Adaptive control method and device for supercharging system of natural gas engine

Abstract

The application provides a natural gas engine supercharging system adaptive control method and device, and belongs to the field of engines. The rotational speed, intake flow, first information and demand torque gradient of the natural gas engine are acquired, and whether the natural gas engine is in a low load working condition is judged based on the rotational speed and the intake flow. The first information includes the throttle opening change rate, the rotational speed change rate, the supercharging pressure and the load change slope. In the case that the natural gas engine is in the low load working condition, it is determined that the current working condition is a steady state working condition or a transient state working condition according to the first information. In the case that the current working condition is the steady state working condition, the opening degree of the bleed valve is controlled to be in a full opening state. In the case that the current working condition is the transient state working condition, the transient state working condition is divided into multiple transient state grades according to the throttle opening change rate and the demand torque gradient, and the opening degree of the bleed valve is controlled according to the transient state grade. The scheme solves the problem that the economy and the power performance of the natural gas engine under low load are difficult to balance.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of engines, in particular to a turbocharging system adaptive control method of a natural gas engine, a turbocharging system adaptive control device of a natural gas engine, a computer readable storage medium and an electronic device. BACKGROUND

[0002] In the engine technology, the application of turbocharging technology enhances the performance of the natural gas engine, but due to the single control strategy of the bleed valve in the turbocharging system, it is difficult to achieve a good balance between economy and transient power response. The timely opening and closing of the bleed valve directly affects the performance of the engine under different working conditions. The control strategy of the turbocharger bleed valve under low load working condition still has technical problems.

[0003] The existing bleed valve control strategy mostly relies on fixed thresholds, that is, the bleed valve is fully opened at low load steady state to reduce pumping loss, and the bleed valve is fully closed at transient acceleration stage to quickly establish boost pressure. In short, this control method either adopts full bleed or full boost at low load operation, and it is difficult to consider economy and power simultaneously. SUMMARY

[0004] The main purpose of the present application is to provide a turbocharging system adaptive control method of a natural gas engine, a turbocharging system adaptive control device of a natural gas engine, a computer readable storage medium and an electronic device, to at least solve the problem that the economy and power of the natural gas engine under low load are difficult to balance in the prior art.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a turbocharging system adaptive control method of a natural gas engine is provided, comprising: acquiring a speed, an intake flow, a first information and a demand torque gradient of the natural gas engine, and judging whether the natural gas engine is in a low load working condition by using a preset speed and intake flow MAP based on the speed and the intake flow, wherein the first information includes a throttle opening rate of change, a speed rate of change, a boost pressure and a load change slope, and the demand torque gradient is a ratio of a torque change amount required by the natural gas engine to a preset time window within the preset time window; in the case that the natural gas engine is in the low load working condition, determining that the current working condition is a steady state working condition or a transient state working condition according to the first information; in the case that the current working condition is the steady state working condition, controlling the opening degree of the bleed valve to be in a full open state, and in the case that the current working condition is the transient state working condition, using fuzzy logic control, dividing the transient state working condition into multiple transient state grades according to the throttle opening rate of change and the demand torque gradient, and controlling the opening degree of the bleed valve according to the transient state grade.

[0006] Optionally, the method further comprises: obtaining historical hidden state information and historical observed state information in a first preset time period, wherein the historical hidden state information comprises historical steady state conditions and historical transient state conditions, and the historical observed state information comprises historical throttle opening rate of change, historical speed rate of change, historical boost pressure, and historical load change slope; determining the historical hidden state information and the historical observed state information as a training data set, and inputting the training data set into a hidden Markov model for training until the hidden Markov model reaches a preset convergence condition to obtain a target hidden Markov model for future state prediction; inputting a current observed state into the target hidden Markov model for prediction to obtain a hidden state sequence in a second preset time period and a change probability of the hidden state sequence; comparing the change probability of the change probability of the hidden state sequence with a preset steady state probability threshold, and adjusting an opening degree of the bleed valve in a case where the change probability exceeds the preset steady state probability threshold.

[0007] Optionally, in a case where the natural gas engine is in the low load condition, determining, according to the first information, that a current condition is a steady state condition or a transient state condition comprises: monitoring the throttle opening rate of change, the speed rate of change, the boost pressure, and the load change slope; and in a case where a preset condition is met within a preset transient window length, determining that the current condition is the transient state condition, wherein the preset condition comprises that the throttle opening rate of change is greater than a first threshold value, the speed rate of change is greater than a second threshold value, a fluctuation range of the boost pressure is greater than a third threshold value, and an absolute value of the load change slope is greater than a fourth threshold value.

[0008] Optionally, after determining whether the natural gas engine is in a low load condition by using a preset speed and intake flow MAP, the method further comprises: in a case where the natural gas engine is not in the low load condition, performing PID control on the bleed valve based on a preset boost pressure of a current operating condition of the natural gas engine, wherein the preset boost pressure is obtained by pre-calibration, and for each operating point in a non-low load condition, there is a unique preset boost pressure corresponding thereto.

[0009] Optionally, in the case that the current operating condition is the transient operating condition, the transient operating condition is divided into multiple transient grades according to the throttle opening rate and the demand torque gradient by using fuzzy logic control, including: in the case that the current operating condition is the transient operating condition, the throttle opening rate is fuzzified into a first fuzzy set, a second fuzzy set and a third fuzzy set, and the demand torque gradient is fuzzified into a first grade, a second grade and a third grade by using the fuzzy logic control; a rule base is set based on the first fuzzy set, the second fuzzy set, the third fuzzy set, the first grade, the second grade and the third grade; and the transient operating condition is divided into multiple transient grades by using the rule base, and the transient grades include a first grade transient, a second grade transient and a third grade transient.

[0010] Optionally, the opening of the bleed valve is controlled according to the transient grade, including: in the case that the transient grade is the first grade transient, the opening of the bleed valve is controlled by using a first preset bleed valve closing slope; in the case that the transient grade is the second grade transient, the opening of the bleed valve is controlled by using a second preset bleed valve closing slope; and in the case that the transient grade is the third grade transient, the opening of the bleed valve is controlled by using a third preset bleed valve closing slope, wherein the first preset bleed valve closing slope, the second preset bleed valve closing slope and the third preset bleed valve closing slope are determined in a bench calibration process.

[0011] Optionally, the preset speed and intake flow MAP includes a hysteresis interval, in the case that the change of the speed and the intake flow of the natural gas engine is within the hysteresis interval, the determination of the current operating condition does not change.

[0012] According to another aspect of the present application, there is provided a turbocharging system adaptive control device of a natural gas engine, comprising: a first acquisition unit configured to acquire a rotational speed of the natural gas engine, an intake flow, first information, and a demanded torque gradient, and determine whether the natural gas engine is in a low load condition based on the rotational speed and the intake flow using a preset rotational speed and intake flow MAP, wherein the first information comprises a throttle opening change rate, a rotational speed change rate, a turbocharging pressure, and a load change slope, and the demanded torque gradient is a ratio of a torque change amount required by the natural gas engine to a preset time window within a preset time window; a determination unit configured to determine, in a case where the natural gas engine is in the low load condition, whether a current condition is a steady condition or a transient condition according to the first information; and a first control unit configured to control, in a case where the current condition is the steady condition, an opening degree of a blow-off valve to be in a full open state, and in a case where the current condition is the transient condition, adopt fuzzy logic control, divide the transient condition into a plurality of transient grades according to the throttle opening change rate and the demanded torque gradient, and control the opening degree of the blow-off valve according to the transient grades.

[0013] According to still another aspect of the present application, there is provided a computer readable storage medium comprising a stored program, wherein the computer readable storage medium is caused to perform any of the turbocharging system adaptive control methods of the natural gas engine when the program is executed.

[0014] According to yet another aspect of the present application, there is provided an electronic device comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs comprise a program for performing any of the turbocharging system adaptive control methods of the natural gas engine.

