Engine purging method and system, storage medium and program product

Abstract

The invention provides an engine purging method and system, a storage medium and a program product, and relates to the technical field of engine control, and the method comprises the steps that running state data and operation data of a vehicle in a current driving cycle are acquired; pre-judging whether the vehicle faces the last engine stop of the current driving cycle based on the operation state data and the operation data; if yes, when an engine stop instruction is received, the engine is controlled to enter a purging mode firstly and then stop; and if not, the engine is controlled not to enter the purging mode. According to the method, the last time of engine shutdown before the vehicle is powered off in each driving cycle is recognized through the cycle operation characteristics, engine purging is carried out, the whole vehicle shutdown time is accurately pre-judged, the timeliness of purging operation is ensured, the engine maintenance cost is reduced, the efficient operation state of the engine is ensured, and the service life of the engine is prolonged. And the service life and the performance stability of the engine are improved.

Description

Technical Field

[0001] This disclosure belongs to the field of engine control technology, specifically relating to an engine purging method, system, storage medium, and program product. Background Technology

[0002] Methanol and natural gas engines need to be purged when the vehicle is powered off to prevent unburned fuel from causing adverse reactions in the engine after the vehicle stops, which could affect the engine's reliability.

[0003] In related technologies, range-extended mining trucks with start-stop functions require a purging process for the engine when the vehicle is powered off to ensure internal cleanliness and extend its service life. However, in actual operation, the engine may already be shut down when the vehicle is powered off. In this case, to complete the purging process, the range extender needs to restart the engine. This process not only increases operational complexity but may also cause additional wear and tear on the engine. More importantly, it affects the user's driving experience. Summary of the Invention

[0004] This disclosure provides an engine purging method, system, storage medium, and program product, aiming to at least partially solve the technical problem that the engine may be pulled up from a stopped state for purging when the vehicle is powered off, resulting in a poor user experience.

[0005] At least one embodiment of this disclosure provides an engine purging method applied to a vehicle performing cyclic operations, including:

[0006] Acquire the vehicle's operating status data and work data in the current driving cycle;

[0007] Based on the operating status data and the operation data, a prediction is made as to whether the vehicle is facing the last engine shutdown of the current driving cycle. The period from the vehicle being powered on to the vehicle being powered off is a complete driving cycle, and each driving cycle includes multiple operations and multiple engine shutdowns.

[0008] If so, upon receiving an engine shutdown command, control the engine to first enter purge mode and then shut down; and,

[0009] If not, control the engine not to enter the purging mode.

[0010] In the method provided in at least one embodiment of this disclosure, the operating status data includes the current time, vehicle running time, and number of engine shutdowns, and the job data includes the current number of jobs.

[0011] In at least one embodiment of the method provided in this disclosure, the step of predicting whether the vehicle is facing the final engine shutdown of the current driving cycle based on the operating status data and the work data includes:

[0012] The operating status data and the operation data are input into a pre-trained parking prediction self-learning model to obtain the predicted probability that the vehicle will face the last engine shutdown in the current driving cycle.

[0013] In response to the predicted probability exceeding a preset probability threshold, it is determined that the vehicle faces the final engine shutdown of the current driving cycle; and,

[0014] In response to the predicted probability being lower than the probability threshold, it is determined that the vehicle is not facing the final engine shutdown of the current driving cycle.

[0015] The method provided in at least one embodiment of this disclosure further includes:

[0016] A parking prediction self-learning model is established, wherein the input of the parking prediction self-learning model is the operating status data and the operation data, and the output of the parking prediction self-learning model is the predicted probability that the vehicle will face the last engine shutdown in the current driving cycle.

[0017] Acquire historical data of the inputs and outputs for multiple dates, wherein the current time of the historical data includes the vehicle power-off time at the end of each driving cycle on each date, the current number of tasks in the historical data includes the number of tasks completed at the end of each driving cycle on each date, and the number of engine shutdowns in the historical data includes the number of engine shutdowns counted when the vehicle power-off occurred in the last driving cycle among multiple driving cycles on each date; and,

[0018] The parking prediction self-learning model is trained based on the historical data to obtain the trained parking prediction self-learning model.

[0019] The method provided in at least one embodiment of this disclosure further includes:

[0020] After the vehicle is powered on, the system acquires the vehicle's lifting signal, the pre-operation heavy-load mileage, and the post-operation unloaded mileage; and...

[0021] Based on the lifting signal, the heavy-load mileage before the operation, and the empty-load mileage after the operation, when the vehicle enters the cyclic operation, first information is generated to characterize the vehicle entering the cyclic operation.

