Instantaneous energy management global optimization method and system oriented to multi-dimensional characteristics

Abstract

An instantaneous energy management global optimization method and system oriented to multi-dimensional characteristics, and the method comprises the steps: selecting working parameters of a vehicle hybrid power module, constructing constraint conditions, and carrying out the optimization processing of the collected working parameters, and obtaining the input data of a model; operating parameters are calculated through an equivalent consumption minimum strategy, and a working model under instantaneous optimization is constructed; global optimization is carried out on the working model under instantaneous optimization of the hybrid power module; the optimal working parameters of the vehicle hybrid power module in the global optimization state are solved by combining input data of the model and the globally optimized model, and the model is updated based on a particle swarm algorithm; and the optimal working parameters are transmitted back to a hybrid power module of the vehicle, and the working state of the vehicle at the next moment is controlled. According to the invention, the instantaneous fuel consumption can be greatly reduced, and the problem of large fluctuation of the SOC of the battery is reduced, so that the stability and recovery of the power battery are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of instantaneous energy optimization, and more specifically, to a global optimization method and system for instantaneous energy management oriented to multi-dimensional characteristics. Background Art

[0002] At present, the hybrid power module field of automobiles faces the challenge of transient power changes under complex driving conditions. Reasonable energy management strategies can optimize energy utilization and reduce energy consumption, thereby improving the energy efficiency of the module and reducing the impact on the environment. However, the construction of energy management strategies is relatively complex and requires a large amount of calculations. It is difficult to solve practical problems in real-time under multiple working conditions.

[0003] The instantaneous optimization algorithm in the existing technology is complex, which leads to increased computing requirements and easily affects the real-time data of the system.

[0004] Prior art document 1 (CN201710883631.6) proposes an intelligent hybrid vehicle energy management control method. For the energy management of the hybrid module, a logical threshold method is used to reduce the computational difficulty in energy management; Prior art document 2 (CN202011212191.X) proposes a deep reinforcement learning-based algorithm, which improves the system's computing efficiency by solving multi-objective optimization problems of fuel economy and fuel cell efficiency.

[0005] However, the energy management strategies targeted by the above-mentioned prior arts do not consider the optimization of algorithm parameters, and have deficiencies in improving model calculation accuracy and predictive control.

[0006] Therefore, in order to solve the transient control problem, establishing an energy management strategy with transient characteristics becomes a key task. Summary of the invention

[0007] In order to solve the deficiencies in the prior art, the present invention provides a global optimization method for instantaneous energy management for multi-dimensional characteristics, which can improve the accuracy of the calculation model and achieve global optimal energy allocation under instantaneous conditions by updating the optimal parameters of the algorithm.

[0008] The present invention adopts the following technical solution.

[0009] A global optimization method for instantaneous energy management oriented to multi-dimensional characteristics comprises the following steps:

[0010] Select the working parameters of the vehicle hybrid power module and construct constraint conditions, collect the working parameters and optimize the collected working parameters to obtain the input data of the model;

[0011] Calculate the operating parameters through the equivalent consumption minimum strategy and build a working model under instantaneous optimization;

[0012] Perform global optimization on the working model of the hybrid power module under instantaneous optimization;

[0013] Combine the model input data with the globally optimized model to solve the optimal operating parameters of the vehicle hybrid module under the global optimization state, and update the model based on the particle swarm algorithm;

[0014] The optimal operating parameters are transmitted back to the vehicle's hybrid power module to control the vehicle's operating state at the next moment.

[0015] Preferably, the vehicle operating parameters include at least: vehicle speed, engine speed, motor speed, transmission system, power battery SOC, and power battery current;

[0016] The constraints include: setting engine power output limits, battery charge and discharge limits, and motor power output limits;

[0017] Under the premise of meeting the constraints, collect data on various types of vehicle operating parameters over a period of time.

[0018] Preferably, the collected working parameters are optimized, specifically including:

[0019] Adopting the state feature extraction method, the collected vehicle speed, engine speed, motor speed, power battery SOC, and power battery current are optimized and extracted to obtain the data after feature extraction;

[0020] The exponential smoothing method is used to process the data after feature extraction, and the optimized data is used as the input data of the model.

