Burner regeneration temperature control method and device based on energy estimation

Abstract

The invention provides a combustor regeneration temperature control method and device based on energy estimation, and relates to engines, and the method comprises the steps that operation data are obtained, the operation data are input into a heat dynamic model, and particulate matter accumulation prediction data are obtained; and when the particulate matter accumulation prediction data is higher than the first particulate matter accumulation threshold value and lower than the second particulate matter accumulation threshold value, a passive regeneration method is selected to be adopted. And when the particulate matter accumulation prediction data is higher than a second particulate matter accumulation threshold value, an active regeneration method is selected and adopted, the active regeneration method calculates a first heat difference according to the operation data and the particulate matter accumulation prediction data, and then a PID controller conducts multi-stage control on the combustor according to the first heat difference. And when the particulate matter accumulation prediction data is reduced to be lower than the first particulate matter accumulation threshold value again, the active regeneration process or the passive regeneration process is stopped. And through particulate matter accumulation data prediction and multi-stage precise heat PID control, the combustion process of the DPF regeneration temperature is optimized, and the energy utilization efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of engine technology, and in particular to a burner regeneration temperature control method and device based on energy estimation. Background Art

[0002] The Diesel Particulate Filter (DPF) in the power system plays an important role in reducing particulate matter generated during diesel vehicle emissions. During the combustion process of a diesel engine, complex tiny particles are formed due to incomplete combustion. The continuous accumulation of these particles will affect the normal function of the DPF. At present, the commonly used DPF regeneration temperature control method is to increase the temperature in the DPF by injecting fuel in front of the DOC (Diesel Oxidation Catalyst), so that the tiny particles are oxidized, thereby allowing the DPF to regain the ability to capture tiny particles. However, this method has many problems. On the one hand, the combustion efficiency is affected by factors such as the engine operating conditions and the injection strategy, and not all injected fuel can be completely burned; on the other hand, due to the inertia and hysteresis of the temperature, accurate regeneration control cannot be achieved, and more energy is consumed, which seriously affects the performance of the entire system.

[0003] Therefore, how to efficiently and stably and accurately control the DPF regeneration temperature is a technical problem that technicians in this field need to solve. Summary of the invention

[0004] The present invention provides a burner regeneration temperature control method and device based on energy estimation, which are used for performing stable and accurate DPF regeneration temperature control.

[0005] In a first aspect, a burner regeneration temperature control method based on energy estimation is provided. The method comprises:

[0006] Obtaining operating data, inputting the operating data into a thermal dynamic model, and obtaining particle accumulation prediction data;

[0007] When the particle accumulation prediction data is higher than a first particle accumulation threshold and lower than a second particle accumulation threshold, a passive regeneration method is selected, and the first particle accumulation threshold is lower than the second particle accumulation threshold;

[0008] When the particle accumulation prediction data is higher than the second particle accumulation threshold, an active regeneration method is selected, and the active regeneration method calculates a first heat difference according to the operation data and the particle accumulation prediction data, and then the PID controller performs multi-level control on the burner according to the first heat difference;

[0009] When the particle accumulation prediction data drops below the first particle accumulation threshold again, the active regeneration or passive regeneration process is stopped.

[0010] In one possible design, the operating data includes engine target temperature, burner outlet temperature, engine exhaust flow, engine exhaust temperature and heat loss data.

[0011] In one possible design, the thermal dynamic model is pre-trained by historical operation data;

[0012] The heat dynamics model includes a time series module, a convolutional neural network module, and a random forest module.

[0013] In one possible design, the passive regeneration method includes:

[0014] The temperature of the DPF is increased to a first preset temperature according to the operating data, and the first preset temperature ranges from 280°C to 360°C.

[0015] Optionally, the active regeneration method calculates the first heat difference according to the operating data and the particulate matter accumulation prediction data, including:

[0016] Calculate the required heat based on the engine target temperature, burner outlet temperature and burner heat exchange efficiency;

[0017] Calculate the actual heat according to the engine exhaust flow, engine exhaust temperature and exhaust gas heat exchange efficiency;

[0018] A first heat difference is calculated based on the required heat, the actual heat, the heat loss data and the particle accumulation prediction data.

