Vehicle full load time determination method, device and storage medium

Abstract

The application discloses a kind of vehicle full load time determination method, equipment and storage medium.It includes: when meeting activation condition, the equivalent pressure curve of target vehicle is collected;Determine effective loading event according to equivalent pressure curve, and determine the bucket number count value based on effective loading event;Full load time calculation model is constructed, and the full load time of target vehicle is determined according to full load time calculation model and bucket number count value.Through setting activation condition, the equivalent pressure curve of target vehicle is collected, which can accurately limit data acquisition scene, avoid signal interference of non-loading condition, and guarantee the effectiveness of original data.Through identifying effective loading event and counting bucket number count value, counting can be completed relying on real load change, effectively avoiding the counting deviation caused by empty shovel and material scattering, and improving the statistical precision of loading bucket number;Using full load time calculation model can dynamically calculate the remaining loading time, improve the prediction accuracy, and provide a reliable basis for subsequent scheduling work.

Description

Technical Field

[0001] This invention relates to the field of unmanned mining vehicles, and in particular to a method, device and storage medium for determining the full load time of a vehicle. Background Technology

[0002] Currently, open-pit mines commonly use unmanned mining trucks for material transportation operations. As the core node of the mining truck transportation process, the loading process, including the counting of loading buckets, monitoring of loading progress, and prediction of full load time, is an important foundation for the mine's unmanned intelligent scheduling system.

[0003] Currently, the mainstream loading monitoring and full-load prediction methods in the industry are mainly divided into two categories. One type relies on the excavator to collect action signals such as bucket lifting and unloading to complete the unloading count, and roughly judges the loading progress by combining the preset rated number of buckets. The other type uses the mine car suspension pressure sensor to carry out static weighing verification only after loading is completed, thereby verifying the vehicle's load. Both types of solutions rely on a fixed single-bucket loading cycle to statically estimate the full-load time. Some solutions also combine manual visual judgment to issue a departure command. Overall, the main implementation method is based on single signal acquisition at the equipment end, post-event verification, and static duration estimation.

[0004] In existing technologies, the excavator-side counting cannot determine whether material has actually fallen into the truck bed, and is prone to inflated counts due to empty scooping or material spillage. The weighing scheme can only verify the result after loading is completed, and cannot count the actual number of buckets loaded in real time. At the same time, it only uses static estimation at a fixed period, which cannot adapt to the excavator's operating rhythm and the real-time changes in material density, resulting in low accuracy in predicting the full load time. Summary of the Invention

[0005] This invention provides a method, device, and storage medium for determining the full load time of a vehicle, which solves the technical problems of low counting accuracy, large deviation in full load time prediction, inability to support dynamic intelligent scheduling, high hardware modification costs, and poor adaptability of computing power to complex working conditions in existing open-pit mine unmanned mining truck loading schemes.

[0006] According to one aspect of the present invention, a method for determining the full load time of a vehicle is provided, the method comprising: When the activation conditions are met, the equivalent pressure curve of the target vehicle is collected; The effective loading events are determined based on the equivalent pressure curve, and the number of buckets is determined based on the effective loading events; A full-load time calculation model is constructed, and the full-load time of the target vehicle is determined based on the full-load time calculation model and the number of buckets counted.

[0007] Optionally, the equivalent pressure curve of the target vehicle is acquired, including: acquiring multi-source sensor data of the target vehicle based on a preset sampling frequency, wherein the multi-source sensor data includes pressure data of each hydraulic spring and vehicle status data; performing outlier removal and linear interpolation to complete the multi-source sensor data to obtain the removed data; sequentially performing moving average filtering and wavelet noise reduction on the removed data to obtain each single-path smooth pressure curve; determining the allocation weight according to the load ratio of each hydraulic spring, and performing weighted fusion of each single-path smooth pressure curve based on the allocation weight to obtain the equivalent pressure curve of the target vehicle.

[0008] Optionally, a valid loading event is determined based on the equivalent pressure curve, including: acquiring the initial empty reference pressure of the target vehicle in a stationary state, and obtaining the pre-calibrated minimum pressure threshold per bucket, full-load reference pressure, and rated full-load number of buckets; determining the first steady-state pressure and the second steady-state pressure based on the equivalent pressure curve, and calculating the pressure difference between the second steady-state pressure and the first steady-state pressure; determining the rise of the first steady-state pressure to its peak value within a first specified time period; determining the fall of the peak value back to the second steady-state pressure within a second specified time period; determining the target fluctuation range based on the minimum pressure threshold per bucket; and determining a valid loading event when the rise is greater than or equal to the minimum pressure threshold per bucket, the fall is less than or equal to a specified proportion of the rise, the fluctuation range of the second steady-state pressure is within the target fluctuation range, the duration is greater than or equal to a preset time, and the pressure difference is greater than or equal to a specified proportion of the minimum pressure threshold per bucket.

[0009] Optionally, the bucket count value is determined based on the effective loading event, including: triggering bucket count counting every time a valid loading event is identified; obtaining a preset counting dead time, and not triggering repeated counting of bucket count when a valid loading event occurs within the counting dead time; determining a secondary threshold based on the minimum pressure threshold of a single bucket, and performing a secondary verification on the equivalent pressure curve when the pressure difference exceeds the secondary threshold, and triggering supplementary counting of bucket count when the secondary verification passes; and pausing bucket count counting when vehicle movement or non-loading interference events are detected.

[0010] Optionally, a full-load time calculation model is constructed, including: obtaining the average cycle and sliding average cycle of a single bucket, and determining the current number of buckets loaded based on the bucket count value; calculating the difference between the rated full-load number of buckets and the current number of buckets loaded, and taking the larger value between the bucket count difference and 0 as the remaining number of buckets to be loaded; using the product of the average cycle of a single bucket and the remaining number of buckets to be loaded as the first calculation model; using the product of the sliding average cycle and the remaining number of buckets to be loaded as the second calculation model; and using the first calculation model and the second calculation model as the full-load time calculation model.

[0011] Optionally, the full-load time of the target vehicle is determined based on the full-load time calculation model and the bucket count value, including: when the bucket count value is less than the preset bucket count, the bucket count value is substituted into the first calculation model to determine the base time of the target vehicle; otherwise, the bucket count value is substituted into the second calculation model to determine the base time of the target vehicle; a correction factor is obtained, and the base time is corrected based on the correction factor to obtain the full-load time of the target vehicle, wherein the correction factor includes material density, operation rhythm and full-load correction.