[0021] Preferably, the feature optimization extraction of the working parameters specifically includes:

[0022] Perform feature optimization and extraction on various types of working parameters respectively, and calculate the corresponding feature mean μj for the jth working parameter:

[0023]

[0024] In the formula, n represents the number of features, X ij represents the i-th data collected by the j-th working parameter;

[0025] Calculate the standard deviation σ j

[0026]

[0027] After standardizing the data, we get X ij '

[0028]

[0029] The covariance matrix C is obtained by constructing the data matrix:

[0030] Cv=βv

[0031] Among them, β is the data after feature extraction, and v is the feature vector.

[0032] Preferably, the data after feature extraction is processed by exponential smoothing method to obtain optimized data as input data of the model, which specifically includes:

[0033] Calculate the smoothed value of the data after feature extraction at each moment:

[0034] S t =αY t +(1-α)(S t-1 +T t-1 )

[0035] In the formula, S t is the smoothed value at time t; Y t is the data after the feature extraction of each parameter at time t; S t-1 is the smoothing value of t-1; a is the smoothing coefficient.

[0036] Preferably, the construction of the working model under instantaneous optimization specifically includes:

[0037] Taking the hybrid module battery SOC as the state variable and the torque control as the control variable, the instantaneous equivalent fuel consumption is optimized and the augmented cost function J(t e ) as a working model under instantaneous optimization:

[0038]

[0039] Among them, t e is the system termination time; T m (t) is the instantaneous torque of the motor; m e is the fuel consumption, F[x(t e )] is the constraint condition of the augmented cost function.

[0040] Preferably, the augmented cost function J(t e ) constraint F[x(t e )]satisfy:

[0041]

[0042] in, is the penalty coefficient; SOC e SOC is the battery end time; SOC t is the battery target SOC;

[0043] By introducing the co-state quantity λ, the following Hamiltonian function is obtained:

[0044]

[0045] Among them, T m (t) represents the motor torque, λ(t) represents the covariate variable, m e (t) represents the equivalent fuel consumption, is the system state equation.

[0046] Preferably, the parameters of the working model under instantaneous optimization are obtained by solving the Hamiltonian function, and the solution of the Hamiltonian function specifically includes:

[0047] System dynamic equations satisfy:

[0048]

[0049] Where, I(t) is the instantaneous current of the battery; C represents the battery capacity;

[0050] The instantaneous current I(t) of the battery satisfies:

[0051]

[0052] Among them, P batt (t) is the instantaneous power of the battery, U is the open circuit voltage of the battery;

[0053] Therefore, the Hamiltonian function can be equivalent to:

[0054]

[0055] Taking partial derivatives of the Hamiltonian function, we get:

[0056]

[0057] Where SOC represents the battery state of charge, and H is the Hamiltonian function.

[0058] Preferably, the globally optimizing the working model of the hybrid power module under instantaneous optimization specifically includes:

[0059] Optimize the Hamiltonian function:

[0060]

[0061] P fc * (t) = arg min H [SOC p (t), P fc (t),λ(t),t]

[0062] In the formula, Indicates the fuel consumption rate of the vehicle;

[0063] P fc (t) represents the engine output power;

[0064] Indicates the rate of change of battery state of charge under PMP theory;

[0065] represents the optimal engine output power sequence

[0066] SOC p (t) represents the state variable.

[0067] Among them, the state variable SOC p (t) and the covariate variable λ(t) need to satisfy:

[0068]

[0069]

[0070] In the formula, and Respectively represent the state variable SOC p (t) is differentiated with respect to the covariate variable λ(t).

[0071] At the same time, it is necessary to determine the state variables at the endpoint time, which includes the initial time t=t0 and the final time t=tf. The state variables at the endpoint time meet the following constraints:

[0072]

[0073] Among them, SOC t0 , SOC tf Respectively represent the battery state of charge at the initial time and the end time, SOC initial , SOC target Represent the SOC values ​​at the initial time and the end time respectively.

[0074] Preferably, the optimal operating parameters of the vehicle hybrid power module under the global optimization state include the engine, motor operating state, equivalent factor, and battery state of charge regression characteristics;

[0075] The particle swarm algorithm is used to update the working model under instantaneous optimization after global optimization, and the updated model is used for the optimal system working parameters at the next moment.