[0019] In a possible design, the PID controller performs multi-level control on the burner according to the first heat difference, including:

[0020] When the first heat difference is within a first preset heat difference range, the fuel supply of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the primary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply of the burner and the particle accumulation prediction data;

[0021] When the first heat difference exceeds the first preset heat difference range, the fuel supply of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the secondary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply of the burner and the particle accumulation prediction data;

[0022] The primary fuel supply range is smaller than the secondary fuel supply range.

[0023] Optionally, the gain parameters of the PID controller include proportional gain, integral gain and differential gain;

[0024] The initial setting of the gain parameters was determined by the Ziegler-Nichols method.

[0025] Optionally, the gain parameter adjustment of the PID controller is modified by the MPC adaptive module;

[0026] The MPC adaptive module is pre-trained by the historical operating data and historical particle accumulation data of the burner;

[0027] The MPC adaptive module performs optimal control calculations on the burner operation data and particle accumulation prediction data to obtain the adaptive gain parameters of the PID controller.

[0028] In a possible design solution, the method further includes:

[0029] When the particle accumulation prediction data is higher than the third particle accumulation threshold, an abnormal excess particle alarm is issued, and the fuel supply of the burner is directly adjusted to the third level fuel supply range.

[0030] In a second aspect, a burner regeneration temperature control device based on energy estimation is provided. The device comprises:

[0031] An acquisition module, used to acquire operation data, input the operation data into a thermal dynamic model, and acquire particle accumulation prediction data;

[0032] A passive regeneration module, for selecting a passive regeneration method when the particle accumulation prediction data is higher than a first particle accumulation threshold and lower than a second particle accumulation threshold, and the first particle accumulation threshold is lower than the second particle accumulation threshold;

[0033] An active regeneration module, for selecting an active regeneration method when the particle accumulation prediction data is higher than a second particle accumulation threshold, wherein the active regeneration method calculates a first heat difference according to the operation data and the particle accumulation prediction data, and then the PID controller performs multi-stage control on the burner according to the first heat difference;

[0034] The recovery module is used to stop the active regeneration or passive regeneration process when the particle accumulation prediction data drops below the first particle accumulation threshold again.

[0035] The present invention provides a burner regeneration temperature control method and device based on energy estimation. The method includes: obtaining operation data, inputting the operation data into a thermal dynamic model, and obtaining particle accumulation prediction data. When the particle accumulation prediction data is higher than a first particle accumulation threshold and lower than a second particle accumulation threshold, a passive regeneration method is selected, and the first particle accumulation threshold is less than the second particle accumulation threshold. When the particle accumulation prediction data is higher than the second particle accumulation threshold, an active regeneration method is selected. The active regeneration method calculates a first heat difference according to the operation data and the particle accumulation prediction data, and then the PID controller performs multi-level control on the burner according to the first heat difference. When the particle accumulation prediction data drops below the first particle accumulation threshold again, the active regeneration or passive regeneration process is stopped. That is, by obtaining the operation data and inputting it into the thermal dynamic model, the particle accumulation situation is analyzed and predicted in real time, so that the current particle accumulation situation can be understood more immediately and corrective measures can be taken in advance. In addition, two methods, passive regeneration and active regeneration, are designed according to the particle accumulation prediction data, which can optimize energy use and extend the life of the equipment. In the active regeneration method, the first heat difference is calculated based on the operating data and the particle accumulation prediction data, and the PID controller performs multi-level control on the burner based on the first heat difference, which can more accurately control the fuel supply and valve opening of the burner, ensure the effective combustion of the particles, and avoid excessive heating and equipment loss. Compared with the traditional regeneration method using direct heating, the present invention provides a more comprehensive control method to better cope with the changing particle accumulation situation, improve the overall efficiency of the burner through multi-level control to reduce unnecessary energy consumption, achieve more accurate renewable control, and extend the service life of the equipment. At the same time, it can also prevent extreme or harmful heat fluctuations to ensure that the power system is reliable and efficient.

[0036] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements.

[0038] Figure 1 It is a flow chart of a burner regeneration temperature control method based on energy estimation according to an embodiment of the present invention;

[0039] Figure 2 It is a schematic diagram of the structure of the thermal dynamic model of an embodiment of the present invention;

[0040] Figure 3 A flow chart of calculating a first heat difference according to an embodiment of the present invention;

[0041] Figure 4 It is a broken line diagram of the DPF temperature change according to an embodiment of the present invention;

[0042] Figure 5 It is a schematic structural diagram of a burner regeneration temperature control device based on energy estimation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0044] It should be noted that the description of the embodiments of the present invention is only for more clearly illustrating the technical solutions of the embodiments of the present invention, and does not constitute a limitation on the technical solutions provided by the embodiments of the present invention.