[0015] The technical scheme of the application is applied to obtain the rotating speed, intake flow, first information and demand torque gradient of the natural gas engine, and based on the rotating speed and the intake flow, the preset rotating speed and intake flow MAP is used to determine whether the natural gas engine is in a low load working condition, wherein the first information includes the throttle opening degree change rate, the rotating speed change rate, the supercharging pressure and the load change slope, and the demand torque gradient is the ratio of the torque change amount required by the natural gas engine to the preset time window within the preset time window; in the case that the natural gas engine is in the low load working condition, the current working condition is determined to be a steady state working condition or a transient state working condition according to the first information; in the case that the current working condition is the steady state working condition, the opening degree of the exhaust valve is controlled to be in a full opening state, and in the case that the current working condition is the transient state working condition, the fuzzy logic control is adopted, the transient state working condition is divided into a plurality of transient state grades according to the throttle opening degree change rate and the demand torque gradient, and the opening degree of the exhaust valve is controlled according to the transient state grade. In the scheme, whether the natural gas engine is in the low load working condition is identified, if the natural gas engine is in the low load working condition, the steady state or the transient state is determined, in the case of the transient state, the transient state is graded by using the fuzzy logic control, and the opening degree of the exhaust valve is controlled according to the grading, so that fine control is realized, power delay or energy waste caused by the transient response in the prior art is avoided, the exhaust valve is fully opened in the steady state low load, unnecessary pump loss caused by the exhaust gas driving turbine is reduced, good economy is achieved, and the problem that the economy and the power performance of the natural gas engine under the low load are difficult to balance is solved. BRIEF DESCRIPTION OF DRAWINGS

[0016] The drawings accompanying the specification of the present application form a part thereof, serve to provide further understanding of the application, and together with the description of the application, serve to explain the application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for executing a supercharging system adaptive control method of a natural gas engine is shown according to an embodiment of the present application;

[0018] Figure 2 A flowchart of a supercharging system adaptive control method of a natural gas engine is shown according to an embodiment of the present application;

[0019] Figure 3 A preset rotating speed and intake flow MAP of a supercharging system adaptive control method of a natural gas engine is shown according to an embodiment of the present application;

[0020] Figure 4 A flowchart of a specific supercharging system adaptive control method of a natural gas engine is shown according to an embodiment of the present application;

[0021] Figure 5A diagram of adjustment slope of the exhaust valve opening degree in the part transient state of a specific turbocharging system adaptive control method of a natural gas engine is shown according to the embodiment of the application.

[0022] Figure 6 A structural block diagram of a turbocharging system adaptive control device of a natural gas engine is shown according to the embodiment of the application.

[0023] Among them, the above-mentioned drawings include the following reference signs:

[0024] 102, processor; 104, memory; 106, transmission device; 108, input and output device. DETAILED DESCRIPTION

[0025] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The technical scheme in the embodiments of the present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0026] In order for those skilled in the art to better understand the present application, the technical scheme in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, not necessarily to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] As introduced in the background, the exhaust valve control strategy in the prior art adopts full exhaust or full supercharging when running at low load, which is difficult to balance economy and power simultaneously. To solve the problem that economy and power of the natural gas engine in the prior art are difficult to balance at low load, the embodiments of the present application provide a turbocharging system adaptive control method of a natural gas engine, a turbocharging system adaptive control device of a natural gas engine, a computer readable storage medium and an electronic device.

[0029] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for an adaptive control method of a natural gas engine boost system according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0031] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the device information display method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned networks include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] An adaptive control method of a turbocharging system of a natural gas engine running on a mobile terminal, a computer terminal or a similar computing device is provided in the embodiment. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0033] Figure 2 is a flowchart of an adaptive control method of a turbocharging system of a natural gas engine according to the embodiment of the present application. As Figure 2 shown, the method comprises the following steps:

[0034] Step S201, obtaining the speed, intake flow, first information and demand torque gradient of the natural gas engine, and determining whether the natural gas engine is in a low load condition based on the above-mentioned speed and the above-mentioned intake flow, using a preset speed and intake flow MAP, wherein the first information includes throttle opening rate, speed change rate, boost pressure and load change slope, and the demand torque gradient is the ratio of the torque change amount required by the natural gas engine to the preset time window within the preset time window;

[0035] Specifically, first, the key data of the natural gas engine (hereinafter referred to as engine) running is obtained, including speed, intake flow, first information (including throttle opening rate, speed change rate, boost pressure and load change slope) and demand torque gradient. These parameters are crucial for real-time monitoring of engine state and making adaptive control decisions. The speed of the engine can be obtained by a crankshaft position sensor or a camshaft position sensor, and the intake flow can be obtained by an intake flow sensor. By comparing the real-time speed and intake flow of the engine with the preset speed and intake flow MAP, it is determined whether the engine is working in a low load condition. The preset speed and intake flow MAP is calibrated according to a large amount of experimental data, which can reflect the load condition of the engine under a specific speed and intake flow combination. As Figure 3 shown, the preset speed and intake flow MAP is used to determine whether it is in the region where the exhaust valve can be fully opened and fully closed (i.e. low load condition determination). Referring to Figure 3 , the region where the exhaust valve can be fully opened and fully closed is 1, i.e. when in region 1, whether the natural gas engine is in a low load condition.

[0036] The first information includes the throttle position change rate, speed change rate, boost pressure, and load change slope. These are key indicators reflecting the engine's current operating status and operating condition trends. The throttle position change rate refers to the magnitude of the throttle position change over a short period of time. It reflects the driver's operating intention and is an important indicator for identifying transient operating conditions. The throttle position change rate can be obtained from the throttle position sensor. The speed change rate indicates the rate of change of engine speed over time and is also a key parameter for determining transient operating conditions. The speed change rate can be calculated from the speed obtained by the crankshaft position sensor or camshaft position sensor. For example, the speed difference between two sampling points is calculated and divided by the time difference to obtain the instantaneous speed change rate. Boost pressure directly affects the intake air volume, which in turn affects the engine's power output and combustion efficiency. Boost pressure can be obtained from the boost pressure sensor. The load change slope reflects the load change trend over time and is helpful for predicting future operating conditions and adjusting control strategies. Load can be estimated by monitoring intake air flow and engine speed. The load change slope is the amount of load change per unit time. The load change slope is calculated by continuously monitoring the load.

[0037] The demand torque gradient measures the engine's ability to increase or decrease torque per unit time. It is calculated by calculating the ratio of the change in demand torque within a preset time window to the length of that window. The demand torque gradient helps quickly respond to varying levels of torque demand, particularly in transient conditions, allowing timely adjustment of the blow-off valve opening to meet power response and energy conservation requirements. The demand torque gradient is calculated by combining information such as the driver's accelerator pedal position, vehicle acceleration, and driving conditions. The demand torque gradient is calculated by monitoring changes in demand torque, specifically the change in demand torque per unit time.

[0038] Step S201 significantly improves the operating efficiency and power response of natural gas engines under low-load conditions. Specifically, by real-time monitoring and analysis of key parameters such as speed, intake air flow, throttle opening rate of change, speed rate of change, boost pressure, load change slope, and required torque gradient, combined with preset speed and intake air flow map, it accurately determines whether the engine is in a low-load condition. This establishes a comprehensive operating condition identification system, laying a solid foundation for subsequent selection of the purge valve control strategy.

[0039] Step S202: when the natural gas engine is in the low-load operating condition, determining whether the current operating condition is a steady-state operating condition or a transient operating condition based on the first information;

[0040] Specifically, the steady-state condition refers to a situation where the engine's operating parameters, such as speed, intake volume, load, etc., remain relatively stable over a longer period of time. In this case, the throttle opening rate, speed change rate, boost pressure, and load change slope all exhibit small fluctuations or are almost zero, indicating that the engine is in a stable operating state. The transient condition refers to a situation where the engine state changes rapidly, such as acceleration, deceleration, or sudden load increase. In the transient condition, the parameters in the first information will change significantly, such as the throttle opening rate increasing sharply, the speed change rate being significant, and the boost pressure and load change slope also increasing. The significant fluctuations in these indicators indicate that the engine is experiencing a transient condition. By continuously monitoring the first information (throttle opening rate, speed change rate, boost pressure, and load change slope), these data can reflect the dynamic relationship between the driver's operation and the engine's response. According to the preset threshold or evaluation criteria (such as the size of the throttle opening rate, whether the speed change rate exceeds a certain limit, etc.), it is determined whether the current condition is transient or still within the steady-state range.

[0041] In the low-load operating state of the natural gas engine, by real-time monitoring and analysis of the first information such as the throttle opening rate, speed change rate, boost pressure, and load change slope, the engine's steady-state and transient conditions are accurately distinguished. This distinguishing ability ensures that the bleed valve control strategy can accurately respond to the engine's real operating mode, thereby significantly improving the flexibility and efficiency of the engine's operation under low-load conditions.

[0042] Step S203, in the case where the current condition is the steady-state condition, the opening degree of the bleed valve is maintained in the fully open state, and in the case where the current condition is the transient condition, the opening degree of the bleed valve is controlled according to the fuzzy logic control, the transient condition is divided into multiple transient levels according to the throttle opening rate and the required torque gradient, and the opening degree of the bleed valve is controlled according to the transient level.

[0043] Specifically, in the case where the current condition is determined to be a steady-state condition, the opening degree of the bleed valve is maintained in the fully open state. The steady-state condition means that the engine operating parameters are relatively stable, and the torque and power demand do not change dramatically. The fully open bleed valve setting can minimize the pumping loss and improve the combustion efficiency, thereby significantly reducing fuel consumption and enhancing the economic performance of the engine under low-load conditions. This is because at steady low load, the engine does not need to generate excessive compressed air through the turbocharger, and the fully open bleed valve can allow excess exhaust gas to be directly discharged, avoiding unnecessary energy loss.

