Indicates the real-time driving speed ratio of the inspection robot, the value range is (0,1), and the maximum speed is 1;

[0156] When the minimum heat dissipation efficiency coefficient The closer it is to 0 and the local thermal radiation coefficient in front When the value is closer to 1, the inspection robot automatically reduces the driving speed ratio. , ensuring safe heat dissipation;

[0157] When the minimum heat dissipation efficiency coefficient The closer it is to 1 and the local thermal radiation coefficient in front As the value approaches 0, the inspection robot automatically increases the driving speed ratio. , in order to improve inspection efficiency.

[0158] The beneficial effects of this embodiment are as follows:

[0159] Realize refined heat dissipation management: By precisely matching the test points on the outer surface with the specific heat dissipation parts of key internal electronic components, accurate local heat detection can be achieved, ensuring that active heat dissipation measures accurately act on the corresponding heat-sensitive electronic components, avoiding blind or ineffective heat dissipation, and improving the effectiveness and accuracy of heat dissipation control.

[0160] Improve the operational stability and safety of the robot: The test points are clearly mapped to specific electronic components, enabling the robot to accurately monitor the temperature rise of each component in real time, proactively detect thermal anomalies or potential thermal risks in advance, and promptly take active ionization heat dissipation measures or other necessary thermal management measures, significantly reducing the risk of thermal runaway of electronic components, thereby ensuring the safe and stable operation of the robot during long-term inspection tasks.

[0161] Improve overall thermal management efficiency: Since the heat dissipation efficiency calculation directly corresponds to the specific component location, the heat dissipation efficiency coefficient is dynamically adjusted through classification, achieving precise allocation of active heat dissipation resources, avoiding resource waste, ensuring maximum heat dissipation performance, and extending the overall service life of electronic components and robots.

[0162] Enhance the maintainability and reliability of the system: Clear correspondence makes it easier for maintenance personnel to quickly locate heat dissipation problems, improves fault diagnosis efficiency and maintenance convenience, and significantly improves the system reliability and maintainability of the inspection robot in long-term operation.

[0163] Example 2:

[0164] In the actual implementation process, a 500-meter-long pipeline corridor in a chemical park was selected for robot inspection test. There are 6 key path nodes in the test pipeline corridor, which are respectively , and set up several local thermal radiation collection points between every two adjacent path nodes The inspection robot is equipped with a real-time air ion concentration sensor, an electrostatic field strength sensor, an electrode voltage sensor, and a precise positioning system to determine its current position.

[0165] Six test points were selected on the robot's surface, corresponding to the robot's main control chip heat sink, power module heat sink, electrode driver power tube heat sink, communication module amplifier chip heat sink, motor driver heat sink, and lidar control circuit heat sink. Each test point recorded the surface temperature of the electronic components in real time. The robot collected data every five seconds during the inspection process, calculated the local thermal radiation coefficient and heat dissipation efficiency coefficient, and used this data as input to construct a multivariable autonomous control adjustment model.

[0166] During the experiment, when the robot encountered an area with a high localized thermal emissivity, the control model autonomously increased the electrode voltage to an appropriate level, simultaneously reducing the power output ratio of the corresponding electronic components by 5% to 10% in real time and dynamically reducing the driving speed by 10% to 15% to ensure a balance between heat dissipation requirements and inspection efficiency. When the thermal emissivity returned to a normal range, the model automatically adjusted back to its original operating state. The entire experiment lasted approximately 20 minutes, and the data results were recorded in real time in a data table for subsequent analysis to verify the advantages and technical effectiveness of the inspection robot's intelligent heat dissipation control strategy.

[0167] Table 1 Research on autonomous control adjustment models:

[0168] Parameter name\test object <![CDATA[At the pipe gallery node P1]]> <![CDATA[At the pipe gallery node P2]]> <![CDATA[At the pipe gallery node P3]]> <![CDATA[At the pipe gallery node P4]]> <![CDATA[At the pipe gallery node P5]]> <![CDATA[At the pipe gallery node P6]]> Local thermal radiation coefficient 0.21 0.34 0.75 0.82 0.47 0.19 Heat dissipation efficiency coefficient-main control chip 0.07 0.2 0.68 0.74 0.29 0.06 Main control chip temperature 52.5 54.1 49.8 48.6 52.2 53.7 Electrode driving voltage (kV) 3 3.5 4.8 5.2 4.1 3.1 Power output ratio (%) 100 97 90 88 95 100 Travel speed (m / s) 0.6 0.58 0.51 0.49 0.56 0.6

