Vehicle intelligent driving camera dirty hardware-in-the-loop test system and method

Abstract

The invention discloses a vehicle intelligent driving camera dirty hardware-in-the-loop test system and method, and relates to the field of vehicle simulation testing, and the system comprises a tail gas generation module, a soot online calibration and quality closed-loop module, a transmissivity monitoring and hard triggering module, and an AEB synchronous recording and data fusion module. The tail gas generation module is used for generating standardized nuclear soot flow matched with the optical characteristics of the road diesel black carbon; the soot online calibration and mass closed-loop module is used for carrying out online accurate measurement on the deposition mass of the soot flow on the surface of the test carrier and enabling the deposition mass to stably reach a preset target value; the transmissivity monitoring and hard triggering module is used for monitoring the transmissivity attenuation condition of the test carrier in real time, and when attenuation reaches a preset threshold value, the HIL scene server is triggered to enter an AEB working condition in a low-delay mode; and the AEB synchronous recording and data fusion module is used for synchronously acquiring vehicle operation data under an AEB working condition and fusing pollutant deposition amount and transmissivity data to construct a quantitative calibration curve.

Description

Technical Field

[0001] This invention relates to the field of vehicle simulation testing, and in particular to a hardware-in-the-loop testing system for dirty driving cameras, a method for testing dirty driving cameras, electronic devices, storage media, and testing platforms. Background Technology

[0002] In recent years, some vehicle models have begun to be equipped with urban NOA (Noise, Arrival, and Surveillance) functions, aiming to achieve continuous operation "in all scenarios, all weather conditions, and all time periods." This means that the camera must maintain a perception confidence level of >99% even in harsh environments such as rain, snow, dust, and exhaust fumes. Heavy-duty diesel trucks account for 7% of the total number of motor vehicles, but contribute more than 70% of PM1.0 black carbon emissions. During peak hours, following another vehicle for 3 minutes can create a light-absorbing deposition layer of 20 μg / cm² on the camera window, which is the primary external cause of NOA phantom braking complaints in urban areas (China Automobile Dealers Association 2023 Annual Report).

[0003] For testing purposes, it is impossible to "safely and repeatably" reproduce critical dirt on a real vehicle, mainly for the following reasons:

[0004] ① High safety risk: It requires driving close to the rear of a truck (<8 m) for a long time, and must cover scenarios with instantaneous high smoke, such as cold start in the morning and heavy load on uphill, which can easily cause rear-end collisions.

[0005] ②Uncontrollable boundaries: Road wind speed, wind direction, vehicle distance, and light intensity all change with the external environment. Even if the same vehicle fleet is used for the test, the amount of sediment will also be deviated, and a quantitative curve cannot be obtained.

[0006] ③Possibility of tightening regulations: The industry anticipates that future camera anti-pollution testing standards may not be able to meet the requirements for batch, rapid, and repeatable verification on real-world roads.

[0007] Domestic and international mainstream laboratories still follow the "spray-diffuse blackboard + uniform light source" approach, specifically manifested as follows:

[0008] ① Particulate source distortion: Graphite ink or carbon powder spray has a mass absorption cross section of 0.3-0.5 m² / g, which is more than 3 times different from diesel black carbon of 1.5 m² / g. The HDR misjudgment probability curve shifts to the left as a whole. If the company obtains an "overly optimistic" qualification report, it will also produce ghost braking after the vehicle is put on the road.

[0009] ② Deposition amount open loop: There is no online concentration calibration. It relies on offline statistics of "weighing filter membrane-drying-balance". The test cycle is 4 hours and the error is ±30%. It is impossible to lock the critical boundary of 20μg / cm² in real time.

[0010] ③ No hard trigger synchronization: After the dirt film is prepared, the camera is manually pushed forward for testing. The scene and the dirt are out of sync, and the AEB response of "transmittance drops by 2% moment" cannot be recorded. This results in the lack of "time-deceleration" correspondence, and the subsequent calibration can only be compensated by engineers' experience.