[0022] The method provided in at least one embodiment of this disclosure further includes:

[0023] In response to the predicted probability exceeding a preset probability threshold, second information is generated to characterize that the vehicle will lose power during the current engine shutdown in the current driving cycle.

[0024] In at least one embodiment of the method provided in this disclosure, the vehicle is a range-extended mining truck, and the step of acquiring the vehicle's operating status data and work data in the current driving cycle includes:

[0025] Obtain the current time, vehicle runtime, and engine shutdown count; generate a first array containing the current time, vehicle runtime, and engine shutdown count; and label this array as the operating status data; and,

[0026] The vehicle's lifting signal, load status signal, and mileage are acquired. The vehicle's lifting signal, load status signal, and mileage are input into a pre-set work cycle identification and statistical model to obtain the current number of tasks for the current driving cycle. A second array containing the current number of tasks is generated and marked as the work data.

[0027] At least one embodiment of this disclosure also provides a system for controlling engine purging, applied to a vehicle performing cyclic operations, comprising:

[0028] The data acquisition unit is configured to acquire the vehicle's operating status data and work data in the current driving cycle;

[0029] The preprocessing unit is configured to predict whether the vehicle is facing the last engine shutdown of the current driving cycle based on the operating status data and the operation data. The period from the vehicle being powered on to the vehicle being powered off is a complete driving cycle, and each driving cycle includes multiple operations and multiple engine shutdowns.

[0030] A first control unit is configured to, if so, control the engine to first enter a purge mode and then shut down upon receiving an engine shutdown command; and,

[0031] The second control unit is configured to prevent the engine from entering the purging mode if not.

[0032] At least one embodiment of this disclosure also provides a storage medium storing a program or instructions, wherein the program or instructions, when executed by a processor, implement the steps of the method provided in any embodiment of this disclosure.

[0033] At least one embodiment of this disclosure also provides a product including a program or instructions, wherein the program or instructions, when executed by a processor, implement the steps of the method provided in any embodiment of this disclosure.

[0034] Compared to related technologies, the engine purging method, system, storage medium, and program products provided in this disclosure offer a solution for automatically predicting vehicle power-off. This solution utilizes the characteristics of cyclical operations to identify the last engine shutdown before the vehicle's power-off in each driving cycle, i.e., predicting subsequent vehicle power-off and performing engine purging when the engine stops. This solution not only significantly improves the automation level of engine maintenance but also effectively reduces maintenance costs. By accurately predicting the engine shutdown timing, the timeliness of the purging operation is ensured, preventing the accumulation of deposits inside the engine and maintaining its efficient operation. Furthermore, this solution fully considers the working characteristics of vehicles in cyclical operations, making the purging operation more closely aligned with actual vehicle usage, further improving engine lifespan and performance stability. It also solves the technical problem in related technologies where the engine may be pulled from a stopped state for purging when the vehicle is powered off, resulting in a poor user experience.

[0035] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this disclosure, 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 this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 A flowchart of an engine purging method provided in at least one embodiment of this disclosure;

[0038] Figure 2 A schematic diagram of a vehicle power-off prediction scheme provided in at least one embodiment of this disclosure;

[0039] Figure 3 A schematic diagram illustrating the training of a parking prediction self-learning model provided in at least one embodiment of this disclosure;

[0040] Figure 4 A schematic diagram of a statistical scheme for reciprocating operation of a range-extended mining truck provided in at least one embodiment of this disclosure;

[0041] Figure 5 A structural block diagram of a system for controlling engine purging provided in at least one embodiment of this disclosure;

[0042] Figure 6 A schematic diagram illustrating the composition of a program product provided for at least one embodiment of this disclosure.

[0043] Figure label:

[0044] 1-System for controlling engine purging; 11-Data acquisition unit; 12-Preprocessing unit; 13-First control unit;

[0045] 14-Second control unit; 21-Processor; 22-Memory; 23-Input device; 24-Output device. Detailed Implementation

[0046] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the disclosure. Similarly, the following embodiments are only some, not all, embodiments of the present disclosure, and all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0047] The terms "first," "second," and "third" used in the embodiments of this disclosure are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first," "second," and "third" may explicitly or implicitly include at least one of that feature.

[0048] In the description of this disclosure, "multiple" means at least two, such as two or three, unless otherwise expressly and specifically limited.

[0049] In this disclosure, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0050] The terms “comprising” and “having”, and any variations thereof, used in this disclosure are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or components inherent to such processes, methods, products, or devices.

[0051] In this disclosure, the term "range extender" refers to the vehicle's powertrain or auxiliary powertrain, including the engine and generator.