[0076] The present invention also proposes a global optimization system for instantaneous energy management oriented to multi-dimensional characteristics using the instantaneous energy management global optimization method, comprising: a parameter acquisition module, a parameter optimization module, a model construction module, a model optimization module, a solution module, a model update module and a control module;

[0077] The parameter acquisition module is used to select the working parameters of the vehicle hybrid power module and construct constraint conditions, and collect parameters under the constraint conditions;

[0078] The parameter optimization module is used to optimize the collected working parameters to obtain the input data of the model;

[0079] The model building module calculates the operating parameters through the equivalent consumption minimum strategy and builds a working model under instantaneous optimization;

[0080] The model optimization module is used to globally optimize the working model under the instantaneous optimization of the hybrid power module;

[0081] The solution module is used to combine the input data of the model and the globally optimized model to solve the optimal system working parameters under the global optimization state;

[0082] The model updating module is used to update the working model under instantaneous optimization in the global optimization state based on the particle swarm algorithm;

[0083] The control module is used to control the hybrid power module of the vehicle according to the optimal working parameters.

[0084] The present invention also provides a terminal, comprising a processor and a storage medium;

[0085] The storage medium is used to store instructions;

[0086] The processor is used to operate according to the instructions to execute the steps of the instantaneous energy management global optimization method for multi-dimensional characteristics.

[0087] The present invention also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the global optimization method of instantaneous energy management for multi-dimensional characteristics are implemented.

[0088] The beneficial effect of the present invention is that, compared with the prior art, the present invention aims at the problem of slow dynamic response of traditional global optimization, etc., by optimizing the vehicle parameters, combining the equivalent consumption minimum strategy with the PMP principle, establishing a new energy management strategy, and realizing a global optimization method with instantaneous characteristics. The vehicle controlled by this method can more efficiently recover energy during the braking phase, which significantly improves the overall energy utilization efficiency. After optimization by the particle swarm algorithm, the working performance of the engine and the motor is significantly improved, and a more efficient and balanced energy distribution is achieved. Compared with other energy management strategies, this optimization scheme greatly reduces instantaneous fuel consumption, and has a significant effect in solving the problem of large fluctuations in battery SOC in ECMS and other new strategies, thereby significantly improving the stability and recovery of the power battery. In addition, by accurately predicting and adjusting the working state of the battery, the algorithm can flexibly adapt to the changing driving environment and further improve the efficiency of energy utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 It is a flow chart of the instantaneous energy management global optimization method for multi-dimensional characteristics in the present invention;

[0090] Figure 2 is a comparison result diagram of SOC values ​​obtained under different energy management methods in the simulation example of the present invention;

[0091] Figure 3 is a comparison result diagram of instantaneous fuel consumption obtained under different energy management methods in the simulation example of the present invention;

[0092] Figure 4 It is a structural diagram of the instantaneous energy management global optimization system for multi-dimensional characteristics in the present invention. DETAILED DESCRIPTION

[0093] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0094] like Figure 1 As shown, the present invention proposes a global optimization method for instantaneous energy management oriented to multi-dimensional characteristics, and the method comprises the following steps:

[0095] Step 1: Analyze the working characteristics and working principle of the hybrid power module of the vehicle, select the working parameters of the vehicle and construct constraint conditions, and optimize the collected working parameters to obtain the input data of the model;

[0096] Vehicle operating parameters include: vehicle speed, engine speed, motor speed, transmission system, power battery SOC (State of Charge), and power battery current.

[0097] The constraints set by the present invention include:

[0098] (1) Engine power output limitation: The engine must be operated within its maximum allowable power range to avoid overload operation;

[0099] (2) Battery charge and discharge limits: Batteries have certain capacity and charge and discharge rate limits. Ensure that the battery charge and discharge rate does not exceed its limit to avoid damage or affect the battery life.

[0100] (3) Motor power output limitation.

[0101] Furthermore, under the premise of meeting the constraints, data of various types of vehicle operating parameters are collected over a period of time.

[0102] The collected working parameters are optimized to obtain the input data of the model, including:

[0103] Adopting the state feature extraction method, the collected vehicle speed, engine speed, motor speed, power battery SOC, and power battery current are optimized and extracted to obtain the data after feature extraction;

[0104] Feature extraction specifically includes:

[0105] Perform feature optimization and extraction on various types of working parameters respectively, and calculate the corresponding feature mean μ for the jth working parameter j :

[0106]

[0107] In the formula, n represents the number of features, X ij represents the i-th data collected by the j-th working parameter;

[0108] Calculate the standard deviation σ j

[0109]

[0110] After standardizing the data, we get X ij '

[0111]

[0112] The covariance matrix C is obtained by constructing the data matrix:

[0113] Cv=βv

[0114] Among them, β is the data after feature extraction, and v is the feature vector.