[0045] The embodiment of the present invention provides a burner regeneration temperature control method based on energy estimation. Figure 1 FIG. 1 is a flow chart of a burner regeneration temperature control method based on energy estimation according to an embodiment of the present invention. Figure 1 , the method comprising:

[0046] S101. Obtain operating data, input the operating data into a thermal dynamic model, and obtain particle accumulation prediction data.

[0047] In this embodiment, the particle accumulation prediction data is obtained through the thermal dynamic model to prevent the accumulation of particle matter in advance, which can reduce the total particle emission, so as to judge in advance whether it is necessary to start a specific regeneration strategy in the future, and avoid the waste of resources caused by excessive maintenance or repair.

[0048] Optionally, the operating data includes engine target temperature, burner outlet temperature, engine exhaust flow, engine exhaust temperature and heat loss data.

[0049] In this embodiment, by monitoring and recording operating data such as engine target temperature, burner outlet temperature, engine exhaust flow, engine exhaust temperature and heat loss data, a sufficient data basis is provided for subsequent particulate matter accumulation prediction and DPF regeneration control.

[0050] Optionally, the thermal dynamic model is pre-trained by historical operating data of the burner;

[0051] The heat dynamics model includes a time series module, a convolutional neural network module, and a random forest module.

[0052] Figure 2 FIG. 1 is a schematic diagram of the structure of the thermal dynamic model of an embodiment of the present invention. Figure 2 As shown:

[0053] Among them, the time series module LSTM (Long Short-Term Memory) has a total of 64 units, and the output data is 64 dimensions; the convolutional neural network module CNN (Convolutional Neural Networks) includes a convolution layer with 32 3x3 filters, a ReLU (Rectified Linear Unit) activation layer, a 2x2 maximum pooling layer, a convolution layer with 64 3x3 filters, a ReLU activation layer and a pooling layer, and the output data is 64 dimensions; the random forest module consists of 100 decision trees, each with a maximum depth of 10, and the output data is 1 dimension.

[0054] In this embodiment, a complex model structure is used to fully utilize the historical operating data of the burner to provide a high-precision prediction of particulate accumulation for DPF regeneration control.

[0055] S102. When the particle accumulation prediction data is higher than a first particle accumulation threshold and lower than a second particle accumulation threshold, a passive regeneration method is selected, and the first particle accumulation threshold is lower than the second particle accumulation threshold.

[0056] For example, the preset first particle accumulation threshold (Threshold_1) is 10g / L, and the second particle accumulation threshold (Threshold_2) is 20g / L. When the particle accumulation prediction data output by the thermal dynamic model is 15g / L, which is higher than the first particle accumulation threshold (Threshold_1) of 10g / L and lower than the second particle accumulation threshold (Threshold_2) of 20g / L, the passive regeneration method is automatically selected for DPF regeneration control.

[0057] In this embodiment, when the particle accumulation prediction data is higher than the first particle accumulation threshold and lower than the second particle accumulation threshold, a passive regeneration method is selected to reasonably control the accumulation of particle matter, reduce the demand for additional energy, and reduce the energy consumption and maintenance cost of the equipment.

[0058] Optionally, the passive regeneration method comprises:

[0059] The temperature of the DPF is increased to a first preset temperature according to the operating data, and the first preset temperature ranges from 280°C to 360°C.

[0060] In the present invention, the passive regeneration method adopts the DOC fuel injection method. Among them, in the early stage of DOC fuel injection, a lower injection amount is selected for preliminary temperature increase to avoid the impact of sudden temperature rise on the DPF. Then, as the temperature gradually approaches the first preset temperature, the injection amount is gradually increased, and the stability of the injection frequency is maintained to ensure that the internal temperature of the DPF is maintained within the target range. Since the passive regeneration method does not require additional external energy input, it mainly uses DOC fuel injection to generate heat to reach the first preset temperature, so that the particulate matter is burned, which significantly reduces energy consumption while also achieving efficient particulate matter removal.

[0061] In this embodiment, the first preset temperature range of passive regeneration is set to 280° C.-360° C. to meet the partial low energy consumption requirements for DPF regeneration and reduce the cost of DPF regeneration control.