[0052] In this disclosure, the term "PTO signal" refers to the output signal of the power take-off (PTO) of a range-extended mining truck. During mining truck operations, the PTO signal is often used to identify specific operating states of the vehicle, such as the execution of lifting actions.

[0053] The relevant technology has a technical problem: when the vehicle is powered off, the engine may be pulled up from its stopped state for cleaning, resulting in a poor user experience.

[0054] To address the aforementioned technical issues, this disclosure proposes an engine purging method based on the prediction of a vehicle power failure (the last engine shutdown in the current driving cycle), that is, predicting that a subsequent vehicle power failure will occur and performing purging when the engine stops.

[0055] Vehicles operating in a cyclical manner, including but not limited to range-extended mining trucks, load materials or goods from one platform and transport them to another platform for unloading or hauling during normal operation. The routes are fixed and repetitive, with each driving cycle completing multiple tasks. Each driving cycle refers to the period from when the vehicle is powered on to when it is powered off. Cyclic operations are repetitive, and the number of tasks completed in different driving cycles each day shows a clear repetitive pattern. Based on this, by identifying whether the vehicle is facing the final engine shutdown of the current driving cycle, it is possible to predict subsequent vehicle power-offs and control the engine to purge before the vehicle stops.

[0056] Figure 1 A flowchart illustrating a power generation switching method provided in at least one embodiment of this disclosure. This method is applied to vehicles engaged in cyclical operations. Figure 1 As shown, the method may include the following steps S10-S40.

[0057] Step S10: Obtain the vehicle's operating status data and work data in the current driving cycle.

[0058] Step S20: Based on the operating status data and work data, predict whether the vehicle will face the last engine shutdown of the current driving cycle. The period from the vehicle being powered on to the vehicle being powered off is a complete driving cycle. Each driving cycle includes multiple operations and multiple engine shutdowns.

[0059] Step S30: If so, upon receiving an engine shutdown command, control the engine to first enter the purge mode and then shut it down.

[0060] Step S40: If not, control the engine not to enter the purging mode.

[0061] It should be noted that this disclosure does not limit the relationship between a single operation and engine shutdown. A single operation may include one or more engine starts and corresponding engine shutdowns. In practical applications, the number of engine starts and shutdowns in a single operation may vary depending on the specific operational needs of the vehicle and the characteristics of cyclical operations. Regardless of the number of engine starts and shutdowns in a single operation, the method provided by this disclosure can effectively predict whether the vehicle is facing the final engine shutdown of the current driving cycle, and if the prediction result is yes, control the engine to purge before the vehicle stops, thereby reducing emissions and protecting the environment.

[0062] In the above scheme, the vehicle's operating status data and work data in the current driving cycle contain the reciprocating characteristics of the cycle operation. Therefore, based on the vehicle's operating status data and work data in the current driving cycle, it is possible to accurately determine whether the vehicle is facing the last engine shutdown in the current driving cycle, and control the vehicle to perform engine purging when the last engine shutdown in the current driving cycle occurs, rather than towing up the engine for purging after the engine has stopped and the vehicle has stopped.

[0063] In the above scheme, operational status data includes, but is not limited to, current time, vehicle runtime, and number of engine shutdowns; it may also include ambient temperature and humidity. Work data includes, but is not limited to, the current number of jobs; it may also include job type, job duration, and workload. This combination of data comprehensively reflects the actual situation of the vehicle during operation, providing a reliable basis for accurately predicting whether the vehicle is facing the final engine shutdown of the current driving cycle.

[0064] Some embodiments of this disclosure also provide systems, storage media, and program products corresponding to the methods described above.

[0065] The method provided by at least one embodiment of this disclosure is applicable to any existing cyclical vehicle application scenario. The method can be applied to an engine controller, range extender controller, or vehicle controller. For example, in the mining industry, the method can be applied to range-extended mining trucks to ensure that the engine remains clean and reduces performance degradation due to deposits during frequent trips between the mining area and unloading point. In agriculture, for agricultural machinery vehicles performing cyclical operations such as sowing and fertilizing in the fields, the method can effectively manage engine status and extend engine life. Furthermore, in urban sanitation operations, garbage trucks, water trucks, and other vehicles can also benefit from this embodiment, ensuring efficient and stable engine operation during continuous street sweeping and garbage collection tasks. These application scenarios demonstrate the broad applicability and practicality of the embodiments of this disclosure.