[0115] Furthermore, the exponential smoothing method is used to process the optimized data to accelerate the convergence speed of the particle swarm optimization algorithm, so that the algorithm can find the optimal solution in fewer iterations. The energy consumption data obtained by optimization can obtain a more stable input after smoothing. The data obtained after smoothing is as follows:

[0116] S t =αY t +(1-α)(S t-1 +T t-1 )

[0117] In the formula, S t is the smoothed value at time t; Y t is the data after the feature extraction of each parameter at time t; S t-1 is the smoothing value of t-1; a is the smoothing coefficient.

[0118] Step 2: quickly calculate the operating parameters through the equivalent consumption minimum strategy to obtain the working model of the hybrid power module under instantaneous optimization.

[0119] By building an equivalent consumption minimum strategy model and obtaining an instantaneous optimization algorithm, the instantaneous equivalent fuel consumption at a certain moment in the future can be expressed as:

[0120]

[0121] in, is the total instantaneous equivalent fuel consumption; is the instantaneous fuel consumption of the engine, Indicates the equivalent instantaneous fuel consumption of the motor;

[0122] Furthermore, the instantaneous fuel consumption of the engine It can be expressed as:

[0123]

[0124] Among them, P e (t) is the engine power, η e is the engine efficiency, Q lhv The lower calorific value of the fuel.

[0125] Motor equivalent instantaneous fuel consumption It can be expressed as:

[0126]

[0127] Among them, P batt(t) is the instantaneous power of the battery, S(t) is the equivalent factor, which changes with the charging and discharging state of the battery. The expression of the equivalent factor S(t) is:

[0128] S(t)=[S charge (t), S discharge (t)] (4)

[0129] Among them, S charge (t) and S discharge (t) represent the equivalent factors of battery charging and discharging respectively.

[0130] Assume that the state equation of the vehicle hybrid module is for:

[0131]

[0132] Among them, u(t) is the control variable, x(t) is the state variable, f[·] represents the objective function, and t represents the time.

[0133] Obtain the working model of instantaneous optimization based on the state equation, specifically:

[0134] Taking the hybrid module battery SOC as the state variable and the torque control as the control variable, the instantaneous equivalent fuel consumption is optimized and the augmented cost function J(t e ) as the working model of the hybrid power module under instantaneous optimization, as shown below:

[0135]

[0136] Among them, t e The end time of the vehicle hybrid module operation; T m (t) is the instantaneous torque of the motor; m e is the fuel consumption, F[x(t e )] is the constraint condition of the augmented cost function.

[0137] Augmented cost function J(t e ) constraint F[x(t e )] can be expressed as:

[0138]

[0139] in, is the penalty coefficient; SOC e SOC is the battery end time; SOC t is the battery target SOC.

[0140] By introducing the co-state quantity λ, the following Hamiltonian function can be obtained:

[0141]

[0142] Among them, T m (t) represents the motor torque, λ(t) represents the covariate variable, m e (t) represents the equivalent fuel consumption.

[0143] Solving the Hamiltonian function can obtain the working parameters of the working model under instantaneous optimization. Further, the solution of the Hamiltonian function specifically includes:

[0144] is the system dynamic equation, which can be expressed as:

[0145]

[0146] Where, I(t) is the instantaneous current of the battery; C represents the battery capacity;

[0147] The instantaneous current I(t) of the battery can be expressed as:

[0148]

[0149] Among them, P batt (t) is the instantaneous power of the battery, and U is the open circuit voltage of the battery.

[0150] Therefore, the Hamiltonian function can be equivalent to:

[0151]

[0152] Taking partial derivatives of the Hamiltonian function, we get:

[0153]

[0154] Where SOC represents the battery state of charge, and H is the Hamiltonian function.

[0155] Therefore, by solving the formula, the global optimization problem is transformed into an instantaneous optimization problem that is solved forward, and the global optimal torque distribution can be obtained.

[0156] At the same time, the working model of the constructed hybrid power module under instantaneous optimization needs to meet the following constraints:

[0157]

[0158] Among them, x(t0) represents the state variable at the initial value, λ(t e ) represents the co-state variable at the termination time, and x0 represents the initial value of the state variable.