[0062] S103. When the particle accumulation prediction data is higher than the second particle accumulation threshold, an active regeneration method is selected. The active regeneration method calculates a first heat difference based on the operating data and the particle accumulation prediction data, and then the PID controller performs multi-stage control on the burner based on the first heat difference.

[0063] For example, the preset second particulate matter accumulation threshold (Threshold_2) is 20g / L. When the particulate matter accumulation prediction data output by the thermal dynamic model is 30g / L, which is higher than the second particulate matter accumulation threshold (Threshold_2) of 20g / L, the active regeneration method is automatically selected for DPF regeneration control.

[0064] In this embodiment, when the predicted data of particle accumulation is higher than the second particle accumulation threshold, the active regeneration method is selected to perform adaptive adjustment according to the predicted data of particle accumulation to ensure active regeneration in the most appropriate time period, thereby reducing unnecessary combustion and energy consumption and improving fuel efficiency. In addition, the active regeneration method uses a PID controller to perform multi-stage control of the burner according to the first heat difference, which can achieve precise adjustment of the DPF regeneration control and improve the overall reliability and operational stability of the system. Compared with the traditional DPF regeneration control method, the method of calculating the heat difference can more effectively avoid temperature overshoot, has stronger adaptability, ensures more precise temperature control during the regeneration process, and makes the regeneration process safer and more reliable.

[0065] Optionally, the active regeneration method calculates the first heat difference according to the operating data and the particulate matter accumulation prediction data, including:

[0066] Calculate the required heat based on the engine target temperature, burner outlet temperature and burner heat exchange efficiency;

[0067] Calculate the actual heat according to the engine exhaust flow, engine exhaust temperature and exhaust gas heat exchange efficiency;

[0068] A first heat difference is calculated based on the required heat, the actual heat, the heat loss data and the particle accumulation prediction data.

[0069] First, the formula for calculating the required heat based on the engine target temperature, burner outlet temperature and burner heat exchange efficiency is as follows:

[0070] Q necessary =(T target -T out )×η e .

[0071] Among them, Q necessary is the required heat, T target is the target engine temperature, T out is the burner outlet temperature, η e is the burner heat exchange efficiency.

[0072] Secondly, the formula for calculating the actual heat based on the engine exhaust flow, engine exhaust temperature and exhaust gas heat exchange efficiency is as follows:

[0073] Q actual =F e ×(T exh -T cold )×η f .

[0074] Among them, Q actual is the actual heat, F e is the engine exhaust flow rate, T exh is the engine exhaust temperature, T cold is the ambient temperature, η f is the exhaust gas heat exchange efficiency.

[0075] Finally, the formula for calculating the first heat difference based on the required heat, actual heat, heat loss data and particle accumulation prediction data is as follows:

[0076] Q1=Q necessary -Q actual +Q loss +(k×M pre ).

[0077] Among them, Q1 is the first heat difference, Q loss is the heat loss data, k is the parameter for calculating the heat loss of particles based on the particle accumulation prediction data (more particles will lead to increased heat demand), Mpre is the particle accumulation prediction data. In addition, k is calculated based on the historical particle accumulation prediction data collected in advance and the corresponding particle loss heat. The calculation formula of k is:

[0078] k= ΔQ M .

[0079] ΔM pre

[0080] Among them, ΔQ M is the heat loss difference per unit particle, ΔM pre It is the unit particle accumulation prediction data.

[0081] Figure 3 Flow chart of calculating the first heat difference according to an embodiment of the present invention, as shown in FIG. Figure 3 shown.

[0082] In this embodiment, the active regeneration method calculates the first heat difference based on the operating data and the particulate matter accumulation prediction data, and then the PID controller performs multi-stage control of the burner based on the first heat difference. Compared with the commonly used method of calculating the temperature difference, more heat losses are taken into account, and the DPF active regeneration control can be adjusted more accurately to supplement the required heat.

[0083] Optionally, the PID controller performs multi-stage control on the burner according to the first heat difference, including:

[0084] When the first heat difference is within a first preset heat difference range, the fuel supply of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the primary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply of the burner and the particle accumulation prediction data;

[0085] When the first heat difference exceeds the first preset heat difference range, the fuel supply of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the secondary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply of the burner and the particle accumulation prediction data;

[0086] The primary fuel supply range is smaller than the secondary fuel supply range.