[0012] Optionally, the method further includes: stopping the determination of the full load time of the target vehicle when the hibernation condition is met; wherein the hibernation condition includes any one of the following: the target vehicle leaves the electronic fence of the loading area for a preset departure time, the target vehicle's operating status changes to transportation / unloading / waiting for dispatch, the target vehicle's speed exceeds a preset threshold, the target vehicle's lifting action is triggered, the target vehicle receives a loading completion instruction, and the sensor malfunction reaches a fault threshold.

[0013] Optionally, activation conditions include: the target vehicle remaining in the loading position for a preset duration, the target vehicle being stationary and the parking brake being activated, the target vehicle being in the loading / loading state, and the target vehicle's lifting cylinder being in the lowering lock state.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform a method for determining the full load time of a vehicle as described in any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer storage medium is provided, the computer storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute a method for determining the full load time of a vehicle as described in any embodiment of the present invention.

[0016] The technical solution of this invention, by setting activation conditions to collect the equivalent pressure curve of the target vehicle, can accurately limit the data collection scenario, avoid signal interference in non-loading conditions, and ensure the validity of the original data. By identifying valid loading events and counting the bucket count, counting can be completed based on actual load changes, effectively avoiding counting deviations caused by empty shovels and material spillage, and improving the accuracy of bucket count statistics. By using a full-load time calculation model combined with bucket count values ​​to determine the full-load time, the remaining loading time can be dynamically calculated, improving the accuracy of full-load time prediction and providing a reliable basis for subsequent scheduling work.

[0017] 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

[0018] 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.

[0019] Figure 1 This is a flowchart of a method for determining the full load time of a vehicle according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of another method for determining the full load time of a vehicle according to Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of a vehicle full load time determination device according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements a method for determining the full load time of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0020] 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.

[0021] 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.

[0022] Example 1 Figure 1 This is a flowchart illustrating a method for determining vehicle full-load time according to Embodiment 1 of the present invention. This embodiment is applicable to mining truck transportation scenarios. The method can be executed by a vehicle full-load time determination device, which can be implemented in hardware and / or software. This device can be configured in the original mining truck's unmanned driving domain controller, vehicle control unit (VCU), or other computer controllers. Figure 1 As shown, the method includes: S110. When the activation conditions are met, collect the equivalent pressure curve of the target vehicle.

[0023] The activation condition refers to the multiple judgment conditions for the algorithm to start running. The target vehicle can be an unmanned mining truck in open-pit mining operations. The equivalent pressure curve is a curve reflecting the actual load change of the entire vehicle, obtained by performing multi-level preprocessing on the data from the original oil and gas spring pressure sensors of the mining truck.

[0024] Optionally, activation conditions include: the target vehicle remaining in the loading position for a preset duration, the target vehicle being stationary and the parking brake being activated, the target vehicle being in the loading / loading state, and the target vehicle's lifting cylinder being in the lowering lock state.

[0025] Specifically, the activation conditions are a crucial mechanism to ensure that the algorithm only starts running when the mining truck is in an actual loading operation scenario, and four conditions must be met simultaneously. The first is the location condition, which relies on the mining truck's built-in Real-Time Kinematic-Global Navigation Satellite System (RTK-GNSS) high-precision positioning module to determine whether the target vehicle is within the electronic fence of the loading position in the loading operation area pre-defined by the scheduling system, and whether this stationary state lasts for a preset stationary time, such as 2 seconds. This condition limit can prevent the algorithm from being accidentally triggered when the vehicle briefly passes by or temporarily stops. The second is the vehicle status condition, which requires the target vehicle to be in a completely stationary parking state. This is determined by the data from the vehicle's Controller Area Network (CAN) bus, and must simultaneously meet the following conditions: vehicle speed is 0 km / h, parking brake is engaged, vehicle gear is in neutral, and the status condition must last for a preset duration, such as 2 seconds, to ensure that the vehicle is in a stable loading preparation state, excluding non-loading situations such as driving or not parking. The third condition is the task condition. The algorithm retrieves vehicle task tags from the autonomous driving dispatch system in real time. It is only considered valid when the task status is marked as "awaiting loading" or "loading in progress." This effectively distinguishes between non-loading tasks such as temporary stops, equipment malfunctions, and vehicle maintenance, filtering out interference from a business perspective. The fourth condition is the safety status condition. It monitors the working status and lifting angle of the cargo box lifting cylinder in real time, requiring the cylinder to be fully lowered and locked, and the lifting angle to be 0 degrees. This condition excludes scenarios where the vehicle is unloading or undergoing lifting maintenance, ensuring that the mine car's cargo box is in a normal state capable of receiving materials. Only when all four conditions are simultaneously met and each lasts for a specified duration will the algorithm be activated, beginning subsequent tasks such as identifying the number of loading hoppers and predicting the filling time.

[0026] Optionally, the method further includes: stopping the determination of the full load time of the target vehicle when the hibernation condition is met; wherein the hibernation condition includes any one of the following: the target vehicle leaves the electronic fence of the loading area for a preset departure time, the target vehicle's operating status changes to transportation / unloading / waiting for dispatch, the target vehicle's speed exceeds a preset threshold, the target vehicle's lifting action is triggered, the target vehicle receives a loading completion instruction, and the sensor malfunction reaches a fault threshold.

[0027] The hibernation conditions refer to specific scenarios or state conditions that trigger the algorithm related to determining vehicle full-load time to stop running. When any one of these conditions is met, the algorithm enters hibernation mode. The loading area electronic fence is a virtual geographical boundary defined by the scheduling system to delineate the area where vehicles perform loading operations. It is typically based on high-precision positioning data for area division. The preset departure time is a pre-set threshold for when the algorithm triggers hibernation after the vehicle leaves the loading area electronic fence, ensuring that the vehicle has actually left the loading area and is not merely briefly crossing the boundary. The target vehicle's operational status is the current task status of the vehicle recorded by the scheduling system, including waiting to load, loading, transporting, unloading, and waiting to be scheduled, used to distinguish different operational stages. The preset speed threshold is a speed cutoff value set to determine whether the vehicle is in motion. When the speed exceeds this value, it indicates that the vehicle has left the loading stationary state. The lifting action refers to the operation of lifting the target vehicle's cargo box, typically used for unloading materials. Triggering the lifting action means that the loading operation is complete. The loading completion command is a control command issued by the scheduling system to the target vehicle, indicating that its loading operation has ended. The sensor fault threshold is a critical value that measures the degree of abnormality in sensor data. When the degree of fault exceeds this threshold, the sensor data is unreliable and calculations based on the data must be stopped.

