Energy management method and device for double-source power supply vehicle, computer equipment and medium

Abstract

The invention relates to the technical field of double-source power supply, in particular to an energy management method and device for a double-source power supply vehicle, computer equipment and a medium. The method comprises the following steps: S1, acquiring various types of operation data of the double-source power supply vehicle in a sliding time window; s2, predicting the predicted energy consumption of the dual-source power supply vehicle in a prediction time domain by using the trained energy consumption prediction model based on the multiple types of operation data; s3, determining availability information of a contact network for supplying power to the double-source power supply vehicle in the prediction time domain, and battery constraint conditions and pantograph constraint conditions of the double-source power supply vehicle; s4, taking the predicted energy consumption, the availability information, the battery constraint condition and the pantograph constraint condition as constraint conditions of the target function, and generating an energy configuration strategy by minimizing the target function; the energy configuration strategy comprises an energy distribution strategy of the vehicle-mounted battery and the pantograph, a pantograph operation strategy and a vehicle-mounted battery charging and discharging strategy. By adopting the method, energy switching can be carried out in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dual-source power supply, in particular to an energy management method and device for a dual-source power supply vehicle, a computer device and a medium. BACKGROUND

[0002] With the deepening of the policy, the dual-source power supply vehicle becomes an important direction to replace the traditional fuel vehicle. The dual-source power supply technology combines the advantages of flexible endurance and efficient energy supply, and is widely used in high-intensity working conditions such as ports, mining areas, and intercity short-haul transportation.

[0003] At present, the dual-source power supply vehicle in the patent CN120663811A often determines whether to use the battery or the pantograph to provide energy for the motor of the vehicle according to whether there is a catenary above the vehicle. In this way, it is necessary to start using the power grid after entering the catenary area and switch to the battery after leaving the catenary, which cannot prepare in advance according to the road conditions in front, thereby causing the energy switching to lag and the energy consumption to be high. SUMMARY

[0004] Therefore, it is necessary to provide an energy management method and device for a dual-source power supply vehicle, a computer device and a medium to solve the above technical problems.

[0005] An energy management method for a dual-source power supply vehicle, the method comprising:

[0006] S1, obtaining multiple types of running data of the dual-source power supply vehicle in a sliding time window;

[0007] Preferably, the dual-source power supply vehicle is a vehicle powered by a catenary and an on-board battery;

[0008] Preferably, the length of the sliding time window is fixed, and the end time of the sliding time window is the current time;

[0009] Preferably, the multiple types of running data include running state data, environmental data and driver operation data of the dual-source power supply vehicle;

[0010] S2, using a trained energy consumption prediction model to predict the predicted energy consumption of the dual-source power supply vehicle in a prediction time domain based on the multiple types of running data;

[0011] S3, determining the availability information of the catenary for supplying power to the dual-source power supply vehicle in the prediction time domain, the battery constraint condition of the dual-source power supply vehicle and the pantograph constraint condition;

[0012] Preferably, the availability information of the catenary in the prediction horizon refers to information that whether the catenary is in a normal working state in the prediction horizon and whether the catenary can provide stable and reliable power for the double-source power supply vehicle;

[0013] Preferably, the battery constraint condition includes but is not limited to a state of charge constraint, a charge-discharge power constraint, a charge-discharge rate constraint, and a battery discharge frequency constraint.

[0014] Preferably, the pantograph constraint condition includes but is not limited to a lifting constraint, a pantograph residence constraint, a pantograph hysteresis constraint, and a lifting frequency and time limit of the lifting pantograph.

[0015] S4, taking the predicted energy consumption, the availability information, the battery constraint condition, and the pantograph constraint condition as constraint conditions of an objective function, generating an energy configuration strategy by minimizing the objective function; the energy configuration strategy includes an energy distribution strategy of the on-board battery and the pantograph, a pantograph operation strategy, and a charge-discharge strategy of the on-board battery.

[0016] In one of the embodiments, the step S4 includes:

[0017] establishing an objective function; the constraint conditions of the objective function include the predicted energy consumption, the availability information, the battery constraint condition, and the pantograph constraint condition;

[0018] generating an energy configuration strategy by minimizing the objective function;

[0019] The expression of the objective function Z is:

[0020]

[0021] wherein c grid [k] is the catenary electricity price at time step k; P grid [k] is the pantograph power at time step k; P batt [k] is the battery power at time step k; SOC[k] is the battery state of charge at time step k; SOC ref is the desired state of charge; c deg,1 and c deg,1 are the weights of the battery aging cost; P batt,max is the maximum allowed charge-discharge power of the battery; λ SOC is the weight of the state of charge tracking error; λ sm is the weight of the power change rate; λ ρ is the weight of the soft constraint penalty; ρ[k] is the soft constraint relaxation at time step k; Δt is the time step length; and N is the number of time steps.

[0022] In one of the embodiments, the step S4 further includes:

[0023] At the current time in the predicted time domain, the motor of the dual-source powered vehicle is powered according to the energy configuration strategy, and the energy utilization rate, response time efficiency and state of charge stability of the dual-source powered vehicle are obtained;

[0024] Based on the energy utilization rate, response time efficiency and state of charge stability of the dual-source powered vehicle, the constraint conditions and weights of the target function are optimized to generate a new energy configuration strategy based on the optimized target function.

[0025] In one of the embodiments, the multiple types of running data include the speed, load, slope of the driving route of the dual-source powered vehicle, operation information for the dual-source powered vehicle and environmental temperature on the driving route.