[0159] Step 3, globally optimizing the working model under instantaneous optimization constructed in step 2;

[0160] Apply PMP theory to energy management strategy and perform global optimization on the working model of hybrid power module under instantaneous optimization, including:

[0161] Optimize the Hamiltonian function:

[0162]

[0163] P fc * (t) = arg min H [SOC p (t), P fc (t),λ(t),t] (15)

[0164] In the formula, Indicates the fuel consumption rate of the vehicle;

[0165] P fc (t) represents the engine output power;

[0166] Indicates the rate of change of battery state of charge under PMP theory;

[0167] represents the optimal engine output power sequence

[0168] SOC p (t) represents the state variable.

[0169] Among them, the state variable SOC p (t) and the covariate variable λ(t) need to satisfy:

[0170]

[0171]

[0172] In the formula, and Respectively represent the state variable SOC p (t) is differentiated with respect to the covariate variable λ(t).

[0173] At the same time, it is necessary to determine the state variables at the endpoint time, which includes the initial time t=t0 and the final time t=tf. The state variables at the endpoint time meet the following constraints:

[0174]

[0175] Among them, SOC t0 , SOC tf Respectively represent the battery state of charge at the initial time and the end time, SOC initial, SOC target Represent the SOC values ​​at the initial time and the end time respectively.

[0176] Step 4, using the particle swarm algorithm to solve the optimal operating parameters of the vehicle hybrid power module under the global optimization state, including the engine and motor operating states, equivalent factors, and battery state of charge regression characteristics.

[0177] Specifically, the input data obtained in step 1 is input into the working model under instantaneous optimization after global optimization in step 3 to obtain the optimal working parameters of the vehicle hybrid power module, including the working state of the engine and motor, the equivalent factor, and the battery state of charge regression characteristics.

[0178] Furthermore, the model is updated by particle swarm algorithm, including:

[0179] Assume that the objective function to be optimized is f(x), where x is the solution vector of the problem. In the PSO algorithm framework, the position of each particle is determined by x. i The speed is represented by v i Indicates that i refers to the i-th particle.

[0180] During the calculation process, the fitness value f(x i ) is calculated. For all particles, the individual historical optimal position of each particle will be recorded, and a global optimal position g will be identified in the group. The global optimal position is calculated and updated by the following formula:

[0181] g = argmin(f(p i )) (19)

[0182] g min (λ)=arg∑(f soc , f loss ) (20)

[0183] Among them, p i is the optimal position of the individual, f soc represents the reproducibility of the vehicle's state of charge, f loss Represents the energy conversion efficiency index of the generator.

[0184] Update the particle velocity. The update formula of particle velocity is as follows:

[0185]

[0186] in: is the speed of the current particle at time t; it is used to balance the exploration ability of individual particles and group searches; c1 and c2 represent the learning factors of individuals and society respectively; rand1 and rand2 represent random numbers between 0 and 1, which are used to introduce randomness to increase the diversity and exploration ability of the algorithm, and help to better explore potential solutions in the search space; p i -x i Indicates the difference between the individual's optimal position and the current position, which is used for learning from individual experience; gx i It represents the difference between the global optimal position and the current position, which is used for learning group experience; ω is the inertia weight, which is responsible for adjusting the degree to which the particle retains the previous velocity state, thereby affecting its sensitivity to individual historical experience and group shared knowledge. The inertia weight ω can be expressed as:

[0187]

[0188] Among them, ω max is the initial value of the inertia weight, k is the current number of iterations, k max is the maximum number of iterations, ω min is the final value of the inertia weight.

[0189] The update formula of particle position can be expressed as:

[0190]

[0191] The above steps are repeatedly executed until a preset termination condition is reached. The preset termination condition may be that the objective function value reaches an expected convergence standard or achieves a maximum number of iterations.

[0192] Step 5, transmitting the obtained optimal working parameters to the vehicle, and the vehicle executes according to the optimal working parameters to achieve its optimal working state.