[0169] The above data results demonstrate that the inspection robot, through its autonomous control model, dynamically adjusts the power output ratio, electrode drive voltage, and travel speed of electronic components to stabilize the surface temperature of each key electronic component. In particular, when the thermal radiation coefficient reaches a high level at path nodes P3 and P4, the model automatically improves the heat dissipation efficiency coefficient while reducing the power output ratio and the robot's travel speed, effectively lowering the surface temperature of the electronic components and avoiding the risk of thermal runaway. Compared to traditional fixed heat dissipation control methods, this embodiment verifies the innovativeness and practicality of the autonomous control adjustment model, improving the safety, reliability, and long-term operational stability of the robot.

[0170] Example 3:

[0171] See also Figure 2 and Figure 3 , an artificial intelligence-based autonomous control system for a chemical pipeline corridor inspection robot, the system is used to execute the artificial intelligence-based autonomous control method for a chemical pipeline corridor inspection robot, comprising:

[0172] Data acquisition module: used to measure the air ion concentration, electrostatic field strength, and combustible gas concentration at the current location of the inspection robot in real time as it moves along the preset inspection route. At the same time, it collects local thermal radiation distribution data at the preset collection point adjacent to and closest to the route.

[0173] Analyze the local thermal radiation distribution data at the preset collection points to obtain the corresponding local thermal radiation coefficient;

[0174] Ion wind generation module: This module is used to establish an active ionization control system for the inspection robot's surface. It includes an ion generator and an electrode drive circuit. The electrode drive circuit has a built-in low-power current-limiting safety barrier for stabilizing the output and regulating the high voltage. The generated electrode voltage is applied to the electrode tip of the ion generator to drive the ionization of the surrounding air and form an ion wind.

[0175] Coefficient calculation module: used to integrate and analyze the real-time collected air ion concentration, electrostatic field strength and electrode voltage output by the electrode drive circuit to calculate the active ion release enhancement coefficient; based on the active ion release enhancement coefficient, the heat dissipation efficiency coefficient of each test point on the surface of the inspection robot is calculated;

[0176] Model building module: This module uses the real-time calculation of the heat dissipation efficiency coefficient and local thermal radiation coefficient of each test point as input, and uses a multivariable correlation method to build an autonomous control adjustment model. The autonomous control adjustment model is used to:

[0177] Dynamically optimize the power output ratio of the internal electronic components corresponding to the test point j on the surface of the inspection robot to reduce the surface temperature of the electronic components;

[0178] Automatically adjust the electrode voltage output by the electrode drive circuit to cooperate with the ion wind to enhance heat dissipation;

[0179] Adjust the inspection robot's travel speed to balance heat dissipation requirements and inspection efficiency.

[0180] It should be noted that: All calculation formulas in this application document use regression analysis including but not limited to machine learning algorithms to deeply analyze the relevant parameters collected and identify their natural trends and relationships. Use professional software, such as Python's Scikit-learn library or R language, to automatically generate mathematical models that match the data. Then, objectively evaluate the performance of the model through methods such as cross-validation, and combine continuous feedback and optimization to ensure that the created formula truly reflects the inherent laws of the data, thereby ensuring its effectiveness and accuracy. In all calculation formulas in this application, the parameters in each formula are dimensionally non-dimensionalized within a consistent range to ensure that different physical quantities are compared on the same scale; dimensionless technical means include but are not limited to Min-Max-Normalization and Z-Score standardization;