[0026] In one of the embodiments, the dual-source powered vehicle includes a display interaction unit for displaying the energy configuration strategy and receiving operation instructions of the user.

[0027] In one of the embodiments, step S1 further includes:

[0028] When the sampling time of each type of running data in the multiple types of running data is inconsistent, any type of running data is taken as reference data;

[0029] The reference sampling time of the reference data is determined, and the data collected at the adjacent time of the reference sampling time is determined from each type of non-reference data;

[0030] Based on the parameters collected at the adjacent time, the data of each type of non-reference data at the reference sampling time is calculated;

[0031] The data of each type of non-reference data at the reference sampling time and the reference data are denoised and missing data repaired to obtain multiple types of preprocessed data;

[0032] Based on the multiple types of preprocessed data, the time sequence features, frequency domain features and vehicle derived features of the dual-source powered vehicle are counted and normalized, and the energy consumption is predicted through the normalized time sequence features, frequency domain features and vehicle derived features.

[0033] In one of the embodiments, the determination process of the predicted time domain in step S2 includes:

[0034] A plurality of candidate predicted time domains and screening conditions are preset;

[0035] Based on the historical predicted energy consumption and historical real energy consumption of each candidate predicted time domain, the deviation, interval coverage rate and interval width of each candidate predicted time domain are calculated;

[0036] determining an initial prediction time domain as the candidate prediction time domain satisfying the screening condition, and obtaining a reliability curve of each initial prediction time domain based on the bias, the interval coverage rate and the interval width of the initial prediction time domain;

[0037] determining a target indicator participating in reliability scoring from the bias, the interval coverage rate and the interval width according to the reliability curve of each initial prediction time domain;

[0038] obtaining a reliability score of each initial prediction time domain based on the target indicator of the initial prediction time domain;

[0039] determining the initial prediction time domain corresponding to the maximum value in the reliability score as a prediction time domain.

[0040] An energy management device of a dual-source powered vehicle, the device comprising:

[0041] a data acquisition module configured to acquire multiple types of running data of the dual-source powered vehicle within a sliding time window;

[0042] an energy consumption prediction module configured to predict a predicted energy consumption of the dual-source powered vehicle within a prediction time domain based on the multiple types of running data and using a trained energy consumption prediction model;

[0043] a condition determination module configured to determine availability information of a catenary supplying power to the dual-source powered vehicle within the prediction time domain, a battery constraint condition of the dual-source powered vehicle and a pantograph constraint condition;

[0044] a strategy acquisition module configured to generate an energy configuration strategy by minimizing an objective function with the predicted energy consumption, the availability information, the battery constraint condition and the pantograph constraint condition as constraint conditions of the objective function; the energy configuration strategy comprising an energy distribution strategy of an on-board battery and a pantograph, a pantograph operation strategy and a charging and discharging strategy of the on-board battery.

[0045] A computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the above method when executing the computer program.

[0046] A computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the steps of the above method.

[0047] The energy management method, device, computer equipment and medium of the double-source powered vehicle can obtain multiple types of running data of the double-source powered vehicle in a sliding time window, use a trained energy consumption prediction model to predict the predicted energy consumption of the double-source powered vehicle in a prediction time domain based on the multiple types of running data, determine the availability information of the catenary for supplying power to the double-source powered vehicle in the prediction time domain, the battery constraint condition of the double-source powered vehicle and the pantograph constraint condition, use the predicted energy consumption, the availability information, the battery constraint condition and the pantograph constraint condition as constraint conditions of an objective function, and generate an energy configuration strategy by minimizing the objective function; the energy configuration strategy includes an energy distribution strategy of the on-board battery and the pantograph, a pantograph operation strategy and a charging and discharging strategy of the on-board battery, so that the energy supply path of the double-source powered vehicle can be switched in a timely manner according to the generated energy configuration strategy, and passive switching of the energy supply path after the energy of the on-board battery is close to depletion or the vehicle load is suddenly changed is avoided, thereby saving energy consumption. In addition, the dynamic proportioning distribution between the on-board battery and the pantograph can be coordinated through the energy configuration strategy, the phenomenon of redundant energy supply or energy waste is avoided, and the energy utilization rate is improved. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 An application environment diagram of the energy management method of the double-source powered vehicle in an embodiment;

[0049] Figure 2 A flowchart of the energy management method of the double-source powered vehicle in an embodiment;

[0050] Figure 3 A flowchart of data collection and energy consumption prediction in an embodiment;

[0051] Figure 4 A control response flowchart in an embodiment;

[0052] Figure 5 A whole flowchart of the energy management method of the double-source powered vehicle in an embodiment. DETAILED DESCRIPTION

[0053] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0054] The energy management method of the double-source powered vehicle provided by the embodiments of the present application can be applied to a double-source powered vehicle such as a train. Figure 1The application environment shown. Among them, the dual-source powered vehicle includes a control module, the control module is used for acquiring multi-class running data of the dual-source powered vehicle in a sliding time window, based on the multi-class running data, using the trained energy consumption prediction model to predict the predicted energy consumption of the dual-source powered vehicle in the prediction time domain, determining the availability information of the catenary for power supply to the dual-source powered vehicle in the prediction time domain, the battery constraint condition of the dual-source powered vehicle and the pantograph constraint condition, taking the predicted energy consumption, the availability information, the battery constraint condition and the pantograph constraint condition as the constraint condition of the objective function, and generating an energy configuration strategy by minimizing the objective function; The energy configuration strategy includes the energy distribution strategy of the on-board battery and the pantograph, the pantograph operation strategy and the on-board battery charging and discharging strategy.