[0011] For example, a Chinese patent, titled "A Method for Testing Dirt in Wide-Angle Camera Modules" (patent number CN201711436952.8), mainly describes a method for testing dirt in wide-angle camera modules. It addresses the difficulty of detecting dirt in existing wide-angle cameras. However, this patent is only for factory testing of modules on the production line and does not provide any particle source or dirt generation device; it relies on template images and cannot simulate the light absorption characteristics of real road black carbon (σ_abs≈1.5 m² / g); it lacks online closed-loop control, cannot dynamically adjust the amount of dirt as the test progresses, and has no AEB (Automatic Emergency Braking) trigger function.

[0012] For example, a Chinese patent, titled "Dirty Detection Device and Method for Vehicle-Mounted Cameras," patent number CN202011001333.8, provides a dirty detection device and method for vehicle-mounted cameras. The device includes: a preprocessing module for obtaining original image frames from real-time images captured and transmitted by the vehicle-mounted camera and dividing them into multiple image blocks; a feature calculation module for calculating the global light source vector of the original image frame and the sub-light source vectors of the image blocks, and calculating the actual spatial domain information entropy, actual information entropy matrix, and actual variance of the image blocks; a region filtering module for calculating the actual angle between the sub-light source vectors and the global light source vector, determining a first candidate region, and determining a second candidate region based on the actual spatial domain information entropy, actual information entropy matrix, and actual variance; a noise calculation module for fitting a first actual probability density function, a second actual probability density function, and a reference probability density function; and a dirty detection module for calculating a first actual difference value and a second actual difference value and determining the dirty object. This patent is an algorithm patent, without physical contamination or online calibration; it can only provide "present / absent" or area mask, and cannot provide a continuous "transmittance-deposition amount" curve; it does not control the optical properties of particles, is unrelated to the exhaust gas black carbon absorption mechanism, and cannot be used for HDR misjudgment boundary quantification. Summary of the Invention

[0013] In view of this, the purpose of the present invention is to provide a hardware-in-the-loop testing system for dirty driving cameras of vehicles, a method for testing dirty driving cameras of vehicles, electronic devices and storage media, electronic devices, storage media and testing platforms, which aim to solve the technical problems existing in the prior art by simulating the particulate source of real burning black carbon, using dual laser closed loop as the measurement chain and hard triggering as the synchronization means.

[0014] This invention provides the following solution:

[0015] According to one aspect of the present invention, a hardware-in-the-loop testing system for dirt and grime in a vehicle intelligent driving camera is provided, comprising:

[0016] The exhaust gas generation module, the LII online calibration and quality closed-loop module, the transmittance monitoring and hard triggering module, and the AEB synchronous recording and data fusion module;

[0017] The exhaust gas generation module is used to generate a standardized nucleated soot stream that matches the optical characteristics of black carbon from road diesel fuel.

[0018] The LII online calibration and quality closed-loop module is used to accurately measure the deposition quality of soot flow on the surface of the test carrier online, and to stabilize the deposition quality to the preset target value through closed-loop control.

[0019] The transmittance monitoring and hard triggering module is used to monitor the transmittance decay of the test carrier in real time. When the decay reaches a preset threshold, the HIL scenario server is triggered to enter the AEB mode with low latency.

[0020] The AEB synchronous recording and data fusion module is used to synchronously collect vehicle operation data under AEB conditions and fuse pollutant deposition and transmittance data to construct a quantitative calibration curve.

[0021] Furthermore, the actual exhaust gas generation module includes: a combustion tower, a fuel supply unit, and a secondary dilution duct;

[0022] The fuel supply unit delivers a propane-butane mixed fuel to the combustion tower;

[0023] The fuel in the combustion tower is burned under lean combustion conditions, and the combustion temperature is maintained within a preset temperature threshold range.

[0024] A secondary dilution duct is installed at the combustion tower outlet to stabilize the output PM1.0 concentration at a preset threshold.

[0025] Furthermore, the LII online calibration and quality closed-loop module includes: a laser excitation unit, a radiation signal acquisition and preprocessing unit, an online calibration unit, and a quality closed-loop control unit;

[0026] The laser unit is used to generate laser pulses focused soot streams.

