A fuel filling amount determination method, device and electronic equipment

Abstract

Embodiments of the present application disclose a fuel filling amount determination method and device and electronic equipment. The method comprises: when a target unmanned vehicle meets a refueling trigger condition, collecting a refueling process sound signal corresponding to the target unmanned vehicle through a sound pickup device; determining an effective refueling duration of refueling the target unmanned vehicle based on the refueling process sound signal; and determining an actual fuel filling amount corresponding to the target unmanned vehicle based on the effective refueling duration and a rated flow of a refueling machine calibrated in advance. The abnormal working condition information such as midway stop, abnormal start-stop and oil stealing / leakage can be accurately identified without increasing labor costs, and the accuracy of the actual fuel filling amount is ensured.

Description

Technical Field

[0001] This invention relates to the field of flow monitoring technology, and in particular to a method, apparatus and electronic device for determining fuel filling amount. Background Technology

[0002] Accurately determining the amount of fuel to fill is a crucial aspect of vehicle fuel management, energy consumption calculation, refueling control, and safety protection, and is widely used in passenger cars, commercial vehicles, and construction machinery. The amount of fuel filled not only affects refueling efficiency and operating costs, but also directly impacts the fuel tank's thermal expansion space, fuel vapor emissions, and driving safety.

[0003] In existing technologies, the amount of fuel dispensed for unmanned vehicles is typically determined based on liquid level sensors or industrial cameras. Specifically, the liquid level sensor-based fuel dispensing method involves installing a float-type or ultrasonic liquid level sensor inside the fuel tank to measure the liquid level in real time. This, combined with a pre-calibrated fuel level-volume relationship, calculates the difference in fuel volume before and after dispensing, thus obtaining the amount of fuel dispensed per transaction. The industrial camera-based fuel dispensing method uses an industrial camera to photograph the fuel dispenser's display interface and then uses optical character recognition (OCR) technology to read the dispensing amount displayed on the interface, which serves as the basis for calculating the amount of fuel dispensed per transaction.

[0004] However, fuel filling measurement schemes based on liquid level sensors, without the addition of an additional anti-sloshing structure for the fuel tank, will still cause violent shaking of the fuel in the tank even when refueling while parked on uneven roads. This results in large fluctuations in the liquid level data collected by the liquid level sensor, making it impossible to obtain stable liquid level values ​​before and after refueling, ultimately leading to errors in the determined fuel filling amount.

[0005] Secondly, fuel dispensing measurement schemes based on industrial cameras have three drawbacks: first, they rely on manual operation to align the equipment with the fuel gauge, which is cumbersome; second, industrial cameras often only focus on the final amount of fuel dispensed, which may lead to measurement fraud; and third, the authenticity of the captured images cannot be effectively guaranteed. Given these three drawbacks, fuel dispensing measurement schemes based on industrial cameras often cannot accurately determine the amount of fuel dispensed at low cost. Summary of the Invention

[0006] This invention provides a method, apparatus, and electronic device for determining fuel filling quantity, which solves the problem that fuel filling quantity measurement schemes based on liquid level sensors and fuel filling quantity measurement schemes based on industrial cameras cannot accurately determine the actual fuel filling quantity at low cost. It can accurately identify abnormal operating conditions such as mid-process stopping, abnormal start-stop, and fuel theft without increasing labor costs, thus ensuring the accuracy of the actual fuel filling quantity.

[0007] In a first aspect, embodiments of the present invention provide a method for determining fuel refueling quantity, comprising: when a target unmanned vehicle reaches a refueling trigger condition, acquiring a refueling process sound signal corresponding to the target unmanned vehicle through a sound pickup device; determining an effective refueling duration for refueling the target unmanned vehicle based on the refueling process sound signal; and determining the actual fuel refueling quantity corresponding to the target unmanned vehicle based on the effective refueling duration and a pre-calibrated rated flow rate of the fuel dispenser.

[0008] Secondly, embodiments of the present invention also provide a fuel filling quantity determination device, comprising: a sound signal acquisition module, used to acquire a refueling process sound signal corresponding to the target unmanned vehicle through a sound pickup device when the target unmanned vehicle reaches the refueling trigger condition; a refueling duration determination module, used to determine the effective refueling duration for refueling the target unmanned vehicle based on the refueling process sound signal; and a filling quantity determination module, used to determine the actual fuel filling quantity corresponding to the target unmanned vehicle based on the effective refueling duration and a pre-calibrated rated flow rate of the fuel dispenser.

[0009] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the fuel filling quantity determination method provided in any embodiment of the present invention.

[0010] The technical solution of this invention solves the problem that fuel dispensing methods based on liquid level sensors and industrial cameras cannot accurately determine the actual fuel dispensing amount at low cost. It involves collecting sound signals of the refueling process corresponding to the target unmanned vehicle (UAV) when the refueling trigger condition is met; determining the effective refueling time based on the sound signals; and determining the actual fuel dispensing amount based on the effective refueling time and the pre-calibrated rated flow rate of the fuel dispenser. This method can accurately identify abnormal operating conditions such as mid-process refueling stops, abnormal starts / stops, and fuel theft without increasing labor costs, ensuring the accuracy of the actual fuel dispensing amount.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a method for determining fuel filling amount according to Embodiment 1 of the present invention.

[0014] Figure 2 This is a flowchart of another method for determining fuel filling amount provided in Embodiment 2 of the present invention.

[0015] Figure 3 This is a flowchart of another method for determining fuel filling amount provided in Embodiment 3 of the present invention.

[0016] Figure 4 This is a schematic diagram of a fuel filling quantity determination device provided in Embodiment 4 of the present invention.

[0017] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] Example 1 Figure 1This is a flowchart of a method for determining fuel filling quantity according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the fuel filling quantity is determined. The method can be executed by a fuel filling quantity determining device, which can be implemented in hardware and / or software and can be configured in an electronic device such as a computer.

[0021] like Figure 1 As shown, this embodiment discloses a method for determining the amount of fuel to be added, including steps S110-S130.

[0022] S110. When the target unmanned vehicle reaches the refueling trigger condition, the sound signal of the refueling process corresponding to the target unmanned vehicle is collected by the sound pickup device.