[0055] In some embodiments, the control module is also used for fault detection, so as to realize fault-tolerant switching of energy management in abnormal state.

[0056] In some embodiments, the control module can be a VCU (Vehicle Control Unit, vehicle controller) or an integrated VMS (Vehicle Management System, vehicle management system).

[0057] In one embodiment, as Figure 2 shown, an energy management method of a dual-source powered vehicle is provided, and the method is applied to the control module in Figure 1 for example, including the following steps:

[0058] S1, acquiring multi-class running data of the dual-source powered vehicle in a sliding time window;

[0059] Among them, the dual-source powered vehicle is a vehicle combining catenary power supply and on-board energy storage two power sources. For example, a dual-source electrified heavy truck combining catenary power supply and on-board battery power supply, a hybrid power motor train unit combining catenary power supply and on-board battery power supply.

[0060] In some embodiments, the length of the sliding time window is fixed, and the end time of the sliding time window is the current time. For example, the sliding time window is 30 minutes, and the current time is 13:00, then the sliding time window is 12:31 to 13:00.

[0061] In some embodiments, the length of the sliding time window is fixed, and the start time of the sliding time window is updated once every preset period. For example, the preset period is 2 minutes, the current time is 13:00, and the sliding time window is 12:31 to 13:00. Then at 13:02, the start time of the sliding time window is updated to 12:33 to 13:02.

[0062] The multi-type operation data includes operation state data, environmental data and driver operation data of the dual-source power supply vehicle. The multi-type operation data can be collected by sensors and then directly obtained by the control module from the sensors. Further, different types of operation data are collected using different sensors. For example, the temperature in the environmental data is collected using a temperature sensor, and the vehicle speed in the operation state data is collected using a vehicle speed sensor.

[0063] In some embodiments, the multi-type operation data can also be obtained from the OBD (On-Board Diagnostics) through the CAN (Controller Area Network Bus) bus.

[0064] The obtained multi-type operation data is at least one time node data. For example, in a sliding time window of 12:31 to 13:00, the temperature data obtained includes the temperature at 12:31, the temperature at 12:35, the temperature at 12:41, the temperature at 12:50, and the temperature at 12:55. Further, the time node of the obtained multi-type operation data can be determined according to the sampling time node of the sensor.

[0065] S2, based on the multi-type operation data, using the trained energy consumption prediction model to predict the predicted energy consumption of the dual-source power supply vehicle in the prediction time domain;

[0066] The trained energy consumption prediction model is a model capable of predicting the energy consumption (predicted energy consumption) of the dual-source power supply vehicle in a future period of time (prediction time domain). The energy consumption prediction model includes but is not limited to LSTM (Long Short-Term Memory), Transformer model, GRU (Gated Recurrent Unit), 1D-CNN (One-Dimensional Convolutional Neural Network), XGBoost (eXtreme Gradient Boosting).

[0067] The prediction time domain refers to a future time range. For example, 1 hour in the future, 20 minutes in the future. The prediction time domain includes multiple time periods. For example, the total length of the prediction time domain is 1 hour, and the prediction time domain is divided into 60 time periods with a step of 1 minute, and each time period has a corresponding predicted energy consumption. The predicted energy consumption can be an interval value or a specific value.

[0068] The starting time of the sliding time window is updated each time, and the multi-class running data is also updated synchronously. The updated multi-class running data is used to predict the predicted energy consumption in the prediction time domain.

[0069] The predicted energy consumption refers to the equivalent electric power or electric energy required by the dual-source power supply vehicle to overcome various resistances and maintain driving while meeting the needs of vehicle accessory loads under specific transportation tasks and driving conditions. It can also be the net energy taken from the battery after the battery-side output energy is returned to the battery, and the net energy taken from the pantograph after the pantograph-side input energy is returned to the grid. Vehicle accessory loads refer to air conditioning, air compressor, electric steering, etc.

[0070] In some embodiments, after obtaining the predicted energy consumption, a prediction error analysis and uncertainty evaluation are performed based on the predicted energy consumption and the actual energy consumption. The prediction error analysis and uncertainty evaluation use a five-layer mechanism of "online error monitoring + confidence interval estimation + uncertainty decomposition + online calibration + strategy style modulation":

[0071] 1. Error monitoring: the prediction residuals in the sliding time window are subjected to root mean square error, mean absolute error, mean absolute percentage error, negative log likelihood, calibration error statistics, and drift detection, and the results of drift detection are output.

[0072] 2. Uncertainty estimation: joint use of model integration or use of MCDropout (Monte Carlo Dropout) to estimate cognitive uncertainty, use of heteroscedastic regression, or quantile regression, or shape-preserving prediction to estimate noise uncertainty.

[0073] 3. Interval or quantile output: give the prediction interval of the predicted energy consumption, so that the coverage rate of the prediction interval can be effectively controlled at a set confidence level.

[0074] 4. Online calibration and fallback: temperature scaling or order-preserving regression is used to calibrate the prediction interval of the predicted energy consumption. When the confidence is low or the error is explosive, the shape-preserving prediction is used to dynamically adjust the width of the prediction interval.

[0075] 5. Strategy coupling: variance, width of prediction interval, and coverage rate are used as risk signals to input reinforcement learning and controller to realize opportunity constraints and risk aversion.

[0076] Temperature scaling is to scale the variance of Gaussian prediction or to calibrate the probability output with temperature, so that the nominal coverage rate is approximately equal to the actual coverage rate.

[0077] Order-preserving regression is a monotonic mapping calibration for quantile or probability output, which eliminates systematic bias.