[0027] The radiation signal acquisition and preprocessing unit is used to acquire the radiation signal of the soot stream and perform preprocessing.

[0028] An online calibration unit is used to establish and calibrate a quantitative correlation model between LII radiation signal and soot characteristic concentration Csoot;

[0029] The quality closed-loop control unit is used to adjust burner parameters and control deposition quality based on the soot characteristic concentration Csoot using a PID algorithm.

[0030] Furthermore, the quality closed-loop control unit also includes:

[0031] Sedimentation quality monitoring unit;

[0032] The sedimentation quality monitoring unit is used to measure the sedimentation quality per unit area in real time to verify the control effect.

[0033] Used to acquire control error, and triggers an alarm when the control error exceeds a preset threshold.

[0034] Furthermore, the transmittance monitoring and hard triggering module also includes:

[0035] Logic control module;

[0036] The transmittance was calculated by combining the transmission characteristics of near-ultraviolet single-mode laser with the initial light intensity recorded by the detector and the transmitted light intensity recorded by the detector on the contaminated side.

[0037] Based on the transmittance, a preset safety threshold is obtained. When the attenuation rate of the transmittance reaches the preset safety threshold, the logic control module outputs a standard level signal within a preset time period, triggering the target system to enter the preset safety operating condition.

[0038] Furthermore, the AEB synchronous recording and data fusion module includes:

[0039] Vehicle operating data includes vehicle braking deceleration data;

[0040] Based on the vehicle braking deceleration data, the repeatability error of braking deceleration is obtained.

[0041] According to a second aspect of the present invention, a method for testing the dirt and grime hardware-in-the-loop of a vehicle intelligent driving camera is provided, comprising the following steps:

[0042] The test carrier is deployed at the preset work station, and a soot flow matching the optical characteristics of road diesel black carbon is generated according to the preset soot flow matching parameters, deposition quality target value, transmittance attenuation threshold and AEB working condition triggering conditions.

[0043] Apply the soot stream to the surface of the test carrier;

[0044] By adjusting the soot flow, the soot deposition quality on the surface of the test carrier is stabilized to reach the preset deposition quality target value.

[0045] The transmittance attenuation of the test carrier is monitored in real time. The monitored transmittance attenuation data is compared with the preset transmittance attenuation threshold. When the monitored transmittance attenuation reaches the preset threshold, the HIL scenario server is triggered to enter the AEB working condition with low latency through transmittance monitoring and hard trigger module.

[0046] Vehicle operation data under AEB conditions were collected, and pollutant deposition and transmittance data were integrated to construct a quantitative calibration curve.

[0047] According to three aspects of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0048] The memory stores a computer program, which, when executed by a processor, causes the processor to perform the steps of a hardware-in-the-loop test method for dirty driving cameras in vehicles.

[0049] According to four aspects of the present invention, a computer-readable storage medium is provided that stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a method for testing the dirt hardware-in-the-loop of a vehicle intelligent driving camera.

[0050] According to five aspects of the present invention, a detection platform is provided, comprising:

[0051] Electronic equipment, comprising the steps of a method for testing the dirt hardware-in-the-loop of a vehicle intelligent driving camera;

[0052] A processor that runs a program and executes steps of a vehicle intelligent driving camera dirt-in-the-loop test method based on data output from an electronic device when the program is running.

[0053] A storage medium for storing programs, which, when run, execute steps of a vehicle intelligent driving camera dirt-in-the-loop test method for data output from an electronic device.

[0054] Compared with the prior art, the present invention has the following advantages:

[0055] This application provides data support for pollution protection design by precisely controlling pollution levels and comprehensively testing camera performance; it also intuitively quantifies pollution resistance capabilities, helping to improve the stability and market competitiveness of urban NOA systems. The stable testing conditions and reliable results facilitate research and development optimization and certification, thereby enhancing system reliability. Attached Figure Description

[0056] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0057] Figure 1This is a structural diagram of a vehicle intelligent driving camera dirt hardware-in-the-loop testing system provided by one or more embodiments of the present invention.

