CN110852482B - Real-time global optimization intelligent control system and method for fuel cell bus - Google Patents
Real-time global optimization intelligent control system and method for fuel cell bus Download PDFInfo
- Publication number
- CN110852482B CN110852482B CN201910977702.8A CN201910977702A CN110852482B CN 110852482 B CN110852482 B CN 110852482B CN 201910977702 A CN201910977702 A CN 201910977702A CN 110852482 B CN110852482 B CN 110852482B
- Authority
- CN
- China
- Prior art keywords
- fuel cell
- soc
- real
- time
- working condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000005457 optimization Methods 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000004891 communication Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000007726 management method Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 10
- 230000001133 acceleration Effects 0.000 description 9
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 7
- 229910052739 hydrogen Inorganic materials 0.000 description 7
- 239000001257 hydrogen Substances 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000010606 normalization Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000011425 standardization method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L50/00—Electric propulsion with power supplied within the vehicle
- B60L50/50—Electric propulsion with power supplied within the vehicle using propulsion power supplied by batteries or fuel cells
- B60L50/75—Electric propulsion with power supplied within the vehicle using propulsion power supplied by batteries or fuel cells using propulsion power supplied by both fuel cells and batteries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/40—Application of hydrogen technology to transportation, e.g. using fuel cells
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Sustainable Energy (AREA)
- Sustainable Development (AREA)
- Life Sciences & Earth Sciences (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Fuel Cell (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a real-time global optimization intelligent control system and a method for a fuel cell bus, wherein when the fuel cell bus is at a driving starting point, a vehicle driving communication unit downloads prediction model parameters to a fuel cell vehicle controller; the battery management system and the driving motor real-time power calculation module respectively obtain the real-time SOC and the real-time power of the battery pack, the optimal SOC prediction model module obtains the predicted value of the optimal SOC reference track of the next working condition segment, the MPC prediction control module obtains a power reference value, and the parameters are all input into the fuel cell control unit to judge the working state of the fuel cell. In the running process, the bus continuously uploads fragmented working condition information through the vehicle running communication unit, and the cloud analysis workstation performs incremental learning training through the real-time uploaded working condition information after each trip is completed, so that the optimal SOC prediction model is updated. The invention can accurately and flexibly control the fuel cell bus in real time and reduce the fuel consumption.
Description
Technical Field
The invention belongs to the technical field of energy management of new energy vehicles, and particularly relates to a real-time global optimization intelligent control system and method for a fuel cell bus.
Background
With the increasing automobile keeping quantity in China, the energy and environmental pressure of the automobile industry is also increasing. As the external dependence of non-renewable energy sources such as petroleum and the like is increased year by year, the implementation of energy source substitution is imminent, so that hydrogen can enter the public vision with higher heat value, rich reserves and excellent environmental friendliness; from the application of hydrogen energy, fuel cell vehicles become one of the major research directions, and statistics shows that more than 40 vehicles and enterprises in the current Chinese market participate in the production and manufacturing of hydrogen fuel cell vehicles. On the other hand, the use of public transport means also plays a great role in slowing down the energy and environmental pressure, so that the market of fuel cell electric buses is imperative.
Machine learning is a younger branch of artificial intelligence research, is the science of artificial intelligence, and the main research object of the machine learning is artificial intelligence, particularly how to improve the performance of a specific algorithm in empirical learning; incremental learning is a dynamic gradual updating algorithm, which means that all knowledge bases do not need to be rebuilt every time data is newly added, and the updating caused by the newly added data is trained only on the basis of the original knowledge bases; the method is more consistent with the thinking principle of people, and repeated learning under the condition of mass data can be avoided. In a real database, the amount of data tends to increase gradually. Thus, in the face of new data, the learning method should be able to make some changes to the trained system to learn the knowledge implied in the new data, and the time cost of modifying a trained system is usually lower than the cost required to retrain a system.
The invention relates to a plug-in hybrid vehicle energy management method based on deep reinforcement learning, which has the following defects: 1) rules related to data change are not modified, deep reinforcement learning is only to perform dimension reduction and fusion processing by using the condition of mass data, and a system needs to be retrained when new data is added; 2) the dynamic gradual updating algorithm is not involved, the data in the database are dynamically changed, and when new data are encountered, the learning method can change the trained system to learn the knowledge contained in the new data. The prior art also relates to an energy management method of a plug-in hybrid electric vehicle based on intelligent prediction, and the method has the following defects: 1) model prediction by adopting deep learning has great influence on timeliness and accuracy of database search, so that the prediction range can only reach a short period; 2) and when the difference with the target driving route is larger, the model needs to be reconstructed.
Therefore, how to reflect the change of data conveniently and effectively becomes a more urgent research topic. The design of a set of high-efficiency, accurate and flexible real-time global optimization intelligent control system and method for the fuel cell bus has extremely high practical significance.
Disclosure of Invention
The invention provides a real-time global optimization intelligent control system and a real-time global optimization intelligent control method for a fuel cell bus.