[0193] In order to further verify the beneficial effects of the present invention, the method proposed in the present invention is applied to the energy management of the vehicle hybrid power module, and combined with other energy management strategies for management, and simulation experiments and comparative analysis are carried out. The results obtained are as follows Figure 2 , 3 As shown, there are respectively schematic diagrams of curve comparison of the SOC value and fuel consumption of the vehicle changing with time under the original vehicle, the energy management strategy based on ECMS, other new energy management strategies and the energy management method proposed by the present invention;

[0194] It can be seen that the optimization method proposed in the present invention significantly improves the energy distribution of the engine and the motor and reduces the instantaneous fuel consumption. The average fuel economy of the hybrid module is increased to 37mi / gal, which is 3.35% higher than before optimization and 38.58% higher than the original vehicle. The optimization algorithm can accurately predict and adjust the battery state to adapt to dynamically changing driving conditions. Under the management of this optimization method, the initial SOC value of the battery was 60%, which rose to 62.26% at the end of the operation, achieving a positive growth of only 2.26%, and the SOC fluctuations throughout the process were maintained within a safe range. It proves the effectiveness of the optimization method in solving the problem of large fluctuations in battery SOC in ECMS and other new strategies, thereby significantly improving the stability and recovery of the power battery.

[0195] This result proves that the present invention can significantly reduce instantaneous fuel consumption, and has a significant effect in solving the problem of large fluctuations in battery SOC existing in ECMS and other new strategies, thereby significantly improving the stability and recovery of the power battery.

[0196] like Figure 4 As shown, the present invention also proposes a global optimization system for instantaneous energy management facing multi-dimensional characteristics. The global optimization method for instantaneous energy management facing multi-dimensional characteristics can be implemented based on the system. The system includes a parameter acquisition module, a parameter optimization module, a model building module, a model optimization module, a solution module, a model update module and a control module;

[0197] Specifically, the parameter acquisition module is used to select the working parameters of the vehicle hybrid power module and construct constraint conditions, and to collect parameters under the constraint conditions;

[0198] The parameter optimization module is used to optimize the collected working parameters to obtain the input data of the model;

[0199] The model building module calculates the operating parameters through the equivalent consumption minimum strategy and builds a working model under instantaneous optimization;

[0200] The model optimization module is used to globally optimize the working model under the instantaneous optimization of the hybrid power module;

[0201] The solution module is used to combine the input data of the model and the globally optimized model to solve the optimal system working parameters under the global optimization state;

[0202] The model updating module is used to update the working model under instantaneous optimization in the global optimization state based on the particle swarm algorithm;

[0203] The control module is used to control the hybrid power module of the vehicle according to the optimal working parameters.

[0204] The beneficial effect of the present invention is that, compared with the prior art, the present invention can significantly reduce instantaneous fuel consumption, has a significant effect in solving the problem of large fluctuations in battery SOC existing in ECMS and other new strategies, and thus significantly improves the stability and recovery of the power battery.

[0205] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0206] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0207] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0208] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages-such as Smalltalk, C++, etc., and conventional procedural programming languages-such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network-including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) may be personalized by utilizing the state information of a computer-readable program instruction, and the electronic circuit may execute a computer-readable program instruction, thereby realizing various aspects of the present disclosure.

[0209] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A global optimization method for instantaneous energy management based on multi-dimensional characteristics, characterized in that: The steps include: Select the working parameters of the vehicle hybrid power module and construct constraint conditions, collect the working parameters and optimize the collected working parameters to obtain the input data of the model; Calculate the operating parameters through the equivalent consumption minimum strategy and build a working model under instantaneous optimization; Perform global optimization on the working model of the hybrid power module under instantaneous optimization; Combine the model input data with the globally optimized model to solve the optimal operating parameters of the vehicle hybrid module under the global optimization state, and update the model based on the particle swarm algorithm; The optimal operating parameters are transmitted back to the vehicle's hybrid power module to control the vehicle's operating state at the next moment.

2. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 1 is characterized in that: The vehicle operating parameters include at least: vehicle speed, engine speed, motor speed, transmission system, power battery SOC, and power battery current; The constraints include: setting engine power output limits, battery charge and discharge limits, and motor power output limits; Under the premise of meeting the constraints, collect data on various types of vehicle operating parameters over a period of time.

3. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 1 is characterized in that: Optimize the collected working parameters, including: Adopting the state feature extraction method, the collected vehicle speed, engine speed, motor speed, power battery SOC, and power battery current are optimized and extracted to obtain the data after feature extraction; The exponential smoothing method is used to process the data after feature extraction, and the optimized data is used as the input data of the model.

4. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 3 is characterized in that: The feature optimization and extraction of working parameters specifically includes: Perform feature optimization and extraction on various types of working parameters respectively, and calculate the corresponding feature mean μ for the jth working parameter j : In the formula, n represents the number of features, X ij represents the i-th data collected by the j-th working parameter; Calculate the standard deviation σ j After standardizing the data, we get X ij ' The covariance matrix C is obtained by constructing the data matrix: Cv=βv Among them, β is the data after feature extraction, and v is the feature vector.

5. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 3 is characterized in that: The exponential smoothing method is used to process the data after feature extraction, and the optimized data is used as the input data of the model, including: Calculate the smoothed value of the data after feature extraction at each moment: S t =αY t +(1-α)(S t-1 +T t-1 ) In the formula, S t is the smoothed value at time t; Y t is the data after the feature extraction of each parameter at time t; S t-1 is the smoothing value of t-1; a is the smoothing coefficient.

6. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 1 is characterized in that: The construction of the working model under instantaneous optimization specifically includes: Taking the hybrid module battery SOC as the state variable and the torque control as the control variable, the instantaneous equivalent fuel consumption is optimized and the augmented cost function J(t e ) as a working model under instantaneous optimization: Among them, t e is the system termination time; T m (t) is the instantaneous torque of the motor; m e is the fuel consumption, F[x(t e )] is the constraint condition of the augmented cost function.

7. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 6 is characterized in that: Augmented cost function J(t e ) constraint F[x(t e )]satisfy: in, is the penalty coefficient; SOC e SOC is the battery end time; SOC t is the battery target SOC; By introducing the co-state quantity λ, the following Hamiltonian function is obtained: Among them, T m (t) represents the motor torque, λ(t) represents the covariate variable, m e (t) represents the equivalent fuel consumption, is the system state equation.

8. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 7 is characterized in that: The parameters of the working model under instantaneous optimization are obtained by solving the Hamiltonian function. The solution of the Hamiltonian function specifically includes: System dynamic equations satisfy: Where, I(t) is the instantaneous current of the battery; C represents the battery capacity; The instantaneous current I(t) of the battery satisfies: Among them, P batt (t) is the instantaneous power of the battery, U is the open circuit voltage of the battery; Therefore, the Hamiltonian function can be equivalent to: Taking partial derivatives of the Hamiltonian function, we get: Where SOC represents the battery state of charge, and H is the Hamiltonian function.

9. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 1 is characterized in that: The global optimization of the working model under the instantaneous optimization of the hybrid power module specifically includes: Optimize the Hamiltonian function: P fc * (t)=argminH[SOC p (t),P fc (t),λ(t),t] In the formula, Indicates the fuel consumption rate of the vehicle; P fc (t) represents the engine output power; Indicates the rate of change of battery state of charge under PMP theory; represents the optimal engine output power sequence SOC p (t) represents the state variable; Among them, the state variable SOC p (t) and the covariate variable λ(t) need to satisfy: In the formula, and Respectively represent the state variable SOC p (t) is differentiated with the covariate variable λ(t); At the same time, the state variables at the endpoint time are determined. The endpoint time includes the initial time t=t0 and the terminal time t=tf. The state variables at the endpoint time meet the following constraints: Among them, SOC t0 , SOC tf Respectively represent the battery state of charge at the initial time and the end time, SOC initial , SOC target Represent the SOC values ​​at the initial time and the end time respectively.

10. The instantaneous energy management global optimization method for multi-dimensional characteristics according to claim 1, characterized in that: The optimal operating parameters of the vehicle hybrid power module under the global optimization state include the engine, motor operating state, equivalent factor, and battery state of charge regression characteristics; The particle swarm algorithm is used to update the working model under instantaneous optimization after global optimization, and the updated model is used for the optimal system working parameters at the next moment.

11. A global optimization system for instantaneous energy management with multi-dimensional characteristics using the global optimization method for instantaneous energy management according to any one of claims 1 to 10, characterized in that: include: Parameter acquisition module, parameter optimization module, model building module, model optimization module, solution module, model updating module and control module; The parameter acquisition module is used to select the working parameters of the vehicle hybrid power module and construct constraint conditions, and collect parameters under the constraint conditions; The parameter optimization module is used to optimize the collected working parameters to obtain the input data of the model; The model building module calculates the operating parameters through the equivalent consumption minimum strategy and builds a working model under instantaneous optimization; The model optimization module is used to globally optimize the working model under the instantaneous optimization of the hybrid power module; The solution module is used to combine the input data of the model and the globally optimized model to solve the optimal system working parameters under the global optimization state; The model updating module is used to update the working model under instantaneous optimization in the global optimization state based on the particle swarm algorithm; The control module is used to control the hybrid power module of the vehicle according to the optimal working parameters.

12. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images