[0044] However, once the current operating condition is detected to be a transient operating condition, i.e., the engine faces acceleration, load mutation, etc., a more complex fuzzy logic control algorithm will be activated. At this time, according to the throttle opening rate and the demand torque gradient, the transient operating condition is subdivided into multiple levels, each level corresponding to a different speed and amplitude of the exhaust valve closing slope, thereby achieving fine control of the transient response. The core of fuzzy logic control is that it can handle non-binary and non-precise inputs, such as "throttle opening rate" and "demand torque gradient", which may have some uncertainty or gradual nature, rather than a simple "on" or "off" state. By mapping these inputs to pre-defined fuzzy sets, the severity of the transient operating condition can be evaluated, and the most suitable exhaust valve control strategy can be selected based on the evaluation result. For example, for a slight transient operating condition (such as gentle acceleration), a relatively gentle exhaust valve closing slope can be selected to ensure the smoothness of power output while avoiding excessive pumping loss. For a strong transient operating condition (such as emergency acceleration), a more steep exhaust valve closing slope can be used to quickly establish a higher boost pressure to meet the sudden torque demand and ensure the power response speed of the engine. This hierarchical control mechanism makes the adjustment of the exhaust valve more in line with the actual needs of the engine, ensuring both sufficient power support in transient state and good economic performance in steady state, thereby achieving a dynamic balance between power and economy of the natural gas engine in different operating conditions.

[0045] In summary, by distinguishing between steady and transient operating conditions and combining fuzzy logic control, the problem of considering both economy and power response of the engine under low load conditions is effectively solved, improving the adaptability and efficiency of the control system in dealing with complex operating environments.

[0046] Through this embodiment, multi-dimensional information such as speed, intake flow, throttle opening rate, speed change rate, boost pressure, and load change slope is integrated, combined with pre-set speed and intake flow MAP to accurately determine whether the natural gas engine is in a low load stage, and further accurately diagnose the operating condition as steady or transient. In steady state, the exhaust valve remains fully open, minimizing pumping loss and significantly enhancing economy; while in transient state, the method intelligently classifies transient levels based on the dynamic changes of throttle opening rate and demand torque gradient through fuzzy logic control, and then accurately regulates the exhaust valve opening to ensure rapid response and smooth transition of power output under different transient demand scenarios. This method not only effectively balances the power and economy of the natural gas engine under low load conditions, but also significantly improves the flexibility and overall performance of the engine through intelligent operating condition recognition and adaptive control, thereby solving the problem of balancing economy and power of the natural gas engine under low load.

[0047] In the implementation process, the method further includes: obtaining historical hidden state information and historical observation state information in a first preset time period, wherein the historical hidden state information includes historical steady state conditions and historical transient conditions, and the historical observation state information includes historical throttle opening rate, historical speed change rate, historical boost pressure and historical load change slope; determining the historical hidden state information and the historical observation state information as a training data set, inputting the training data set into a hidden Markov model for training until the hidden Markov model reaches a preset convergence condition, and obtaining a target hidden Markov model for future state prediction; inputting a current observation state into the target hidden Markov model for prediction to obtain a hidden state sequence in a second preset time period and a change probability of the hidden state sequence; comparing the change probability of the change probability of the hidden state sequence with a preset steady state probability threshold, and adjusting the opening degree of the bleed valve when the change probability exceeds the preset steady state probability threshold.

[0048] In this embodiment, a working condition prediction mechanism based on a hidden Markov model (HMM) is introduced to further improve the adaptive control accuracy of the power and economic performance of the natural gas engine under low load conditions. This mechanism collects and analyzes historical working condition data to predict future working conditions, thereby adjusting the opening degree of the bleed valve in advance to ensure that the engine can adapt to the upcoming changes more smoothly and efficiently. Under the framework of the hidden Markov model, the hidden state refers to the internal state of the system that cannot be directly observed, while the observation state is the external manifestation that can be directly measured by sensors or other devices. In this embodiment, the hidden state corresponds to the working condition category of the engine: steady state or transient state, while the observation state includes measurable specific parameters such as throttle opening rate, speed change rate, boost pressure and load change slope.

[0049] Specifically, engine operation data over a past period (i.e., a first preset time period) is acquired, including historical throttle opening rate of change, historical speed rate of change, historical boost pressure, and historical load change slope. These data reflect the past operation state of the engine and the change of external load. The setting of the first preset time period is mainly derived from engineering experience and experimental research and dynamic response and control theory. Engineers usually determine the appropriate preset time period length based on past experimental data and engine operation characteristics. For example, by analyzing the time required for the engine to transition from one operating condition to another, as well as the change rate and stability of various parameters (such as throttle opening, speed, boost pressure, etc.) during this process. The first preset time period should be long enough to capture the typical operating condition change period, but also avoid data redundancy and computational burden caused by being too long. The dynamic response characteristics of the bleed valve control and the supercharging system are also important references for setting the first preset time period, which involves the concepts of delay time and response time in control system theory. For example, if the bleed valve needs a few seconds to fully open or close, then the first preset time period should at least include this time span so that the model can take into account the dynamic behavior of the bleed valve; at the same time, the first preset time period also needs to match the torque response time of the engine, ensuring that in transient operating conditions, the adjustment of the bleed valve can timely affect the output torque of the engine, thereby better adapting to the driver's operation intention and road condition requirements. In addition, the setting of the first preset time period will also be affected by noise filtering, computational resources, prediction accuracy, and robustness. In summary, the setting of the first preset time period is a comprehensive consideration, balancing engine dynamic characteristics, control response time, noise filtering needs, and computational resource constraints, etc. The purpose is to build a model that can accurately reflect historical operating condition information and efficiently predict future states, in order to achieve precise control of the supercharging system of the natural gas engine.

[0050] Next, based on these historical data, historical operating condition states are identified and classified, i.e., historical steady-state operating conditions and historical transient operating conditions. This process involves in-depth analysis of the data, identifying periods with small parameter changes and stable engine operation as historical steady-state operating condition samples, while periods with large parameter fluctuations and rapid engine response are classified as historical transient operating condition samples.

[0051] Historical hidden state information and historical observed state information are combined into a training dataset for learning and training a hidden Markov model. The hidden Markov model infers a hidden state sequence based on the observed state information, i.e., a time series of steady-state or transient operating conditions. Model parameters are continuously updated to enable the model to accurately predict the relationship between the observed and hidden states until the model reaches a preset convergence condition. This means that the model's prediction accuracy meets a predetermined standard or the prediction error no longer improves significantly. The preset convergence condition can be set based on a maximum number of iterations or a parameter change threshold. Model training can be set to a maximum number of iterations. Once this limit is reached, training will terminate regardless of whether the model is truly stable. This helps prevent the model from falling into an endless training loop and also limits training time and computing resource consumption. During each iteration, model parameters (such as state transition probabilities and emission probabilities) are updated. If the parameter change within several consecutive iterations is less than a preset threshold, this indicates that the model parameters have stabilized and the learning curve has flattened. At this point, the model is considered to have converged and training is terminated. After model training is complete, a target hidden Markov model is obtained. This target hidden Markov model can be used to predict the hidden state sequence within a second preset time period based on current observed state information (such as the real-time throttle opening rate of change and engine speed rate of change). This is the series of possible steady-state and transient operating conditions that the engine may experience. The probability of a hidden state sequence change refers to the probability of transitioning from one hidden state to another at each moment in the second preset time period. For example, the probability of transitioning from a steady state to a transient state, or from a transient state back to a steady state, is predicted. This probability distribution not only predicts the hidden state at the next moment but also provides information about the uncertainty of future state transitions, which is crucial for understanding the continuity and randomness of system behavior. The second preset time period is primarily determined by the characteristics of the engine operating state transitions and the control system's response time requirements. The selection of the second preset time period needs to comprehensively consider the effectiveness of the operating condition prediction, the response time of the control system, engineering practice experience, and safety and performance considerations. Specifically, it needs to be long enough to capture potential operating condition changes, but not too long that the prediction becomes inaccurate or outdated. Generally speaking, the lower limit of this period is determined by the conversion time of the engine operating condition (such as from steady state to transient) and the complexity of the prediction model; the control system needs time to receive the prediction information and make corresponding adjustments, such as adjusting the opening of the bleed valve. The second preset time period should be greater than or equal to the time required for the control system to respond, so as to ensure that the prediction information can be effectively utilized before the actual operating condition changes and pre-adaptive adjustments can be made; based on past test and usage data, it can be understood on what time scale the engine tends to undergo operating condition conversion under specific operating conditions.For example, according to experience, the transition of a natural gas engine from low-load steady state to transient acceleration may occur within a few seconds to tens of seconds, so the second preset time period should cover this range; in order to ensure that the engine can obtain the required power in time under any circumstances, while avoiding unnecessary energy waste, the second preset time period should also take into account the need for safety redundancy and performance optimization. For example, in the case of emergency acceleration, a shorter prediction time window may be more advantageous, as this requires the system to respond more quickly.