[0087] Among them, the first preset heat difference range, the primary fuel supply range and the secondary fuel supply range can all be adjusted according to actual conditions.

[0088] Among them, when the first heat difference is within the first preset heat difference range, the fuel supply of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the primary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply of the burner and the particle accumulation prediction data. For example, the first preset heat difference range can be [-50kJ, 50kJ]. When the calculated first heat difference is 30kJ, within the first preset heat difference range, the PID controller can output the fuel supply adjustment signal according to the first heat difference, and then map it to the primary fuel supply range according to the fuel supply adjustment signal to obtain the final fuel supply of the burner to be adjusted. If the primary fuel supply range can be [1L / min, 5L / min], and the fuel supply adjustment signal output by the PID controller is 50%, then the fuel supply of the burner after mapping it to the primary fuel supply range = ((50%) / (50-(-50)))×(5-1)+1=1.02L / min. At the same time, the formula for adjusting the valve opening accordingly according to the fuel supply amount and the particulate matter accumulation prediction data is: valve opening = α×(fuel supply amount / particulate matter accumulation prediction data), where α is a preset coefficient determined by experiments.

[0089] Among them, when the first heat difference exceeds the first preset heat difference range, the fuel supply of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the secondary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply of the burner and the particle accumulation prediction data. For example, the first preset heat difference range can be [-50kJ, 50kJ]. When the calculated first heat difference is 70kJ, within the first preset heat difference range, the PID controller can output a fuel supply adjustment signal according to the first heat difference, and then map it to the primary fuel supply range according to the fuel supply adjustment signal to obtain the final fuel supply of the burner to be adjusted. If the primary fuel supply range is [5L / min, 15L / min], and the fuel supply adjustment signal output by the PID controller is 50%, then the fuel supply of the burner after mapping it to the primary fuel supply range = ((50%) / (50-(-50))×(15-5)+5=5.05L / min. At the same time, the formula for adjusting the valve opening according to the fuel supply and the particle accumulation prediction data is: valve opening = α×(fuel supply / particle accumulation prediction data), where α is a preset coefficient determined by experiments.

[0090] In this embodiment, the PID controller performs multi-level control on the burner according to the first heat difference, ensuring the accuracy and efficiency of the active regeneration process. The multi-level control mechanism can select the appropriate fuel supply range and the corresponding valve opening according to the different heat differences. For mild accumulation of particulate matter, active regeneration control can be completed by only slightly increasing the fuel supply. For severe accumulation of particulate matter, the fuel supply can be quickly increased to meet the high temperature conditions required for active regeneration control.

[0091] Optionally, the gain parameters of the PID controller include proportional gain, integral gain and differential gain;

[0092] The initial setting of the gain parameters was determined by the Ziegler-Nichols method.

[0093] Among them, the Ziegler-Nichols method is a commonly used method for setting the gain parameters of the PID controller, which determines the optimal gain parameters of the PID controller through the system's response. The basic steps of the Ziegler-Nichols method are as follows: First, set the integral gain Ki and the differential gain Kd to 0, that is, Ki = 0, Kd = 0. Then, gradually increase the proportional gain Kp until the system oscillates. The proportional gain value at this time is recorded as Ku, and the oscillation period is recorded as Tu. Finally, according to the values ​​of the proportional gain value Ku and the oscillation period Tu, the proportional gain Kp, integral gain Ki and differential gain Kd of the PID controller are calculated in turn.

[0094] In this embodiment, the gain parameters of the PID controller are preliminarily set by the Ziegler-Nichols method, which provides a good basis for the subsequent tuning of the PID controller.

[0095] Optionally, the gain parameter adjustment of the PID controller is modified by the MPC adaptive module;

[0096] The MPC adaptive module is pre-trained by the historical operating data and historical particle accumulation data of the burner;

[0097] The MPC adaptive module performs optimal control calculations on the burner operation data and particle accumulation prediction data to obtain the adaptive gain parameters of the PID controller.

[0098] The MPC (Model Predictive Control) adaptive algorithm is an advanced optimization control strategy that predicts the future development of the system and optimizes the control input to achieve the desired output. In the present invention, in order to better control the burner to optimize the particle accumulation, the MPC adaptive module is used to dynamically adjust the gain parameters of the PID controller. In addition, the MPC adaptive module is pre-trained by the historical operating data and historical particle accumulation data of the burner. Combined with the training results, the MPC adaptive module is continuously optimized, and then the PID control parameters are optimized to improve the control accuracy and response speed.