[0078] The conformal prediction is to calculate the non-parametric confidence interval width on-line according to the prediction residual distribution of the sliding time window, and guarantee the limited sample coverage rate at the set confidence level.

[0079] S3, determining the availability information of the catenary for powering the dual-source powered vehicle in the prediction time domain, the battery constraint condition of the dual-source powered vehicle, and the pantograph constraint condition;

[0080] The catenary is a facility capable of externally powering the dual-source powered vehicle. The availability information of the catenary in the prediction time domain refers to information that whether the catenary is in a normal working state in the prediction time domain and whether the catenary can provide stable and reliable power for the dual-source powered vehicle.

[0081] The battery constraint condition includes but is not limited to state of charge constraint, charging and discharging power constraint, charging and discharging rate constraint, and battery discharge times constraint. The state of charge constraint can ensure that the state of charge of the battery always remains within a safe range, protects the battery life, and prevents damage. The charging and discharging power constraint is also a power slope limiting, which can prevent the battery from overheating or performance degradation due to excessive current. The charging and discharging rate constraint can ensure that the battery works within a safe current range. The battery discharge times constraint is also a battery aging constraint, which limits the number of deep discharges to ensure that the battery is in a healthy and safe state and avoids rapid battery aging.

[0082] The pantograph constraint condition includes but is not limited to lifting constraint, pantograph dwell constraint, pantograph hysteresis constraint, lifting and lowering times and time limit of the pantograph. The lifting constraint means that the pantograph can only take power from the catenary when the pantograph is raised and the dual-source powered vehicle is located in a network section. The pantograph will be raised only when the pantograph is raised and the dual-source powered vehicle is located in a network section. The pantograph must be lowered in a network-free section, a tunnel, a turnout or a fault section. The pantograph hysteresis constraint means that when the dual-source powered vehicle enters a network section, the pantograph will not be raised immediately, but will be raised when the hysteresis condition is met. For example, the state of charge of the on-board battery is lowered below the first threshold (such as 30%), and the pantograph is raised to start taking power. The pantograph dwell constraint means that when the dual-source powered vehicle is about to leave the network section, the pantograph will not be lowered immediately, but will continue to take power until the state of charge of the battery is charged to above the second threshold (such as 80%) or it is confirmed that the dual-source powered vehicle has completely left the network section.

[0083] S4, taking the prediction energy consumption, the availability information, the battery constraint condition and the pantograph constraint condition as the constraint condition of the objective function, and generating an energy configuration strategy by minimizing the objective function; the energy configuration strategy includes an energy distribution strategy of the on-board battery and the pantograph, a pantograph operation strategy, and a charging and discharging strategy of the on-board battery.

[0084] In generating the energy source configuration strategy, the energy management problem can be constructed into a constrained mathematical optimization problem, and in each sliding time window, a global optimal solution is solved by using the predicted energy consumption to roll, that is, the energy source configuration strategy is generated in real time. The prediction curve can be used as a constraint, and the real-time energy source configuration strategy includes the energy distribution strategy of the on-board battery and the pantograph, the pantograph operation strategy, and the on-board battery charging and discharging strategy, and is optimized by a reward function. The prediction curve is the energy consumption demand sequence predicted in the future prediction time domain at a fixed step length in the default implementation.

[0085] In some embodiments, the minimization of the objective function can be performed by a PPO (Proximal Policy Optimization) reinforcement learning model, a DDPG (Deep Deterministic Policy Gradient) reinforcement learning model, a DQN (Deep Q-Network), or a double-delay deep deterministic policy gradient algorithm, so as to generate an optimal energy source configuration strategy under the current working condition.

[0086] The energy distribution strategy of the on-board battery and the pantograph includes how much power the on-board battery should provide and how much power the pantograph should take from the catenary. The pantograph operation strategy includes when the pantograph can be raised and when it can be lowered. The on-board battery charging and discharging strategy includes when the on-board battery should be charged and when it should be discharged.

[0087] The energy management method, device, computer equipment and medium of the dual-source powered vehicle described above, by obtaining multiple types of running data of the dual-source powered vehicle in a sliding time window, based on the multiple types of running data, using a trained energy consumption prediction model to predict the predicted energy consumption of the dual-source powered vehicle in a prediction time domain, determining the availability information of the catenary for powering the dual-source powered vehicle in the prediction time domain, the battery constraint condition of the dual-source powered vehicle and the pantograph constraint condition, taking the predicted energy consumption, the availability information, the battery constraint condition and the pantograph constraint condition as constraint conditions of the objective function, and generating an energy source configuration strategy by minimizing the objective function; the energy source configuration strategy includes the energy distribution strategy of the on-board battery and the pantograph, the pantograph operation strategy, and the on-board battery charging and discharging strategy, so that the energy supply path of the dual-source powered vehicle can be switched in time according to the generated energy source configuration strategy, and passive switching of the energy supply path after the energy of the on-board battery is close to depletion or the vehicle load suddenly changes can be avoided, and energy consumption can be saved. In addition, through the energy source configuration strategy, dynamic proportioning distribution between the on-board battery and the pantograph can be coordinated, and the phenomenon of redundant energy supply or energy waste can be avoided, and the energy utilization rate can be improved.