[0023] In this embodiment, the target unmanned vehicle can be understood as an autonomous vehicle that requires automatic refueling and simultaneously measures the amount of fuel added, such as an unmanned mining truck in an open-pit mine. The refueling trigger condition can be understood as the conditions under which a refueling operation is initiated for the target unmanned vehicle, such as the target unmanned vehicle being within a predefined compliant refueling area, the target unmanned vehicle being in a stable, stationary state, the target unmanned vehicle being in an off state, and the fuel tank cap of the target unmanned vehicle being open. The sound pickup device can be understood as a sound signal acquisition device deployed based on the unmanned vehicle's operating scenario. For example, when the unmanned vehicle's operating scenario is a non-fixed refueling station, a four-microphone linear array can be deployed on the target unmanned vehicle as the sound pickup device; when the unmanned vehicle's operating scenario is a fixed refueling station with a limited budget, a single-channel industrial-grade explosion-proof microphone can be deployed on the target unmanned vehicle as the sound pickup device; when the unmanned vehicle's operating scenario is a special mining scenario with high methane and extremely high explosion-proof requirements, a fiber optic microphone can be deployed on the target unmanned vehicle as the sound pickup device. The refueling process sound signal can be understood as the sound signal used to reflect the sound during the operation of the refueling machine.

[0024] Specifically, this step involves monitoring whether the target autonomous vehicle has met the refueling trigger condition. If so, a refueling operation is initiated for the target autonomous vehicle, and the corresponding audio signal of the refueling process is collected using a microphone. If not, the process returns to the previous step of monitoring whether the target autonomous vehicle has met the refueling trigger condition.

[0025] For example, suppose the refueling trigger condition includes four sub-conditions: the target unmanned vehicle is within a predefined compliant refueling area, the target unmanned vehicle is in a stable, stationary state, the target unmanned vehicle is in an off state, and the target unmanned vehicle's fuel tank cap is open. To verify the first sub-condition, the target unmanned vehicle's global navigation satellite position and the corresponding geofence to the compliant refueling area can be obtained. If the global navigation satellite position is within the geofence, the first sub-condition is satisfied. To verify the second sub-condition, the target unmanned vehicle's speed and braking status can be obtained. If the speed is 0 and braking has been triggered, the target unmanned vehicle is in a stable, stationary state, thus satisfying the second sub-condition. To verify the third sub-condition, it can be determined whether the target unmanned vehicle is in an off state. If the target unmanned vehicle is in an off state, the third sub-condition is satisfied. To verify the fourth sub-condition, it can be determined whether the target unmanned vehicle's fuel tank cap is open. If the target unmanned vehicle's fuel tank cap is open, the fourth sub-condition is satisfied. Furthermore, when all four sub-conditions are met simultaneously, the target unmanned vehicle is determined to have reached the refueling trigger condition.

[0026] S120. Based on the sound signals during the refueling process, determine the effective refueling time for the target unmanned vehicle.

[0027] Effective refueling time can be understood as the purely effective refueling time during the refueling process.

[0028] In one specific implementation, for scenarios with extremely low edge computing power, the start and end times of refueling can be determined based on the sound signals during the refueling process. Then, based on these start and end times, the total refueling time for the target autonomous vehicle can be determined. Next, periods of interruption and sudden abnormal noise can be removed from the total refueling time to obtain the refueling time to be corrected. Finally, the start and end times of the refueling time to be corrected can be adjusted for refueling machine response delay to obtain the effective refueling time for the target autonomous vehicle.

[0029] In another specific implementation, for scenarios with sufficient edge computing power, a pre-built refueling time recognition model can be used to process the sound signal during the refueling process to obtain the effective refueling time for the target unmanned vehicle, thereby further improving the accuracy of time recognition in extremely noisy environments. The refueling time recognition model can be understood as an end-to-end lightweight deep learning model.

[0030] Optionally, in order to continuously improve the recognition accuracy and stability in complex environments, the refueling process sound signals after on-site annotation can be continuously collected through a cloud platform, and the refueling time recognition model can be retrained and optimized on a monthly cycle.

[0031] Optionally, determining the effective refueling time for the target unmanned vehicle based on the refueling process sound signal may include: using a four-microphone linear array to locate the sound source based on the refueling process sound signal, generating an acoustic imaging map corresponding to the fuel tank filler neck; spatially matching the energy center position in the acoustic imaging map with the center position of the fuel tank filler neck, and calculating the matching confidence; when the matching confidence is greater than a preset confidence threshold, and the time-frequency characteristics of the collected refueling process sound signal match the preset refueling sound signature characteristics, determining to enter the refueling time detection state; in the refueling time detection state, determining the effective refueling time for the target unmanned vehicle based on the refueling process sound signal.

[0032] Specifically, when the spatial matching degree between the energy center location and the refueling nozzle center location is greater than a preset matching degree threshold, the matching confidence degree is greater than a preset confidence degree threshold, and the time-frequency characteristics of the collected refueling process sound signal conform to the preset refueling sound signature characteristics, the system is determined to enter the refueling duration detection state. The preset refueling sound signature characteristics are standard acoustic feature templates for refueling sound sources that are pre-constructed and stored offline, composed of time-domain, frequency-domain, and array spatial features of refueling noise, used for on-site sound source type identification. Then, in the refueling duration detection state, the effective refueling duration for refueling the target unmanned vehicle can be determined based on the refueling process sound signal.

[0033] The above settings ensure the availability of the collected audio signals during the refueling process, thereby guaranteeing the accuracy of the effective refueling time and providing a basis for accurately determining the actual fuel amount added.

[0034] S130. Based on the effective refueling time and the pre-calibrated rated flow rate of the fuel dispenser, determine the actual fuel amount corresponding to the target unmanned vehicle.

[0035] In this step, specifically, the standard measuring instrument method can be used to repeatedly calibrate the fuel dispenser more than 10 times to obtain a stable rated flow rate. Then, the formula can be directly applied. Determine the actual fuel refueling amount corresponding to the target unmanned vehicle. Among these, This refers to the actual amount of fuel added. The rated flow rate of the fuel dispenser, For effective refueling time.

[0036] Alternatively, for target unmanned vehicles without liquid level sensors, after determining the estimated fuel refueling amount based on the effective refueling time and the rated flow rate of the fuel dispenser, the validity of the estimated fuel refueling amount can be determined using the cumulative fuel consumption data from the vehicle's fuel consumption metering system and the vehicle weight change data before and after refueling collected by a weighbridge. If the estimated fuel refueling amount is valid, it is used as the actual fuel refueling amount for the target unmanned vehicle. An alarm is triggered if the estimated fuel refueling amount is invalid.