[0028] Specifically, the system starts timing when the high-precision positioning data of the target vehicle shows that it has left the loading area's electronic fence. If the continuous departure time reaches a preset departure duration, such as 3 seconds, the sleep condition is met. Simultaneously, the system can acquire the vehicle's operational status from the dispatch system in real time. If the operational status changes from "pending loading" or "loading" to "transporting," "unloading," or "awaiting dispatch," and this status lasts for a preset duration, such as 2 seconds, the sleep condition is met. Vehicle speed data is collected in real time via the data bus. If the vehicle speed exceeds a preset threshold, such as 5 kilometers per hour, and the duration reaches a preset duration, such as 1 second, the sleep condition is met. The lifting cylinder's lifting angle is monitored. If the lifting angle is greater than 0 degrees, it indicates a lifting action has been triggered, or a loading completion command has been received from the dispatch system. Either of these conditions fulfills the sleep condition. Additionally, the system can monitor sensor fault states in real time, such as open circuits, short circuits, and abnormal data fluctuations. When the sensor fault level reaches a preset fault threshold, the sleep condition is met. When any of the above sleep conditions are met, the algorithm logic related to determining the full load time will immediately stop running, including the number of urns for identification and the calculation of the estimated full load time. At the same time, the algorithm will enter a sleep state and wait to be restarted when the activation conditions are met again.

[0029] In one specific implementation, this application adopts a layered architecture with vehicle-side edge computing as the main component and cloud platform as the auxiliary component. This architecture can fully reuse the original hardware of the mining truck, effectively reducing the cost of adding new equipment. At the same time, it has the advantages of low latency and high reliability. Compared with the existing technology, this solution does not require the addition of excavator-side equipment and loading area vision peripherals. All core computing logic is completed on the local edge side of the mining truck, and it can form a two-way closed loop with the unmanned driving scheduling system and the vehicle control system. The perception layer is based on the original hydraulic spring pressure transmitter of the mining truck, and reuses the original RTK-GNSS positioning module, the vehicle CAN bus, and the vehicle-side communication unit of the unmanned driving dispatch system. Without adding new core perception hardware, it completes the synchronous collection of pressure data, vehicle status data, operation scenario data, and positioning data. The edge computing layer is deployed in the original unmanned driving domain controller of the mining truck or the vehicle VCU. It is mainly responsible for functions such as algorithm lifecycle management, signal preprocessing, bucket number recognition, real-time calculation of estimated filling time, local data storage, and abnormal alarms. All core logic runs locally on the vehicle, and the end-to-end latency is controlled within 100ms. The cloud platform layer is deployed on the mine's private cloud or dispatch center server. It mainly realizes functions such as full operation data storage, algorithm model self-learning iteration, operation data analysis, visualization display, and equipment lifecycle management.

[0030] In an alternative implementation, if the original computing power of the mining truck is limited and cannot support local edge computing logic, the core algorithm can be deployed on an edge computing node near the loading area. The mining truck is only responsible for data collection and instruction execution. Low-latency data transmission is achieved with the help of 5G local area network. The core method logic of the whole solution remains unchanged and can still complete the tasks of identifying the number of hoppers and calculating the full load time.

[0031] S120. Determine the effective loading event based on the equivalent pressure curve, and determine the bucket count value based on the effective loading event.

[0032] Among them, a valid loading event refers to a single loading behavior in which material is actually loaded into the mine car compartment, forming an increase in load. The bucket count value refers to the actual number of buckets loaded by identifying valid loading events. Each time a valid loading event is identified, the count value is incremented by 1. At the same time, the logic to prevent duplicate counting and missing counting is provided to ensure the accuracy of the value.

[0033] Optionally, a valid loading event is determined based on the equivalent pressure curve, including: acquiring the initial empty reference pressure of the target vehicle in a stationary state, and obtaining the pre-calibrated minimum pressure threshold per bucket, full-load reference pressure, and rated full-load number of buckets; determining the first steady-state pressure and the second steady-state pressure based on the equivalent pressure curve, and calculating the pressure difference between the second steady-state pressure and the first steady-state pressure; determining the rise of the first steady-state pressure to its peak value within a first specified time period; determining the fall of the peak value back to the second steady-state pressure within a second specified time period; determining the target fluctuation range based on the minimum pressure threshold per bucket; and determining a valid loading event when the rise is greater than or equal to the minimum pressure threshold per bucket, the fall is less than or equal to a specified proportion of the rise, the fluctuation range of the second steady-state pressure is within the target fluctuation range, the duration is greater than or equal to a preset time, and the pressure difference is greater than or equal to a specified proportion of the minimum pressure threshold per bucket.

[0034] The initial no-load reference pressure is obtained by averaging the equivalent pressure data collected within one second while the vehicle is stationary after algorithm activation. This averages the data and serves as the zero point for the current loading, mitigating baseline drift caused by changes in oil spring temperature, aging, and differences in vehicle no-load conditions. The minimum pressure threshold per bucket is a pre-calibrated static pressure value, representing the minimum pressure change that should occur after one bucket of material falls into the car, used to determine if it constitutes a valid loading event. The full-load reference pressure is a pre-calibrated static pressure value, corresponding to the equivalent pressure at the mine car's rated full load, used to determine if the mine car has reached its full load state. The rated full-load bucket count is a pre-calibrated static value representing the standard number of buckets required to load when the mine car reaches its rated full load. The first steady-state pressure is the pressure value when the equivalent pressure curve is in a stable state before the valid loading event occurs. The second steady-state pressure is the pressure value when the equivalent pressure curve reaches a stable state again after the transient impact and subsequent drop following the valid loading event. The pressure difference is the difference between the second and first steady-state pressures, reflecting the actual load increment brought about by this loading event. The rise rate is the pressure change of the equivalent pressure curve from the first steady-state pressure to the peak value within a first specified time period, i.e., no more than 200 milliseconds. The fall rate is the pressure change of the equivalent pressure curve from the peak value back to the second steady-state pressure within a second specified time period, i.e., no more than 500 milliseconds. The target fluctuation range is determined based on the minimum pressure threshold of a single bucket, and can be ±2% of the minimum pressure threshold of a single bucket, used to determine whether the second steady-state pressure is stable. The specified percentage of the fall rate can be 30% of the rise rate, used to determine whether the fall rate meets the characteristics of an effective loading event. The specified percentage of the pressure difference is 80% of the minimum pressure threshold of a single bucket, used to confirm whether the pressure difference meets the requirements of the effective load increment. The preset time is 300 milliseconds, used to verify whether the second steady-state pressure can be maintained stably, confirming that the material has stabilized in the truck bed. Specifically, after the algorithm is activated, it immediately collects equivalent pressure data within 1 second while the vehicle is stationary. The average value is taken as the initial empty reference pressure for this loading. Simultaneously, it retrieves the pre-statically calibrated minimum pressure threshold per bucket, the full-load reference pressure, and the rated number of buckets for full load from the system. Then, it continuously monitors the equivalent pressure curve to identify the first steady-state pressure before the effective loading event occurs (i.e., the stable pressure value before the impact) and the second steady-state pressure after the impact and subsequent fall (i.e., the new stable pressure value). The pressure difference between the second and first steady-state pressures is calculated. When determining the transient impact rise edge characteristic, the equivalent pressure curve is observed to rise from the first steady-state pressure to its peak value within a first specified time period of no more than 200 milliseconds. The rise amplitude is calculated. If the rise amplitude is greater than or equal to the minimum pressure threshold per bucket, the transient impact rise edge characteristic of the effective loading event is satisfied. When determining the steady-state characteristics of the load drop, observe the equivalent pressure curve from its peak to the second steady-state pressure within a second specified time period not exceeding 500 milliseconds. Calculate the drop amplitude. If the drop amplitude is less than or equal to 30% of the rise amplitude, the steady-state characteristics of the effective loading event are met, excluding situations with no continuous load increase, such as empty shovels. When determining the steady-state maintenance characteristics, the target fluctuation range can be determined based on the minimum pressure threshold of a single bucket, which is ±2% of the minimum pressure threshold. Monitor the second steady-state pressure. If its fluctuation range is within the target fluctuation range and the duration is greater than or equal to 300 milliseconds, the steady-state maintenance characteristics are met, verifying that the material has stabilized in the truck bed. When determining the effective load increase characteristics, check whether the pressure difference is greater than or equal to 80% of the minimum pressure threshold of a single bucket. If so, it confirms that the event has led to an increase in effective load.