[0088] In one embodiment, step S4 comprises:

[0089] establishing a target function; the constraint conditions of the target function include predicted energy consumption, availability information, battery constraint conditions and pantograph constraint conditions;

[0090] generating an energy configuration strategy by minimizing the target function;

[0091] The expression of the target function Z is:

[0092]

[0093] wherein c grid [k] is the catenary electricity price at time step k; P grid [k] is the pantograph power at time step k; P batt [k] is the battery power at time step k; SOC[k] is the battery state of charge at time step k; SOC ref is the desired state of charge; c deg,1 and c deg,1 are the weights of battery aging cost; P batt,max is the maximum allowable charging and discharging power of the battery; λ SOC is the weight of state of charge tracking error; λ sm is the weight of power change rate; λ ρ is the weight of soft constraint penalty; ρ[k] is the soft constraint relaxation at time step k; Δt is the time step length; and N is the number of time steps.

[0094] A time step can be understood as a time period within a prediction time domain. For example, if the total length of the prediction time domain is 1 hour, and the prediction time domain is divided into 60 time periods with a step length of 1 minute, then the first time period is also the first time step.

[0095] The pantograph power P grid [k] at time step k and the battery power P batt [k] at time step k are both variables to be solved. Among them, the pantograph power P grid [k] greater than 0 indicates that the pantograph is to be raised, the pantograph power P grid [k] equal to 0 indicates that the pantograph is to be lowered, the battery power P batt [k] greater than 0 indicates that the on-board battery is to be discharged, and the battery power P batt [k] less than 0 indicates that the on-board battery is to be charged.

[0096] When minimizing the target function, the generated energy configuration strategy needs to meet the constraint conditions of the target function.

[0097] In this embodiment, the energy configuration strategy is generated by minimizing the objective function, so that multi-objective collaborative optimization can be achieved, the "single-point optimal" limitation can be broken, the comprehensive operation cost can be reduced, the energy management can be upgraded from "passive response" to "active planning", and from "experience-driven" to "data and model-driven", and finally safe, efficient, economic and long-life operation can be achieved, and sustainable optimization and autonomous learning can be achieved, which has strong adaptability.

[0098] In one embodiment, the multi-type operation data includes the speed of the dual-source power vehicle, the load, the slope of the driving route of the dual-source power vehicle, the operation information for the dual-source power vehicle, and the environmental temperature on the driving route.

[0099] The speed can be collected by a speed sensor, the load can be collected by a load sensor, the slope can be collected by a slope sensor, the environmental temperature can be collected by a temperature sensor, and the operation information can be collected by an operation information collection device. The operation information refers to various operations performed by the operator in the dual-source power vehicle, such as the operation of raising and lowering the pantograph, the battery charging operation, and the battery discharging operation. After the dual-source power vehicle starts, the various sensors start data collection work. Further, after the multi-type operation data is obtained, the edge processor deployed at the network edge (close to the data source or terminal device) can perform data aggregation and preprocessing on the multi-type operation data, and the processed data can be transmitted to the energy consumption prediction model deployed in the prediction module for prediction. The specific diagram is shown in Figure 3 The prediction module can be deployed in the vehicle-mounted edge computing unit or the cloud real-time scheduling system to support real-time modeling and reasoning.

[0100] In this embodiment, the multi-type operation data includes the speed of the dual-source power vehicle, the load, the slope of the driving route of the dual-source power vehicle, the operation information for the dual-source power vehicle, and the environmental temperature on the driving route, which can significantly improve the prediction accuracy and enhance the system robustness and anti-interference ability.

[0101] In one embodiment, step S4 further includes:

[0102] When the current time is in the prediction time domain, the motor of the dual-source power vehicle is energized according to the energy configuration strategy, and the energy utilization rate, response time, and state of charge stability of the dual-source power vehicle are obtained;

[0103] Based on the energy utilization rate, response time, and state of charge stability of the dual-source power vehicle, the constraint conditions and weights of the objective function are optimized to generate a new energy configuration strategy based on the optimized objective function.

[0104] In the current time in the prediction time domain, the energy supply of the motor of the dual-source powered vehicle according to the energy configuration strategy means that when the current time has rolled into the prediction time domain, the energy supply of the motor of the dual-source powered vehicle according to the energy configuration strategy of the current time. For example, the energy configuration strategy from 12:01 to 12:30 is obtained at 12:00, and at 12:01, the motor of the dual-source powered vehicle is energized according to the energy configuration strategy of 12:01 to drive the dual-source powered vehicle.

[0105] When the motor of the dual-source powered vehicle is energized according to the energy configuration strategy, the BMS (Battery Management System), the motor controller, and the pantograph lifting controller can work together to achieve specific energy distribution execution. Specifically, after obtaining the energy configuration strategy, the control module sends a control signal to the BMS controller or the pantograph lifting controller according to the energy configuration strategy. When the BMS controller receives the control signal, it controls the battery to provide power to the motor and sends a control signal to the motor to control the motor to drive the dual-source powered vehicle. When the pantograph lifting controller receives the control signal, it provides power to the motor through the pantograph and sends a control signal to the motor to control the motor to drive the dual-source powered vehicle. The specific control response flow chart is shown in Figure 4 The control module is in communication connection with the BMS, the pantograph lifting controller, and the motor controller. The control module supports bidirectional flow control and seamless switching between the pantograph and the battery

[0106] Since the predicted energy consumption is updated with the sliding of the sliding time window, the energy configuration strategy is also updated with the update of the predicted energy consumption, that is, although the energy configuration strategy corresponding to the prediction time domain is generated, the energy configuration strategy will not be completely executed. For example, the energy configuration strategy from 12:01 to 12:30 is obtained at 12:00, and at 12:01, the motor of the dual-source powered vehicle is energized according to the energy configuration strategy of 12:01 to drive the dual-source powered vehicle, and the energy configuration strategy from 12:02 to 12:31 is obtained at 12:01, and at 12:02, the motor of the dual-source powered vehicle is energized according to the newly generated energy configuration strategy of 12:02.