[0052] The change probability of the predicted hidden state sequence is compared with a preset steady state probability threshold. When the change probability of the hidden state sequence exceeds the preset steady state probability threshold, it indicates that the engine is about to enter or is in a transient operating condition, and the opening of the bleed valve is adjusted in advance to optimize the power output and smoothness of the engine. This active control based on probability prediction improves the ability to respond to future operating condition changes and avoids the control delay caused by passive response. Specifically, when the change probability of the hidden state sequence exceeds the preset steady state probability threshold, it indicates that the engine is about to enter or is in a transient operating condition. At this time, based on this prediction result, the opening of the bleed valve is adjusted in advance to ensure that the engine can respond to transient operating conditions in time, while maintaining smoothness and high efficiency of operation. The specific steps for adjusting the opening of the bleed valve are: selecting the corresponding bleed valve closing slope according to the transient level. The higher the transient level, the steeper the closing slope of the bleed valve, in order to quickly increase the boost pressure and intake air quantity to meet the sudden increase in power demand. The opening of the bleed valve is adjusted in advance according to the selected bleed valve closing slope.

[0053] By introducing the hidden Markov model, not only can the current operating condition be responded to, but also the future operating condition change trend can be anticipated, so that a response can be made in advance, avoiding the power delay or energy waste that may be caused by lag response in traditional control. Through the learning of historical data by the hidden Markov model, the transition of the engine operating condition can be more accurately predicted, especially the transition from transient to steady state or vice versa under low load, thereby realizing more precise bleed valve control and ensuring that the power and economy of the engine can achieve the best balance under various operating conditions, significantly improving the overall performance and operating efficiency of the engine. In summary, through the learning and prediction of the hidden Markov model, not only can the engine operating condition type be judged in real time according to the current observation state, but also the future operating condition change trend within a short time can be predicted, thereby realizing more precise and forward-looking supercharging system control, significantly improving the flexibility, power and economy of the natural gas engine under low load operating conditions.

[0054] Further, in the case that the natural gas engine is in the low load working condition, determining the current working condition as a steady state working condition or a transient state working condition according to the first information comprises: monitoring the throttle opening rate of change, the speed rate of change, the boost pressure and the load change slope; and in the case that a preset condition is met within a preset transient state window length, determining the current working condition as the transient state working condition, wherein the preset condition comprises that the throttle opening rate of change is greater than a first threshold value, the speed rate of change is greater than a second threshold value, a fluctuation range of the boost pressure is greater than a third threshold value, and an absolute value of the load change slope is greater than a fourth threshold value.

[0055] Specifically, the throttle opening rate of change directly reflects the operation intention of the driver, especially during acceleration or deceleration, rapid change of the throttle opening is an important sign of transient state working condition; the speed rate of change, observing the rate of change of the engine speed over time, sudden increase or decrease of the speed, especially a larger change beyond the normal steady state fluctuation range, suggests the occurrence of transient state working condition; the boost pressure fluctuation range, evaluating the fluctuation of the boost pressure provided by the turbocharger over time, in steady state operation, the boost pressure is relatively stable; while in transient state working condition, the boost pressure will have a larger fluctuation; the load change slope, monitoring the rate of change of the engine load over time, an increase in the load change slope means a rapid response of the engine to external condition changes, which is also a feature of transient state working condition.

[0056] The preset transient window length is a short period of time for collecting and analyzing key parameters to determine whether a transient condition occurs. The preset transient window length needs to be selected according to the engine characteristics and the control system response time to ensure that the transient event can be captured in time without being too long to cause delay in identification. The preset conditions in the embodiment include: the throttle opening rate is greater than a first threshold value: if the throttle opening changes too fast within the preset transient window length and exceeds the first threshold value set in advance, it indicates that the engine is in the acceleration stage and enters the transient condition. The speed change rate is greater than a second threshold value: similarly, the rapid change of the speed also indicates the transient condition, so if the speed change rate exceeds the second threshold value, the change is considered as a transient signal. The boost pressure fluctuation range is greater than a third threshold value: significant fluctuations in boost pressure, if exceeding the third threshold value, mean that the process of transition from steady state to transient state is being experienced. The absolute value of the load change slope is greater than a fourth threshold value: the rapid change of engine load (whether increasing or decreasing), if the absolute value of its change slope exceeds the fourth threshold value, is also considered as a trigger factor of the transient condition. The setting of the first threshold value, the second threshold value, the third threshold value and the fourth threshold value comprehensively considers the bench test data, engine physical model analysis, typical driver operation mode, speed and range of condition change, and strict consideration of safety and performance. By quantitatively analyzing the transition characteristics of the engine between steady state and transient state, combined with historical data statistics and physical limits, each threshold value is designed to distinguish different conditions to ensure timely and accurate response to transient events, while avoiding the negative effects of excessive regulation.

[0057] By continuously monitoring the above-mentioned key parameters and checking whether the above-mentioned preset conditions are met (i.e. the throttle opening rate is greater than the first threshold value, the speed change rate is greater than the second threshold value, the boost pressure fluctuation range is greater than the third threshold value, and the absolute value of the load change slope is greater than the fourth threshold value) within the preset transient window length, it can be quickly and effectively determined whether the engine is currently in a transient condition. If the monitored parameters meet all the above-mentioned preset conditions, the current condition is marked as a transient condition, otherwise it is considered as a steady state condition. The setting of the preset transient window length not only refers to the average time of the engine transition from steady state to transient state under different driving modes, but also considers the shortest period required for the control system to perceive changes and respond. By analyzing a large amount of experimental data and historical operation records, combined with engine physical model prediction, the time range that can capture the early signal of the transient condition is found, while avoiding the influence of window length being too long to delay response or window length being too short to filter noise.

[0058] By monitoring the throttle opening rate, the speed change rate, the boost pressure fluctuation, and the load change slope in real time, and combining the threshold conditions in the preset transient window length, it can be quickly identified whether the engine is entering a transient state. This mechanism ensures that the response is accurate at the initial stage of the transient condition, and effectively balances the power and economy by adjusting the opening strategy of the bleed valve, reduces unnecessary pumping loss, and enhances the power response speed and smoothness of the engine. More importantly, it can adapt to various driving scenarios and driver operation habits, ensuring that the engine can maintain its optimal performance state under complex and variable operating conditions, improving the stability and reliability of the overall system. At the same time, by monitoring multiple parameters rather than a single indicator, the robustness and accuracy of the working condition determination are improved, reducing the possibility of misjudgment and ensuring stable operation under complex conditions.

[0059] In some embodiments of the present application, after determining whether the natural gas engine is in a low load condition using the preset speed and intake flow MAP, the method further comprises: if the natural gas engine is not in the low load condition, performing PID control on the bleed valve based on a preset boost pressure of the current operating condition of the natural gas engine, wherein the preset boost pressure is obtained by pre-calibration, and for each operating point under non-low load conditions, there is a unique preset boost pressure corresponding thereto.

[0060] Specifically, when it is determined that the natural gas engine is not in a low load condition, i.e., the engine is operating in a medium-high load or other specific condition, a PID control algorithm (Proportional-Integral-Derivative Control) is used to finely adjust the bleed valve. For each operating point under non-low load conditions, there is a pre-calibrated preset boost pressure, which is calculated accurately according to the engine characteristic curve and ideal operating state. The calibration process usually includes a large number of tests and data analysis, aiming to provide the engine with the optimal boost pressure under different conditions to achieve dual optimization of power and economy.

[0061] When the natural gas engine is operating in a non-low load condition, the preset boost pressure under the current condition is determined by looking up the preset MAP (mapping table or characteristic curve) according to the real-time monitored engine speed and intake flow. Then, using the PID algorithm, the actual measured boost pressure is compared with the preset boost pressure, the deviation is calculated, and the opening of the bleed valve is adjusted according to the deviation. The PID controller quickly responds to the deviation through the proportional term P, eliminates static error through the integral term I, and estimates future changes through the derivative term D, so that the bleed valve can be quickly and accurately adjusted to achieve the preset boost pressure, thereby ensuring that the engine performs well under various conditions.

[0062] This control strategy ensures that the bleed valve adjustment is more intelligent and personalized under non-low load conditions of the engine. By dynamically adjusting the boost pressure, it can meet the high requirements for power performance under medium and high load conditions, while also considering fuel economy during non-steady state operation. This fine control logic improves the overall performance of the engine. In summary, by introducing dynamic PID control and preset boost pressure concepts under non-low load conditions, intelligent adjustment of the boost system is achieved throughout the engine operating range, thereby comprehensively improving the overall performance of the engine.