[0181] The technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random-access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0182] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0183] The above embodiments are only intended to help understand the method and core concept of the present invention. It should be noted that, without departing from the principles of the present invention, a number of improvements and modifications may be made to the present invention by those skilled in the art, and such improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. An artificial intelligence-based autonomous control method for a chemical pipeline inspection robot, characterized in that: The specific steps include: Step S1: When the inspection robot moves along the preset inspection route, it measures the air ion concentration, electrostatic field strength, and combustible gas concentration at its current location in real time. At the same time, it collects local thermal radiation distribution data at the preset collection point adjacent to and closest to the route. Analyze the local thermal radiation distribution data at the preset collection points to obtain the corresponding local thermal radiation coefficient; Step S2: Establish an active ionization control system for the inspection robot surface, including an ion generator and an electrode drive circuit. The electrode drive circuit has a built-in low-power current-limiting safety barrier for stabilizing the output and regulating the high voltage. The generated electrode voltage is applied to the electrode tip of the ion generator to drive the ionization of the surrounding air and form an ion wind. Step S3: The real-time collected air ion concentration, electrostatic field strength, and electrode voltage output by the electrode drive circuit are integrated and analyzed to calculate the active ion release enhancement coefficient; based on the active ion release enhancement coefficient, the heat dissipation efficiency coefficient of each test point on the surface of the inspection robot is calculated; Step S4: Using the real-time calculated heat dissipation efficiency coefficient and local thermal radiation coefficient of each test point as input, a multivariate correlation method is used to construct an autonomous control adjustment model. The autonomous control adjustment model is used to: Dynamically optimize the power output ratio of the internal electronic components corresponding to the test point j on the surface of the inspection robot to reduce the surface temperature of the electronic components; Automatically adjust the electrode voltage output by the electrode drive circuit to cooperate with the ion wind to enhance heat dissipation; Adjust the inspection robot's travel speed to balance heat dissipation requirements and inspection efficiency.

2. The method for autonomously controlling a chemical pipeline corridor inspection robot based on artificial intelligence according to claim 1 is characterized in that: Drive along the preset inspection route and each time travel to the preset collection point closest to the current route node When the infrared thermal radiation sensor is started to scan the local radiation intensity, the original thermal radiation data is obtained. ; The original thermal radiation data obtained Take the maximum value of the region With minimum value , and normalized to the dimensionless local thermal radiation coefficient ,and ; i is the representation of "normalization", the same below; The original values measured by multiple ion concentration sensors are averaged and the averaged results are normalized to dimensionless air ion concentration. ,and ; Normalize the electrostatic field strength sensor measurement value to dimensionless electrostatic field strength ,and ; Real-time monitoring of the raw values measured by multiple combustible gas concentration sensors , the original values measured by multiple combustible gas concentration sensors Perform averaging and normalize the averaging results to dimensionless combustible gas concentration ,and ; Set combustible gas concentration Safety threshold .

3. The autonomous control method of the chemical pipeline corridor inspection robot based on artificial intelligence according to claim 2 is characterized in that: Multiple conical stainless steel ion generator electrodes are installed around the inspection robot housing; each ion generator electrode is connected to the high-voltage driver circuit board in the cabin through the same shielded wire harness; The high-voltage driver circuit board consists of a DC-DC boost module and a microcontroller unit (MCU). The MCU performs closed-loop regulation on the boost module output through PWM signals. Feedback voltage of the boost module read by the MCU Normalized processing is performed to obtain the electrode voltage ,and ; The low-power current-limiting safety barrier includes an RC current-limiting network consisting of a high-voltage current-limiting resistor and a ceramic capacitor; and an avalanche diode is added to clamp overshoot, ultimately limiting the overall discharge current and discharge energy to a preset safety range; Receive normalized combustible gas concentration ; If a safety lockout condition is detected during any measurement cycle When the output PWM duty cycle is set to 0%, , and then the normalized electrode voltage ; To prohibit ionizing discharge; When high voltage is applied to the tip of the ion generator electrode, a local electric field strength is generated, causing the surrounding air molecules to ionize, forming positive and negative ions; the positive and negative ions are accelerated by the high voltage field and ejected radially along the tip, forming a perceptible "ion wind" airflow.

4. The method for autonomously controlling a chemical pipeline corridor inspection robot based on artificial intelligence according to claim 3 is characterized in that: Real-time acquisition of air ion concentration parameters with unified dimensions , electrostatic field strength and electrode voltage , active ion release enhancement coefficient is calculated by linear weighted fusion ,and ; Based on preset collection points The local thermal radiation coefficient calculated at The heat dissipation efficiency coefficient of each test point j on the surface of the inspection robot is calculated by the classification function. Perform graded calculations and set ;and , M1 is the total number of points to be tested; when The closer it is to 0, the less heat dissipation capacity of the inspection robot surface at the test point j is, and the greater the active ion release intensity that needs to be improved; when The closer it is to 1, the closer the heat dissipation efficiency is to the maximum state, the stronger the active heat dissipation capability is, and the more necessary it is to ensure the stability and long-term working performance of the internal electronic components corresponding to the test point j on the surface of the inspection robot.