[0066] Compared to related technologies, the method proposed in this disclosure provides an automated method for predicting vehicle power-off. It utilizes the characteristics of cyclical operations to identify the last engine shutdown before the vehicle's power-off in each driving cycle, thus predicting a subsequent vehicle power-off and performing engine purging when the engine stops. This method significantly improves the automation level of engine maintenance and effectively reduces maintenance costs. By accurately predicting the engine shutdown timing, it ensures the timeliness of the purging operation, preventing the accumulation of deposits inside the engine and maintaining its efficient operation. Furthermore, this method fully considers the working characteristics of vehicles in cyclical operations, making the purging operation more aligned with actual vehicle usage, further improving engine lifespan and performance stability. It also solves the technical problem of related technologies where the engine may be pulled up from a shutdown state for purging when the vehicle is powered off, resulting in a poor user experience.

[0067] In step S10, the operational status data covers key indicators of the vehicle's operational status, while the task data covers relevant information about the vehicle performing specific tasks. Together, these data constitute a comprehensive description of the vehicle's current operating status, providing a solid foundation for subsequent judgment and processing.

[0068] In step S20, the system analyzes operational status and task data, employing advanced algorithms or models to identify whether the vehicle is about to complete its current driving cycle and face engine shutdown. This process requires not only accurate and complete data but also highly intelligent and adaptable algorithm models to handle various complex driving scenarios and task demands. Through this step, the system can accurately predict the timing of engine shutdown, providing crucial information for the timely execution of subsequent purging operations, thereby ensuring efficient engine operation and maintenance.

[0069] In step S30, during the purging mode, the engine performs internal cleaning according to a preset program, effectively removing residual fuel and impurities, preventing carbon buildup and corrosion, thereby maintaining the cleanliness and operating efficiency of the engine interior. This step relies not only on precise command control but also on close collaboration between the engine management system and the purging device to ensure the smooth operation of the purging process.

[0070] Comparing step S40, the prediction result indicates that the engine's current state is not suitable for entering the purging mode. Since this is not the last engine shutdown of the current driving cycle, the purging procedure will not be triggered to avoid unnecessary energy consumption or potential damage to the engine. This decision-making process reflects the system's high level of intelligence and safety considerations, ensuring that the engine receives the most appropriate maintenance and handling under any circumstances.

[0071] Through steps S10-S40, the system can flexibly adjust the purging strategy according to actual conditions, ensuring efficient engine operation while effectively avoiding unnecessary energy consumption and potential damage. This series of steps not only demonstrates the advanced nature and precision of the engine management system but also lays a solid foundation for the long-term stable operation of the engine. In practical applications, this method can significantly improve engine maintenance efficiency and operational performance, and has broad market application prospects.

[0072] In some embodiments, to improve the accuracy and efficiency of engine purging, the operating status data is configured to include the current time, vehicle runtime, and number of engine stops, and the operation data is configured to include the current number of operations. The current time reflects the specific time period during which the vehicle performs purging operations. For example, during morning and evening rush hours, due to frequent vehicle starts and stops, more impurities tend to accumulate inside the engine. In this case, the system can automatically increase the purging intensity to ensure efficient engine operation. At night or during off-peak hours, the purging intensity can be appropriately reduced to decrease energy consumption and noise pollution. The vehicle runtime reflects the total operating time of the vehicle from start-up to the current moment, helping to assess the engine's workload and wear level. The number of engine stops records the number of times the engine stops during the operation. The current number of operations represents the number of operation cycles the vehicle has currently completed, providing an important reference for optimizing the engine purging strategy. Through comprehensive analysis and utilization of these data, the accuracy and efficiency of engine purging can be further improved.

[0073] In some embodiments, in order to ensure the timeliness and effectiveness of the engine purging operation, step S20 is refined to include the following sub-steps S201-S203.

[0074] Sub-step S201: Input the running status data and operation data into the pre-trained parking prediction self-learning model to obtain the predicted probability (also known as the vehicle power-off probability) of the vehicle facing the last engine shutdown in the current driving cycle.

[0075] Sub-step S202: In response to the predicted probability exceeding a preset probability threshold, determine that the vehicle is facing the last engine shutdown of the current driving cycle (also known as the vehicle will undergo a complete power-off).

[0076] Sub-step S203: In response to the predicted probability being lower than a preset probability threshold, determine that the vehicle is not facing the last engine shutdown of the current driving cycle (also known as the vehicle temporarily not shutting down).

[0077] It should be noted that the probability threshold is used to determine whether to enter purge mode. The probability threshold can be a calibrated fixed value, determined through analysis of multiple offline data points, and not adjusted after determination. Alternatively, the probability threshold can also be a variable value, adjusted based on the driving data of a fixed user (including driving habit information) to achieve a more accurate predictive effect.