[0063] The present embodiment can introduce a fusion control model that can consider multiple conditions such as steady state, transient state, and initial engine start-up, making the bleed valve adjustment more accurate. This model can identify the characteristics of different conditions and fuse them to provide a globally optimal control strategy. When it identifies that the engine is in a low load state at the initial start-up, it automatically switches to a special control mode to avoid unnecessary pumping loss during the start-up phase, while ensuring rapid establishment of boost pressure. As the engine stabilizes, it gradually transitions to the regular transient and steady state control modes. The multi-condition fusion intelligent control strategy can solve the control problem of the boost system during the initial start-up of the engine, achieving smooth transition from start-up to operation. Through comprehensive consideration of multiple conditions, the intelligence and flexibility of the control system are improved, which can cope with more complex driving situations and reduce energy waste during the initial start-up, further improving the economy and environmental performance of the engine under various operating conditions.

[0064] To further increase the power and economy of the engine under transient conditions, in the case where the current operating condition is a transient condition, fuzzy logic control is used to divide the transient condition into multiple transient levels based on the throttle opening rate and the required torque gradient. In the case where the current operating condition is a transient condition, the fuzzy logic control is used to fuzz the throttle opening rate into a first fuzzy set, a second fuzzy set, and a third fuzzy set, and to fuzz the required torque gradient into a first level, a second level, and a third level. A rule base is set based on the first fuzzy set, the second fuzzy set, the third fuzzy set, the first level, the second level, and the third level. The transient condition is divided into multiple transient levels using the rule base, and the transient levels include a first transient, a second transient, and a third transient.

[0065] Specifically, when determining that the natural gas engine is in transient condition, fuzzy logic control is introduced to subdivide the degree of transience into multiple levels in order to adjust the response of the bleed valve more accurately. This process involves two key parameters: throttle opening rate of change and demand torque gradient. The throttle opening rate of change is divided into three fuzzy sets, namely a first fuzzy set (indicating light acceleration, low throttle rate of change), a second fuzzy set (indicating medium acceleration, medium throttle rate of change), and a third fuzzy set (indicating emergency acceleration, high throttle rate of change). By fuzzifying the throttle rate of change, the true intention of the driver can be better understood and reflected, and reasonable control decisions can be made even when the throttle operation is between two clear levels. Similarly, the demand torque gradient is also fuzzified into a first level (small), a second level (medium), and a third level (large). This reflects the magnitude of the required power output change of the engine under transient conditions, further refining the description of transient conditions.

[0066] Then, based on the above-mentioned fuzzified throttle opening rate of change and demand torque gradient, a rule base is established to specify the specific division of transient levels under different combinations. For example, when the throttle rate of change is high and the demand torque gradient is large, the highest level of transient response is triggered, while when the throttle rate of change is low and the demand torque gradient is small, it is classified as the lowest level of transient level. Through this rule base, the transient condition can be accurately assigned to one of the three levels: first-level transient, second-level transient, or third-level transient, according to the instantaneous throttle rate of change and demand torque gradient. Each level corresponds to a different bleed valve closing slope and control strategy in order to reduce unnecessary energy loss while ensuring sufficient power response, optimizing the operating efficiency of the engine.

[0067] The use of fuzzy logic control enables a more intelligent response to the driver's operation, especially during transient conditions. The introduction of fuzzy logic control overcomes the discontinuity of control and the problem of excessive or insufficient response caused by the use of fixed thresholds in traditional control strategies. Through fine transient level division, the adjustment of the bleed valve becomes smoother and more efficient, not only improving driving comfort and safety, but also further increasing the power and economy of the engine under transient conditions.

[0068] In some embodiments of the present application, the opening of the bleed valve is controlled according to the above-mentioned transient level, including: if the transient level is a first-level transient, a first preset bleed valve closing slope is used to control the opening of the bleed valve; if the transient level is a second-level transient, a second preset bleed valve closing slope is used to control the opening of the bleed valve; if the transient level is a third-level transient, a third preset bleed valve closing slope is used to control the opening of the bleed valve, wherein the first preset bleed valve closing slope, the second preset bleed valve closing slope, and the third preset bleed valve closing slope are determined in a bench calibration process.

[0069] Specifically, the system uses fuzzy logic to determine the engine's transient level and automatically selects the appropriate bleed valve closing slope for adjustment. This mechanism ensures an appropriate response based on the intensity of the transient condition, avoiding unnecessary energy loss due to overreaction or power loss due to underreaction. Specifically, level 1 transient corresponds to mild acceleration or slight load changes. In these situations, the bleed valve opening is controlled using the first preset bleed valve closing slope. This results in a gentler response, ensuring a smooth transition during the transient and minimizing the impact on driving comfort. When transient conditions intensify slightly, such as during normal acceleration, the system switches to the second preset bleed valve closing slope. This is faster than the first level, more effectively increasing boost pressure to meet the engine's demand for higher torque. For urgent acceleration or high load changes, the third preset bleed valve closing slope is used, providing the fastest response level and designed to quickly build the required boost pressure to meet sudden power demands.

[0070] The determination of the first, second, and third preset bleed valve closing slopes requires calibration on a professional test bench. This process typically includes: Simulating different transient levels: Reproducing various transient operating conditions on the test bench, including light acceleration and deceleration, moderate acceleration, and emergency acceleration, to collect engine operating data under these conditions; Parameter optimization: By continuously adjusting the bleed valve closing slope, find the optimal slope value that can quickly respond to power demand without excessively sacrificing economy at each transient level; Verification and calibration: Applying the selected closing slopes to actual operating conditions, repeatedly testing and verifying them to ensure they can produce the expected results in the actual driving environment; Standard setting: Finally, based on the results of the test bench calibration, corresponding bleed valve closing slope standards are set for different transient levels.

[0071] By controlling the bleed valve closing slope that matches the transient level, the boost system can provide appropriate power support under transient conditions of varying intensities while minimizing pumping losses and other forms of energy waste. This graded response strategy improves the engine's power performance and fuel economy, especially under frequently changing driving conditions, demonstrating greater flexibility and efficiency, thereby enhancing user satisfaction and driving experience. At the same time, the preset slope based on bench calibration ensures the reliability and consistency of the control strategy. In short, by clarifying the bleed valve closing slope corresponding to different transient levels, more accurate and efficient management of the engine's transient conditions is achieved, which is of great significance to improving the overall performance and operating economy of natural gas engines.

[0072] The present embodiment can introduce an adaptive learning mechanism, which continuously optimizes the parameters of the fuzzy logic control, such as the boundaries of fuzzy sets, the weights of rule base, etc., through real-time data feedback. That is, it automatically adapts to changes in engine and vehicle characteristics during operation without frequent manual adjustments. Specifically, through a machine learning-based parameter self-optimization algorithm, the slope control of the bleed valve is optimally matched with the actual pumping loss, transient response time, and power output characteristics of the engine. The algorithm automatically adjusts the slope control curve through online learning to minimize fuel consumption and maximize power response. The adaptive learning mechanism reduces the dependence on manual calibration and adjustment, reduces maintenance costs, realizes self-adaptation to dynamic environment and engine characteristics, and improves the robustness and adaptability of the system. Through continuous optimization, performance can be continuously improved over time, better meeting user needs.

[0073] In some embodiments of the present application, the preset speed and intake flow MAP includes a hysteresis interval. When the changes in the speed and intake flow of the natural gas engine are within the hysteresis interval, the determination of the current operating condition does not change.

[0074] Specifically, the preset speed and intake flow MAP is used to store the set parameters of the engine at different speeds and intake flows, such as the opening of the bleed valve or the target value of the boost pressure. However, during engine operation, the speed and intake flow will fluctuate due to various factors (such as load changes, driver operation, etc.). If appropriate measures are not taken, it will frequently switch between different control modes, resulting in unstable control and reduced engine performance. To solve the above problem, a hysteresis interval is introduced in the preset speed and intake flow MAP. The hysteresis interval can be seen in Figure 3 In short, the hysteresis interval sets a tolerance range for the changes in speed and intake flow. Within this range, although the two parameters have changed, the current operating condition will not be re-evaluated, and the control strategy of the bleed valve will not be changed. For example, assume that the hysteresis interval is set to a speed change of no more than a preset value ΔN and an intake flow change of no more than a preset value ΔQ. When the control system determines that the natural gas engine is in a low load operating condition based on the current speed and intake flow, and adopts the corresponding control strategy, even if the two parameters fluctuate in the short term afterwards, as long as the change is less than ΔN and ΔQ, it will be determined that the current operating condition is still valid, and a new control mode switch will not be triggered. Only when the parameter change exceeds the upper limit of the hysteresis interval, will the operating condition be re-evaluated and the corresponding control adjustment will be made.