5. The autonomous control method of the chemical pipeline corridor inspection robot based on artificial intelligence according to claim 4 is characterized in that: Autonomous control adjustment model, including: According to the heat dissipation efficiency coefficient The real-time change of the measured point j is introduced, and the maximum rated power output ratio of the electronic component is set. , and linearly multiply and The correlation result is used to represent the power output ratio of the electronic components corresponding to the test point j on the inspection robot. ; when The closer it is to 0, the more the electronic component corresponding to the test point j needs to actively reduce power to prevent thermal runaway; when The closer it is to 1, the closer the power output ratio of the electronic component corresponding to the measured point j is to .

6. The method for autonomously controlling a chemical pipeline corridor inspection robot based on artificial intelligence according to claim 5 is characterized in that: According to the real-time local thermal radiation coefficient and heat dissipation efficiency coefficient , determine the heat dissipation efficiency coefficient of all test points j Minimum value of , dynamically adjust the electrode voltage , and obtain the normalized electrode voltage after real-time adjustment ; Only when the local thermal radiation coefficient Increased heat dissipation efficiency coefficient Lower, that is The closer it is to 0, Increase, the electrode voltage increases to generate stronger ion wind to enhance heat dissipation; When the local thermal radiation coefficient Reduce or heat dissipation efficiency coefficient Increase, that is The closer it is to 1, Reduce and save energy consumption; When the local thermal radiation coefficient and heat dissipation efficiency coefficient When both remain unchanged, .

7. The autonomous control method of the chemical pipeline corridor inspection robot based on artificial intelligence according to claim 6 is characterized in that: According to the heat dissipation efficiency coefficient of all test points Minimum value of and local thermal radiation coefficient , automatically adjust the real-time driving speed ratio of the inspection robot ; When the minimum heat dissipation efficiency coefficient The closer it is to 0 and the local thermal radiation coefficient of the preset collection point in front When the value is closer to 1, the inspection robot automatically reduces the driving speed ratio. , ensuring safe heat dissipation; When the minimum heat dissipation efficiency coefficient The closer it is to 1, the local thermal radiation coefficient of the preset collection point in front As the value approaches 0, the inspection robot automatically increases the driving speed ratio. , in order to improve inspection efficiency.

8. An artificial intelligence-based autonomous control system for a chemical pipeline corridor inspection robot, characterized by: The system is used to execute the artificial intelligence-based autonomous control method for a chemical pipeline corridor inspection robot according to any one of claims 1 to 7, comprising: Data acquisition module: used to measure the air ion concentration, electrostatic field strength, and combustible gas concentration at the current location of the inspection robot in real time as it moves along the preset inspection route. At the same time, it collects local thermal radiation distribution data at the preset collection point adjacent to and closest to the route. Analyze the local thermal radiation distribution data at the preset collection points to obtain the corresponding local thermal radiation coefficient; Ion wind generation module: This module is used to establish an active ionization control system for the inspection robot's surface. It includes an ion generator and an electrode drive circuit. The electrode drive circuit has a built-in low-power current-limiting safety barrier for stabilizing the output and regulating the high voltage. The generated electrode voltage is applied to the electrode tip of the ion generator to drive the ionization of the surrounding air and form an ion wind. Coefficient calculation module: used to integrate and analyze the real-time collected air ion concentration, electrostatic field strength and electrode voltage output by the electrode drive circuit to calculate the active ion release enhancement coefficient; based on the active ion release enhancement coefficient, the heat dissipation efficiency coefficient of each test point on the surface of the inspection robot is calculated; Model building module: This module uses the real-time calculation of the heat dissipation efficiency coefficient and local thermal radiation coefficient of each test point as input, and uses a multivariable correlation method to build an autonomous control adjustment model. The autonomous control adjustment model is used to: Dynamically optimize the power output ratio of the internal electronic components corresponding to the test point j on the surface of the inspection robot to reduce the surface temperature of the electronic components; Automatically adjust the electrode voltage output by the electrode drive circuit to cooperate with the ion wind to enhance heat dissipation; Adjust the inspection robot's travel speed to balance heat dissipation requirements and inspection efficiency.

Images