The technical scheme of the invention is as follows:
a real-time global optimization intelligent control system for a fuel cell bus comprises a vehicle running communication unit, a vehicle running information prediction analysis unit, a fuel cell whole vehicle control unit and a vehicle running information acquisition unit, wherein the fuel cell whole vehicle control unit is in signal connection with the vehicle running information prediction analysis unit through the vehicle running communication unit, and the fuel cell whole vehicle control unit is also in signal connection with the vehicle running information acquisition unit; the vehicle running information prediction analysis unit acquires prediction model parameters and downloads the prediction model parameters to the fuel cell whole vehicle control unit for updating the optimal SOC prediction model; and the whole fuel cell vehicle control unit controls the working state of the fuel cell.
In the technical scheme, the fuel cell vehicle control unit controls the working state of the fuel cell according to the power reference value and the real-time power of the driving motor, the predicted value of the optimal SOC reference track of the next working condition segment of the vehicle and the real-time SOC value of the battery pack.
In the above technical solution, the real-time SOC of the battery pack is detected by a battery management system BMS in real time.
In the above technical solution, the predicted value of the reference trajectory of the optimal SOC of the next operating condition segment is obtained by receiving the characteristic parameters of the current operating condition segment by an optimal SOC prediction model module in the vehicle control unit of the fuel cell, and by Y*Min + f (x) (max-min), where f (x) is a regression function, max is the maximum value of the sample data, min is the minimum value of the sample data, Y is obtained*And the optimal SOC reference track predicted value is the next working condition segment.
In the above technical solution, the power reference value of the driving motor is calculated by an MPC prediction control module in the entire vehicle control unit of the fuel cell according to the optimal SOC reference trajectory prediction value of the next operating condition segment.
In the above technical solution, the real-time power of the driving motor is calculated by the driving motor real-time power calculating module.
In the technical scheme, the prediction model parameters are obtained by transmitting the characteristic parameters calculated by the characteristic parameter calculation module to the incremental learning model and training; and the characteristic parameter calculation module receives the vehicle running condition information and the optimal SOC reference track sent by the speed information receiving module and the dynamic planning module.
In the technical scheme, the incremental learning model trains characteristic parameters to obtain a regression model SVM1 and a support vector set SV1, integrates newly added working condition information, synthesizes new sample library data with the support vector set SV1, and continues to train to obtain a brand-new regression model SVM2 and a support vector set SV2 as final models.
A real-time global optimization intelligent control method for a fuel cell bus comprises the following steps:
training the obtained working condition information and the optimal SOC reference track by using an incremental learning model to obtain optimal SOC prediction model parameters, and downloading the optimal SOC prediction model parameters to an optimal SOC prediction model module to update the optimal SOC prediction model;
inputting the characteristic parameters of the current working condition segment into an optimal SOC prediction model module, and outputting the predicted value of the optimal SOC reference track of the next working condition segment;
inputting the predicted value of the reference trajectory of the optimal SOC of the next working condition segment into an MPC prediction control module to obtain a power reference value of the driving motor;
judging the SOC value and the power by the FCU to control the working state of the fuel cell;
step five, the VCU of the vehicle controller judges whether the bus finishes a journey or not, and if the journey is not finished, the VCU returns to the step two to carry out the circulation; and if the optimal SOC prediction model is finished, the cloud analysis workstation downloads the updated prediction model parameters to the VCU of the vehicle control unit again to update the optimal SOC prediction model.
Further, the fourth step is specifically: judging whether the real-time SOC value of the battery pack is larger than the maximum value SOC of the predicted value of the optimal SOC reference track of the next working condition segmentmaxIf SOC > SOCmaxThen determine whether the real-time power P is less than the power reference value PminIf P < PminIf yes, the fuel cell control unit FCU is turned off and no longer charged; if P ≧ PminThen, it is continuously determined whether the real-time power P is greater than the power reference value PmaxIf P > PmaxThe fuel cell control unit FCU starts to operate when Pmin≤P≤PmaxIf so, the fuel cell control unit FCU remains unchanged; when real-time SOC < SOCminOr SOCmin≤SOC≤SOCmaxAnd P > PmaxThe fuel cell control unit FCU turns on and discharges the fuel cell stack, otherwise the state remains unchanged.
The invention has the beneficial effects that:
1) repeated learning under the condition of mass data is avoided. When data is newly added, all knowledge bases do not need to be rebuilt, and only the update caused by the newly added data is trained on the basis of the original model.
2) The cloud storage space is saved, and the cost is reduced. Due to the adoption of incremental learning, original training data can be deleted after training is finished, so that data accumulation is avoided, and the cost is saved.
3) The working condition adaptability is continuously improved. After a journey of the vehicle is finished, the cloud carries out incremental training on newly-added data, and downloads the trained model to the vehicle, so that the working condition adaptability of the vehicle on the same commuting route is continuously improved.