[0075] The setting of the hysteresis interval significantly improves the robustness when facing small disturbances, reduces unnecessary control actions, and avoids engine operation instability caused by frequent switching of control modes. In addition, this mechanism also helps to simplify the control logic, reduce the computational burden, make the control more efficient, and at the same time ensure the smoothness and safety of the engine in complex driving environments, and improve the overall driving experience and engine performance.

[0076] In order to enable those skilled in the art to more clearly understand the technical solutions of the present application, the implementation process of the natural gas engine supercharging system adaptive control method of the present application will be described in detail below in conjunction with specific embodiments.

[0077] The present embodiment relates to a specific natural gas engine supercharging system adaptive control method, as shown in Figure 4 , including region judgment, initial working condition state recognition, transient classification and bleed valve slope control, working condition prediction control.

[0078] 1. Region judgment:

[0079] First, according to the pre-calibrated MAP (preset speed and intake flow MAP) based on engine speed and intake flow, it is judged whether it is in the region where the bleed valve can be fully opened and fully closed (i.e. low load working condition judgment). The preset speed and intake flow MAP is a calibration MAP, which can be seen in Figure 3 , the region where the bleed valve can be fully opened and fully closed is 1. When not in the low load working condition, the bleed valve is controlled by PID according to the pre-set set pressure (each working condition point has its corresponding set pressure); when in the low load working condition, enter the next step of judgment in the dashed box in Figure 3 . The pre-calibrated MAP has a certain hysteresis interval (the hysteresis interval is also a calibration quantity, which is to prevent the bleed valve opening from changing abruptly) to prevent the bleed valve opening from fluctuating when the working condition jumps back and forth, affecting the stability of the engine operation.

[0080] 2. Initial working condition state recognition:

[0081] The main working condition characteristics can be covered according to the driver data (throttle opening rate), environmental parameters (intake temperature / pressure), system state (current boost pressure, speed), and historical data (load change trend) to accurately distinguish between steady and transient states. In this embodiment, if the throttle change rate is greater than 10% / s, the speed change rate is greater than 200 rpm / s, the boost pressure fluctuation is greater than 0.5 bar / s, and the load change slope absolute value is greater than 1% / s, it is determined to be transient, wherein the transient window length is 1s). The related signal processing module increases the time window filtering (the steady state window length is 5s) to avoid misjudgment of transient state caused by short disturbance.

[0082] When the initial operating condition is identified as steady state, the bleed valve adopts full open control mode to ensure economy. Conversely, when the initial operating condition is identified as transient, the next step of transient classification is entered.

[0083] 3. Transient classification and bleed valve slope control:

[0084] Fuzzy logic control is adopted to divide the transient level through throttle opening rate, demand torque gradient, etc. to avoid the step response inconsistency caused by fixed threshold. The input signals are fuzzified, for example, the throttle change rate is divided into three fuzzy sets (0%~10% for low-mild acceleration, 5%~20% for medium-medium acceleration, and 15%~30% for high-emergency acceleration, the overlap of the intervals represents “fuzziness”), and the demand torque gradient is divided into small, medium, and large. The rule base is formulated, for example, if the throttle change rate is “high” and the torque gradient is “large”, the transient level is level 3, and if the throttle change rate is “medium” and the torque gradient is “medium”, the transient level is level 2. The output is clarified, and the fuzzy rule calculation result is finally converted into a specific transient level (level 1 / 2 / 3) and bleed valve closing slope. The schematic diagram of bleed valve opening adjustment slope under classified transient operating condition is shown in FIG. 2. Figure 5

[0085] The specific transient level division, corresponding bleed valve transition slope (bleed valve closing slope), and application scenarios are shown in Table 1.

[0086] Table 1. Correspondence table of transient level and bleed valve transition slope

[0087]

[0088] 4. Operating condition prediction control:

[0089] It contains two types of states: hidden state (not directly observable, such as steady state and transient state) and observed state (directly measurable, such as sensor signals). By collecting historical data, the relationship between “hidden state” and “observed state” is learned, and a hidden Markov model is adopted, in which there are two states, i.e. hidden state and observed state. For example, the hidden state is level 3 transient state, and the probability of observing a throttle change rate > 20% is 80%. Then, according to the current observation signal, the most likely hidden state to appear in the future is inferred, i.e. the prediction stage in the hidden Markov model, according to the current observation state to infer the most likely hidden state sequence to appear in the future, which is beneficial to predict the probability of transient level changing from level 3 to level 2 to level 1 within 5s in the future). Compare it with the preset steady state probability threshold (the preset steady state probability threshold can be calibrated based on big data, and different models for different purposes have different calibration values) to execute the next operating condition of the bleed valve. The function of this module is to predict the probability distribution of the next operating condition, help to adjust the state of the bleed valve in advance, and make more reasonable actions. ​

[0090] Figure 4 "0: Target value full off" and "1: Target PID control" in the table are for different operation modes of the bleed valve, corresponding to the control strategies of the engine in different working conditions, aiming to optimize the performance of the engine, especially the balance between power and economy. "0: Target value full off" means that when the engine enters transient conditions such as emergency acceleration or load mutation, the target is to quickly increase the output torque. At this time, the control system immediately closes the bleed valve, forcing all exhaust gas to flow through the turbine, accelerating its speed, thereby quickly increasing the boost pressure and intake volume to meet the power demand. This immediate response mode is particularly suitable for scenarios where power needs to be quickly increased. "1: Target PID control" means that during non-transient or steady-state operation, the control system finely adjusts the bleed valve opening through the PID algorithm to maintain the boost pressure at the optimal level. PID control dynamically adjusts the proportional, integral, and derivative parameters based on the deviation of real-time engine state (such as speed, boost pressure, etc.) from the preset target value, ensuring stable operation of the boost system, avoiding energy waste, and optimizing economy without sacrificing power response. "0: Target value full off" is one of the responses of the control system in extreme transient conditions (such as three-stage transient - emergency acceleration), i.e., quickly closing the bleed valve to the full-off state to speed up power output. "1: Target PID control" is used in other conditions (including steady state and non-extreme transient) to maintain the bleed valve opening at the optimal level through the PID control algorithm, responding to transient demand while considering economy.

[0091] In this embodiment, based on sensor signals and time window filtering, it is determined whether the engine is currently in steady state or transient state. Fuzzy logic control is used to divide transient conditions into levels one (mild), two (moderate), and three (emergency), and match different bleed valve slopes. This achieves fine control and avoids the power delay or energy waste caused by the "one-size-fits-all" transient response in traditional control. The probability distribution of the next working condition is predicted to help adjust the state of the bleed valve in advance and make more reasonable actions. Compared with traditional control methods, this embodiment has the following core advantages: balancing response speed and smoothness: transient classification achieves gradual response, and predictive control offsets mechanical delay by acting in advance. Power is available when overtaking and there is no jerk when fuel is collected. Significant improvement in economy: traditional control methods close the bleed valve at low load, resulting in high pumping loss and poor economy. This embodiment keeps the bleed valve open at low load in steady state, providing good economy. Adapt to complex road conditions: through accurate identification of working condition prediction, adjust the opening of the bleed valve to the optimal opening of this road condition.

[0092] The embodiment of the present application further provides a natural gas engine supercharging system adaptive control device. It should be noted that the natural gas engine supercharging system adaptive control device of the embodiment of the present application can be used to execute the natural gas engine supercharging system adaptive control method provided by the embodiment of the present application. The device is used to realize the above-mentioned embodiment and preferred embodiment, and the description has been made and will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that realizes a predetermined function. Although the device described in the following embodiment is preferably realized in software, the realization of hardware, or a combination of software and hardware, is also possible and conceived.

[0093] The natural gas engine supercharging system adaptive control device provided by the embodiment of the present application is introduced below.

[0094] Figure 6 is a structural block diagram of the natural gas engine supercharging system adaptive control device according to the embodiment of the present application. As shown in Figure 6 , the device comprises a first acquisition unit 10, a determination unit 20 and a first control unit 30. The first acquisition unit is used to acquire the speed of the natural gas engine, the intake flow, the first information and the demand torque gradient, and to determine whether the natural gas engine is in a low load condition based on the above-mentioned speed and the above-mentioned intake flow, using a preset speed and intake flow MAP, wherein the first information includes the throttle opening rate, the speed change rate, the supercharging pressure and the load change slope, and the demand torque gradient is the ratio of the torque change amount required by the natural gas engine to the preset time window within the preset time window; the determination unit is used to determine whether the current condition is a steady state condition or a transient state condition according to the first information when the natural gas engine is in the low load condition; the first control unit is used to control the opening degree of the exhaust valve to be in a full open state when the current condition is the steady state condition, and to use fuzzy logic control to divide the transient state condition into a plurality of transient state grades according to the throttle opening rate and the demand torque gradient when the current condition is the transient state condition, and to control the opening degree of the exhaust valve according to the transient state grade.