[0035] In summary, a valid loading event can be determined to have occurred when all the above conditions are met simultaneously: the increase is greater than or equal to the minimum pressure threshold of a single bucket, the decrease is less than or equal to 30% of the increase, the second steady-state pressure fluctuation range is within ±2% of the minimum pressure threshold of a single bucket and the duration is greater than or equal to 300 milliseconds, and the pressure difference is greater than or equal to 80% of the minimum pressure threshold of a single bucket.

[0036] In an alternative implementation, for complex operational scenarios with strong on-site interference, the current time-domain feature recognition scheme can be replaced with a lightweight deep learning model. The model can be trained using massive amounts of labeled loading pressure data to achieve end-to-end intelligent recognition of effective loading events, thereby further improving the recognition accuracy in extreme scenarios.

[0037] Optionally, the bucket count value is determined based on the effective loading event, including: triggering bucket count counting every time a valid loading event is identified; obtaining a preset counting dead time, and not triggering repeated counting of bucket count when a valid loading event occurs within the counting dead time; determining a secondary threshold based on the minimum pressure threshold of a single bucket, and performing a secondary verification on the equivalent pressure curve when the pressure difference exceeds the secondary threshold, and triggering supplementary counting of bucket count when the secondary verification passes; and pausing bucket count counting when vehicle movement or non-loading interference events are detected.

[0038] The counting dead zone time is a time window set to prevent multiple vibrations caused by material impact from a single bucket from being misjudged as multiple buckets. The counting dead zone time can be calibrated based on the excavator's fastest loading cycle, such as 10 seconds. During the counting dead zone time, repeated counting will not be triggered. The secondary threshold is an auxiliary judgment threshold set based on the minimum pressure threshold of a single bucket. It can be 60% of the minimum pressure threshold of a single bucket and is used to detect small incremental load events caused by off-center loading or material spillage, avoiding missed counts.

[0039] Specifically, after identifying a complete valid loading event, the bucket count is immediately incremented to complete the basic count. Simultaneously, the timestamp and single-bucket load increment for this loading are recorded, providing a clear statistical overview of the number of buckets loaded. It's important to note that after an excavator completes a bucket load, there is a mechanical operation interval, and loading will not continue for a short period. Therefore, a counting dead time can be set to prevent residual vibration from a single bucket impact or sensor noise from being mistaken for a new loading event. Each time the bucket count is triggered, the counting dead timer starts immediately. During the dead time, even if the equivalent pressure curve shows a signal matching the characteristics of a valid loading event, the bucket count will not increase until the timer expires. Counting is allowed again after the dead time ends. It should be noted that in actual loading, factors such as uneven loading or material spillage may cause the single-bucket load increment to exceed the secondary threshold but not the primary threshold. In such cases, a secondary verification is required to confirm whether it is a valid load and avoid missed detections. The secondary verification combines the time since the last count, requiring it to exceed the dead zone time and the cumulative load change trend to see if it shows a continuous increase. If the conditions are met, it is determined to be a valid loading event, triggering the bucket count value to be incremented by 1. Finally, false judgment suppression is performed by monitoring the vehicle status in real time. When the vehicle speed is determined to be >5km / h (i.e., the vehicle is moving) through CAN bus data, or when a non-loading interference event is identified through pressure signal characteristics, the bucket count value is immediately paused. The counting logic is restarted only after the vehicle returns to a stationary parking state, the vehicle speed is 0km / h, the parking brake is engaged, the gear is in neutral, and the interference event has ended.

[0040] S130. Construct a full-load time calculation model, and determine the full-load time of the target vehicle based on the full-load time calculation model and the bucket count value.

[0041] The full-load time calculation model is a calculation model that integrates static calibration parameters and real-time dynamic data. Based on the remaining number of buckets to be loaded and the loading cycle of a single bucket, it adds multiple correction factors such as material density, excavator operation rhythm, and load ratio to dynamically calculate the remaining time for a vehicle to reach full load. Full-load time refers to the estimated time from the first effective loading event to the vehicle reaching its rated load or full-load benchmark pressure. Through real-time dynamic correction by the full-load time calculation model, it provides the dispatching system with a decision-making basis for "loading as soon as the vehicle arrives and leaving immediately after loading."

[0042] Optionally, a full-load time calculation model is constructed, including: obtaining the average cycle and sliding average cycle of a single bucket, and determining the current number of buckets loaded based on the bucket count value; calculating the difference between the rated full-load number of buckets and the current number of buckets loaded, and taking the larger value between the bucket count difference and 0 as the remaining number of buckets to be loaded; using the product of the average cycle of a single bucket and the remaining number of buckets to be loaded as the first calculation model; using the product of the sliding average cycle and the remaining number of buckets to be loaded as the second calculation model; and using the first calculation model and the second calculation model as the full-load time calculation model.

[0043] The average cycle time per bucket refers to the average time taken for all effective loading events completed during the current loading process, reflecting the overall loading rhythm. The moving average cycle time refers to the average time taken for the last 3 effective loading events, dynamically reflecting the excavator's latest operating rhythm and being more sensitive to real-time changes. The bucket count is the cumulative number of buckets after identifying effective loading events, which is the current number of buckets loaded. The remaining buckets to be loaded is the difference between the rated full-load bucket count and the current number of buckets loaded; if the difference is negative, it is set to 0. The first calculation model is the full-load time calculated based on the average cycle time per bucket and the remaining buckets to be loaded, reflecting the estimated time under the overall loading rhythm. The second calculation model is the full-load time calculated based on the moving average cycle time and the remaining buckets to be loaded, reflecting the dynamic estimated time under the recent loading rhythm.