[0037] The technical solution of this embodiment solves the problem that fuel dispensing methods based on liquid level sensors and industrial cameras cannot accurately determine the actual fuel dispensing amount at low cost. It involves collecting sound signals of the refueling process corresponding to the target unmanned vehicle when the refueling trigger condition is met; determining the effective refueling time based on the sound signals; and determining the actual fuel dispensing amount corresponding to the target unmanned vehicle based on the effective refueling time and the pre-calibrated rated flow rate of the fuel dispenser. This approach addresses the issue that fuel dispensing measurement schemes based on liquid level sensors and industrial cameras cannot accurately determine the actual fuel dispensing amount at low cost. It can accurately identify abnormal operating conditions such as mid-process refueling stops, abnormal starts / stops, and fuel theft without increasing labor costs, ensuring the accuracy of the actual fuel dispensing amount.

[0038] Example 2 Figure 2 This is a flowchart of another method for determining fuel refueling quantity according to Embodiment 2 of the present invention. This embodiment is a further optimization and extension based on the above embodiments and can be combined with various optional technical solutions in the above embodiments.

[0039] like Figure 2 As shown, this embodiment discloses a method for determining the amount of fuel to be added, including steps S210-S270.

[0040] S210. When the target unmanned vehicle reaches the refueling trigger condition, the sound signal of the refueling process corresponding to the target unmanned vehicle is collected by the sound pickup device.

[0041] Optionally, the sound pickup device is a four-microphone linear array. Before acquiring the refueling process sound signal corresponding to the target unmanned vehicle through the sound pickup device, the method further includes: obtaining the location information of the fuel tank filler neck on the target unmanned vehicle; based on the location information, arranging the four-microphone linear array at a set distance from the outside of the fuel tank filler neck; controlling the sound beam emission port of the four-microphone linear array to be aligned with the outside of the fuel tank filler neck, so as to acquire the refueling process sound signal corresponding to the target unmanned vehicle through the sound beam emitted by the sound beam emission port.

[0042] For example, a four-microphone linear array can be fixedly installed 10-20cm outside the fuel tank filler neck, and the pickup beam emitter of the four-microphone linear array can be controlled to be aligned with the outside of the fuel tank filler neck, so that the pickup beam emitted by the pickup beam emitter is perpendicular to the fuel dispenser outlet, thereby collecting the sound signal of the refueling process when the fuel dispenser refuels the target unmanned vehicle through the pickup beam direction.

[0043] Optionally, after the four-microphone linear array is fixedly installed, beamforming calibration can be performed on the four-microphone linear array to ensure that the pickup beam is accurately focused on the fuel dispenser outlet and to shield noise from non-target directions.

[0044] S220. The minimum variance distortionless response beamforming algorithm is used to perform first-level noise reduction on the sound signal during the refueling process to obtain a first-level noise-reduced sound signal.

[0045] In this step, specifically, when the sound pickup device is a four-microphone linear array, the acquired four parallel refueling process sound signals can be processed by analog-to-digital conversion, frame windowing, pre-emphasis, and minimum variance distortionless response beamforming to obtain a first-level noise-reduced sound signal.

[0046] S230. Adaptive spectral subtraction is used to denoise the first-level noise-reduced audio signal to obtain the second-level noise-reduced audio signal.

[0047] S240. Based on the secondary noise reduction sound signal, determine the effective refueling time for refueling the target unmanned vehicle.

[0048] In one example, the start and end times of refueling can be determined based on a level-two noise-reduced audio signal. Then, based on these start and end times, the effective refueling time for the target autonomous vehicle can be determined. Next, periods of interruption and sudden abnormal noise can be removed from the total refueling time to obtain the refueling time to be corrected. Finally, the start and end times of the refueling time to be corrected can be adjusted for fuel dispenser response delay to obtain the effective refueling time for the target autonomous vehicle.

[0049] In another example, features can be extracted from the secondary noise-reduced audio signal to obtain time-domain and frequency-domain feature values ​​corresponding to the secondary noise-reduced audio signal. Then, based on the time-domain and frequency-domain feature values, the refueling start and end times can be determined. Finally, based on the refueling start and end times, the effective refueling duration for the target autonomous vehicle can be determined.

[0050] The advantage of this setup is that by first performing noise reduction on the refueling process sound signal, a narrow beam can be formed that suppresses ambient noise in all directions outside the beam, improves the signal-to-noise ratio by more than 20dB, and points towards the refueling nozzle. By then performing second-level noise reduction on the narrow beam, residual background noise can be further eliminated, and a pure refueling sound signal can be extracted, thereby significantly improving the accuracy of determining the effective refueling time.

[0051] S250, based on the effective refueling time and the pre-calibrated rated flow rate of the fuel dispenser, determines the estimated amount of fuel to be dispensed for the target unmanned vehicle.

[0052] In this step, specifically, the effective refueling time and the rated flow rate of the fuel dispenser can be multiplied to obtain the estimated amount of fuel to be dispensed for the target unmanned vehicle.

[0053] S260. Obtain the change in fuel tank volume after the target unmanned vehicle terminates refueling, and determine whether the estimated fuel refueling amount is valid based on the change in fuel tank volume.

[0054] In one specific implementation, liquid level data can be collected within 30 seconds after refueling of the target unmanned vehicle, and the average of the liquid level data within 30 seconds can be calculated to obtain the stable liquid level after refueling. Then, based on the stable liquid level after refueling and a predefined liquid level-volume reference table, the volume of the fuel tank after refueling can be determined. To accommodate both regular and irregular fuel tank structures, a liquid level-volume reference table for the entire liquid level range can be obtained through 3D modeling of the fuel tank and actual water filling calibration.

[0055] Next, the fuel tank volume before refueling can be obtained, and the volume after refueling can be subtracted from the volume before refueling to obtain the change in fuel tank volume after the target unmanned vehicle terminates refueling. Finally, the validity of the estimated fuel refueling amount can be determined based on the absolute value of the difference between the change in fuel tank volume and the estimated fuel refueling amount.

[0056] In another specific implementation, to adapt to scenarios where protocol interoperability is not possible, such as older fuel dispensers and mobile refueling vehicles, and to improve the independence and tamper-proof capability of flow data, an industrial-grade explosion-proof flow sensor can be installed at the fuel nozzle outlet to directly collect real-time fuel flow data. This real-time flow data is then used to determine the change in fuel tank volume of the target unmanned vehicle. Finally, the validity of the estimated fuel refueling amount can be determined based on the absolute value of the difference between the change in fuel tank volume and the estimated fuel refueling amount.