[0078] The parking prediction self-learning model mentioned in sub-step S201 can adopt existing models or empirical models. Existing models include neural network models or logistic regression models. This parking prediction self-learning model can comprehensively consider operating status data and operation data, such as current time, vehicle running time, number of engine shutdowns, and current operation count, to predict the probability that the vehicle will face the last engine shutdown in the current driving cycle, that is, the probability that the vehicle will soon undergo a complete power-off.

[0079] In sub-step S202, if the predicted probability exceeds the preset probability threshold, the system determines that the vehicle is facing the last engine shutdown in the current driving cycle. That is, the vehicle will be powered down when the engine shuts down in the current driving cycle. This determination helps to start the engine purging.

[0080] In sub-step S203, if the predicted probability is lower than a preset probability threshold, the system determines that the vehicle is not facing the final engine shutdown of the current driving cycle. Since the vehicle may still have subsequent driving tasks or operations, the system does not shut down the entire vehicle to avoid unnecessary energy waste and driving interruption. This flexible judgment mechanism ensures the timeliness and effectiveness of the engine purging operation, while also improving the vehicle's driving experience and operating efficiency.

[0081] Figure 2 This is a schematic diagram of a vehicle power-off prediction scheme provided in at least one embodiment of this disclosure. Figure 2 As shown, when a vehicle needs to stop, the current number of operations, vehicle runtime, current time, and number of engine shutdowns are input into the parking prediction self-learning model to obtain the predicted probability of the vehicle facing the last engine shutdown in the current driving cycle, i.e., the vehicle power-off probability, corresponding to sub-step S201. If the predicted probability is high, it means that the vehicle is likely to undergo a long-term shutdown after completing the current driving cycle. In this case, it is appropriate to power off the entire vehicle and start engine purging. This process design not only improves the targeting and efficiency of engine purging but also effectively avoids driving interruptions and energy waste caused by unnecessary vehicle power-offs, thus improving the overall user experience.

[0082] In some embodiments, in order to improve the efficiency and accuracy of engine purging, the method may further include the following steps S01-S03.

[0083] Step S01: Establish a parking prediction self-learning model, wherein the input of the parking prediction self-learning model is the operating status data and the operation data, and the output of the parking prediction self-learning model is the predicted probability of the vehicle facing the last engine shutdown in the current driving cycle.

[0084] Step S02: Obtain historical input and output data for multiple dates. The current time of the historical data includes the vehicle power-off time at the end of each driving cycle on each date. The current number of tasks in the historical data includes the number of tasks completed at the end of each driving cycle on each date. The number of engine shutdowns in the historical data includes the number of engine shutdowns counted when the vehicle power-off occurred in the last driving cycle of multiple driving cycles on each date.

[0085] Step S03: Train the parking prediction self-learning model based on historical data to obtain the trained parking prediction self-learning model.

[0086] It should be noted that steps S01-S03 can be set before step S10.

[0087] Steps S01-S03 utilize the characteristics of cyclical operations to train the parking prediction self-learning model, enabling it to self-learn power-off judgments and perform the purging action upon the last engine shutdown. Through continuous learning and optimization, the parking prediction self-learning model can gradually improve its prediction accuracy, providing reliable data support for subsequent steps. This step not only enhances the method's intelligence level but also improves the efficiency and accuracy of engine purging.

[0088] Figure 3 This is a schematic diagram illustrating the training of a parking prediction self-learning model provided in at least one embodiment of this disclosure. Figure 3 As shown, historical data from multiple dates can be used to train a parking prediction self-learning model by inputting the current number of jobs, vehicle runtime, vehicle power-off time (as the current time), and engine shutdown count. During training, the parking prediction self-learning model comprehensively considers multiple dimensions such as the current number of jobs, vehicle runtime, current time, and engine shutdown count. Through complex algorithmic logic, it gradually learns the probability of engine shutdown and its correlation with purging actions under different workloads, runtimes, and time periods. This process not only enhances the model's generalization ability but also enables it to more accurately predict parking timing, thereby triggering purging actions at the appropriate time, avoiding unnecessary energy consumption and emissions, and improving the overall system efficiency and environmental performance.

[0089] In some embodiments, in order to enhance the accuracy of determining the timing of purging, the method may further include the following steps S04-S05.

[0090] Step S04: After the vehicle is powered on, acquire the vehicle's lifting signal, the heavy-load mileage before operation, and the unloaded mileage after operation.

[0091] Step S05: Based on the lifting signal, the heavy-load driving mileage before the operation and the empty-load driving mileage after the operation, identify when the vehicle enters the cyclic operation, and generate the first information to characterize the vehicle entering the cyclic operation.