[0044] Specifically, firstly, the average cycle per bucket and the moving average cycle are obtained, and the current number of buckets loaded is determined. For each valid loading event identified, the completion timestamp of that bucket is recorded synchronously. The difference between the completion timestamps of two adjacent buckets is the cycle per bucket. The arithmetic mean of the cycle per bucket for all loaded buckets is obtained as the average cycle per bucket. The arithmetic mean of the cycle per bucket for the three most recent buckets is then calculated to obtain the moving average cycle. Next, a first calculation model and a second calculation model are constructed. The first calculation model is obtained by multiplying the average cycle per bucket by the remaining number of buckets to be loaded, and the second calculation model is obtained by multiplying the moving average cycle by the remaining number of buckets to be loaded.

[0045] Optionally, the full-load time of the target vehicle is determined based on the full-load time calculation model and the bucket count value, including: when the bucket count value is less than the preset bucket count, the bucket count value is substituted into the first calculation model to determine the base time of the target vehicle; otherwise, the bucket count value is substituted into the second calculation model to determine the base time of the target vehicle; a correction factor is obtained, and the base time is corrected based on the correction factor to obtain the full-load time of the target vehicle, wherein the correction factor includes material density, operation rhythm and full-load correction.

[0046] The preset number of buckets is a threshold set in the algorithm, which can be 2 buckets. It is used to switch the basic time calculation model. The first calculation model calculates the basic time based on the standard single-bucket loading cycle when the number of loaded buckets is low, i.e., less than the preset number of buckets. The second calculation model calculates the basic time based on the most recent actual loading cycle of multiple buckets when the number of loaded buckets reaches or exceeds the preset number of buckets. The basic time is the estimated remaining loading time before correction, and it is the initial value for calculating the full load time. The correction factors are parameters used to dynamically adjust the basic time, including material density correction factor, operation rhythm correction factor, and full load correction factor.

[0047] Specifically, the first step is to select a base time calculation model based on the bucket counter value. The current bucket counter value is compared with the preset bucket count. If the bucket counter value is less than 2, the first calculation model is used, where the base time equals the remaining buckets to be loaded multiplied by the standard single-bucket loading cycle. The remaining buckets to be loaded are the larger of the maximum value between the rated full-load bucket count and the current loaded bucket count, and 0. This is because the number of loaded buckets is low, resulting in insufficient real-time data; therefore, a pre-calibrated standard single-bucket loading cycle for each material type is used as a benchmark. If the bucket counter value is greater than or equal to 2, the second calculation model is used, where the base time equals the remaining buckets to be loaded multiplied by the moving average cycle of the most recent 3 buckets. This is because the number of loaded buckets is sufficient, and the actual loading cycles of the most recent 3 buckets (the moving average) reflect the current excavator operation rhythm, replacing the static standard cycle and improving real-time performance.

[0048] Furthermore, the base time can be corrected using correction factors. The material density correction factor is a coefficient calculated based on the ratio of the actual average load per bucket to the standard load per bucket, used to adapt to the impact of different types and densities of materials on loading rhythm and load volume. The operation rhythm correction factor is a coefficient generated by combining the recent trends in multi-bucket loading cycles, used to match the fluctuations in loading time caused by the excavator operator's work speed and habits. The full load correction factor is a coefficient set for when the load approaches the rated full load state in the later stages of loading, used to promptly stop timing when the load reaches the target, preventing overloading or deviations in time prediction. By multiplying the base time sequentially by the material density correction factor, operation rhythm correction factor, and full load correction factor, multi-level dynamic corrections are completed, ultimately calculating the precise full load time for the target vehicle.

[0049] In an alternative implementation, if the excavator's operating rhythm exhibits non-linear changes, the existing multi-factor modified linear model can be replaced with a time series prediction model. This model uses historical bucket cycle data from the current loading to predict the subsequent single-bucket loading time, thereby improving the accuracy of full-load time calculation.

[0050] In one specific implementation, this application also achieves standardized two-way interface with the unmanned driving dispatch system, effectively solving the defects of data disconnection and high transmission latency in the existing technology, realizing closed-loop interaction between vehicle-mounted data and the dispatch system, and providing core input for intelligent dispatch. The vehicle-side system uses the CAN bus protocol with a data refresh rate of no less than 10Hz. The vehicle-side system and the cloud-based scheduling system use the Message Queuing Telemetry Transport (MQTT) protocol for encrypted transmission with a real-time data refresh rate of no less than 1Hz. The scheduling system sends data such as the loading area's electronic fence, work task status, material type, and rated full-load capacity to the vehicle-side algorithm. The vehicle-side algorithm uploads data such as loading status, number of loaded buckets, loading start time, cumulative load percentage, full-load time, and abnormal alarms to the scheduling system in real time. The scheduling system plans the arrival time of waiting mining trucks in advance based on the full-load time of multiple mining trucks, realizing "loading as soon as the truck arrives and leaving immediately after loading," eliminating the problems of mining truck queuing and excavator idleness. At the same time, it completes the optimal transportation route planning in advance, so that mining trucks can depart immediately after being fully loaded, eliminating waiting delays and completing a comprehensive upgrade from rigid planned scheduling to dynamic real-time scheduling.

[0051] The technical solution of this invention, by setting activation conditions to collect the equivalent pressure curve of the target vehicle, can accurately limit the data collection scenario, avoid signal interference in non-loading conditions, and ensure the validity of the original data. By identifying valid loading events and counting the bucket count, counting can be completed based on actual load changes, effectively avoiding counting deviations caused by empty shovels and material spillage, and improving the accuracy of bucket count statistics. By using a full-load time calculation model combined with bucket count values ​​to determine the full-load time, the remaining loading time can be dynamically calculated, improving the accuracy of full-load time prediction and providing a reliable basis for subsequent scheduling work.

[0052] Example 2 Figure 2 This is a flowchart of a method for determining the full load time of a vehicle according to Embodiment 2 of the present invention. This embodiment adds a specific process for collecting the equivalent pressure curve of the target vehicle based on Embodiment 1. The specific content of steps S250-S260 is largely the same as steps S120-S130 in Embodiment 1, and therefore will not be repeated in this embodiment. Figure 2 As shown, the method includes: S210. When the activation conditions are met, multi-source sensor data of the target vehicle are collected based on a preset sampling frequency. The multi-source sensor data includes pressure data of each oil spring and vehicle status data.