[0057] Optionally, determining the validity of the fuel refueling estimate based on the change in fuel tank volume includes: calculating the absolute value of the difference between the change in fuel tank volume and the fuel refueling estimate to obtain the refueling deviation value; calculating the division result between the refueling deviation value and the change in fuel tank volume to obtain the refueling relative deviation rate; and determining the validity of the fuel refueling estimate based on the comparison result between the refueling relative deviation rate and a preset deviation rate threshold.

[0058] Specifically, the relative deviation rate of the injection volume can be determined using the following specific calculation formula: .

[0059] in, The relative deviation rate of the injection volume. Estimate the amount of fuel to be added. This represents the change in fuel tank volume.

[0060] Then, the estimated fuel refueling amount is determined to be valid if the relative deviation rate of the refueling amount is less than or equal to a preset deviation rate threshold. The estimated fuel refueling amount is determined to be invalid if the relative deviation rate of the refueling amount is greater than the preset deviation rate threshold. If the estimated fuel refueling amount is determined to be invalid, it is further determined whether the relative deviation rate of the refueling amount is less than or equal to a preset maximum deviation rate.

[0061] If the relative deviation rate of the refueling amount is less than or equal to the preset maximum deviation rate, the calculated fuel refueling estimate is considered slightly abnormal. In this case, manual review can be triggered, the entire original data is encrypted and retained, and the settlement process begins after the review is passed. If the relative deviation rate of the refueling amount is greater than the preset maximum deviation rate, or if it falls under non-compliant scenarios such as a fuel refueling estimate of 0 or a negative number, the calculated fuel refueling estimate is considered severely abnormal. In this case, the data is deemed invalid, the settlement process is prohibited, and a platform-wide tiered alarm is triggered simultaneously. The preset deviation rate threshold and the preset maximum deviation rate can be determined based on user needs and historical experience. For example, the preset deviation rate threshold and the preset maximum deviation rate can be set to 3% and 5%, respectively.

[0062] S270. When the estimated fuel refueling amount is valid, the estimated fuel refueling amount shall be used as the actual fuel refueling amount corresponding to the target unmanned vehicle.

[0063] Optionally, after determining the actual fuel refueling amount corresponding to the target unmanned vehicle, the actual fuel refueling amount, as well as information such as the refueling process sound signals and changes in fuel tank volume related to the calculation process of the actual fuel refueling amount, can be backed up locally and in the cloud. Tampering is prohibited within a storage period of more than or equal to 6 months, supporting full traceability and verification at any time, thus avoiding the risk of fraud from the root.

[0064] The technical solution of this embodiment employs a minimum variance distortionless response beamforming algorithm to perform primary noise reduction on the refueling process sound signal, obtaining a primary noise-reduced sound signal. Adaptive spectral subtraction is then used to further reduce the noise of the primary noise-reduced sound signal, resulting in a secondary noise-reduced sound signal. Based on the secondary noise-reduced sound signal, the effective refueling time for the target unmanned vehicle is determined. This effectively suppresses ambient noise from non-target directions, ensuring accurate extraction of the refueling sound signal in the complex noise environment of open-pit mines, providing a foundation for accurate calculation of the fuel refueling amount. Secondly, based on the effective refueling time and the pre-calibrated rated flow rate of the refueling machine, the estimated fuel refueling amount corresponding to the target unmanned vehicle is determined. The change in fuel tank volume after the target unmanned vehicle terminates refueling is obtained, and the validity of the estimated fuel refueling amount is determined based on this change. When the estimated fuel refueling amount is valid, it is used as the actual fuel refueling amount corresponding to the target unmanned vehicle. This achieves high-precision, high-reliability, anti-cheating, and fully automated fuel refueling measurement, perfectly adapting to the harsh working conditions of open-pit mines and the unmanned operation requirements of unmanned mining trucks.

[0065] Example 3 Figure 3 This is a flowchart of another method for determining fuel refueling quantity according to Embodiment 3 of the present invention. This embodiment is a further optimization and extension based on the above embodiments and can be combined with various optional technical solutions in the above embodiments.

[0066] like Figure 3 As shown, this embodiment discloses a method for determining the amount of fuel to be added, including steps S310-S3100.

[0067] S310. When the target unmanned vehicle reaches the refueling trigger condition, the sound signal of the refueling process corresponding to the target unmanned vehicle is collected by the sound pickup device.

[0068] S320. Extract features from the sound signal during the refueling process to obtain the time-domain and frequency-domain feature values ​​corresponding to the sound signal during the refueling process.

[0069] In this embodiment, time-domain features may include short-time energy and short-time zero-crossing rate, while frequency-domain features may include 12-dimensional Mel frequency cepstral coefficients, spectral centroid, and spectral flatness.

[0070] For example, when the sound pickup device is a four-microphone linear array, feature extraction can be performed on the four collected refueling process sound signals to obtain time-domain feature values ​​and frequency-domain feature values ​​that correspond to the four refueling process sound signals.

[0071] S330. If the time domain feature value and the frequency domain feature value both exceed the preset maximum threshold, and the time length exceeding the preset maximum threshold reaches the first set duration, then the system time when the first time the preset maximum threshold is exceeded to the first set duration is recorded as the start time of the refueling event.

[0072] In this embodiment, the first set duration can be understood as a duration set based on user needs and historical experience. The preset maximum threshold can be understood as a threshold dynamically adjusted based on real-time environmental noise levels.

[0073] For example, when both the time domain feature value and the frequency domain feature value exceed the preset maximum threshold at the same time, and the time length exceeding the preset maximum threshold reaches 500ms, the system time that first exceeds the preset maximum threshold by 500ms can be recorded as the start time of the refueling event.

[0074] S340. After the start of the refueling event, determine whether the sound signal during the refueling process is interrupted. If so, execute S350; otherwise, execute S380.

[0075] In this step, specifically, since the refueling machine follows the state transition rule of "dormant state - waiting to be triggered state - refueling state - paused state - end state", it can determine whether the sound signal of the refueling process is interrupted after the start of the refueling event, that is, in the refueling state.

[0076] S350: Determine whether the interruption duration of the sound signal during the refueling process exceeds the predefined interruption duration threshold. If yes, execute S360; otherwise, execute S370.

[0077] In this embodiment, the interruption duration threshold can be understood as a duration threshold set based on user needs and historical experience.

[0078] For example, if the sound signal is interrupted during refueling, it can be determined whether the interruption duration exceeds 3 seconds. If so, the refueling machine is considered to be in an "end" state, and the actual refueling termination time can be recorded. If not, the refueling machine is considered to be in a "paused" state, and the timer can be paused.