[0095] Through the embodiment, multi-dimensional information such as rotation speed, intake air flow, throttle opening rate, rotation speed change rate, supercharging pressure and load change slope is integrated, and preset rotation speed and intake air flow MAP are combined to accurately determine whether the natural gas engine is in a low load stage, and further accurately diagnose the working condition state as steady state or transient state. In the steady state working condition, the bleed valve is kept fully open, which maximally reduces the pumping loss and significantly enhances the economy; and in the transient state working condition, the method intelligently divides the transient grade according to the throttle opening rate and the dynamic change of the required torque gradient through fuzzy logic control, and then accurately regulates the bleed valve opening, so as to ensure the rapid response and smooth transition of power output in different transient demand scenarios. This method not only effectively balances the power performance and economy of the natural gas engine under low load conditions, but also significantly improves the flexibility and overall performance of the engine operation through intelligent working condition recognition and adaptive control, thereby solving the problem that the economy and power performance of the natural gas engine under low load are difficult to balance.

[0096] In the specific implementation process, the above device further includes a second acquisition unit, a training unit, a prediction unit and an adjustment unit. The second acquisition unit is configured to acquire historical hidden state information and historical observation state information in a first preset time period, wherein the historical hidden state information includes historical steady state working conditions and historical transient state working conditions, and the historical observation state information includes historical throttle opening rate, historical rotation speed change rate, historical supercharging pressure and historical load change slope; the training unit is configured to determine the historical hidden state information and the historical observation state information as a training data set, and input the training data set into a hidden Markov model for training until the hidden Markov model reaches a preset convergence condition, to obtain a target hidden Markov model for future state prediction; the prediction unit is configured to input a current observation state into the target hidden Markov model for prediction, to obtain a hidden state sequence in a second preset time period and a change probability of the hidden state sequence; and the adjustment unit is configured to compare the change probability of the change probability of the hidden state sequence with a preset steady state probability threshold, and adjust the opening of the bleed valve when the change probability exceeds the preset steady state probability threshold.

[0097] By introducing the hidden Markov model, not only can respond to the current working condition, but also can look ahead to the trend of future working condition, so that it can make a response in advance, avoid the power lag or energy waste that may lead to the traditional control. Through the learning of the hidden Markov model to the historical data, it can more accurately predict the conversion of engine working condition, especially the transient to steady state or vice versa under low load, so as to realize more accurate control of the exhaust valve, ensure that the power and economy of the engine can achieve the best balance under various working conditions, significantly improve the overall performance and operating efficiency of the engine. In short, through the learning and prediction of the hidden Markov model, not only can the engine working condition type be judged in real time according to the current observation state, but also the future working condition change trend in a short time can be predicted, so as to realize more fine and forward-looking control of the supercharging system, significantly improve the flexibility, power and economy of the natural gas engine under low load working condition.

[0098] Further, the determination unit includes a monitoring module and a determination module. The monitoring module is configured to monitor the throttle opening rate, the speed change rate, the supercharging pressure and the load change slope. The determination module is configured to determine that the current working condition is the transient working condition when the preset conditions are met within the preset transient window length, wherein the preset conditions include that the throttle opening rate is greater than a first threshold, the speed change rate is greater than a second threshold, the fluctuation range of the supercharging pressure is greater than a third threshold, and the absolute value of the load change slope is greater than a fourth threshold.

[0099] By real-time monitoring of the throttle opening rate, the speed change rate, the supercharging pressure fluctuation and the load change slope, and combining the threshold conditions in the preset transient window length, it can quickly identify whether the engine is entering a transient state. This mechanism ensures that the transient working condition can be accurately responded to at the initial stage, and the power and economy are effectively balanced by adjusting the opening strategy of the exhaust valve, reducing unnecessary pumping loss and enhancing the power response speed and smoothness of the engine. More importantly, it can adapt to various driving scenarios and driver operation habits, ensuring that the engine can maintain the best performance state under complex and variable operating conditions, improving the stability and reliability of the overall system. At the same time, by monitoring multiple parameters rather than a single indicator, the robustness and accuracy of working condition determination are improved, the possibility of misjudgment is reduced, and the stable operation under complex working conditions is ensured.

[0100] In some embodiments of the present application, the device further comprises a second control unit configured to, after determining whether the natural gas engine is in the low load condition using the preset rotational speed and the intake flow rate MAP, perform PID control on the bleed valve based on a preset boost pressure corresponding to the current operating condition of the natural gas engine when the natural gas engine is not in the low load condition, wherein the preset boost pressure is obtained by pre-calibration, and for each operating point in the non-low load condition, there is a unique preset boost pressure corresponding thereto.

[0101] This control strategy ensures that the adjustment of the bleed valve in the non-low load condition of the engine is more intelligent and personalized. By dynamically adjusting the boost pressure, the high requirements for power performance in the medium and high load conditions can be met, while the fuel economy in the non-steady state operation is also taken into account. This fine control logic improves the overall performance of the engine. In summary, by introducing the concepts of dynamic PID control and preset boost pressure in the non-low load condition, intelligent adjustment of the boost system in the entire engine operating range is achieved, thereby comprehensively improving the overall performance of the engine.

[0102] In order to further increase the power and economy of the engine in transient conditions, the first control unit comprises a first fuzzy module, a second fuzzy module and a division module. The first fuzzy module is configured to, when the current condition is the transient condition, use the fuzzy logic control to fuzz the throttle opening rate change rate into a first fuzzy set, a second fuzzy set and a third fuzzy set, and to fuzz the required torque gradient into a first level, a second level and a third level. The second fuzzy module is configured to set a rule base based on the first fuzzy set, the second fuzzy set, the third fuzzy set, the first level, the second level and the third level. The division module is configured to divide the transient condition into a plurality of transient levels using the rule base, wherein the transient levels include a first transient, a second transient and a third transient.

[0103] The use of fuzzy logic control enables more intelligent response to the driver's operation, especially during transient conditions. The introduction of fuzzy logic control overcomes the problem of control discontinuity and excessive or insufficient response caused by the use of fixed thresholds in traditional control strategies. Through fine transient level division, the adjustment of the bleed valve becomes smoother and more efficient, not only improving the comfort and safety of driving, but also further increasing the power and economy of the engine in transient conditions.

[0104] In some embodiments of the present application, the first control unit comprises a first control module, a second control module and a third control module. The first control module is configured to control the opening degree of the exhaust valve using a first preset exhaust valve closing slope if the transient level is level one transient. The second control module is configured to control the opening degree of the exhaust valve using a second preset exhaust valve closing slope if the transient level is level two transient. The third control module is configured to control the opening degree of the exhaust valve using a third preset exhaust valve closing slope if the transient level is level three transient. The first, second and third preset exhaust valve closing slopes are determined during the bench calibration process.

[0105] By controlling the exhaust valve closing slope matched with the transient level, the supercharging system can provide appropriate power support under different intensity transient operating conditions, while minimizing pumping loss and other forms of energy waste. This hierarchical response strategy improves the power performance and fuel economy of the engine, especially under frequently changing driving conditions, showing higher flexibility and efficiency, improving user satisfaction and driving experience. At the same time, the preset slope based on the bench calibration ensures the reliability and consistency of the control strategy. In summary, by specifying the exhaust valve closing slope corresponding to different transient levels, more accurate and efficient management of engine transient operating conditions is achieved, which is of great significance to improve the overall performance and operating economy of natural gas engines.

[0106] In some embodiments of the present application, the preset speed and intake flow MAP comprises a hysteresis interval. If the change in the speed and intake flow of the natural gas engine is within the hysteresis interval, the determination of the current operating condition does not change.

[0107] The setting of the hysteresis interval significantly improves the robustness when facing small disturbances, reduces unnecessary control actions, and avoids engine operation instability that may be caused by frequent switching of control modes. In addition, this mechanism helps to simplify the control logic, reduce the computational burden, make the control more efficient, and at the same time ensure the smoothness and safety of the engine under complex driving conditions, improving the overall driving experience and engine performance.

[0108] The supercharging system adaptive control device of the natural gas engine comprises a processor and a memory. The first acquisition unit, the determination unit, the first control unit and the like are stored in the memory as program units, and the corresponding functions are realized by the processor executing the program units stored in the memory. The modules are located in the same processor; or the modules are located in different processors in any combination.

[0109] The memory can include non-persistent memory in a computer readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory, including at least one memory chip.

[0110] The embodiment of the present application provides a computer readable storage medium, which comprises a stored program, wherein the program controls a device where the computer readable storage medium is located to perform the adaptive control method of the supercharging system of the natural gas engine when the program is running.

[0111] The embodiment of the present application provides an electronic device, which comprises a processor, a memory and a program stored in the memory and capable of running on the processor, and the processor implements the steps of the adaptive control method of the supercharging system of the natural gas engine when running the program. The device herein can be a server, a PC, a PAD, a mobile phone or the like.