[0053] The sampling frequency is the number of times data is collected per unit time. It can be 50Hz, which means 50 times of data collection per second, to ensure that the temporal resolution of the data meets the requirements of real-time analysis.

[0054] Specifically, when the activation conditions are met, pressure data from all hydraulic spring pressure sensors on the mining truck and vehicle status data need to be collected synchronously. First, the sampling frequency is set to 50Hz, meaning data is collected every 20ms. Then, real-time pressure values ​​from all hydraulic springs on the mining truck, such as the left and right sides of the front and rear axles, are collected to reflect load changes in each suspension. Additionally, vehicle status data such as vehicle speed, parking brake status, gear position, and lifting angle can be collected via the vehicle's CAN bus for subsequent data synchronization verification, such as determining the validity of data in a stationary state. Finally, data synchronization alignment is performed, with timestamps aligned to all collected data at 10ms granularity to ensure that pressure data and vehicle status data at the same moment correspond and match, providing a unified time reference for subsequent processing.

[0055] In an alternative implementation, for mining trucks that use leaf spring suspension and are not equipped with hydraulic spring pressure sensors, the pressure sensing source can be replaced with a strain gauge load sensor, which is installed between the leaf spring and the frame to collect load strain signals instead of hydraulic spring pressure signals.

[0056] Optionally, activation conditions include: the target vehicle remaining in the loading position for a preset duration, the target vehicle being stationary and the parking brake being activated, the target vehicle being in the loading / loading state, and the target vehicle's lifting cylinder being in the lowering lock state.

[0057] Optionally, the method further includes: stopping the determination of the full load time of the target vehicle when the hibernation condition is met; wherein the hibernation condition includes any one of the following: the target vehicle leaves the electronic fence of the loading area for a preset departure time, the target vehicle's operating status changes to transportation / unloading / waiting for dispatch, the target vehicle's speed exceeds a preset threshold, the target vehicle's lifting action is triggered, the target vehicle receives a loading completion instruction, and the sensor malfunction reaches a fault threshold.

[0058] S220. Perform outlier removal and linear interpolation to complete the multi-source sensor data to obtain the removed data.

[0059] Outlier removal refers to identifying and removing outliers in sensor data caused by faults, interference, etc., such as open circuits, short circuits, and instantaneous spikes, to ensure data reliability. Linear interpolation completion fills the gaps in the data after outlier removal by using the linear relationship between adjacent valid data, ensuring the continuity of the data sequence.

[0060] Specifically, outlier removal is performed first. For example, the 3σ criterion can be used to calculate the mean and standard deviation of the continuous sequence of single-channel oil spring pressure data. When a data point exceeds the range of ±3 times the standard value, it is judged as an outlier, such as a sudden pressure drop caused by sensor open circuit, a sudden pressure rise caused by short circuit, or a spike caused by instantaneous electromagnetic interference. This data point is directly removed. Then, linear interpolation is performed to complete the data. For the missing data positions after outlier removal, linear interpolation is performed using two adjacent valid data points. The formula is y=y1+[(y2-y1)(x-x1)] / (x2-x1), where x is the timestamp, y is the pressure value, and (x1,y1) and (x2,y2) are adjacent valid data points. The completed data sequence will remain continuous, which can avoid the impact of data gaps on subsequent filtering and fusion effects.

[0061] S230. The removed data are then subjected to moving average filtering and wavelet denoising to obtain the smooth pressure curves of each individual channel.

[0062] Moving average filtering is a fundamental time-domain filtering method that smooths curves and removes high-frequency noise, such as interference from engine idling or excavator vibration, by calculating the average value of data within a certain window. Wavelet denoising is a signal processing technique based on wavelet transform. It decomposes the signal into different frequency channels, removes low-frequency baseline drift, such as interference from oil spring temperature changes and micro-vibrations, and retains effective signal characteristics.

[0063] Specifically, when performing moving average filtering, a 5-point moving average window can be used. For each data point, the average of the two data points before and after it (a total of 5 points) is calculated as the filtered result. The purpose of moving average filtering is to remove high-frequency noise, such as engine idling vibration and rapid fluctuations caused by mechanical impact during excavator operation, thus initially smoothing the curve. When performing wavelet denoising, a 3-level decomposition using the db4 wavelet basis function can be used to decompose the signal into approximate components of different frequencies: low frequency and detail components (high frequency). Then, thresholding, such as soft thresholding, is applied to the decomposed detail components to remove low-frequency baseline drift, such as slow pressure shifts caused by changes in oil spring temperature and low-frequency interference from minor vehicle vibrations. Wavelet reconstruction yields the final single-path smooth pressure curve, preserving the transient characteristics of load changes, such as unloading impact, while eliminating noise interference.

[0064] S240. Determine the allocation weight based on the load ratio of each oil spring, and perform weighted fusion of each single-path smooth pressure curve based on the allocation weight to obtain the equivalent pressure curve of the target vehicle.

[0065] Among them, weighted fusion is based on the actual proportion of each oil spring in the vehicle load. For example, the oil spring of the rear axle has a larger load and a higher weight. The single-path smooth pressure curve is weighted and calculated to obtain the equivalent pressure curve that comprehensively reflects the load of the whole vehicle, thus solving the problem of single sensor data distortion caused by unilateral loading and off-center loading.

[0066] Specifically, the first step is to calibrate the load-bearing weight distribution. Based on the mine truck's structural design and static weighing experiments, the load-bearing weight distribution of each pneumatic spring is determined. For example, the rear axle pneumatic spring has a higher load-bearing weight distribution, typically around 30% for the front axle and 70% for the rear axle. Specific values ​​need to be calibrated based on the vehicle model. For instance, if a mine truck has four pneumatic springs—front left, front right, rear left, and rear right—with each side of the rear axle accounting for 35% and each side of the front axle accounting for 15%, then the weights would be 0.15, 0.15, 0.35, and 0.35, respectively. Then, a weighted fusion calculation is performed. The filtered pressure data from each single-path smoothed pressure curve (front left, front right, rear left, and rear right) are weighted and summed according to their respective weights to obtain the equivalent pressure curve of the target vehicle. It can be seen that the final equivalent pressure curve comprehensively reflects the load changes of the entire vehicle, unaffected by factors such as unilateral loading or off-center loading, providing an accurate data foundation for subsequent identification of the number of loading buckets and calculation of load increments.

[0067] S250. Determine the effective loading event based on the equivalent pressure curve, and determine the bucket count value based on the effective loading event.