[0107] Since the current time has been in the prediction time domain, and the motor of the dual-source powered vehicle has been energized according to the energy configuration strategy, it means that the energy utilization rate, response time, and state of charge stability of the dual-source powered vehicle can be obtained.

[0108] The energy utilization rate, also referred to as system energy efficiency, is used to measure the efficiency or unit mileage energy consumption of the conversion of "net input energy on the power side" into "effective traction output". The state of charge stability is used to measure the fluctuation of the SOC (State of Charge) around the target band / reference value and the slope (charging and discharging rate) control quality. The response time is used to measure the delay and setting time from the issuance of the energy configuration strategy to the execution object and to the configuration condition planned by the energy configuration strategy.

[0109] The energy utilization rate, the response time and the state of charge stability of the dual-source power supply vehicle can be obtained through the standard bus signals and the DC bus power meter of the BMS, the inverter, the motor controller, the pantograph controller, the VCU and the energy meter of the dual-source power supply vehicle.

[0110] In the optimization of the constraint conditions and the weights of the objective function based on the energy utilization rate, the response time and the state of charge stability of the dual-source power supply vehicle, in a short period, the prediction time domain, the power slope limit, the pantograph residence constraint, the pantograph hysteresis constraint and the weight are adjusted. In a medium period, the expected state of charge, the weight of the contact network price and the battery aging cost and the fluctuation range of the parameters are adjusted. In a long period, the energy utilization rate, the response time and the state of charge stability trigger retraining, calibration and threshold reestimation. The length of the short period is less than the length of the medium period, and the length of the medium period is less than the length of the long period.

[0111] In the embodiment, the motor of the dual-source power supply vehicle is energized according to the energy configuration strategy when the current time is in the prediction time domain, and the energy utilization rate, the response time and the state of charge stability of the dual-source power supply vehicle are obtained. The constraint conditions and the weights of the objective function are optimized based on the energy utilization rate, the response time and the state of charge stability of the dual-source power supply vehicle, so as to generate a new energy configuration strategy based on the optimized objective function. In this way, the actual situation of the dual-source power supply vehicle in the running process and the response situation of the execution object can be considered, so that the optimized constraint conditions and weights are closer to the real running demand, the problem of "theoretically optimal but actually poor" is avoided, and the engineering landing value of the strategy is improved. In addition, the control response time can also be reduced.

[0112] In one embodiment, the dual-source power supply vehicle includes a display interaction unit, and the display interaction unit is configured to display the energy configuration strategy and receive an operation instruction of a user.

[0113] In the embodiment, the generated energy configuration strategy is displayed in the display interaction unit, so that the operator can directly obtain the energy configuration strategy, and thus operates the dual-source power supply vehicle according to the energy configuration strategy.

[0114] In one embodiment, step S1 further includes:

[0115] When the sampling times of each type of operation data in multiple types of operation data are inconsistent, any type of operation data is used as the reference data;

[0116] Determine the reference sampling time of the reference data, and from each type of non-reference data, determine the data collected at a time adjacent to the reference sampling time;

[0117] Based on the parameters collected at the adjacent time, calculate the data of each type of non-reference data at the reference sampling time;

[0118] Perform denoising and missing value repair on the data of each type of non-reference data at the reference sampling time and the reference data to obtain multiple types of preprocessed data;

[0119] Based on the multiple types of preprocessed data, statistically analyze the time series features, frequency domain features, and vehicle-derived features of the dual-source power supply vehicle, and perform normalization processing to predict energy consumption through the normalized time series features, frequency domain features, and vehicle-derived features.

[0120] Among them, the reference data can be any type of operation data. For example, if the vehicle speed is the reference data, then all other data except the vehicle speed are non-reference data.

[0121] The data of each type of non-reference data at the reference sampling time can be calculated by interpolation.

[0122] The denoising methods include but are not limited to exponential smoothing, Kalman filtering, and wavelet denoising.

[0123] Missing value repair is mainly for repairing the "new missing values" or "data damage" introduced during the denoising process. The repair methods include but are not limited to interpolation repair and random forest repair.

[0124] The time series features and frequency domain features refer to the mean, variance, trend, and FFT (Fast Fourier Transform) spectrum of each type of operation data. The vehicle-derived features refer to the features obtained based on the physical laws of the vehicle. For example, the instantaneous power is determined by multiplying the voltage and current of the on-vehicle battery; the slope of the driving route of the dual-source power supply vehicle is determined by the difference between the actual acceleration and the theoretical acceleration on flat road of the dual-source power supply vehicle; the regenerative braking efficiency is determined by the ratio of the energy recovered and the energy lost by the dual-source power supply vehicle.

[0125] The normalization methods include but are not limited to min-max normalization, standard deviation normalization, and logarithmic normalization.

[0126] After normalization, the normalized time series features, frequency domain features, and vehicle-derived features will be input into the energy consumption prediction model for energy consumption prediction.

[0127] In this embodiment, when the sampling times of each type of operational data are inconsistent across multiple types of operational data, a reference sampling time is determined by using any one type of operational data as the reference data. Data collected near the reference sampling time is then identified from various types of non-reference data. Based on the parameters collected near the reference sampling time, the data for each type of non-reference data at the reference sampling time is calculated. This solves the problem of asynchronous multi-source data and achieves spatiotemporal alignment. Denoising and missing data repair are performed on the data at the reference sampling time for each type of non-reference data and the reference data, improving data quality and enhancing model robustness. Based on multiple types of preprocessed data, the temporal, frequency, and vehicle-derived features of dual-source powered vehicles are statistically analyzed and normalized. Energy consumption prediction is then performed using these normalized features, transforming the original data into higher-level features with greater physical meaning and predictive value. This constructs a multi-dimensional, information-rich feature set, enabling the energy consumption prediction model to more comprehensively understand energy consumption influencing factors and significantly improve prediction accuracy.