[0079] S360: The signal interruption time of the refueling process sound signal is taken as the actual refueling termination time, and the effective refueling time for refueling the target unmanned vehicle is determined based on the start time of the refueling event and the actual refueling termination time.

[0080] In this step, specifically, if the interruption duration of the audio signal during refueling exceeds the interruption duration threshold, the signal interruption time can be taken as the actual refueling termination time. Then, the effective refueling time for the target unmanned vehicle can be obtained by subtracting the refueling event start time from the actual refueling termination time.

[0081] S370. Based on multiple refueling start times and multiple refueling end times, determine the effective refueling time for refueling the target unmanned vehicle.

[0082] In this step, specifically, since the time intervals between the initial refueling start time and the initial signal interruption time, as well as the time intervals between the second refueling start time and the second signal interruption time / refueling termination time, are all valid time intervals, the effective refueling time for refueling the target unmanned vehicle can be obtained by summing the duration between the refueling event start time and the signal interruption time, and the duration between the second refueling start time and the second refueling termination time, provided that the sound signal is interrupted only once during the refueling process.

[0083] In cases where the sound signal is interrupted multiple times during the refueling process, the duration between the initial refueling start time and the initial signal interruption time, the duration between the second refueling start time and the second signal interruption time, and the duration between multiple refueling start times and multiple refueling termination times are accumulated to obtain the effective refueling time for refueling the target unmanned vehicle.

[0084] Optionally, after determining whether the interruption duration of the refueling process sound signal exceeds a predefined interruption duration threshold, the method further includes: if the interruption duration of the refueling process sound signal does not exceed the predefined interruption duration threshold, then the start time of the refueling event is taken as the first refueling start time, the signal interruption time of the refueling process sound signal is taken as the first refueling termination time, and a first refueling duration corresponding to the target unmanned vehicle is determined based on the first refueling start time and the first refueling termination time; if the refueling process sound signal is not interrupted again, a second refueling start time and a second refueling termination time corresponding to the target unmanned vehicle are obtained; a second refueling duration corresponding to the target unmanned vehicle is determined based on the second refueling start time and the second refueling termination time; if the sum of the first refueling duration and the second refueling duration does not exceed the rated refueling duration, then the sum of the first refueling duration and the second refueling duration is taken as the effective refueling duration for refueling the target unmanned vehicle; the rated refueling duration is the time required to fill the fuel tank of the target unmanned vehicle from empty to full at a preset calibrated flow rate; if the sum of the first refueling duration and the second refueling duration exceeds the rated refueling duration, then an abnormal refueling duration prompt message is sent to the user.

[0085] Specifically, the first refueling end time and the first refueling start time can be subtracted to obtain the first refueling duration corresponding to the target unmanned vehicle. Then, the second refueling end time and the second refueling start time can be subtracted to obtain the second refueling duration corresponding to the target unmanned vehicle. Finally, the first and second refueling durations are added together. If the sum of the first and second refueling durations does not exceed the rated refueling duration, then both the first and second refueling durations are considered to be within the rated refueling duration limit, and the sum can be used as the valid refueling duration for refueling the target unmanned vehicle. If the sum of the first and second refueling durations exceeds the rated refueling duration, then the refueling duration is considered abnormal, and an abnormal refueling duration warning message can be sent to the user.

[0086] Optionally, the timing can be automatically resumed when the signal is restored and five consecutive frames meet the refueling characteristics, and the resumed timing time can be used as the second refueling start time, thus perfectly adapting to the complex scenario of stopping the nozzle and re-inserting it during refueling.

[0087] S380 When the time domain feature value and the frequency domain feature value are both lower than the preset minimum threshold, and the time length of time that is lower than the preset minimum threshold reaches the second set duration, the system time that first falls below the preset minimum threshold for the second set duration is recorded as the end time of the refueling event.

[0088] In this embodiment, the second set duration can be understood as a duration set based on user needs and historical experience. The preset minimum threshold can be understood as a threshold dynamically adjusted based on real-time environmental noise.

[0089] For example, when both the time domain feature value and the frequency domain feature value are lower than a preset minimum threshold, and the time length of time that is lower than the preset minimum threshold reaches 1 second, the system time that is lower than the preset minimum threshold for the first time for 1 second can be recorded as the end time of the refueling event.

[0090] S390. Based on the start time and end time of the refueling event, determine the effective refueling duration for refueling the target unmanned vehicle.

[0091] In this step, specifically, the subtraction operation can be performed between the end time and the start time of the refueling event to obtain the effective refueling time for refueling the target unmanned vehicle.

[0092] S3100 determines the actual fuel dispensing amount corresponding to the target unmanned vehicle based on the effective refueling time and the pre-calibrated rated flow rate of the fuel dispenser.

[0093] The technical solution of this embodiment extracts features from the refueling process sound signal to obtain time-domain and frequency-domain feature values ​​corresponding to the refueling process sound signal; the moment when both the time-domain and frequency-domain feature values ​​continuously exceed a preset maximum threshold for a first set duration is taken as the start time of the refueling event; after the start time of the refueling event, it is determined whether the refueling process sound signal is interrupted; if so, if the interruption duration of the refueling process sound signal exceeds the interruption duration threshold, the signal interruption time of the refueling process sound signal is taken as the actual refueling termination time, and based on the refueling event start time and the actual refueling termination time, the effective refueling duration for refueling the target unmanned vehicle is determined; during the interruption of the refueling process sound signal... If the duration does not exceed the interruption duration threshold, the effective refueling duration for refueling the target unmanned vehicle is determined based on multiple refueling start times and multiple refueling end times. Otherwise, the moment when both the time domain feature value and the frequency domain feature value are lower than the preset minimum threshold for the second consecutive set duration is taken as the refueling event termination time. The effective refueling duration for refueling the target unmanned vehicle is determined based on the refueling event start time and the refueling event termination time. Based on the effective refueling duration and the pre-calibrated rated flow rate of the fuel dispenser, the technical means of determining the actual fuel dispensing amount corresponding to the target unmanned vehicle can accurately identify the refueling start and end times, and perfectly adapt to complex refueling scenarios such as mid-process stoppages and re-insertion of the nozzle, thus eliminating missed judgments and misjudgments from the source.