Drawings
FIG. 1 is a diagram of a real-time global optimization intelligent control system of a fuel cell bus according to the present invention;
FIG. 2 is a schematic view of a fuel cell bus configuration according to the present invention;
FIG. 3 is a schematic diagram of the overall control of a fuel cell bus according to the present invention;
FIG. 4 is a schematic diagram of the optimal SOC prediction model generation of the present invention;
FIG. 5 is a diagram of a structure of an incremental learning model network based on a support vector machine according to the present invention;
FIG. 6 is a flow chart of a fuel cell bus real-time global optimization intelligent control operation of the present invention;
FIG. 7 is a diagram illustrating case analysis of burst conditions according to the present invention;
wherein: the method comprises the following steps of 1-a fuel cell bus, 2-a vehicle controller VCU, 3-a wireless communication system, 4-a satellite, 5-a base station, 6-a wired communication system, 7-a cloud analysis workstation, 8-an incremental learning model, 9-an optimal SOC prediction model module, 10-an MPC prediction control module, 11-a fuel cell control unit FCU, 12-a fuel cell hydrogen storage tank, 13-a fuel cell stack, 14-a speed sensor, 15-an acceleration sensor, 16-a driving motor real-time power calculation module, 17-a motor controller MCU, 18-a driving motor, 19-a battery management system BMS, 20-a speed information receiving module, 21-a dynamic planning module and 22-a characteristic parameter calculation module.
Detailed Description
The structure and the working principle of the real-time global optimization intelligent control system and the method for the fuel cell bus are described below with reference to the accompanying drawings.
As shown in fig. 1 and fig. 2, the real-time global optimization intelligent control system for a fuel cell bus of the present invention includes a vehicle driving communication unit, a vehicle driving information prediction and analysis unit, a fuel cell vehicle control unit, and a vehicle driving information acquisition unit. The vehicle running communication unit comprises a wireless communication system 3, a satellite 4, a base station 5 and a wired communication system 6, the vehicle running information prediction analysis unit comprises a cloud analysis workstation 7, the fuel cell vehicle control unit comprises a vehicle control unit VCU 2, a fuel cell control unit FCU 11, a fuel cell hydrogen storage tank 12, a fuel cell stack 13, a motor controller MCU 17 and a driving motor 18, and the fuel cell hydrogen storage tank 12 supplies fuel to the fuel cell stack 13; the vehicle running information acquisition unit comprises a speed sensor 14, an acceleration sensor 15 and a driving motor real-time power calculation module 16, wherein the speed sensor 14 and the acceleration sensor 15 are in signal connection with the VCU 2 of the whole vehicle controller, and the driving motor real-time power calculation module 16 is in signal connection with the FCU 11 and the MCU 17 of the fuel cell control unit.
As shown in fig. 2, the vehicle control unit VCU 2, the fuel cell control unit FCU 11, the driving motor 18, the motor controller MCU 17, the speed sensor 14, the acceleration sensor 15, the driving motor real-time power calculation module 16, the fuel cell hydrogen storage tank 12, and the fuel cell stack 13 are all disposed on the top of the fuel cell bus 1.
In the running process of a vehicle, a vehicle control unit VCU 2 is connected with a satellite 4 through a wireless communication system 3, the satellite 4 is connected with a base station 5 through the wireless communication system 3, and the base station 5 is connected with a cloud analysis workstation 7 through a wired communication system 6; as shown in fig. 4, a speed information receiving module 20 and a dynamic planning module 21 which are connected with each other are arranged inside the cloud analysis workstation 7, the speed information receiving module 20 and the dynamic planning module 21 are both connected with a characteristic parameter calculating module 22, and the characteristic parameter calculating module 22 is connected with the incremental learning model 8; the fuel cell bus 1 downloads the prediction model parameters to the vehicle control unit VCU 2 through the vehicle running communication system at the running starting point, the vehicle control unit VCU 2 is provided with an optimal SOC prediction model 9 and MPC prediction control 10 which are connected with each other, and finally the fuel cell control unit FCU 11 integrates the power reference value and the real-time power of the driving motor 18 and outputs the working state of the fuel cell.
As shown in FIG. 3, the VCU 2 of the vehicle control unit includes a vehicle control unitA secondary connected optimal SOC prediction model module 9 and an MPC prediction control module 10; the optimal SOC prediction model module 9 receives the characteristic parameters of the current working condition segment, and the characteristic parameters are represented by Y*And obtaining an optimal SOC reference track predicted value of the next working condition segment (min + f) (x) (max-min), transmitting the predicted value to the MPC prediction control module 10, calculating by the MPC prediction control module 10 to obtain a driving motor power reference value, and transmitting the driving motor power reference value to the fuel cell control unit FCU 11. The battery management system BMS 19 detects the SOC value of the battery pack in real time, the driving motor real-time power calculation module 16 is in signal connection with the motor controller MCU 17, and the motor controller MCU 17 acquires the rotating speed and the torque of the driving motor 18 so as to obtain real-time power; the fuel cell control unit FCU 11 receives the power reference value and the real-time power of the driving motor 18, the predicted value of the optimal SOC reference trajectory for the next operating condition segment, and the real-time SOC value of the battery pack, and controls the fuel cell to be turned on, turned off, and maintained.