[0092] The lifting signal can be used to determine whether the vehicle has performed cargo loading and unloading operations. The lifting signal can be a PTO (Push-to-Trip) signal. The pre-operation heavy-load mileage reflects the vehicle's driving conditions when loaded, while the post-operation empty-load mileage reflects the vehicle's driving status after unloading. By comprehensively analyzing this information, the system can accurately identify whether the vehicle has entered a new cyclical operation. Once the vehicle is confirmed to have entered a cyclical operation, the system immediately generates initial information. This information is crucial for determining the timing of subsequent engine purging, ensuring that the purging action is performed at the appropriate time, avoiding unnecessary energy waste and effectively protecting the engine from damage.

[0093] In some embodiments, to accommodate different types of vehicles, the lifting signal can be obtained through load sensors installed on the vehicle, cargo box tilt sensors, or by inferring the load from the generator's torque and vehicle speed. Load sensors directly measure the weight carried by the vehicle; changes in load during loading and unloading are captured by the sensor, generating a corresponding lifting signal. Cargo box tilt sensors indirectly determine whether cargo has been loaded or unloaded by detecting the tilt angle of the cargo box, as loading and unloading typically involve tilting the cargo box. Furthermore, inferring the load from the generator's torque and vehicle speed is a more complex but equally effective method. It estimates the current load by analyzing the vehicle's power output and driving status, thus determining whether a lifting action has occurred. These methods each have different applicable scenarios and advantages, and can be flexibly selected according to the specific vehicle type and operational requirements.

[0094] In some embodiments, in order to more clearly demonstrate the engine purging action to the user, the method may further include the following step S50.

[0095] Step S50: In response to the predicted probability exceeding a preset probability threshold, generate second information to characterize that the vehicle will lose power during the current engine shutdown in the current driving cycle.

[0096] The second piece of information not only serves as the basis for determining when the vehicle loses power when the engine stops, but also as a signal to trigger a series of subsequent safety checks and preparatory measures. For example, the system will preemptively shut down unnecessary electrical equipment to ensure a smooth power transition, while simultaneously checking the status of various vehicle systems to ensure the vehicle's safety and stability after power loss. This step further enhances the intelligence of vehicle operation, reduces potential risks caused by improper operation or equipment malfunction, and provides more comprehensive protection for users and the vehicle.

[0097] In some embodiments, the vehicle is a range-extended mining truck. In order to obtain valid data on the engine purging operation, step S10 is refined to include the following sub-steps S101-S102.

[0098] Sub-step S101: Obtain the current time, vehicle running time, and engine shutdown count, generate a first array containing the current time, vehicle running time, and engine shutdown count, and mark it as running status data.

[0099] Sub-step S102: Obtain the vehicle's lifting signal, load status signal, and mileage. Based on the vehicle's lifting signal, load status signal, and mileage, input a pre-set work cycle identification and statistical model to obtain the current number of tasks in the current driving cycle. Generate a second array containing the current number of tasks in the current driving cycle and mark it as work data.

[0100] It should be noted that the statistical models for identifying job cycles include, but are not limited to, logistic regression models and neural network patterns.

[0101] The lifting signal indicates the lifting status of the vehicle's cargo box, while the load status signal indicates the vehicle's current load. The driving cycle number distinguishes different driving cycles, and the number of operations represents the number of operations completed in the current or previous driving cycles. The collection and analysis of this data helps to more accurately grasp the vehicle's operating status and provides data support for subsequent engine purging decisions for range-extended mining trucks.

[0102] In some embodiments, in order to obtain valid data on the engine purging operation, step S10 is refined to include the following sub-steps S101*-S102*.

[0103] Sub-step S101*: Obtain the current time, vehicle runtime, and engine shutdown count, generate a first array containing the current time, vehicle runtime, and engine shutdown count, and mark it as running status data.

[0104] Sub-step S102*: Obtain the vehicle's lifting signal, load status signal, and mileage. Based on the vehicle's lifting signal, load status signal, and mileage, input a pre-set work cycle identification and statistical model to obtain the driving cycle number of the current driving cycle in the current date, the current number of jobs in the current driving cycle, and the number of jobs completed at the end of each driving cycle before the current driving cycle. Generate a second array containing the driving cycle number, the current number of jobs in the current driving cycle, and the number of jobs completed at the end of each driving cycle before the current driving cycle, and mark it as work data.