[0128] In one embodiment, the process of determining the prediction time domain in step S2 includes:

[0129] Multiple candidate prediction time domains and filtering conditions can be preset;

[0130] Based on the historical predicted energy consumption and historical actual energy consumption of each candidate prediction time domain, the deviation, interval coverage and interval width of each candidate prediction time domain are calculated.

[0131] Candidate prediction time domains that meet the screening criteria are determined as initial prediction time domains. Based on the deviation, interval coverage, and interval width of the initial prediction time domains, the reliability curves of each initial prediction time domain are obtained.

[0132] Based on the reliability curves of each initial prediction time domain, determine the target indicators for reliability scoring among deviation, interval coverage, and interval width;

[0133] Based on the target indicators in the initial prediction time domain, the reliability score for each initial prediction time domain is obtained.

[0134] The initial prediction time domain corresponding to the maximum value in the reliability score is determined as the prediction time domain.

[0135] Each candidate prediction time domain corresponds to a screening condition, which includes a deviation threshold. Interval coverage threshold and interval width threshold These thresholds are derived from quantile thresholds obtained from offline backtesting statistics and can be calibrated online or adaptively adjusted. Since both historical predicted energy consumption and historical actual energy consumption are interval values, the deviation is the root mean square error between the historical predicted energy consumption and the historical actual energy consumption. The selection criteria for each candidate prediction time domain can be consistent or inconsistent.

[0136] Interval coverage refers to the overlap ratio between historical predicted energy consumption and historical actual energy consumption. For example, if the historical actual energy consumption is (A1, A2) and the historical predicted energy consumption is (B1, B2), then the interval coverage is Overlap / (A2-A1), and the Overlap is min(A2,B2)−max(A1,B1). Interval width is the result of subtracting the minimum value from the maximum value of historical actual energy consumption. For example, continuing the above example, the interval width is the result of subtracting A1 from A2.

[0137] The initial prediction time domain that meets the screening criteria refers to the candidate prediction time domain that meets at least one of the following conditions: deviation is less than the deviation threshold, interval coverage is less than the interval coverage threshold, and interval width is less than the interval width threshold.

[0138] The reliability curve is a two-dimensional curve with the candidate prediction time domain as the horizontal axis and the deviation, interval coverage, and interval width as the vertical axis.

[0139] Furthermore, based on the thresholds in the screening criteria, the target indicators are normalized, and based on the normalized target indicators, the reliability scores for each initial prediction time domain are obtained.

[0140] The formula for reliability scoring is: After obtaining R h Afterwards, smoothing processing is required to obtain the final reliability score for each initial prediction time domain. Here, w1(h), w2(h), w3(h), and w4(h) are all weights of the initial prediction time domain h, and S... err (h) is the deviation score calculated based on the normalized deviation, S cov (h) is the interval coverage calculated based on the normalized interval coverage, S w (h) is the interval width calculated based on the normalized interval width. Reliability scoring formula. Characterization bias, interval width, and interval coverage are all target indicators. , , , RMSE h The root mean square error (RMSE) of the initial prediction time domain h is given by rmse. best (h) is the preset optimal reference value, ε rmse (h) is the initial prediction time domain deviation threshold h, CoverGaph The initial prediction interval coverage of time domain h, W is the initial interval coverage threshold for the prediction time domain h. h The initial prediction time domain interval width, As the initial prediction interval width threshold h, DriftScore h This is the drift index value.

[0141] In some embodiments, a comprehensive reliability score can be calculated based on the deviation score, interval width score, interval coverage score, and drift reliability score. The drift reliability score is the score obtained from drift detection.

[0142] In this embodiment, by presetting multiple candidate prediction time domains and screening conditions, and based on the historical predicted energy consumption and historical actual energy consumption of each candidate prediction time domain, the deviation, interval coverage, and interval width of each candidate prediction time domain are calculated. The candidate prediction time domains that meet the screening conditions are determined as the initial prediction time domains. Based on the deviation, interval coverage, and interval width of the initial prediction time domains, the reliability curves of each initial prediction time domain are obtained. According to the reliability curves of each initial prediction time domain, the target indicators for reliability scoring in deviation, interval coverage, and interval width are determined. Based on the target indicators of the initial prediction time domains, the reliability scores of each initial prediction time domain are obtained. The initial prediction time domain corresponding to the maximum value in the reliability scores is determined as the prediction time domain. This achieves adaptive optimization of the prediction time domain, and significantly improves the accuracy, robustness, and overall energy efficiency of the energy management strategy for dual-source powered vehicles while ensuring system safety.

[0143] This application also provides an application scenario in which the above-described energy management method for a dual-source powered vehicle is applied. Specifically, the application of the energy management method for a dual-source powered vehicle in this scenario is as follows:

[0144] Sensors are used to collect various types of operational data from the dual-powered vehicle within a sliding time window. This data is then cleaned and preprocessed, and features are extracted. Based on these features, an energy consumption prediction model is used to predict energy consumption in the prediction time domain. Error analysis and uncertainty assessment are performed on the predicted energy consumption, and the results are fed back to the energy consumption prediction model to optimize it. The availability information of the overhead contact line supplying the dual-powered vehicle, the battery constraints of the dual-powered vehicle, and the pantograph constraints are determined within the prediction time domain. Using the predicted energy consumption, availability information, battery constraints, and pantograph constraints as the objective function, an energy allocation strategy is generated by minimizing the objective function. The prediction and strategy output flowchart is shown below. Figure 5 As shown.