As shown in fig. 4, in the cloud analysis workstation 7, the speed information receiving module 20 transmits the vehicle driving condition information to the dynamic planning module 21 and obtains the optimal SOC reference track, the speed information receiving module 20 and the dynamic planning module 21 then transmit the vehicle driving condition information and the optimal SOC reference track to the characteristic parameter calculating module 22, the characteristic parameters calculated by the characteristic parameter calculating module 22 are transmitted to the incremental learning model 8, and the prediction model parameters (including the dual parameters α, after training) are obtained*RBF kernel function, offset b); the fuel cell bus 1 downloads the trained prediction model parameters to an optimal SOC prediction model module 9 in the vehicle control unit VCU 2 through a vehicle running communication system at a running starting point; in the running process of the vehicle, the vehicle control unit VCU 2 divides the working condition into equal working condition segments TS according to the time segments, and uploads the equal working condition segments TS to the speed information receiving module 20. After the bus 1 finishes a journey every time, the characteristic parameters are obtained by using the working condition data (including speed and acceleration) of a new journey and the optimal SOC reference track to carry out incremental learning, new prediction model parameters are generated and downloaded to the optimal SOC prediction model module 9 to update the optimal SOC prediction model.
After the cloud analysis workstation 7 is trained by the incremental learning model 8 each time, original training samples can be deleted due to the use of the incremental learning technology, so that a large amount of data accumulation is avoided, and the training burden and the production cost are increased.
As shown in fig. 5, the incremental learning model 8 trains the feature parameters to obtain a regression model SVM1 and a support vector set SV1, integrates the information of the newly added operating conditions, synthesizes new sample library data with the support vector set SV1, and continues to train to obtain a completely new regression model SVM2 and a support vector set SV2 as final models. The characteristic parameters of the current working condition segment are input as an increment learning model, the characteristic parameters of the optimal SOC reference track of the next working condition segment are output as the model, the increment learning model is trained by utilizing a large amount of input and output in the morning, the mapping relation between the characteristic parameters of the current working condition segment and the characteristic parameters of the optimal SOC reference track of the next working condition segment is established, and the calculation and prediction of the characteristic parameters of the optimal SOC reference track of the next working condition segment are realized. Optimal SOC reference trajectory Y for the next operating condition segmenti+1It can be expressed as:
the parameters in the above equation represent several characteristics of the optimal SOC reference trajectory of the condition segment respectively: maximum SOC value, minimum SOC value, SOC standard deviation, SOC maximum change rate, average SOC.
SOCmax＝max:SOCj (2)
SOCmin＝min:SOCj (3)
Kmax＝max：Kj (7)
Where n is the number of data points in the operating condition segment, Δ t is the data point time interval, K is the SOC change rate, and j is 1,2, …, n.
In order to realize the optimal SOC reference trajectory prediction of the next working condition segment, the characteristic parameters of the current working condition segment are recorded as:
the parameters in the above formula respectively represent the condition information of the current condition segment: maximum velocity, minimum velocity, maximum acceleration, minimum acceleration, and average velocity.
Vmax＝max：Vj (9)
amax＝max：aj (11)
amin＝min：aj (12)
Where V is the speed of the fuel cell bus 1 and a is the acceleration of the fuel cell bus 1.
Before training of incremental learning, the dynamic planning module 21 is required to calculate road spectrum information of vehicle driving so as to obtain an optimal SOC reference trajectory. The dynamic programming mainly comprises a forward method and a reverse method, wherein the forward method is implemented by utilizing a state transition equation from the first stage and recurrently from front to back, and the principle is as follows:
wherein k is a stage number; skIs a state variable; u. ofkIs a control variable; r iskIs a phase index function; f. ofkIs an optimal index function; t iskIs a state transfer function.
Taking the SOC of the power battery as a state variable, and dividing the whole step length into m stages with the step length of 1 s. Phase index function rkFor the kth stage energy consumption, the following is calculated:
wherein: f (P)fc) At output power P for fuel cellfcTime consuming energy consumption;
equivalent energy consumption for power batteries; z comprises the dynamic working efficiency of the fuel cell, the DC-DC converter and the power cell and can be obtained through experiment or equivalent circuit model calculation. The state transition equations from the k-th stage to the k +1 stage are:
wherein: pb_kOutputting power for the power battery; u shapebIs the bus voltage; cbIs the power battery capacity. The control parameter is the output power P of the fuel cell in the k stagefc_kThe state variable and control variable constraints are:
wherein, Pfc_maxThe maximum output power of the fuel cell; pb_minAnd Pb_maxThe maximum charging and discharging power of the power battery is realized; the optimization goal is to find the optimal control variable P in the whole driving cyclefc_kSo that the energy consumption J is minimal:
setting the state variable SOC at SOCminAnd SOCmaxThe range is divided into N nodes according to a certain step length, and each node stores the optimal track reaching the node. The calculation process of the node i in the k step is as follows: firstly, all nodes which can be transferred to the node i in the step (k-1) under the constraint condition are found, and the accumulated energy consumption f of the state transfer is calculatedkThe state transition with the minimum value is the optimal strategy for passing through the node i in the k step. Recursion to the cycle end point to find fkAnd finding out the optimal SOC reference track through the track information stored by the minimum node.
The characteristic parameter X of the current working condition segment is measurediAs the input of the increment learning model, the optimal SOC reference track Y of the next working condition segment is usedi+1As an output of the incremental learning model. In order to reduce the network prediction error caused by large magnitude difference between input data, normalization processing is carried out on the input data, and the value range of the normalized data is [0,1 ]]. Normalization is carried out by adopting a dispersion standardization method, and the conversion formula is as follows:
wherein max is the maximum value of sample data, min is the minimum value of the sample data, and X is the original training data (including a large number of characteristic parameters X of the current working condition segment)i)，X*To normalize the data.