[0099] Among them, the optimization objective function of the MPC adaptive module to solve the optimal control of the burner operation data and particle accumulation prediction data is:

[0100]

[0101] Among them, i is the optimization period of the MPC adaptive module during the training process, u i is the operating data of the burner, p i is the particle accumulation prediction data, ω1 and ω2 are the hyperparameters for adjusting the relationship between the burner operation data and the particle accumulation data. In addition, the MPC adaptive module converts the continuous time series into discrete time data suitable for use in the MPC controller, so that in each control cycle, the above optimization problem is solved to determine the optimal PID control gain parameters at each moment.

[0102] In this embodiment, by combining the MPC adaptive module and the PID controller, adaptive adjustment of the PID controller is achieved, the control accuracy and response speed of the burner during the active regeneration process are improved, and the regeneration control process of the DPF is optimized.

[0103] S104. When the particle accumulation prediction data drops below the first particle accumulation threshold again, the active regeneration or passive regeneration process is stopped.

[0104] In this embodiment, when the particle accumulation prediction data decreases, stopping the regeneration process can improve the efficiency of the burner, reduce fuel consumption, and reduce the smoke and particulate matter generated during the regeneration process.

[0105] Optionally, the method further comprises:

[0106] When the particle accumulation prediction data is higher than the third particle accumulation threshold, an abnormal excess particle alarm is issued, and the fuel supply of the burner is directly adjusted to the third level fuel supply range.

[0107] For example, the particle accumulation prediction data predicted by the thermal dynamic model is 16g / L, and the third particle accumulation threshold is 15g / L. At this time, the particle accumulation prediction data is higher than the third particle accumulation threshold, and an abnormal excess particle alarm is issued, and the fuel supply of the burner is adjusted to the third-level fuel supply range, which is 200-250L / h. In addition, the current operating data can be fed back to the thermal dynamic model and marked as abnormal data for focus, so as to facilitate subsequent optimization of the model.

[0108] In this embodiment, when the predicted particulate matter accumulation data is higher than the third particulate matter accumulation threshold, that is, before it reaches a dangerous level, an alarm is issued, giving the operator sufficient reaction time, helping to prevent major equipment failures, avoid serious blockage or damage to the DPF, and extend the life of the equipment.

[0109] Figure 4 FIG. 4 is a schematic diagram of the DPF temperature change according to an embodiment of the present invention. Figure 4 As shown:

[0110] Among them, in the passive regeneration method, at the initial start-up, the DOC (diesel oxidation catalyst) will gradually increase the injection volume to slowly increase the temperature of the DPF (diesel particulate filter). As part of the particulate matter burns, the released heat is gradually absorbed and converted into energy to further increase the DPF temperature. When the temperature reaches the first preset temperature, the passive regeneration will maintain this temperature level for a period of time to ensure that the particulate matter in the DPF is fully burned until the particulate matter accumulation prediction data drops below the first particulate matter accumulation threshold, thereby ending the passive regeneration process and completing the regeneration control of the DPF.

[0111] In the active regeneration method, when the first heat difference is within the first preset heat difference range, the fuel supply of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the first-level fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply of the burner and the particle accumulation prediction data. Since the energy required by the DPF itself is higher than that of the passive regeneration when the active regeneration method is required, the active regeneration will give a higher energy input at the initial start-up to quickly increase the temperature to a level close to that of fully burning the particles. In addition, the DIP controller will continuously adjust the fuel supply and combustion intensity according to the temperature feedback inside the DPF, gradually reducing the supply to achieve more precise temperature control. When the heat provided by the active regeneration meets the first heat difference, the active regeneration will maintain this temperature level for a period of time to ensure that the particles in the DPF are fully burned until the particle accumulation prediction data drops below the first particle accumulation threshold, thereby ending the active regeneration process and completing the regeneration control of the DPF. When the first heat difference exceeds the first preset heat difference range, the fuel supply of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the secondary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply of the burner and the particle accumulation prediction data. Compared with when the first heat difference is within the first preset heat difference range, the DPF temperature increase process is basically the same, but because the first heat difference exceeds the first preset heat difference range, more heat needs to be provided, so when the first heat difference exceeds the first preset heat difference range, the temperature increase caused by active regeneration will also be larger. Compared with the passive regeneration method, the active regeneration method realizes more accurate and precise control of the DPF temperature by calculating the first heat difference in real time and using the PID controller for multi-level control to dynamically adjust the combustion intensity of the burner.