[0105] Sub-steps S101*-S102* further analyze the engine's operating status and potential wear. Specifically, the driving cycle number identifies the current driving cycle's position within the overall operation; the current task count for the current driving cycle shows the amount of work completed by the vehicle within that cycle; and the task count completed at the end of each driving cycle preceding the current cycle provides an overview of the vehicle's historical operations. These data collectively constitute a comprehensive description of the vehicle's operating status, providing crucial information for subsequent analysis and decision-making.

[0106] Figure 4 A schematic diagram illustrating a statistical scheme for the reciprocating operation of a range-extended mining truck, provided in at least one embodiment of this disclosure. (See diagram below.) Figure 4 As shown, the system identifies work cycles based on PTO signals, pre-lift heavy-load mileage, and post-lift unloaded mileage. It also counts the current number of operations and the number of operations per driving cycle, and records the number of engine shutdowns during the last work cycle when the vehicle is powered off. This data is used to train the parking prediction self-learning model. The PTO signal, acting as a lifting signal, helps the system determine whether the vehicle is currently in a work cycle. The pre-lift heavy-load mileage and post-lift unloaded mileage provide detailed information about the vehicle's load status and driving path, crucial for accurate work cycle identification. The system also records the number of operations per driving cycle and specifically counts the number of engine shutdowns during the last work cycle when the vehicle is powered off. This data is significant for subsequent decisions regarding engine purging, as it reflects the engine's state at the end of the work cycle, providing data support for maintenance decisions.

[0107] In some embodiments, to improve the accuracy of work cycle identification, the load status signal is directly detected by a load sensor. The load sensor monitors changes in vehicle load in real time, converting this physical quantity into an electrical signal for transmission and processing. When the vehicle is heavily loaded, the load sensor emits a corresponding signal indicating a large load; conversely, when the vehicle is empty or nearly empty, the load sensor emits different signals. This function not only improves the accuracy of work cycle identification but also provides crucial information for triggering engine purging. Because engine wear and carbon buildup are closely related to the vehicle's load status, precise monitoring of the load status allows the system to more intelligently determine when to perform engine purging, effectively extending engine life and improving overall vehicle performance.

[0108] In some embodiments, to improve the timeliness of engine purging, the probability threshold is not a fixed value, and it is determined by optimizing the probability threshold based on multiple sets of historical driving data for the vehicle to balance the false triggering rate and the missed triggering rate of the purging action. The false triggering rate refers to the probability of incorrectly triggering the purging action when engine purging is not required, while the missed triggering rate is the probability of failing to trigger the purging action when engine purging is required. By optimizing the probability threshold, it is ensured that the purging action is accurately triggered when necessary, while unnecessary purging actions are avoided, thereby improving engine operating efficiency and lifespan. This dynamic adjustment method based on historical driving data makes engine purging decisions more intelligent and adaptive.

[0109] Figure 5 This is a structural block diagram of a system for controlling engine purging, provided for at least one embodiment of this disclosure. The system is applied to vehicles performing cyclic operations. Figure 5 As shown, the system 1 for controlling engine purging includes a data acquisition unit 11, a preprocessing unit 12, a first control unit 13, and a second control unit 14.

[0110] The data acquisition unit 11 is configured to acquire the vehicle's operating status data and work data in the current driving cycle.

[0111] The preprocessing unit 12 is configured to predict whether the vehicle is facing the last engine shutdown of the current driving cycle based on the operating status data and the operation data. The period from the vehicle being powered on to the vehicle being powered off is a complete driving cycle, and each driving cycle includes multiple operations and multiple engine shutdowns.

[0112] The first control unit 13 is configured to, if so, control the engine to first enter the purge mode and then shut down when it receives an engine shutdown command.

[0113] The second control unit 14 is configured to prevent the engine from entering the purging mode if not.

[0114] The specific execution methods of each unit in the above system embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0115] In some embodiments, the data acquisition unit 11 can be implemented by a sensor, and the preprocessing unit 12, the first control unit 13 and the second control unit 14 can be implemented by a controller or control module with corresponding programs.

[0116] This disclosure also provides a storage medium storing a program or instructions that, when executed by a processor, implement the steps of the method embodiments described above.

[0117] This disclosure also provides a program product, such as... Figure 6 As shown, the program product includes one or more processors 21 and memory 22. Figure 6 Take a processor 21 as an example.

[0118] The controller may also include an input device 23 and an output device 24.

[0119] The processor 21, memory 22, input device 23, and output device 24 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0120] The processor 21 can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips. The general-purpose processor can be a microprocessor or any conventional processor.

[0121] The memory 22, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 21 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 22, thereby implementing the steps of the above-described method embodiments.