[0068] Optionally, a valid loading event is determined based on the equivalent pressure curve, including: acquiring the initial empty reference pressure of the target vehicle in a stationary state, and obtaining the pre-calibrated minimum pressure threshold per bucket, full-load reference pressure, and rated full-load number of buckets; determining the first steady-state pressure and the second steady-state pressure based on the equivalent pressure curve, and calculating the pressure difference between the second steady-state pressure and the first steady-state pressure; determining the rise of the first steady-state pressure to its peak value within a first specified time period; determining the fall of the peak value back to the second steady-state pressure within a second specified time period; determining the target fluctuation range based on the minimum pressure threshold per bucket; and determining a valid loading event when the rise is greater than or equal to the minimum pressure threshold per bucket, the fall is less than or equal to a specified proportion of the rise, the fluctuation range of the second steady-state pressure is within the target fluctuation range, the duration is greater than or equal to a preset time, and the pressure difference is greater than or equal to a specified proportion of the minimum pressure threshold per bucket.

[0069] Optionally, the bucket count value is determined based on the effective loading event, including: triggering bucket count counting every time a valid loading event is identified; obtaining a preset counting dead time, and not triggering repeated counting of bucket count when a valid loading event occurs within the counting dead time; determining a secondary threshold based on the minimum pressure threshold of a single bucket, and performing a secondary verification on the equivalent pressure curve when the pressure difference exceeds the secondary threshold, and triggering supplementary counting of bucket count when the secondary verification passes; and pausing bucket count counting when vehicle movement or non-loading interference events are detected.

[0070] S260. Construct a full-load time calculation model, and determine the full-load time of the target vehicle based on the full-load time calculation model and the number of buckets counted.

[0071] Optionally, a full-load time calculation model is constructed, including: obtaining the average cycle and sliding average cycle of a single bucket, and determining the current number of buckets loaded based on the bucket count value; calculating the difference between the rated full-load number of buckets and the current number of buckets loaded, and taking the larger value between the bucket count difference and 0 as the remaining number of buckets to be loaded; using the product of the average cycle of a single bucket and the remaining number of buckets to be loaded as the first calculation model; using the product of the sliding average cycle and the remaining number of buckets to be loaded as the second calculation model; and using the first calculation model and the second calculation model as the full-load time calculation model.

[0072] Optionally, the full-load time of the target vehicle is determined based on the full-load time calculation model and the bucket count value, including: when the bucket count value is less than the preset bucket count, the bucket count value is substituted into the first calculation model to determine the base time of the target vehicle; otherwise, the bucket count value is substituted into the second calculation model to determine the base time of the target vehicle; a correction factor is obtained, and the base time is corrected based on the correction factor to obtain the full-load time of the target vehicle, wherein the correction factor includes material density, operation rhythm and full-load correction.

[0073] The technical solution of this invention synchronously collects hydraulic spring pressure data and vehicle status data according to a preset sampling frequency, ensuring the temporal consistency of multi-source data and laying a good foundation for subsequent processing. By performing outlier removal and linear interpolation to complete the data, invalid data caused by faults and interference can be removed and data gaps can be filled, ensuring data integrity and reliability. By sequentially performing moving average filtering and wavelet denoising, high-frequency vibration noise and low-frequency baseline drift can be filtered out respectively, resulting in a stable single-path pressure curve. By performing weighted fusion according to the load ratio, data distortion caused by off-center loading and unilateral loading can be eliminated.

[0074] Example 3 Figure 3 This is a schematic diagram of a vehicle full-load time determination device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: an equivalent pressure curve acquisition module 310, used to acquire the equivalent pressure curve of the target vehicle when the activation conditions are met; The bucket count value determination module 320 is used to determine the effective loading event based on the equivalent pressure curve, and to determine the bucket count value based on the effective loading event; The full load time determination module 330 is used to construct a full load time calculation model and determine the full load time of the target vehicle based on the full load time calculation model and the bucket count value.

[0075] Optionally, the equivalent pressure curve acquisition module 310 is specifically used for: acquiring multi-source sensor data of the target vehicle based on a preset sampling frequency, wherein the multi-source sensor data includes pressure data of each oil spring and vehicle status data; removing outliers and performing linear interpolation to complete the multi-source sensor data to obtain the removed data; sequentially performing moving average filtering and wavelet noise reduction on the removed data to obtain each single-path smooth pressure curve; determining the allocation weight according to the load ratio of each oil spring, and performing weighted fusion of each single-path smooth pressure curve based on the allocation weight to obtain the equivalent pressure curve of the target vehicle.

[0076] Optionally, the bucket count determination module 320 specifically includes: an effective loading event determination unit, used for: collecting the initial empty reference pressure of the target vehicle in a stationary state, and obtaining the pre-calibrated minimum pressure threshold per bucket, full-load reference pressure, and rated full-load bucket count; determining the first steady-state pressure and the second steady-state pressure based on the equivalent pressure curve, and calculating the pressure difference between the second steady-state pressure and the first steady-state pressure; determining the rise amplitude of the first steady-state pressure to the peak value within a first specified time period; determining the fall amplitude of the peak value back to the second steady-state pressure within a second specified time period; determining the target fluctuation range based on the minimum pressure threshold per bucket; and determining an effective loading event when the rise amplitude is greater than or equal to the minimum pressure threshold per bucket, the fall amplitude is less than or equal to a specified proportion of the rise amplitude, the fluctuation range of the second steady-state pressure is within the target fluctuation range, the duration is greater than or equal to a preset time, and the pressure difference is greater than or equal to a specified proportion of the minimum pressure threshold per bucket.

[0077] Optionally, the bucket count determination module 320 specifically includes: a bucket count determination unit, used for: triggering bucket count counting every time a valid loading event is detected; obtaining a preset counting dead zone time, and not triggering repeated counting of bucket count when a valid loading event occurs within the counting dead zone time; determining a secondary threshold based on the minimum pressure threshold of a single bucket, and performing a secondary verification on the equivalent pressure curve when the pressure difference exceeds the secondary threshold, and triggering supplementary counting of bucket count when the secondary verification passes; and pausing bucket count counting when vehicle movement or non-loading interference events are detected.

[0078] Optionally, the full load time determination module 330 specifically includes: a calculation model construction unit, used to: obtain the average cycle and the moving average cycle of a single bucket, and determine the current number of buckets loaded based on the bucket count value; calculate the difference between the rated full load number of buckets and the current number of buckets loaded, and take the larger value between the bucket count difference and 0 as the remaining number of buckets to be loaded; use the product of the average cycle of a single bucket and the remaining number of buckets to be loaded as the first calculation model; use the product of the moving average cycle and the remaining number of buckets to be loaded as the second calculation model; and use the first calculation model and the second calculation model as the full load time calculation model.