[0112] Compared with the traditional DPF regeneration control method, the burner regeneration temperature control method based on energy estimation proposed in the present invention can accurately adjust the heat supply according to the actual needs of the DPF, reduce unnecessary energy consumption, improve the overall combustion efficiency, and extend the service life of the DPF.

[0113] Based on the burner regeneration temperature control method based on energy estimation provided in this embodiment, operation data is obtained, the operation data is input into the thermal dynamic model, and the particle accumulation prediction data is obtained. When the particle accumulation prediction data is higher than the first particle accumulation threshold and lower than the second particle accumulation threshold, the passive regeneration method is selected, and the first particle accumulation threshold is less than the second particle accumulation threshold. When the particle accumulation prediction data is higher than the second particle accumulation threshold, the active regeneration method is selected, and the active regeneration method calculates the first heat difference according to the operation data and the particle accumulation prediction data, and then the PID controller performs multi-level control on the burner according to the first heat difference. When the particle accumulation prediction data drops below the first particle accumulation threshold again, the active regeneration or passive regeneration process is stopped. That is to say, by obtaining the operation data and inputting it into the thermal dynamic model, the particle accumulation situation is analyzed and predicted in real time, and the current particle accumulation situation can be understood more immediately, and corrective measures can be taken in advance. In addition, two methods, passive regeneration and active regeneration, are designed according to the particle accumulation prediction data, which can optimize energy use and extend the life of the equipment. In the active regeneration method, the first heat difference is calculated based on the operating data and the particle accumulation prediction data, and the PID controller performs multi-level control on the burner based on the first heat difference, which can more accurately control the fuel supply and valve opening of the burner, ensure the effective combustion of the particles, and avoid excessive heating and equipment loss. Compared with the traditional regeneration method using direct heating, the present invention provides a more comprehensive control method to better cope with the changing particle accumulation situation, improve the overall efficiency of the burner through multi-level control to reduce unnecessary energy consumption, achieve more accurate renewable control, and extend the service life of the equipment. At the same time, it can also prevent extreme or harmful heat fluctuations to ensure that the power system is reliable and efficient.

[0114] Combination of the above Figure 1-Figure 4 The burner regeneration temperature control method based on energy estimation provided in the embodiment of the present application is described in detail. Figure 5 A burner regeneration temperature control device based on energy estimation for executing the burner regeneration temperature control method based on energy estimation provided in an embodiment of the present application is described in detail.

[0115] Figure 5 FIG. 1 is a schematic diagram of the structure of a burner regeneration temperature control device based on energy estimation according to an embodiment of the present invention. Figure 5 , the device comprises:

[0116] An acquisition module 501 is used to acquire operation data, input the operation data into a thermal dynamic model, and acquire particle accumulation prediction data;

[0117] A passive regeneration module 502, configured to select a passive regeneration method when the particle accumulation prediction data is higher than a first particle accumulation threshold and lower than a second particle accumulation threshold, and the first particle accumulation threshold is lower than the second particle accumulation threshold;

[0118] An active regeneration module 503 is used to select an active regeneration method when the particle accumulation prediction data is higher than a second particle accumulation threshold value, wherein the active regeneration method calculates a first heat difference according to the operation data and the particle accumulation prediction data, and then the PID controller performs multi-level control on the burner according to the first heat difference;

[0119] The recovery module 504 is configured to stop the active regeneration or the passive regeneration process when the PM accumulation prediction data drops below the first PM accumulation threshold again.

[0120] The technical effects of the burner regeneration temperature control device based on energy estimation refer to the technical effects of the burner regeneration temperature control method based on energy estimation mentioned above, which will not be repeated here.

[0121] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a different order from the order marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0122] The units or modules involved in the embodiments of the present invention may be implemented by software or hardware. The units or modules described may also be set in a processor, for example, it may be described as: a processor includes an acquisition module 501, a passive regeneration module 502, an active regeneration module 503, and a recovery module 504, wherein the names of these modules do not constitute a limitation on the modules themselves in some cases.

[0123] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) to form a technical solution.

Claims

1. A burner regeneration temperature control method based on energy estimation, characterized in that: The method comprises: Acquiring operating data, inputting the operating data into a thermal dynamic model, and acquiring particle accumulation prediction data; When the particle accumulation prediction data is higher than a first particle accumulation threshold and lower than a second particle accumulation threshold, a passive regeneration method is selected, and the first particle accumulation threshold is lower than the second particle accumulation threshold; When the particle accumulation prediction data is higher than a second particle accumulation threshold, an active regeneration method is selected, wherein the active regeneration method calculates a first heat difference according to the operation data and the particle accumulation prediction data, and then the PID controller performs multi-stage control on the burner according to the first heat difference; When the particulate matter accumulation prediction data drops below the first particulate matter accumulation threshold again, the active regeneration or passive regeneration process is stopped.

2. The burner regeneration temperature control method based on energy estimation according to claim 1, characterized in that: The operating data includes engine target temperature, burner outlet temperature, engine exhaust flow, engine exhaust temperature and heat loss data.

3. The burner regeneration temperature control method based on energy estimation according to claim 1, characterized in that: The heat dynamic model is obtained by pre-training historical operation data; The thermal dynamic model includes a time series module, a convolutional neural network module and a random forest module.

4. The burner regeneration temperature control method based on energy estimation according to claim 1, characterized in that: The passive regeneration method comprises: The temperature of the DPF is increased to a first preset temperature according to the operation data, and the first preset temperature ranges from 280° C. to 360° C.

5. The burner regeneration temperature control method based on energy estimation according to claim 2, characterized in that: The active regeneration method calculates a first heat difference according to the operation data and the particulate matter accumulation prediction data, including: Calculating the required heat according to the engine target temperature, the burner outlet temperature and the burner heat exchange efficiency; Calculating actual heat according to the engine exhaust flow, the engine exhaust temperature and exhaust gas heat exchange efficiency; The first heat difference is calculated according to the required heat, the actual heat, the heat loss data and the particulate matter accumulation prediction data.

6. The burner regeneration temperature control method based on energy estimation according to claim 1, characterized in that: The PID controller performs multi-stage control on the burner according to the first heat difference, including: When the first heat difference is within a first preset heat difference range, the fuel supply amount of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the primary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply amount of the burner and the particulate matter accumulation prediction data; When the first heat difference exceeds a first preset heat difference range, the fuel supply amount of the burner is adjusted according to the fuel supply adjustment signal output by the PID controller and the secondary fuel supply range, and the valve opening is adjusted accordingly according to the fuel supply amount of the burner and the particulate matter accumulation prediction data; The primary fuel supply range is smaller than the secondary fuel supply range.

7. The burner regeneration temperature control method based on energy estimation according to claim 6, characterized in that: The gain parameters of the PID controller include proportional gain, integral gain and differential gain; The initial setting of the gain parameter is determined by the Ziegler-Nichols method.

8. The burner regeneration temperature control method based on energy estimation according to claim 7, characterized in that: The gain parameter adjustment of the PID controller is corrected by the MPC adaptive module; The MPC adaptive module is pre-trained by the historical operation data and historical particle accumulation data of the burner; The MPC adaptive module performs optimal control solution calculation on the operating data of the burner and the particle accumulation prediction data to obtain the adaptive gain parameters of the PID controller.

9. The burner regeneration temperature control method based on energy estimation according to claim 1, characterized in that: The method further comprises: When the particle accumulation prediction data is higher than the third particle accumulation threshold, an abnormal excess particle alarm is issued, and the fuel supply of the burner is directly adjusted to the third level fuel supply range.

10. A burner regeneration temperature control device based on energy estimation, characterized in that: The device comprises: An acquisition module, used for acquiring operation data, inputting the operation data into a thermal dynamic model, and acquiring particle accumulation prediction data; a passive regeneration module, configured to select a passive regeneration method when the particle accumulation prediction data is higher than a first particle accumulation threshold and lower than a second particle accumulation threshold, the first particle accumulation threshold being lower than the second particle accumulation threshold; an active regeneration module, configured to select an active regeneration method when the particle accumulation prediction data is higher than a second particle accumulation threshold, wherein the active regeneration method calculates a first heat difference according to the operation data and the particle accumulation prediction data, and then the PID controller performs multi-stage control on the burner according to the first heat difference; The recovery module is used to stop the active regeneration or passive regeneration process when the particle accumulation prediction data drops below the first particle accumulation threshold again.

Images