[0094] To illustrate the fuel dispensing quantity determination method and its effects in this invention, a fuel dispensing quantity determination system applied to unmanned mining trucks in open-pit mines is used as an example. This system employs a five-layer edge-cloud collaborative architecture: an on-board perception layer, an edge computing layer, a refueling machine data interface layer, a multi-source verification layer, and a cloud management layer. Specifically, the on-board perception layer includes a directional sound acquisition unit, an on-board status acquisition unit, a liquid level data acquisition unit, a vehicle positioning unit, and a refueling port status detection unit. The directional sound acquisition unit is used to arrange a four-microphone linear array 10-20cm away from the fuel tank refueling port and control the microphone beam emitter of the array to align with the refueling machine's outlet. This allows the sound signal of the refueling process as the refueling machine refuels the target unmanned vehicle to be acquired through the emitted sound beam. The on-board status acquisition unit interfaces with the unmanned mining truck's controller area network (CAN) bus to collect vehicle operation data such as truck speed, parking status, engine speed, and braking status to verify whether the truck meets the refueling trigger conditions. The liquid level data acquisition unit interfaces with the existing float / ultrasonic liquid level sensor in the mining truck's fuel tank to collect stable liquid level data before and after refueling, thereby determining the validity of the estimated fuel filling amount. The vehicle positioning unit collects real-time location data of the mining truck to determine if it is within a preset compliant refueling area, verifying whether the truck has met the refueling trigger conditions. The fuel filler cap status detection unit uses a contact-type industrial sensor to detect the opening and closing status of the fuel filler cap, verifying whether the truck has met the refueling trigger conditions.

[0095] The edge computing layer includes a sound preprocessing unit, a refueling event recognition unit, an effective duration calculation unit, and a local metering unit. The sound preprocessing unit performs multi-level noise reduction on the refueling process sound signal to obtain a two-level noise-reduced sound signal. The refueling event recognition unit extracts the time-domain and frequency-domain feature values ​​from the two-level noise-reduced sound signal and determines the start and end times of the refueling event based on these feature values. The effective duration calculation unit accumulates the pure effective refueling time during the refueling process, removes interruptions and sudden abnormal noise segments, and corrects for the start and end times based on the fuel dispenser response delay, ultimately outputting an accurate effective refueling time. The local metering unit combines the effective refueling time with the pre-calibrated rated flow rate of the fuel dispenser to calculate the estimated fuel refueling volume. When the network is offline, the entire data is stored locally, and automatically uploaded to the cloud upon reconnection to ensure no data loss.

[0096] The fuel dispenser data interface layer is used to calibrate fuel dispensers using a standard measuring instrument method: under rated operating pressure, the fuel dispenser is continuously dispensed for a fixed duration, and the actual dispensing volume is measured using a high-precision standard measuring instrument to calculate the actual calibrated flow rate; each fuel dispenser is calibrated ≥10 times, and the average value is taken as the final calibrated flow rate, ensuring that the relative calibration error is ≤±0.5%. The fuel dispenser data interface layer is also used to perform a monthly flow rate calibration of the fuel dispensers, updating the calibration values ​​and preventing flow rate drift caused by fuel dispenser wear.

[0097] Multi-source verification layer: Adopting an edge-cloud collaborative deployment mode, it communicates with the edge computing layer and the vehicle perception layer to calculate the change in fuel tank volume based on the liquid level data before and after refueling, cross-verifies the refueling amount with the sound meter, and automatically determines the validity of the fuel refueling estimate through three-level verification rules. At the same time, it realizes scenario compliance verification and full-link anti-fraud verification.

[0098] Cloud-based management layer: Deployed on the mine's private / public cloud platform, it communicates with the edge computing layer and multi-source verification layer for full data storage and traceability, automatic generation of settlement statements, real-time monitoring of operational status, graded alarms for abnormal events, and iterative optimization of identification models.

[0099] The advantages of this setup are threefold: First, by directionally collecting the sound signals of the refueling process when the fuel dispenser refuels the target unmanned vehicle, the start and end times of the refueling event and the effective refueling duration can be accurately identified. Combined with the fuel dispenser's rated flow rate, the fuel dispensing amount can be calculated, fundamentally solving the core pain points of existing liquid level sensor solutions being insufficiently accurate due to bumps and vibrations, and visual solutions being easily forged. Second, by using a four-microphone linear array with minimum variance distortion-free response beamforming for directional sound pickup, combined with adaptive spectral subtraction for secondary noise reduction, strong suppression of environmental noise from non-target directions is achieved, ensuring accurate extraction of refueling sound signals in the complex noise environment of open-pit mines. Third, by setting three-level verification rules to automatically determine the validity of metering data, and combining scenario compliance verification and full data encryption with dual backup traceability, the problems of weak anti-fraud capabilities and insufficient settlement compliance in existing solutions are completely solved. Finally, through a multi-condition joint triggering mechanism based on vehicle status, location, and fuel dispenser status, the entire refueling metering process is completed without human intervention, perfectly adapting to the operational scenario of automatic refueling for unmanned mining trucks, solving the pain points of existing visual solutions being complex to operate and unable to adapt to unmanned operations.

[0100] Example 4 Figure 4 This is a schematic diagram of a fuel filling quantity determination device according to Embodiment 4 of the present invention. This embodiment is applicable to the situation of determining the fuel filling quantity. The fuel filling quantity determination device can be implemented in hardware and / or software and can be configured in electronic devices such as computers.

[0101] like Figure 4 As shown, the fuel filling quantity determination device disclosed in this embodiment includes a sound signal acquisition module 41, a refueling time determination module 42, and a filling quantity determination module 43.

[0102] Among them, the sound signal acquisition module 41 is used to acquire the refueling process sound signal corresponding to the target unmanned vehicle through the sound pickup device when the target unmanned vehicle reaches the refueling trigger condition.

[0103] The refueling duration determination module 42 is used to determine the effective refueling duration for the target unmanned vehicle based on the sound signals during the refueling process.

[0104] The refueling quantity determination module 43 is used to determine the actual fuel refueling quantity corresponding to the target unmanned vehicle based on the effective refueling time and the pre-calibrated rated flow rate of the refueling machine.

[0105] The technical solution in this embodiment, through the cooperation of the sound signal acquisition module 41, the refueling time determination module 42, and the refueling quantity determination module 43, solves the problem that neither the fuel refueling quantity measurement scheme based on the liquid level sensor nor the fuel refueling quantity measurement scheme based on the industrial camera can accurately determine the actual fuel refueling quantity at low cost. It can accurately identify abnormal operating conditions such as mid-refueling stoppage, abnormal start-stop, and fuel theft without increasing labor costs, thus ensuring the accuracy of the actual fuel refueling quantity.