[0079] Optionally, the full load time determination module 330 specifically includes: a full load time determination unit, used for: when the bucket counter value is less than the preset bucket count, substituting the bucket count value into the first calculation model to determine the base time of the target vehicle; otherwise, substituting the bucket count value into the second calculation model to determine the base time of the target vehicle; obtaining a correction factor, and correcting the base time based on the correction factor to obtain the full load time of the target vehicle, wherein the correction factor includes material density, operation rhythm and full load correction.

[0080] Optionally, the device further includes a sleep stop module, used to: stop determining the full load time of the target vehicle when sleep conditions are met; wherein, the sleep conditions include any one of the following: the target vehicle leaves the loading area electronic fence for a preset departure time, the target vehicle's operating status changes to transport / unloading / waiting for dispatch, the target vehicle's speed exceeds a preset threshold, the target vehicle's lifting action is triggered, the target vehicle receives a loading completion instruction, and the sensor malfunction reaches a fault threshold.

[0081] The technical solution of this invention, by setting activation conditions to collect the equivalent pressure curve of the target vehicle, can accurately limit the data collection scenario, avoid signal interference in non-loading conditions, and ensure the validity of the original data. By identifying valid loading events and counting the bucket count, counting can be completed based on actual load changes, effectively avoiding counting deviations caused by empty shovels and material spillage, and improving the accuracy of bucket count statistics. By using a full-load time calculation model combined with bucket count values ​​to determine the full-load time, the remaining loading time can be dynamically calculated, improving the accuracy of full-load time prediction and providing a reliable basis for subsequent scheduling work.

[0082] The vehicle full load time determination device provided in this embodiment of the invention can execute the vehicle full load time determination method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0083] Example 4 Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0084] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) or random access memory (RAM), 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 ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. Input / output (I / O) interfaces are also connected to the bus 14.

[0085] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, 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.

[0086] 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 a method for determining the full load time of a vehicle.

[0087] In some embodiments, a method for determining vehicle occupancy time 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 and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle occupancy time determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a vehicle occupancy time determination method by any other suitable means (e.g., by means of firmware).

[0088] 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), payload-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.

[0089] 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.

[0090] 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 (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0091] 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).

[0092] 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.

[0093] 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. It addresses the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0094] 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.

[0095] 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 full load time of a vehicle, characterized in that, include: When the activation conditions are met, the equivalent pressure curve of the target vehicle is collected; The effective loading events are determined based on the equivalent pressure curve, and the number of buckets is determined based on the effective loading events; A full-load time calculation model is constructed, and the full-load time of the target vehicle is determined based on the full-load time calculation model and the bucket count value.

2. The method according to claim 1, characterized in that, The equivalent pressure curve of the target vehicle collected includes: Multi-source sensor data of the target vehicle are collected based on a preset sampling frequency. The multi-source sensor data includes pressure data of each oil spring and vehicle status data. The multi-source sensor data is subjected to outlier removal and linear interpolation to obtain the removed data. The removed data are then subjected to moving average filtering and wavelet denoising in sequence to obtain each single-channel smooth pressure curve; The allocation weight is determined based on the load ratio of each oil spring, and the single-path smooth pressure curves are weighted and fused based on the allocation weight to obtain the equivalent pressure curve of the target vehicle.

3. The method according to claim 1, characterized in that, The step of determining the effective loading event based on the equivalent pressure curve includes: Collect the initial unloaded reference pressure of the target vehicle in a stationary state, and obtain the pre-calibrated minimum pressure threshold per bucket, full load reference pressure, and rated number of full load buckets; The first steady-state pressure and the second steady-state pressure are determined based on the equivalent pressure curve, and the pressure difference between the second steady-state pressure and the first steady-state pressure is calculated. Within a first specified time period, determine the magnitude of the rise of the first steady-state pressure to its peak value; Within a second specified time period, determine the magnitude of the drop from the peak to the second steady-state pressure; The target fluctuation range is determined based on the minimum pressure threshold of a single bucket. A valid loading event is determined when the increase is greater than or equal to the minimum pressure threshold per bucket, the decrease is less than or equal to a specified percentage of the increase, the fluctuation range of the second steady-state pressure is within the target fluctuation range, the duration is greater than or equal to a preset time, and the pressure difference is greater than or equal to a specified percentage of the minimum pressure threshold per bucket.

4. The method according to claim 3, characterized in that, The determination of the bucket count value based on the effective loading event includes: Each time a valid loading event is detected, the bucket count value is triggered to count; Obtain the preset counting dead time. When a valid loading event occurs within the counting dead time, do not trigger the repeated counting of the bucket count value. A secondary threshold is determined based on the minimum pressure threshold of a single bucket. When the pressure difference exceeds the secondary threshold, the equivalent pressure curve is checked a second time. When the second check passes, the bucket count value is supplemented. When vehicle movement or non-loaded interference events are detected, the bucket count is paused.

5. The method according to claim 3, characterized in that, The construction of the full-load time calculation model includes: Obtain the average cycle and moving average cycle of a single bucket, and determine the current number of buckets installed based on the bucket count value; Calculate the difference between the rated full-load number of buckets and the current number of buckets loaded, and take the larger value between the difference and 0 as the remaining number of buckets to be loaded; The product of the average cycle of a single bucket and the number of remaining buckets to be loaded is used as the first calculation model; The product of the moving average period and the remaining number of buckets to be loaded is used as the second calculation model; The first calculation model and the second calculation model are used as the full load time calculation models.

6. The method according to claim 5, characterized in that, Determining the full-load time of the target vehicle based on the full-load time calculation model and the bucket count value includes: When the count value is less than the preset count, the count value is substituted into the first calculation model to determine the base time of the target vehicle; otherwise, the count value is substituted into the second calculation model to determine the base time of the target vehicle. Obtain a correction factor, and correct the base time based on the correction factor to obtain the full-load time of the target vehicle. The correction factor includes material density, operation rhythm, and full-load correction.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: When the hibernation conditions are met, stop determining the full load time of the target vehicle; The sleep conditions include any one of the following: the target vehicle leaves the loading area electronic fence for a preset departure time, the target vehicle's operating status changes to transport / unloading / waiting for dispatch, the target vehicle's speed exceeds a preset threshold, the target vehicle's lifting action is triggered, the target vehicle receives a loading completion instruction, and the sensor malfunction reaches a fault threshold.

8. The method according to any one of claims 1-6, characterized in that, The activation conditions include: the target vehicle stays in the loading position for a preset duration, the target vehicle is stationary and the parking brake is activated, the target vehicle's operating status is pending loading / loading, and the target vehicle's lifting cylinder is in the lowering lock state.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed 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 perform the method of any one of claims 1-8.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions that are used to cause a processor to execute the method of any one of claims 1-8.

Images