[0122] The memory 22 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the use of the processing device operated by the server. Furthermore, the memory 22 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 22 may optionally include memory remotely located relative to the processor 21, and these remote memories may be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0123] Input device 23 can receive input digital or character information, and generate key signal inputs related to driver settings and function control of the server's processing unit. Output device 24 may include display devices such as a display screen.

[0124] One or more modules are stored in memory 22, and when executed by one or more processors 21, they perform actions such as... Figure 1 The method shown.

[0125] Those skilled in the art will understand that all or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory (FM), hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0126] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

[0127] Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. An engine purging method, applied to vehicles performing cyclic operations, characterized in that, include: Acquire the vehicle's operating status data and work data in the current driving cycle; Based on the operating status data and the operation data, a prediction is made as to whether the vehicle is facing the last engine shutdown of the current driving cycle. The period from the vehicle being powered on to the vehicle being powered off is a complete driving cycle, and each driving cycle includes multiple operations and multiple engine shutdowns. If so, upon receiving an engine shutdown command, control the engine to first enter purge mode and then shut down; and, If not, control the engine not to enter the purging mode.

2. The method according to claim 1, characterized in that, The operational status data includes the current time, vehicle runtime, and number of engine shutdowns; the job data includes the current number of jobs.

3. The method according to claim 1 or 2, characterized in that, The prediction of whether the vehicle is facing the final engine shutdown of the current driving cycle based on the operating status data and the work data includes: The operating status data and the operation data are input into a pre-trained parking prediction self-learning model to obtain the predicted probability that the vehicle will face the last engine shutdown in the current driving cycle. In response to the predicted probability exceeding a preset probability threshold, it is determined that the vehicle faces the final engine shutdown of the current driving cycle; and, In response to the predicted probability being lower than the probability threshold, it is determined that the vehicle is not facing the final engine shutdown of the current driving cycle.

4. The method according to claim 3, characterized in that, Also includes: A parking prediction self-learning model is established, wherein the input of the parking prediction self-learning model is the operating status data and the operation data, and the output of the parking prediction self-learning model is the predicted probability that the vehicle will face the last engine shutdown in the current driving cycle. Acquire historical data of the inputs and outputs for multiple dates, wherein the current time of the historical data includes the vehicle power-off time at the end of each driving cycle on each date, the current number of tasks in the historical data includes the number of tasks completed at the end of each driving cycle on each date, and the number of engine shutdowns in the historical data includes the number of engine shutdowns counted when the vehicle power-off occurred in the last driving cycle among multiple driving cycles on each date; and, The parking prediction self-learning model is trained based on the historical data to obtain the trained parking prediction self-learning model.

5. The method according to claim 1 or 2, characterized in that, Also includes: After the vehicle is powered on, the vehicle's lifting signal, the heavy-load mileage before operation, and the unloaded mileage after operation are acquired. as well as, Based on the lifting signal, the heavy-load mileage before the operation, and the empty-load mileage after the operation, when the vehicle enters the cyclic operation, first information is generated to characterize the vehicle entering the cyclic operation.

6. The method according to claim 3, characterized in that, Also includes: In response to the predicted probability exceeding a preset probability threshold, second information is generated to characterize that the vehicle will lose power during the current engine shutdown in the current driving cycle.

7. The method according to claim 4, characterized in that, The vehicle is a range-extended mining truck. The acquisition of the vehicle's operating status data and work data in the current driving cycle includes: Obtain the current time, vehicle runtime, and engine shutdown count; generate a first array containing the current time, vehicle runtime, and engine shutdown count; and label this array as the operating status data; and, The vehicle's lifting signal, load status signal, and mileage are acquired. The vehicle's lifting signal, load status signal, and mileage are input into a pre-set work cycle identification and statistical model to obtain the current number of tasks for the current driving cycle. A second array containing the current number of tasks is generated and marked as the work data.

8. A system for controlling engine purging, applied to a vehicle engaged in cyclical operations, characterized in that, The system includes: The data acquisition unit is configured to acquire the vehicle's operating status data and work data in the current driving cycle; The preprocessing unit is configured to predict whether the vehicle is facing the last engine shutdown of the current driving cycle based on the operating status data and the operation data. The period from the vehicle being powered on to the vehicle being powered off is a complete driving cycle, and each driving cycle includes multiple operations and multiple engine shutdowns. A first control unit is configured to, if so, control the engine to first enter a purge mode and then shut down upon receiving an engine shutdown command; and The second control unit is configured to prevent the engine from entering the purging mode if not specified.

9. A storage medium, characterized in that, The storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 7.

10. A program product comprising a program or instructions, characterized in that, When the program or instructions are executed by a processor, they implement the steps of the method as described in any one of claims 1 to 7.

Images