[0112] The present application also provides a computer program product, which is suitable for executing the program of the adaptive control method of the supercharging system of the natural gas engine when running on a data processing device.

[0113] Obviously, those skilled in the art should understand that the modules or steps of the present application can be realized by general computing devices, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices, and can be realized by program codes executable by the computing devices, so that they can be stored in storage devices and executed by the computing devices, and in some cases, the steps shown or described herein can be executed in different sequences, or they can be manufactured into individual integrated circuit modules or a single integrated circuit module. Therefore, the present application is not limited to any specific combination of hardware and software.

[0114] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0115] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0116] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0117] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0118] In one typical configuration, the computing device includes one or more processors (CPU's), input / output interfaces, network interfaces, and memory.

[0119] The memory can include non-persistent memory and / or persistent memory, such as flash memory, read-only memory (ROM), and / or volatile or non-volatile random access memory (RAM), among others. The memory is an example of computer-readable media.

[0120] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0121] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or apparatus that includes a list of elements does not only include those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0122] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Those skilled in the art can make various changes and modifications to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of adaptive control of a supercharging system of a natural gas engine, characterized in that, The method comprises: obtaining the speed of a natural gas engine, the intake flow, the first information and the demand torque gradient, and determining whether the natural gas engine is in a low load condition based on the speed and the intake flow using a preset speed and intake flow MAP, wherein the first information comprises an accelerator opening degree change rate, a speed change rate, a boost pressure and a load change slope, and the demand torque gradient is the ratio of the torque change amount required by the natural gas engine to a preset time window within the preset time window; in the case that the natural gas engine is in the low load condition, determining the current condition to be a steady state condition or a transient state condition according to the first information; in the case that the current condition is the steady state condition, controlling the opening degree of a bleed valve to be in a full open state, and in the case that the current condition is the transient state condition, using fuzzy logic control to divide the transient state condition into multiple transient state levels according to the accelerator opening degree change rate and the demand torque gradient, and controlling the opening degree of the bleed valve according to the transient state level; wherein, in the case that the current condition is the transient state condition, using fuzzy logic control to divide the transient state condition into multiple transient state levels according to the accelerator opening degree change rate and the demand torque gradient, comprising: using the fuzzy logic control to divide the accelerator opening degree change rate into a first fuzzy set, a second fuzzy set and a third fuzzy set, the first fuzzy set representing light acceleration with low accelerator opening degree change rate, the second fuzzy set representing medium acceleration with medium accelerator opening degree change rate, and the third fuzzy set representing emergency acceleration with high accelerator opening degree change rate; fuzzifying the demand torque gradient into a first level, a second level and a third level, the first level representing small demand torque gradient, the second level representing medium demand torque gradient, and the third level representing large demand torque gradient; setting a rule base based on the first fuzzy set, the second fuzzy set, the third fuzzy set, the first level, the second level and the third level, and using the rule base to divide the transient state condition into multiple transient state levels, the transient state levels comprising a first level transient state, a second level transient state and a third level transient state, in the case that the accelerator opening degree change rate is in the first fuzzy set and the demand torque gradient is in the first level, the transient state level is the first level transient state, in the case that the accelerator opening degree change rate is in the second fuzzy set and the demand torque gradient is in the second level, the transient state level is the second level transient state, and in the case that the accelerator opening degree change rate is in the third fuzzy set and the demand torque gradient is in the third level, the transient state level is the third level transient state.

2. The method of claim 1, wherein, The method further comprises: obtaining historical hidden state information and historical observation state information within a first preset time period, wherein the historical hidden state information comprises historical steady state conditions and historical transient state conditions, and the historical observation state information comprises historical accelerator opening degree change rates, historical speed change rates, historical boost pressures and historical load change slopes; The historical hidden state information and the historical observed state information are determined as a training data set, and the training data set is input to a hidden Markov model for training until the hidden Markov model reaches a preset convergence condition, so as to obtain a target hidden Markov model for future state prediction; The current observed state is input to the target hidden Markov model for prediction, so as to obtain a hidden state sequence in a second preset time period and a change probability of the hidden state sequence; The change probability of the change probability of the hidden state sequence is compared with a preset steady-state probability threshold, and in a case where the change probability exceeds the preset steady-state probability threshold, the opening degree of the bleed valve is adjusted.

3. The method of claim 1, wherein, In a case where the natural gas engine is in the low load working condition, it is determined according to the first information that the current working condition is a steady-state working condition or a transient working condition, comprising: Monitoring the throttle opening rate, the speed change rate, the boost pressure and the load change slope; In a case where a preset condition is met within a preset transient window length, it is determined that the current working condition is the transient working condition, wherein the preset condition comprises that the throttle opening rate is greater than a first threshold, the speed change rate is greater than a second threshold, the fluctuation range of the boost pressure is greater than a third threshold, and the absolute value of the load change slope is greater than a fourth threshold.

4. The method of claim 1, wherein, After determining whether the natural gas engine is in a low load working condition by using a preset speed and intake flow MAP, the method further comprises: In a case where the natural gas engine is not in the low load working condition, performing PID control on the bleed valve based on a preset boost pressure of the current running working condition of the natural gas engine, Wherein, the preset boost pressure is obtained by pre-calibration, and for each working condition point under a non-low load working condition, there is a unique preset boost pressure corresponding thereto.

5. The method of claim 1, wherein, Controlling the opening degree of the bleed valve according to the transient level, comprising: If the transient level is a first-level transient, a first preset bleed valve closing slope is used to control the opening degree of the bleed valve; If the transient level is a second-level transient, a second preset bleed valve closing slope is used to control the opening degree of the bleed valve; If the transient level is a third-level transient, a third preset bleed valve closing slope is used to control the opening degree of the bleed valve, Wherein, the first preset bleed valve closing slope, the second preset bleed valve closing slope and the third preset bleed valve closing slope are determined in a bench calibration process.

6. The method of claim 1, wherein, The preset speed and intake flow MAP comprises a hysteresis interval, and in a case where the change of the speed and the intake flow of the natural gas engine is within the hysteresis interval, it is determined that the judgment of the current working condition does not change.

7. A turbocharging system adaptive control device for a natural gas engine, characterized by, Comprising: The first obtaining unit is configured to obtain a speed of a natural gas engine, an intake flow, first information, and a required torque gradient, and determine whether the natural gas engine is in a low load condition based on the speed and the intake flow using a preset speed and intake flow MAP, wherein the first information includes a throttle opening degree change rate, a speed change rate, a boost pressure, and a load change slope, and the required torque gradient is a ratio of a torque change amount required by the natural gas engine to a preset time window. The determining unit is configured to determine, in a case where the natural gas engine is in the low load condition, whether a current condition is a steady state condition or a transient state condition according to the first information. The first control unit is configured to control an opening degree of a bleed valve to be in a full open state in a case where the current condition is the steady state condition, and to control the opening degree of the bleed valve according to a transient state grade in a case where the current condition is the transient state condition by using a fuzzy logic control to divide the transient state condition into a plurality of transient state grades according to the throttle opening degree change rate and the required torque gradient. The first control unit is configured to divide the throttle opening degree change rate into a first fuzzy set, a second fuzzy set, and a third fuzzy set by using the fuzzy logic control, wherein the first fuzzy set represents a slight acceleration with a low throttle opening degree change rate, the second fuzzy set represents a medium acceleration with a medium throttle opening degree change rate, and the third fuzzy set represents an emergency acceleration with a high throttle opening degree change rate; to fuzz the required torque gradient into a first grade, a second grade, and a third grade, wherein the first grade represents a small required torque gradient, the second grade represents a medium required torque gradient, and the third grade represents a large required torque gradient; to set a rule base based on the first fuzzy set, the second fuzzy set, the third fuzzy set, the first grade, the second grade, and the third grade; and to divide the transient state condition into a plurality of the transient state grades by using the rule base, wherein the transient state grades include a first transient state, a second transient state, and a third transient state, the first transient state is obtained in a case where the throttle opening degree change rate is in the first fuzzy set and the required torque gradient is in the first grade, the second transient state is obtained in a case where the throttle opening degree change rate is in the second fuzzy set and the required torque gradient is in the second grade, and the third transient state is obtained in a case where the throttle opening degree change rate is in the third fuzzy set and the required torque gradient is in the third grade.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium includes a stored program, wherein the program controls a device in which the computer readable storage medium is located to perform the adaptive control method of the supercharging system of the natural gas engine according to any one of claims 1 to 6 when the program is executed.

9. An electronic device, comprising: The computer readable storage medium includes a stored program, wherein the program controls a device in which the computer readable storage medium is located to perform the adaptive control method of the supercharging system of the natural gas engine according to any one of claims 1 to 6 when the program is executed. One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including programs for performing the adaptive control method of the supercharging system of the natural gas engine according to any one of claims 1 to 6.

Images