After the SVM model is used for predicting the optimal SOC reference track of the next working condition segment, the anti-normalization processing is carried out on the prediction result according to the formula (3), so that the data obtained by prediction accords with the actual range and significance. Accordingly, the expression of the optimal SOC reference trajectory for the next operating condition segment is:
in the formula (I), the compound is shown in the specification,
is a non-linear mapping from the input space to the high-order feature space; weight WiAnd the deviation b is obtained by:
wherein W is { W ═ W1,W2,…,Wi,…WN}，
Is a regularization portion; in the second item
Is an empirical risk, and is given by the following insensitive loss function LMeasured as the regression allowed maximum error; c is a weight parameter used to balance the two, called the regularization parameter.
To obtain WiAnd b, passing through RBF kernel function K (X)i,Xj) Converting formula (6) to:
in the formula, alpha and alpha*Are dual parameters.
The regression function then becomes the following exact form:
after the prediction output of the incremental school model is obtained, the predicted value is subjected to inverse normalization and is reduced to be the predicted value of the optimal SOC reference track of the next working condition segment:
Y*＝min+f(X)(max-min) (25)
with reference to fig. 6, the invention discloses a real-time global optimization intelligent control method for a fuel cell bus, which specifically comprises the following steps:
the method comprises the following steps: the speed sensor 14 and the acceleration sensor 15 collect the working condition information of the fuel cell bus 1 in advance and send the working condition information to the vehicle control unit VCU 2, the vehicle control unit VCU 2 sends the working condition information to the speed information receiving module 20, and the speed information receiving module 20 sends the working condition information to the dynamic planning module 21, so that the optimal SOC reference track of the next working condition is obtained. The characteristic parameter calculating module 22 receives the operating condition information and the next operating condition optimal SOC reference trajectory sent by the speed information receiving module 20 and the dynamic programming module 21, and calculates characteristic parameters thereof, respectively.
Step two: and training the obtained working condition information and the optimal SOC reference track by using the incremental learning model 8 so as to obtain optimal SOC prediction model parameters, and downloading the optimal SOC prediction model parameters to the optimal SOC prediction model module 9.
Step three: the characteristic parameters of the current working condition segment are input into an optimal SOC prediction model module 9, and then the predicted value of the optimal SOC reference track of the next working condition segment is output.
Step four: inputting the predicted value of the reference trajectory of the optimal SOC of the next working condition segment into the MPC prediction control module 10, outputting the corresponding rotating speed and torque, and further obtaining a power P reference value, wherein the power P reference value comprises a maximum value PmaxAnd a minimum value Pmin。
Step five: the battery management system BMS 19 monitors the real-time SOC value of the battery pack and outputs the next working condition segment TS together with the step threei+1And comparing the optimal SOC reference track predicted value.
Step six: and the real-time power calculation module 16 of the driving motor further measures the real-time power P according to the rotating speed and the torque of the driving motor 18, and compares the real-time power P with the reference value of the power of the driving motor obtained in the step four.
Step seven: the fuel cell control unit FCU 11 comprehensively judges the SOC value and the power according to the power following energy control strategy, specifically:
firstly, judging whether the real-time SOC value of the battery pack is larger than the maximum value SOC of the predicted value of the optimal SOC reference track of the next working condition segmentmaxIf SOC > SOCmaxThen determine whether the real-time power P is less than the power reference value PminIf P < PminThen the fuel cell control unit FCU 11 is turned off and no longer charged; if P ≧ PminThen, it is continuously determined whether the real-time power is greater than the power reference value PmaxIf P > PmaxThen the fuel cell control unit FCU 11 starts to operate, when Pmin≤P≤PmaxThe fuel cell control unit FCU 11 remains unchanged. When real-time SOC < SOCminOr SOCmin≤SOC≤SOCmaxAnd P > PmaxThe fuel cell control unit FCU 11 turns on and discharges the fuel cell stack 13, otherwise the state is maintained.
Step eight: the VCU 2 of the vehicle control unit judges whether the fuel cell bus 1 reaches the end point to complete a journey, if the journey is not finished, the three steps are returned to; if the updating is finished, the cloud analysis workstation 7 completes incremental learning on the newly added training data through the incremental learning model 8 and downloads the updated prediction model parameters to the optimal SOC prediction model module 9 in the VCU 2 of the vehicle control unit for updating the optimal SOC prediction model.