[0058] Figure 2 This is a flowchart of a hardware-in-the-loop testing method for a vehicle intelligent driving camera, provided by one or more embodiments of the present invention.

[0059] Figure 3 This is a framework diagram of a vehicle intelligent driving camera dirt HIL testing system according to a specific embodiment of the present invention.

[0060] Figure 4 This is a network topology diagram of a vehicle intelligent driving camera dirt HIL testing system according to a specific embodiment of the present invention.

[0061] Figure 5 This is a control flowchart of a vehicle intelligent driving camera dirt HIL testing system according to a specific embodiment of the present invention.

[0062] Figure 6 This is a block diagram of an electronic device structure for a method of testing the hardware-in-the-loop dirt of a vehicle intelligent driving camera, provided by one or more embodiments of the present invention. Detailed Implementation

[0063] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0065] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0066] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0067] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0068] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0069] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0070] Figure 1 This is a structural diagram of a vehicle intelligent driving camera dirt hardware-in-the-loop testing system provided by one or more embodiments of the present invention.

[0071] like Figure 1 As shown, it includes:

[0072] The exhaust gas generation module, the LII online calibration and quality closed-loop module, the transmittance monitoring and hard triggering module, and the AEB synchronous recording and data fusion module;

[0073] The exhaust gas generation module is used to generate a standardized nucleated soot stream that matches the optical characteristics of black carbon from road diesel fuel.

[0074] The LII online calibration and quality closed-loop module is used to accurately measure the deposition quality of soot flow on the surface of the test carrier online, and to stabilize the deposition quality to the preset target value through closed-loop control.

[0075] The transmittance monitoring and hard triggering module is used to monitor the transmittance decay of the test carrier in real time. When the decay reaches a preset threshold, the HIL scenario server is triggered to enter the AEB mode with low latency.

[0076] The AEB synchronous recording and data fusion module is used to synchronously collect vehicle operation data under AEB conditions and fuse pollutant deposition and transmittance data to construct a quantitative calibration curve.

[0077] In one embodiment, the real exhaust gas generation module includes: a combustion tower, a fuel supply unit, and a secondary dilution duct; the fuel supply unit supplies mixed fuel to the combustion tower, and the mixed fuel in the combustion tower is burned under lean combustion conditions, with the combustion temperature maintained within a preset temperature threshold range; the secondary dilution duct is located at the outlet of the combustion tower to stabilize the output PM1.0 concentration at a preset threshold.

[0078] In one embodiment, the LII online calibration and quality closed-loop module includes: a laser excitation unit, a radiation signal acquisition and preprocessing unit, an online calibration unit, and a quality closed-loop control unit;

[0079] A laser unit is used to generate laser pulses to focus the soot stream;

[0080] A radiation signal acquisition and preprocessing unit is used to acquire the radiation signal of the soot stream and perform preprocessing.

[0081] An online calibration unit is used to establish and calibrate a quantitative correlation model between LII radiation signals and soot characteristic concentrations;

[0082] The quality closed-loop control unit is used to adjust burner parameters and control deposition quality based on soot characteristic concentration using a PID algorithm.

[0083] In one embodiment, the quality closed-loop control unit further includes: a deposition quality monitoring unit;

[0084] The sedimentation quality monitoring unit is used to measure the sedimentation quality per unit area in real time to verify the control effect.

[0085] Used to acquire control error, and triggers an alarm when the control error exceeds a preset threshold.

[0086] In one embodiment, the transmittance monitoring and hard triggering module further includes:

[0087] Logic control module;

[0088] The transmittance was calculated by combining the transmission characteristics of near-ultraviolet single-mode laser with the initial light intensity recorded by the detector on the detector side and the transmitted light intensity recorded by the detector on the contaminated side.

[0089] Based on the transmittance, a preset safety threshold is obtained. When the attenuation rate of the transmittance reaches the preset safety threshold, the logic control module outputs a standard level signal within a preset time period, triggering the target system to enter the preset safety operating condition.