[0145] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0146] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0147] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0148] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0149] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0150] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0151] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An energy management method for a dual-source powered vehicle, characterized in that, The method includes: S1. Acquire various types of operational data for dual-powered vehicles within a sliding time window; S2. Based on the aforementioned multi-type operational data, use the trained energy consumption prediction model to predict the predicted energy consumption of the dual-source power supply vehicle in the prediction time domain. S3. Determine the availability information of the contact network supplying power to the dual-source power supply vehicle in the predicted time domain, the battery constraints of the dual-source power supply vehicle, and the pantograph constraints. S4. Using the predicted energy consumption, the availability information, the battery constraints, and the pantograph constraints as the objective function, an energy allocation strategy is generated by minimizing the objective function; the energy allocation strategy includes an energy distribution strategy for the vehicle battery and the pantograph, a pantograph operation strategy, and a vehicle battery charging and discharging strategy.

2. The method according to claim 1, characterized in that, Step S4 includes: Establish an objective function; the constraints of the objective function include the predicted energy consumption, the availability information, the battery constraints, and the pantograph constraints. An energy allocation strategy is generated by minimizing the objective function; The expression for the objective function Z is: ； Among them, c grid [k] represents the overhead contact line electricity price at time step k; P grid [k] represents the pantograph power at time step k; P batt [k] represents the battery power at time step k; SOC[k] represents the battery state of charge at time step k; SOC ref c is the desired state of charge; deg,1 and c deg,1 As a weighting of battery aging costs; P batt,max The maximum allowable charge and discharge power of the battery; λ SOC λ is the weight of the state-of-charge tracking error; sm λ is the weight of the rate of change of power; ρ ρ[k] represents the soft constraint penalty weight; ρ[k] represents the soft constraint relaxation at time step k; Δt represents the time step size; and N represents the number of time steps.

3. The method according to claim 2, characterized in that, Step S4 is followed by: When the current moment is in the predicted time domain, the motor of the dual-source power supply vehicle is powered according to the energy configuration strategy, and the energy utilization rate, response time and charge state stability of the dual-source power supply vehicle are obtained. Based on the energy utilization rate, response time, and state of charge stability of the dual-source power supply vehicle, the constraints and weights of the objective function are optimized to generate a new energy configuration strategy based on the optimized objective function.

4. The method according to claim 1, characterized in that, The various types of operational data include the speed and load of the dual-powered vehicle, the gradient of the route traveled by the dual-powered vehicle, the operational information of the dual-powered vehicle, and the ambient temperature along the route.

5. The method according to claim 1, characterized in that, The dual-source power supply vehicle includes a display and interaction unit, which is used to display the energy configuration strategy and receive user operation commands.

6. The method according to claim 1, characterized in that, Step S1 also includes: When the sampling times of each type of operational data are inconsistent among the multiple types of operational data, any one type of operational data shall be used as the reference data. Determine the reference sampling time of the reference data, and determine the data collected at a time adjacent to the reference sampling time from various types of non-reference data; Based on the parameters collected at the nearest time, the data of each type of non-reference data at the reference sampling time are calculated; Denoising and missing data repair processes are performed on the non-reference data and the reference data at the reference sampling time to obtain multiple types of preprocessed data; Based on multiple types of preprocessed data, the time-series characteristics, frequency domain characteristics, and vehicle-derived characteristics of the dual-source power supply vehicle are statistically analyzed and normalized to predict energy consumption.

7. The method according to claim 1, characterized in that, The process of determining the prediction time domain in step S2 includes: Multiple candidate prediction time domains and filtering conditions can be preset; Based on the historical predicted energy consumption and historical actual energy consumption of each candidate prediction time domain, the deviation, interval coverage and interval width of each candidate prediction time domain are calculated. The candidate prediction time domains that meet the screening conditions are determined as the initial prediction time domains. Based on the deviation, the interval coverage and the interval width of the initial prediction time domains, the reliability curves of each initial prediction time domain are obtained. Based on the reliability curves of each initial prediction time domain, determine the target indicators for reliability scoring among the deviation, the interval coverage, and the interval width; Based on the target index of the initial prediction time domain, a reliability score is obtained for each of the initial prediction time domains; The initial prediction time domain corresponding to the maximum value in the reliability score is determined as the prediction time domain.

8. An energy management device for a dual-source powered vehicle, characterized in that, The device includes: The data acquisition module is used to acquire various types of operating data of dual-source powered vehicles within a sliding time window; The energy consumption prediction module is used to predict the predicted energy consumption of the dual-source power supply vehicle in the prediction time domain based on the multi-type operating data and the trained energy consumption prediction model. The condition determination module is used to determine the availability information of the overhead contact line supplying power to the dual-source power supply vehicle in the prediction time domain, the battery constraints of the dual-source power supply vehicle, and the pantograph constraints. The strategy acquisition module is used to generate an energy configuration strategy by minimizing the objective function, which is defined by the predicted energy consumption, the availability information, the battery constraints, and the pantograph constraints. The energy configuration strategy includes an energy allocation strategy for the vehicle battery and the pantograph, a pantograph operation strategy, and a vehicle battery charging and discharging strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Images