[0106] Optionally, the device also includes a sound pickup device arrangement module, which is used to: acquire the location information of the fuel tank filler neck on the target unmanned vehicle; arrange a four-microphone linear array at a set distance from the outside of the fuel tank filler neck based on the location information; and control the sound pickup beam transmitter of the four-microphone linear array to be aligned with the outside of the fuel tank filler neck, so as to collect the sound signal of the refueling process corresponding to the target unmanned vehicle through the sound pickup beam emitted by the sound pickup beam transmitter.

[0107] Optionally, the refueling time determination module 42 includes a first refueling time determination unit, a second refueling time determination unit, a third refueling time determination unit, a fourth refueling time determination unit, and a fifth refueling time determination unit.

[0108] The first refueling duration determination unit is used to locate the sound source based on the refueling process sound signal using a four-microphone linear array, and generate an acoustic imaging map corresponding to the fuel tank filler neck; spatially match the energy center position in the acoustic imaging map with the center position of the fuel tank filler neck, and calculate the matching confidence; when the matching confidence is greater than a preset confidence threshold, and the time-frequency characteristics of the collected refueling process sound signal match the preset refueling sound signature characteristics, it determines to enter the refueling duration detection state; in the refueling duration detection state, it determines the effective refueling duration for refueling the target unmanned vehicle based on the refueling process sound signal.

[0109] The second refueling duration determination unit is used to perform first-level noise reduction processing on the refueling process sound signal using the minimum variance distortionless response beamforming algorithm to obtain a first-level noise-reduced sound signal; then, it uses adaptive spectral subtraction to further reduce the noise of the first-level noise-reduced sound signal to obtain a second-level noise-reduced sound signal; and finally, based on the second-level noise-reduced sound signal, it determines the effective refueling duration for refueling the target unmanned vehicle.

[0110] The third refueling duration determination unit is used to extract features from the refueling process sound signal to obtain time-domain feature values ​​and frequency-domain feature values ​​corresponding to the refueling process sound signal. If the time-domain feature value and the frequency-domain feature value both exceed a preset maximum threshold, and the time length exceeding the preset maximum threshold reaches a first set duration, then the system time when the first time the preset maximum threshold is exceeded for the first set duration is recorded as the refueling event start time. After the refueling time start time, it is determined whether the refueling process sound signal is interrupted. If not, when the time-domain feature value and the frequency-domain feature value both fall below a preset minimum threshold, and the time length below the preset minimum threshold reaches a second set duration, then the system time when the first time the time falls below the preset minimum threshold for the second set duration is recorded as the refueling event end time. Based on the refueling event start time and the refueling event end time, the effective refueling duration for refueling the target unmanned vehicle is determined.

[0111] The fourth refueling duration determination unit is used to determine whether the interruption duration of the refueling process sound signal exceeds a predefined interruption duration threshold if the refueling process sound signal is interrupted; if the interruption duration of the refueling process sound signal exceeds the predefined interruption duration threshold, the signal interruption time of the refueling process sound signal is taken as the actual refueling termination time; and the effective refueling duration for refueling the target unmanned vehicle is determined based on the refueling event start time and the actual refueling termination time.

[0112] The fifth refueling duration determination unit is used to determine the first refueling start time and the first refueling end time based on the signal interruption time of the refueling process sound signal if the interruption duration of the refueling process sound signal does not exceed a predefined interruption duration threshold. Based on the first refueling start time and the first refueling end time, it determines the first refueling duration corresponding to the target unmanned vehicle. If the refueling process sound signal is not interrupted again, it acquires the second refueling start time and the second refueling end time corresponding to the target unmanned vehicle. Based on the second refueling start time and the second refueling end time, it determines the second refueling duration corresponding to the target unmanned vehicle. If the sum of the first refueling duration and the second refueling duration does not exceed the rated refueling duration, it uses the sum of the first refueling duration and the second refueling duration as the effective refueling duration for refueling the target unmanned vehicle. The rated refueling duration is the time required to fill the fuel tank of the target unmanned vehicle from empty to full at a preset calibrated flow rate. If the sum of the first refueling duration and the second refueling duration exceeds the rated refueling duration, it provides the user with a refueling duration error message.

[0113] Optionally, the fuel filling quantity determination module 43 includes: an estimation quantity determination unit, used to determine the estimated fuel filling quantity corresponding to the target unmanned vehicle based on the effective refueling time and the pre-calibrated rated flow rate of the fuel dispenser; an estimation quantity verification unit, used to obtain the change in fuel tank volume after the target unmanned vehicle terminates refueling, and determine whether the estimated fuel filling quantity is valid based on the change in fuel tank volume; and a fuel filling quantity determination unit, used to take the estimated fuel filling quantity as the actual fuel filling quantity corresponding to the target unmanned vehicle when the estimated fuel filling quantity is valid.

[0114] Optionally, the estimation verification unit is specifically used to: calculate the absolute value of the difference between the change in fuel tank volume and the estimated fuel refueling amount to obtain the refueling amount deviation value; calculate the division result between the refueling amount deviation value and the change in fuel tank volume to obtain the relative deviation rate of refueling amount; and determine whether the estimated fuel refueling amount is valid based on the comparison result between the relative deviation rate of refueling amount and the preset deviation rate threshold.

[0115] The fuel filling quantity determination device provided in this embodiment of the invention can execute the fuel filling quantity determination method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Contents not described in detail in this embodiment can be referred to the descriptions in any method embodiment of this application.

[0116] Example 5 Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement embodiments of the present invention is shown. For example... Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 or a random access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or loaded from storage unit 18 into the random access memory 13. The random access memory 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and random access memory 13 are interconnected via a bus 14. An input / output interface 15 is also connected to the bus 14.

[0117] Multiple components in electronic device 10 are connected to input / output interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0118] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the fuel dispensing quantity determination method.

[0119] In some embodiments, the fuel filler quantity determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of the fuel filler quantity determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the fuel filler quantity determination method by any other suitable means (e.g., by means of firmware).

[0120] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory 12, erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0123] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0124] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0125] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0126] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0127] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining the amount of fuel to be added, characterized in that, The method for determining the fuel filling amount includes: When the target unmanned vehicle reaches the refueling trigger condition, the audio signal of the refueling process corresponding to the target unmanned vehicle is collected by the audio pickup device; Based on the sound signals during the refueling process, the effective refueling time for refueling the target unmanned vehicle is determined; Based on the effective refueling time and the pre-calibrated rated flow rate of the refueling machine, the actual fuel filling amount corresponding to the target unmanned vehicle is determined.