The work flow of the present invention is described in detail below with reference to fig. 7: in the driving process of the fuel cell bus 1, the VCU 2 samples the working condition information, divides the working condition information into segments according to time, and starts to control at the starting time point of each working condition segment; inputting the characteristic parameters of the current working condition segment into an optimal SOC prediction model module 9, obtaining an optimal SOC reference track prediction value of the next working condition segment as input and transmitting the optimal SOC reference track prediction value to an MPC prediction control module 10, obtaining a power reference value of a driving motor by the MPC prediction control module 10, monitoring the SOC value of a fuel cell vehicle battery pack in real time by a battery management system BMS module 19, and monitoring the rotating speed and torque of the motor when the vehicle runs by a driving motor real-time power calculation module 16 through a motor controller MCU 17 so as to calculate the real-time power of the driving motor; and inputting the measured real-time battery pack SOC value, the predicted value of the next section of the optimal SOC reference track predicted by the driving motor real-time power and optimal SOC prediction model module 9 and the MPC prediction control module 10, and the power reference value of the driving motor into the fuel cell control unit FCU 11 together, judging the working state of the fuel cell according to a power following energy control strategy, and further finishing the control of the next working condition section. The fuel cell bus 1 continuously uploads the working condition information of each segment through a vehicle running communication system in the running process, and after each trip is completed, the cloud analysis workstation 7 conducts incremental learning training through the working condition information uploaded in real time. When the original driving route changes before and after the road working condition due to construction transformation, the uploaded working condition information changes accordingly. And after the journey is finished, the cloud analysis workstation 7 performs incremental learning training on the newly added data by using the incremental learning model 8, further updates the model parameters, and downloads the trained model parameters to the VCU 2 of the fuel cell vehicle controller. When the vehicle operates again under the same sudden working condition, the change of a new environment can be adapted.
The above-listed detailed description is only a specific description of a possible embodiment of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.
Claims (9)
1. The utility model provides a real-time global optimization intelligence control system of fuel cell bus which characterized in that: the fuel cell vehicle control unit is in signal connection with the vehicle running information prediction and analysis unit through the vehicle running communication unit, and is also in signal connection with the vehicle running information acquisition unit; the vehicle running information prediction analysis unit acquires prediction model parameters and downloads the prediction model parameters to the fuel cell whole vehicle control unit for updating the optimal SOC prediction model; the whole fuel cell vehicle control unit controls the working state of the fuel cell;
the fuel cell vehicle control unit controls the working state of the fuel cell according to the power reference value and real-time power of the driving motor (18), the predicted value of the optimal SOC reference track of the next working condition segment of the vehicle and the real-time SOC value of the battery pack.
2. The fuel cell bus real-time global optimization intelligent control system of claim 1, characterized in that: the battery pack real-time SOC is detected by a battery management system BMS (19) in real time.
3. The fuel cell bus real-time global optimization intelligent control system of claim 1, characterized in that: the predicted value of the reference trajectory of the optimal SOC of the next working condition segment is obtained by receiving the characteristic parameters of the current working condition segment by an optimal SOC prediction model module (9) in a whole vehicle control unit of the fuel cell and by Y*Min + f (x) (max-min), where f (x) is a regression function, max is the maximum value of the sample data, min is the minimum value of the sample data, Y is obtained*And the optimal SOC reference track predicted value is the next working condition segment.
4. The fuel cell bus real-time global optimization intelligent control system of claim 3, characterized in that: and the power reference value of the driving motor (18) is obtained by calculating an MPC prediction control module (10) in the fuel cell whole vehicle control unit according to the optimal SOC reference track prediction value of the next working condition segment.
5. The fuel cell bus real-time global optimization intelligent control system of claim 1, characterized in that: the real-time power of the driving motor (18) is calculated by a driving motor real-time power calculating module (16).
6. The fuel cell bus real-time global optimization intelligent control system of claim 1, characterized in that: the prediction model parameters are obtained by transmitting the characteristic parameters calculated by the characteristic parameter calculation module (22) to the incremental learning model (8) and training; the characteristic parameter calculation module (22) receives the vehicle running condition information and the optimal SOC reference track sent by the speed information receiving module (20) and the dynamic planning module (21).
7. The fuel cell bus real-time global optimization intelligent control system of claim 6, characterized in that: the incremental learning model (8) trains the characteristic parameters to obtain a regression model SVM1 and a support vector set SV1, integrates the newly added working condition information, synthesizes new sample base data with the support vector set SV1, and continues to train to obtain a brand new regression model SVM2 and a support vector set SV2 as final models.
8. A real-time global optimization intelligent control method for a fuel cell bus is characterized by comprising the following steps: the method comprises the following steps:
training the obtained working condition information and the optimal SOC reference trajectory by using an incremental learning model (8) to obtain optimal SOC prediction model parameters, and downloading the optimal SOC prediction model parameters to an optimal SOC prediction model module (9) to update the optimal SOC prediction model;
inputting the characteristic parameters of the current working condition segment into an optimal SOC prediction model module (9), and outputting the predicted value of the optimal SOC reference track of the next working condition segment;
inputting the predicted value of the optimal SOC reference trajectory of the next working condition segment into an MPC prediction control module (10) to obtain a power reference value of the driving motor;
judging the SOC value and the power by the fuel cell control unit FCU (11) and controlling the working state of the fuel cell;
step five, the vehicle control unit VCU (2) judges whether the bus finishes a journey or not, and if the journey is not finished, the process returns to the step two to be carried out in a circulating way; and if the optimal SOC prediction model is finished, the cloud analysis workstation (7) downloads the updated prediction model parameters to the VCU (vehicle control unit) (2) again to update the optimal SOC prediction model.