[0090] In one embodiment, the AEB synchronous recording and data fusion module includes:

[0091] Vehicle operating data includes vehicle braking deceleration data;

[0092] Based on the vehicle braking deceleration data, the repeatability error of braking deceleration is obtained.

[0093] It is worth noting that although only some basic functional modules are disclosed in this embodiment, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, what this embodiment intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules does not mean that the scope of protection of the claims of this invention is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above device is described separately according to its functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0094] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0095] Figure 2 This is a flowchart of a method for testing the HIL (High-Intensity Leakage) of a vehicle intelligent driving camera, provided by one or more embodiments of the present invention.

[0096] like Figure 2 As shown, it includes the following steps:

[0097] Step S1: Deploy the test carrier at the preset work station and generate a soot flow that matches the optical characteristics of road diesel black carbon according to the preset soot flow matching parameters, deposition quality target value, transmittance attenuation threshold and AEB working condition triggering conditions.

[0098] Step S2: Apply the soot stream to the surface of the test carrier;

[0099] Step S3: By adjusting the soot flow, the soot deposition quality on the surface of the test carrier is stabilized to reach the preset deposition quality target value.

[0100] Step S4: Monitor the transmittance attenuation of the test carrier in real time, compare the monitored transmittance attenuation data with the preset transmittance attenuation threshold, and when the monitored transmittance attenuation reaches the preset threshold, trigger the HIL scenario server to enter the AEB working condition through the low latency of transmittance monitoring and hard trigger module.

[0101] Step S5: Collect vehicle operation data under AEB conditions, and construct a quantitative calibration curve by fusing pollutant deposition and transmittance data.

[0102] Specifically, by simulating the optical properties of black carbon in exhaust gas, the impact of pollution on cameras can be accurately assessed, thus solving the problem of deviation in traditional testing.

[0103] By controlling the deposition rate in a closed loop, the degree of contamination can be precisely controlled, and the camera performance can be comprehensively tested to provide data support for contamination protection design.

[0104] Stable testing conditions and reliable results help with R&D optimization and certification, and improve system reliability.

[0105] Intuitively quantify pollution resistance capabilities to help improve the stability and market competitiveness of urban NOA systems.

[0106] Figure 3 This is a framework diagram of a vehicle intelligent driving camera dirt HIL testing system according to a specific embodiment of the present invention.

[0107] like Figure 3 As shown, it includes:

[0108] The system includes a real exhaust gas generation module, an LII online calibration and quality closed-loop module, a transmittance monitoring and hard triggering module, and an AEB synchronous recording and data fusion module.

[0109] The actual exhaust gas generation module operates under lean combustion conditions using a propane-butane mixed fuel (equivalent ratio φ≈0.85), maintaining a combustion temperature of 1100 °C±30 °C. This ensures complete dehydrogenation of the soot precursor PAH and its conversion to a graphite lamellar structure, achieving a product mass absorption cross-section σabs of up to 1.5 m² / g, with an optical characteristic deviation of <5% from that of road diesel black carbon. A secondary dilution duct is installed at the combustion tower outlet, with a dilution ratio DR=20:1, stabilizing the PM1.0 concentration at 5×10⁻⁶. 5 # / cm³, particle size distribution peak Dp,50=120 nm, meets the "nuclear state" soot characteristic defined in GB 18352.6-2016.