2. The method for determining the fuel filling amount according to claim 1, characterized in that, The sound pickup device is a four-microphone linear array. Before acquiring the refueling process sound signal corresponding to the target unmanned vehicle through the sound pickup device, it also includes: Obtain the location information of the fuel filler neck on the target unmanned vehicle; Based on the location information, the four-microphone linear array is arranged at a set distance from the outside of the fuel tank filler neck; The sound beam transmitter of the four-microphone linear array is controlled to be aimed at the outside of the fuel tank filling port, so as to collect the refueling process sound signal corresponding to the target unmanned vehicle through the sound beam emitted by the sound beam transmitter.

3. The method for determining the fuel filling amount according to claim 2, characterized in that, Based on the sound signals during the refueling process, the effective refueling time for the target unmanned vehicle is determined, including: Based on the sound signal of the refueling process, the sound source is located using the four-microphone linear array, and an acoustic imaging map corresponding to the fuel tank filler neck is generated. Spatially match the energy center position in the acoustic imaging image with the center position of the fuel filler neck of the fuel tank, and calculate the matching confidence level. When the matching confidence level is greater than the preset confidence threshold, and the time-frequency characteristics of the collected refueling process sound signal match the preset refueling soundprint characteristics, it is determined to enter the refueling duration detection state. Under the refueling duration detection state, the effective refueling duration for refueling the target unmanned vehicle is determined based on the sound signal of the refueling process.

4. The method for determining the fuel filling amount according to claim 1, characterized in that, Based on the sound signals during the refueling process, the effective refueling time for the target unmanned vehicle is determined, including: The minimum variance distortionless response beamforming algorithm is used to perform first-level noise reduction on the sound signal of the refueling process to obtain a first-level noise-reduced sound signal. An adaptive spectral subtraction method is used to denoise the first-level noise-reduced audio signal to obtain a second-level noise-reduced audio signal. Based on the secondary noise reduction sound signal, the effective refueling time for refueling the target unmanned vehicle is determined.

5. The method for determining the fuel filling amount according to claim 1, characterized in that, Based on the sound signals during the refueling process, the effective refueling time for the target unmanned vehicle is determined, including: Feature extraction is performed on the sound signal of the refueling process to obtain time-domain feature values ​​and frequency-domain feature values ​​corresponding to the sound signal of the refueling process; If the time domain feature value and the frequency domain feature value both exceed the preset maximum threshold, and the time length for exceeding the preset maximum threshold reaches the first set duration, then the system time when the first time the preset maximum threshold is exceeded to the first set duration is recorded as the start time of the refueling event. After the start of the refueling event, determine whether the audio signal of the refueling process is interrupted; If not, when the time domain feature value and the frequency domain feature value are both lower than the preset minimum threshold, and the time length for which they are lower than the preset minimum threshold reaches the second set duration, the system time when the first time the system time is lower than the preset minimum threshold for the second set duration is recorded as the refueling event termination time. Based on the start time and end time of the refueling event, the effective refueling duration for refueling the target unmanned vehicle is determined.

6. The method for determining the fuel filling amount according to claim 2, characterized in that, After determining whether the audio signal during the refueling process is interrupted, the process further includes: If so, determine whether the interruption duration of the sound signal during the refueling process exceeds a predefined interruption duration threshold; If the interruption duration of the sound signal during the refueling process exceeds a predefined interruption duration threshold, the signal interruption time of the sound signal during the refueling process will be taken as the actual refueling termination time. Based on the start time of the refueling event and the actual end time of the refueling, the effective refueling duration for refueling the target unmanned vehicle is determined.

7. The method for determining the fuel filling amount according to claim 6, characterized in that, After determining whether the interruption duration of the audio signal during the refueling process exceeds a predefined interruption duration threshold, the process further includes: If the interruption duration of the sound signal during the refueling process does not exceed a predefined interruption duration threshold, then the start time of the refueling event is taken as the first refueling start time, the signal interruption time of the sound signal during the refueling process is taken as the first refueling end time, and based on the first refueling start time and the first refueling end time, the first refueling duration corresponding to the target unmanned vehicle is determined. If the sound signal during the refueling process is not interrupted again, obtain the second refueling start time and the second refueling end time corresponding to the target unmanned vehicle; Based on the second refueling start time and the second refueling end time, determine the second refueling duration corresponding to the target unmanned vehicle; If the sum of the first refueling time and the second refueling time does not exceed the rated refueling time, then the sum of the first refueling time and the second refueling time shall be taken as the effective refueling time for refueling the target unmanned vehicle; the rated refueling time is the time to fill the fuel tank of the target unmanned vehicle from empty to full at a preset calibrated flow rate. If the sum of the first refueling time and the second refueling time exceeds the rated refueling time, an abnormal refueling time prompt message will be sent to the user.

8. The method for determining the fuel filling amount according to claim 1, characterized in that, Based on the effective refueling time and the pre-calibrated rated flow rate of the fuel dispenser, the actual fuel dispensing amount corresponding to the target unmanned vehicle is determined, including: Based on the effective refueling time and the pre-calibrated rated flow rate of the fuel dispenser, the estimated amount of fuel to be added corresponding to the target unmanned vehicle is determined. Obtain the change in fuel tank volume after the target unmanned vehicle terminates refueling, and determine whether the estimated fuel refueling amount is valid based on the change in fuel tank volume; When the estimated fuel refueling amount is valid, the estimated fuel refueling amount is used as the actual fuel refueling amount corresponding to the target unmanned vehicle.

9. The method for determining the fuel filling amount according to claim 8, characterized in that, Determining the validity of the estimated fuel refueling amount based on changes in tank volume includes: Calculate the absolute value of the difference between the change in fuel tank volume and the estimated fuel refueling amount to obtain the refueling amount deviation value; The relative deviation rate of the refueling amount is obtained by dividing the refueling amount deviation by the change in tank volume. Based on the comparison between the relative deviation rate of the refueling amount and the preset deviation rate threshold, it is determined whether the estimated fuel refueling amount is valid.

10. A fuel filling quantity determining device, characterized in that, The fuel filling amount determination device includes: The sound signal acquisition module is used to acquire the refueling process sound signal corresponding to the target unmanned vehicle through a sound pickup device when the target unmanned vehicle reaches the refueling trigger condition. The refueling duration determination module is used to determine the effective refueling duration for refueling the target unmanned vehicle based on the sound signals during the refueling process. The refueling quantity determination module is used to determine the actual fuel refueling quantity corresponding to the target unmanned vehicle based on the effective refueling time and the pre-calibrated rated flow rate of the refueling machine.

11. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the fuel filling quantity determination method according to any one of claims 1-9.

Images