9. The fuel cell bus real-time global optimization intelligent control method as claimed in claim 8,the method is characterized in that: the fourth step is specifically as follows: judging whether the real-time SOC value of the battery pack is larger than the maximum value SOC of the predicted value of the optimal SOC reference track of the next working condition segmentmaxIf SOC > SOCmaxThen determine whether the real-time power P is less than the power reference value PminIf P < PminIf so, the fuel cell control unit FCU (11) is turned off and no longer charged; if P ≧ PminThen, it is continuously determined whether the real-time power P is greater than the power reference value PmaxIf P > PmaxThe fuel cell control unit FCU (11) starts to operate when P is reachedmin≤P≤PmaxIf so, the fuel cell control unit FCU (11) keeps the state unchanged; when real-time SOC < SOCminOr SOCmin≤SOC≤SOCmaxAnd P > PmaxThe fuel cell control unit FCU (11) turns on and discharges the fuel cell stack (13), otherwise the state is maintained.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910977702.8A CN110852482B (en) | 2019-10-15 | 2019-10-15 | Real-time global optimization intelligent control system and method for fuel cell bus |
| PCT/CN2020/079244 WO2021073036A1 (en) | 2019-10-15 | 2020-03-13 | Real-time global optimization intelligent control system and method for fuel cell bus |
| CH01054/20A CH717533B1 (en) | 2019-10-15 | 2020-03-13 | Intelligent control system and method with real-time global optimization for a fuel cell bus. |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910977702.8A CN110852482B (en) | 2019-10-15 | 2019-10-15 | Real-time global optimization intelligent control system and method for fuel cell bus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110852482A CN110852482A (en) | 2020-02-28 |
| CN110852482B true CN110852482B (en) | 2020-12-18 |
Family
ID=69596613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910977702.8A Active CN110852482B (en) | 2019-10-15 | 2019-10-15 | Real-time global optimization intelligent control system and method for fuel cell bus |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN110852482B (en) |
| CH (1) | CH717533B1 (en) |
| WO (1) | WO2021073036A1 (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852482B (en) * | 2019-10-15 | 2020-12-18 | 江苏大学 | Real-time global optimization intelligent control system and method for fuel cell bus |
| CN113486698B (en) * | 2021-04-30 | 2023-09-26 | 华中科技大学 | Hydrogen fuel cell work identification prediction method, storage medium and system |
| CN113569947A (en) * | 2021-07-27 | 2021-10-29 | 合肥阳光智维科技有限公司 | Arc detection method and system |
| CN113642863A (en) * | 2021-07-30 | 2021-11-12 | 南京航空航天大学 | Data-driven rapid global SOC (System on chip) planning method |
| CN113733936B (en) * | 2021-08-18 | 2023-05-23 | 中车唐山机车车辆有限公司 | Power control method and device for hybrid drive tramcar and storage medium |
| CN113428049B (en) * | 2021-08-26 | 2021-11-09 | 北京理工大学 | Fuel cell hybrid vehicle energy management method considering battery aging inhibition |
| CN113525179B (en) * | 2021-08-27 | 2024-01-12 | 潍柴动力股份有限公司 | Dynamic response control method of fuel cell |
| CN113904354A (en) * | 2021-09-24 | 2022-01-07 | 国网安徽省电力有限公司经济技术研究院 | Control method, system and equipment for hydrogen fuel cell cogeneration unit |
| CN114103971B (en) * | 2021-11-23 | 2023-10-10 | 北京理工大学 | Energy-saving driving optimization method and device for fuel cell automobile |
| CN114228696B (en) * | 2021-12-10 | 2023-08-15 | 燕山大学 | Cold chain hybrid vehicle real-time optimal control method considering energy consumption of refrigeration system |
| CN114291067B (en) * | 2021-12-29 | 2024-04-02 | 山东大学 | Hybrid electric vehicle convex optimization energy control method and system based on prediction |
| CN114179641B (en) * | 2021-12-29 | 2023-10-20 | 上海重塑能源科技有限公司 | Fuel cell composite power supply system for electric forklift |
| CN114500504A (en) * | 2022-01-19 | 2022-05-13 | 博雷顿科技有限公司 | Intelligent early warning method for motor efficiency deterioration, computer storage medium and vehicle |
| CN114714987B (en) * | 2022-03-08 | 2024-06-25 | 佛山仙湖实验室 | Energy management optimization method and system for fuel cell hybrid electric vehicle |
| CN114821854B (en) * | 2022-03-28 | 2023-06-09 | 中汽研汽车检验中心（天津）有限公司 | Method for evaluating influence of working condition switching on vehicle fuel consumption |
| CN114843561B (en) * | 2022-05-13 | 2024-07-09 | 中国第一汽车股份有限公司 | Control method and device for fuel cell |
| CN115000471A (en) * | 2022-05-18 | 2022-09-02 | 西安交通大学 | Fuel cell catalyst layer prediction-analysis-optimization method based on machine learning |
| CN115587654B (en) * | 2022-10-17 | 2024-03-01 | 国网河北省电力有限公司邯郸供电分公司 | Operation vehicle discharge optimization method and system, electronic equipment and readable storage medium |
| CN115649015B (en) * | 2022-10-19 | 2023-12-15 | 苏州市华昌能源科技有限公司 | Time-period-based vehicle-mounted fuel cell energy management method |
| CN115632145B (en) * | 2022-10-26 | 2023-05-16 | 上海汉翱新能源科技有限公司 | Hydrogen supply pressure optimization method and system for hydrogen fuel cell |
| CN115906622A (en) * | 2022-11-08 | 2023-04-04 | 杭州润氢科技有限公司 | Fuel cell electric vehicle energy control strategy based on model reinforcement learning |