[0110] LII Online Calibration and Quality Closed-Loop Module: A 266 nm Nd:YAG laser pulse (energy E0 = 1 mJ, pulse width τ = 8 ns) is focused onto the soot flow, inducing an instantaneous temperature rise to approximately 4000 K. The particle thermal radiation signal I_λ∝exp(-C2 / λT) is acquired by the PMT in the incandescent wavelength range of 350-800 nm. According to LII theory:

[0111] C_soot = k·∫I_λ dλ / E0;

[0112] Where C_soot is the instantaneous mass concentration within the laser detection volume; E0 is the energy of a single 266 nm laser pulse (commonly 1 mJ = 1 × 10⁻⁻⁴). 6 J); ∫Iλdλ: Integrating over the entire incandescent band to obtain the total radiant power P_LII, Iλ: Voltage response of the photodiode at wavelength λ; k: System constant, including geometric factor, collection efficiency, spectral response, detection gain, etc. (all geometric and photoelectric factors are combined), calibrated by NIST-traceable EC soot standard material. The PID controller uses C_soot as feedback to adjust the burner fuel flow rate in real time, so that the deposition mass M_d reaches 20 μg / cm² within 60s, with a control error ≤5%.

[0113] Transmittance monitoring and hard triggering module: A 405 nm single-mode laser passes through the camera's protective glass, and the reference detector records I0; the contaminated detector records I, and the transmittance T = I / I0, according to the Beer-Lambert law:

[0114] T = exp(-σ_abs·Md);

[0115] Where T is the transmittance and σ_abs is the mass absorption cross section;

[0116] When M_d = 20 μg / cm² and σ_abs = 1.5 m² / g, the theoretical T = 0.970 (attenuation of 3%). In this embodiment, the safety threshold is set to T ≤ 0.98 (attenuation of 2%). At this time, the FPGA outputs a TTL high level within 1 ms, directly triggering the HIL scenario server to enter the AEB mode, ensuring that the "contamination-function" timing error is minimized.

[0117] AEB Synchronous Recording and Data Fusion Module: Upon triggering an AEB scenario, the system synchronously records relevant data such as the vehicle's braking deceleration. Simultaneously, by combining transmittance and braking deceleration data under different deposition levels, a three-dimensional calibration curve of "deposition level-transmittance-deceleration" is constructed. This provides a quantitative basis for assessing the pollution resistance capability of urban NOA systems, facilitating the optimization and application of intelligent driving technology in complex urban environments.

[0118] In one specific embodiment, a complete method for building a dirty HIL test system for intelligent driving cameras based on real exhaust gas combustion and dual-laser closed-loop calibration was simulated, such as... Figure 5 As shown, it includes the following steps:

[0119] Experimental equipment preparation and connection: Place the test system of this invention in the Hardware-in-the-Loop (HIL) laboratory for intelligent driving vehicles, ensuring a stable connection between the system and the camera of the vehicle under test and the HIL test bench. The camera is directly facing the combustion tower outlet, and the 405nm laser emitter is aligned with the camera to ensure that the laser can pass through the camera perpendicularly;

[0120] Combustion tower ignition and parameter settings: Start the combustion tower, set the flow rate of the propane-butane mixture to achieve an equivalence ratio φ≈0.85, ignite the flame, and maintain the combustion temperature at 1100℃±30℃. This temperature range was verified through previous experiments and ensures that the polycyclic aromatic hydrocarbons (PAHs) precursors of soot are fully dehydrogenated and transformed into a graphite lamellar structure, thereby achieving a product mass absorption cross-section σabs of up to 1.5m² / g, with a deviation of less than 5% from the optical characteristics of road diesel black carbon, laying the foundation for subsequent simulation of real exhaust gas environments;

[0121] Secondary dilution and particulate concentration control: After combustion stabilizes, open the secondary dilution air duct and set the dilution ratio DR = 20:1. After dilution, the PM1.0 number concentration generated by combustion can be stabilized at 5 × 10⁻⁶. 5 # / cm³, with a peak particle size distribution Dp,50=120nm, meeting the "nuclear state" soot characteristics defined in GB 18352.6-2016, ensuring that the particles are highly similar to carbon soot particles in real exhaust gas in size and distribution, providing a realistic particle environment for camera dirt testing;

[0122] LII Online Calibration and Quality Monitoring: The 266nm ultraviolet laser-induced incandescent (LII) system at the top of the tower begins operation, performing real-time online calibration of the particles generated during combustion. The laser is focused on the soot stream, and the induced incandescent light signal is received by a photomultiplier tube. The mass concentration C_soot is calculated according to the formula C_soot = k·I_LII / E_laser, and the data is fed back to the PID controller to adjust the burner fuel valve in a closed loop, ensuring that the particle deposition error is <5%. This achieves precise control and monitoring of particle quality, providing a guarantee for accurate subsequent assessment of the degree of fouling.

[0123] Camera window transmittance monitoring and triggering: A 405nm laser emitter continuously emits laser light into the camera window. A silicon PIN diode monitors the transmitted light intensity I in real time and compares it with the initial intensity I0 to calculate the transmittance T = I / I0. When the transmittance T ≤ 98% (i.e., attenuation of 2%), the FPGA outputs a 1ms pulse signal, triggering the HIL simulation platform to switch to the AEB scenario, simulating an emergency braking situation when a city NOA encounters truck exhaust fumes causing the camera to become dirty. This triggering mechanism can accurately capture the moment when dirt affects camera performance, ensuring the timeliness and accuracy of the test.

[0124] Data Acquisition and Analysis: Upon triggering an AEB scenario, the system synchronously records relevant data such as vehicle braking and deceleration. Through repeated experiments, the repeatability error of braking deceleration is statistically analyzed to verify the stability and reliability of the test system. Simultaneously, by combining transmittance and braking deceleration data under different deposition amounts, a three-dimensional calibration curve of "deposition amount-transmittance-deceleration" is constructed, providing a quantitative basis for assessing the pollution resistance capability of urban NOA systems and contributing to the optimization and application of intelligent driving technology in complex urban environments.

[0125] Specifically, by simulating exhaust gas using a combustion tower and combining it with dual-laser closed-loop calibration, the system achieves simulated dirt accumulation on cameras and real-time monitoring. This ensures that the test results accurately reflect the actual scenario, improves test accuracy and efficiency, and provides a quantitative basis for assessing a city's NOA (Noise, Air, and Ocean) pollution resistance capabilities.

[0126] Figure 6 This is a block diagram of an electronic device structure for a method of testing the hardware-in-the-loop dirt of a vehicle intelligent driving camera, provided by one or more embodiments of the present invention.

[0127] like Figure 6 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0128] The memory stores a computer program that, when executed by a processor, causes the processor to perform the steps of a hardware-in-the-loop test method for a vehicle intelligent driving camera.

[0129] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a method for testing the dirty hardware-in-the-loop of a vehicle intelligent driving camera.

[0130] This application also provides a testing platform, including:

[0131] Electronic equipment, comprising the steps of a method for testing the dirt hardware-in-the-loop of a vehicle intelligent driving camera;

[0132] The processor runs a program that, when running, executes the steps of a dirty hardware-in-the-loop test method for a vehicle intelligent driving camera based on data output from an electronic device.

[0133] A storage medium for storing a program that, when run, executes the steps of a hardware-in-the-loop test method for a vehicle intelligent driving camera based on data output from an electronic device.

[0134] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0135] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A hardware-in-the-loop testing system for dirt and grime in vehicle intelligent driving cameras, characterized in that, include: The exhaust gas generation module, the online soot calibration and quality closed-loop module, the transmittance monitoring and hard triggering module, and the AEB synchronous recording and data fusion module; The exhaust gas generation module is used to generate a standardized nucleated soot stream that matches the optical characteristics of road diesel black carbon. The soot online calibration and quality closed-loop module is used to measure the deposition quality of the soot flow on the surface of the test carrier online, and to stabilize the deposition quality to a preset target value through closed-loop control. The transmittance monitoring and hard triggering module is used to monitor the transmittance decay of the test carrier in real time. When the decay reaches a preset threshold, the HIL scenario server is triggered to enter the AEB working condition with low latency. The AEB synchronous recording and data fusion module is used to synchronously collect vehicle operation data under AEB conditions and fuse pollutant deposition and transmittance data to construct a quantitative calibration curve.

2. The vehicle intelligent driving camera dirt hardware-in-the-loop testing system according to claim 1, characterized in that, The exhaust gas generation module includes: a combustion tower, a fuel supply unit, and a secondary dilution air duct; The fuel supply unit delivers mixed fuel to the combustion tower; The mixed fuel in the combustion tower is burned under lean combustion conditions, and the combustion temperature is maintained within a preset temperature threshold range. The secondary dilution duct is located at the combustion tower outlet to stabilize the output PM1.0 concentration at a preset threshold.

3. The vehicle intelligent driving camera dirt hardware-in-the-loop testing system according to claim 1, characterized in that, The soot online calibration and quality closed-loop module includes: a laser excitation unit, a radiation signal acquisition and preprocessing unit, an online calibration unit, and a quality closed-loop control unit; The laser unit is used to generate laser pulses to focus the soot stream; The radiation signal acquisition and preprocessing unit is used to acquire the radiation signal of the soot stream and perform preprocessing. The online calibration unit is used to establish and calibrate a quantitative correlation model between soot radiation signal and soot characteristic concentration; The quality closed-loop control unit is used to adjust burner parameters and control deposition quality based on soot characteristic concentration using a PID algorithm.

4. The vehicle intelligent driving camera dirt hardware-in-the-loop testing system according to claim 3, characterized in that, The quality closed-loop control unit also includes: Sedimentation quality monitoring unit; The deposition quality monitoring unit is used to measure the deposition quality per unit area in real time to verify the control effect. Used to acquire control error, and triggers an alarm when the control error exceeds a preset threshold.

5. A hardware-in-the-loop testing system for dirt and grime in a vehicle intelligent driving camera according to claim 1, characterized in that, The transmittance monitoring and hard triggering module also includes: Logic control module; The transmittance was calculated by combining the transmission characteristics of near-ultraviolet single-mode laser with the initial light intensity recorded by the detector and the transmitted light intensity recorded by the detector on the contaminated side. Based on the transmittance, a preset safety threshold is obtained. When the attenuation rate of the transmittance reaches the preset safety threshold, the logic control module outputs a standard level signal within a preset time period to trigger the target system to enter a preset safety condition.

6. The vehicle intelligent driving camera dirt hardware-in-the-loop testing system according to claim 1, characterized in that, The AEB synchronous recording and data fusion module includes: The vehicle operation data is the vehicle braking deceleration data; Based on the vehicle braking deceleration data, the repeatability error of braking deceleration is obtained.

7. A method for testing the dirt and grime of a vehicle intelligent driving camera in the hardware-in-the-loop, characterized in that, Includes the following steps: The test carrier is deployed at the preset work station, and a soot flow matching the optical characteristics of road diesel black carbon is generated according to the preset soot flow matching parameters, deposition quality target value, transmittance attenuation threshold and AEB working condition triggering conditions. The soot stream is applied to the surface of the test carrier; By adjusting the soot flow, the soot deposition quality on the surface of the test carrier is stabilized to reach the preset deposition quality target value. The transmittance attenuation of the test carrier is monitored in real time. The monitored transmittance attenuation data is compared with the preset transmittance attenuation threshold. When the monitored transmittance attenuation reaches the preset threshold, the HIL scenario server is triggered to enter the AEB working condition with low latency through the transmittance monitoring and hard trigger module. Vehicle operation data under AEB conditions were collected, and pollutant deposition and transmittance data were integrated to construct a quantitative calibration curve.

8. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the dirty hardware-in-the-loop test method for a vehicle intelligent driving camera as described in claim 7.

9. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the dirty hardware-in-the-loop test method for a vehicle intelligent driving camera as described in claim 7.

10. A detection platform, characterized in that, include: An electronic device for implementing the steps of the dirty hardware-in-the-loop test method for a vehicle intelligent driving camera as described in claim 7; The processor runs a program, and when the program runs, it executes the steps of the dirty hardware-in-the-loop test method for a vehicle intelligent driving camera as described in claim 7, based on data output from the electronic device. A storage medium for storing a program that, when running, executes the steps of the dirty hardware-in-the-loop test method for a vehicle intelligent driving camera as described in claim 7 on data output from an electronic device.

Images