| CN116522498B (en) * | 2023-04-28 | 2024-02-02 | 重庆大学 | Energy consumption and emission collaborative optimization method for range-extended electric vehicle and range-extended electric vehicle control method |
| CN116702978B (en) * | 2023-06-07 | 2024-02-13 | 西安理工大学 | Electric vehicle charging load prediction method and device considering emergency characteristics |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818377A (en) * | 2016-09-12 | 2018-03-20 | 法乐第(北京)网络科技有限公司 | Vehicle global optimization control method, system, vehicle and cloud computing platform based on cloud computing platform |
| JP6930592B2 (en) * | 2017-03-01 | 2021-09-01 | 日本電気株式会社 | Warning, Irregular, Unfavorable Mode Predictors and Methods |
| CN107425534B (en) * | 2017-08-25 | 2020-07-31 | 电子科技大学 | Micro-grid scheduling method based on optimization of storage battery charging and discharging strategy |
| CN108197726B (en) * | 2017-12-11 | 2021-11-09 | 浙江科技学院 | Family energy data optimization method based on improved evolutionary algorithm |
| CN109927709B (en) * | 2017-12-15 | 2020-08-28 | 郑州宇通客车股份有限公司 | Vehicle driving route working condition determining method, energy management method and system |
| CN108177648B (en) * | 2018-01-02 | 2019-09-17 | 北京理工大学 | A kind of energy management method of the plug-in hybrid vehicle based on intelligent predicting |
| CN108427985B (en) * | 2018-01-02 | 2020-05-19 | 北京理工大学 | Plug-in hybrid vehicle energy management method based on deep reinforcement learning |
| CN110309978B (en) * | 2019-07-09 | 2022-07-22 | 南京邮电大学 | Neural network photovoltaic power prediction model and method based on secondary dynamic adjustment |
| CN110852482B (en) * | 2019-10-15 | 2020-12-18 | 江苏大学 | Real-time global optimization intelligent control system and method for fuel cell bus |
-
2019
- 2019-10-15 CN CN201910977702.8A patent/CN110852482B/en active Active
-
2020
- 2020-03-13 WO PCT/CN2020/079244 patent/WO2021073036A1/en active Application Filing
- 2020-03-13 CH CH01054/20A patent/CH717533B1/en not_active IP Right Cessation
Also Published As
| Publication number | Publication date |
|---|---|
| CN110852482A (en) | 2020-02-28 |
| CH717533B1 (en) | 2022-01-14 |
| WO2021073036A1 (en) | 2021-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852482B (en) | Real-time global optimization intelligent control system and method for fuel cell bus | |
| Xiong et al. | Towards a smarter hybrid energy storage system based on battery and ultracapacitor-A critical review on topology and energy management | |
| CN110696815B (en) | Prediction energy management method of network-connected hybrid electric vehicle | |
| Yang et al. | Adaptive real-time optimal energy management strategy based on equivalent factors optimization for plug-in hybrid electric vehicle | |
| Yuan et al. | Intelligent energy management strategy based on hierarchical approximate global optimization for plug-in fuel cell hybrid electric vehicles | |
| CN110562239B (en) | Variable-domain optimal energy management control method and device based on demand power prediction | |
| Singh et al. | Fuzzy logic and Elman neural network tuned energy management strategies for a power-split HEVs | |
| Wu et al. | Hierarchical predictive control for electric vehicles with hybrid energy storage system under vehicle-following scenarios | |
| Liu et al. | Energy management for hybrid electric vehicles based on imitation reinforcement learning | |
| CN110549914B (en) | Approximate optimal energy management method for daily operation of fuel cell tramcar | |
| CN112526883B (en) | Vehicle energy management method based on intelligent networking information | |
| Lin et al. | Intelligent energy management strategy based on an improved reinforcement learning algorithm with exploration factor for a plug-in PHEV | |
| CN105667499A (en) | Energy management method for electric automobile in range extending mode | |
| CN113135113B (en) | Global SOC (System on chip) planning method and device | |
| CN115071505A (en) | Fuel cell automobile layered planning method, system, device and storage medium | |
| Cussigh et al. | Optimal charging and driving strategies for battery electric vehicles on long distance trips: A dynamic programming approach | |
| CN116985679A (en) | Real-time energy management method for fuel cell locomotive | |
| CN113297129B (en) | SOC calculation method and system of energy storage system | |
| CN111516702B (en) | Online real-time layered energy management method and system for hybrid electric vehicle | |
| Ren et al. | Battery longevity-conscious energy management predictive control strategy optimized by using deep reinforcement learning algorithm for a fuel cell hybrid electric vehicle | |
| US12085399B2 (en) | Modular machine-learning based system for predicting vehicle energy consumption during a trip | |
| CN115991121A (en) | Method for managing energy of whole fuel cell | |
| CN115352289A (en) | Charging information processing method and device, storage medium, module and controller | |
| CN115571113A (en) | Hybrid power vehicle energy optimization control method and system based on speed planning | |
| CN112837532B (en) | New energy bus cooperative dispatching and energy-saving driving system and control method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |