Oil quantity distribution balancing method and system of intelligent oil distribution tank

Abstract

The invention discloses an oil quantity distribution balancing method and system for an intelligent oil distribution tank, and relates to the technical field of oil quantity distribution regulation, and the method comprises the steps: carrying out the oil quantity demand prediction according to a vehicle operation scheme of a target vehicle, and building an oil quantity demand curve; obtaining a state characteristic sequence of each cavity; carrying out oil supply adjustment on the intelligent oil distribution tank to obtain a first oil supply adjustment space; carrying out equilibrium calculation optimization to obtain a second oil supply adjustment space; scheduling, evaluating, analyzing and optimizing the second oil supply adjusting space to obtain a third oil supply adjusting space; and performing multi-propagation joint optimization, determining an oil supply adjustment optimization result, and performing oil supply management and control. The technical problems of low oil supply management and control efficiency and poor reliability of the target vehicle caused by unbalanced oil quantity distribution and unreasonable oil supply scheduling of the intelligent oil distribution tank in the prior art are solved, and the balance of the oil quantity distribution of the intelligent oil distribution tank and the reasonability of the oil supply scheduling are realized; and the technical effect of improving the oil supply management and control efficiency and reliability of the target vehicle is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil distribution regulation, in particular to an oil distribution balancing method and system of an intelligent oil distribution tank. BACKGROUND

[0002] In a vehicle power system, the intelligent oil distribution tank is a core component for multi-cavity oil supply, and the balancing of oil distribution directly affects the engine operation stability, fuel utilization efficiency and vehicle endurance. The existing oil supply regulation of the oil distribution tank relies on preset thresholds or simple distribution of single-cavity oil quantity feedback, and it is difficult to dynamically adapt to oil quantity demand according to real-time vehicle operation schemes (such as load changes, driving conditions, endurance requirements, etc.). The imbalance phenomenon of some cavities with excessive oil quantity and other cavities with insufficient oil supply often occurs, resulting in lagging response of oil supply scheduling, serious energy waste, and even power interruption risk.

[0003] The existing technology has the technical problem of unbalanced oil distribution of the intelligent oil distribution tank, and unreasonable oil supply scheduling leads to low and poor reliability of target vehicle oil supply control efficiency. SUMMARY

[0004] The present application provides an oil distribution balancing method and system of an intelligent oil distribution tank, which is used to solve the technical problem of unbalanced oil distribution of the intelligent oil distribution tank in the prior art, and unreasonable oil supply scheduling leads to low and poor reliability of target vehicle oil supply control efficiency.

[0005] In view of the above problems, the present application provides an oil distribution balancing method and system of an intelligent oil distribution tank.

[0006] In a first aspect of the present application, an oil distribution balancing method of an intelligent oil distribution tank is provided, the method comprising: According to the vehicle operation scheme of the target vehicle, the oil quantity demand is predicted, and the oil quantity demand curve is established. The intelligent oil distribution tank of the target vehicle is sensed in real time to obtain a sequence of state characteristics of each cavity, and the intelligent oil distribution tank is provided with a plurality of oil tank cavities. Based on the sequence of state characteristics of each cavity, the intelligent oil distribution tank is adjusted according to the oil quantity demand curve to obtain a first space of oil supply adjustment. According to the oil distribution balancing threshold, the first space of oil supply adjustment is calculated and optimized to obtain a second space of oil supply adjustment. Based on the vehicle operation scheme, the second space of oil supply adjustment is evaluated and analyzed according to the oil supply scheduling evaluation model to obtain a third space of oil supply adjustment. Based on the oil distribution balancing threshold and the oil supply scheduling evaluation model, the third space of oil supply adjustment is subjected to multiple reproduction joint optimization to determine the optimization result of oil supply adjustment, and the target vehicle is supplied with oil in combination with the intelligent oil distribution tank.

[0007] In a second aspect of the present application, an oil distribution balancing system of an intelligent oil distribution tank is provided, the system comprising: The oil quantity demand curve establishing module is configured to establish an oil quantity demand curve according to oil quantity demand prediction based on a vehicle operation scheme of a target vehicle; the real-time sensing module is configured to obtain a cavity state feature sequence by performing real-time sensing on an intelligent split oil tank of the target vehicle, the intelligent split oil tank being provided with a plurality of oil tank cavities; the oil supply adjustment module is configured to perform oil supply adjustment on the intelligent split oil tank based on the cavity state feature sequence and according to the oil quantity demand curve, to obtain a first space of oil supply adjustment; the balance calculation and optimization module is configured to perform balance calculation and optimization on the first space of oil supply adjustment according to an oil supply distribution balance threshold, to obtain a second space of oil supply adjustment; the scheduling evaluation and analysis optimization module is configured to perform scheduling evaluation and analysis optimization on the second space of oil supply adjustment according to an oil supply scheduling evaluation model based on the vehicle operation scheme, to obtain a third space of oil supply adjustment; and the oil supply adjustment optimization result determination module is configured to determine an oil supply adjustment optimization result by performing multiple reproduction joint optimizations according to the third space of oil supply adjustment based on the oil supply distribution balance threshold and the oil supply scheduling evaluation model, and to perform oil supply management and control on the target vehicle in combination with the intelligent split oil tank.

[0008] The one or more technical solutions provided in the present application have at least the following technical effects or advantages: Oil quantity demand prediction is performed according to a vehicle operation scheme of a target vehicle, and an oil quantity demand curve is established; real-time sensing is performed on an intelligent split oil tank of the target vehicle, and a cavity state feature sequence is obtained; oil supply adjustment is performed on the intelligent split oil tank according to the oil quantity demand curve, and a first space of oil supply adjustment is obtained; balance calculation and optimization are performed on the first space of oil supply adjustment according to an oil supply distribution balance threshold, and a second space of oil supply adjustment is obtained; scheduling evaluation and analysis optimization are performed on the second space of oil supply adjustment according to an oil supply scheduling evaluation model, and a third space of oil supply adjustment is obtained; multiple reproduction joint optimizations are performed according to the third space of oil supply adjustment, and an oil supply adjustment optimization result is determined, and oil supply management and control are performed. The technical effect of achieving balance of oil quantity distribution and rationality of oil supply scheduling for the intelligent split oil tank is achieved, and the efficiency and reliability of oil supply management and control for the target vehicle are improved. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0010] Figure 1 The oil quantity distribution balance method flowchart of the intelligent split oil tank provided in the embodiments of the present application; Figure 2This is a schematic diagram of the oil quantity distribution and balancing system of the intelligent oil distribution tank provided in the embodiments of this application.

[0011] Figure labeling: Module 10 for establishing oil demand curve, Module 20 for real-time sensing, Module 30 for oil supply regulation, Module 40 for equilibrium calculation and optimization, Module 50 for scheduling evaluation and analysis optimization, and Module 60 for determining the optimization result of oil supply regulation. Detailed Implementation

[0012] This application provides a method and system for balancing fuel distribution in an intelligent fuel tank, which addresses the technical problems of uneven fuel distribution and unreasonable fuel supply scheduling in existing intelligent fuel tanks, resulting in low efficiency and poor reliability in fuel supply control of target vehicles.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] Example 1, as Figure 1 As shown, this application provides a method for balancing fuel distribution in an intelligent fuel tank, the method comprising: Step S100: Based on the vehicle operation plan of the target vehicle, predict the fuel demand and establish a fuel demand curve.

[0015] Specifically, the vehicle operation plan (such as driving route, driving time, load, etc.) of the target vehicle is analyzed to predict the fuel demand of the vehicle at different times, thereby obtaining a fuel demand set containing the fuel demand of each time period; then, a fuel demand coordinate system is constructed with time as the horizontal axis and fuel demand as the vertical axis, and the time and corresponding fuel demand data in the fuel demand set are substituted into the coordinate system for curve fitting, finally generating a fuel demand curve that can reflect the fuel demand change pattern of the vehicle throughout the entire operation process.

[0016] Step S200: Real-time sensing of the intelligent fuel tank of the target vehicle to obtain the state feature sequence of each cavity. The intelligent fuel tank has multiple fuel tank cavities.

[0017] Specifically, by deploying multi-dimensional monitoring devices (such as liquid level sensors, pressure sensors, etc.) on the multiple tank cavities of the intelligent oil distribution tank, the real-time state of each cavity is monitored, and monitoring data including the current oil quantity, liquid level change rate, internal pressure, etc. is collected to form a cavity monitoring set; abnormal data (such as liquid level values exceeding the normal range, pressure mutation values, etc.) in the cavity monitoring set are removed and standardized, and the processed data is sorted by time sequence or cavity number to generate a cavity state feature sequence that can fully reflect the real-time running state of each tank cavity.

[0018] Step S300: Based on the cavity state feature sequence, the oil supply adjustment of the intelligent oil distribution tank is adjusted according to the oil quantity demand curve to obtain a first space of oil supply adjustment.

[0019] Specifically, based on the cavity state feature sequence (containing real-time oil quantity, liquid level change, pressure, etc. of each tank cavity), combined with the established oil quantity demand curve (reflecting the oil quantity demand change of the vehicle at different times), an oil supply adjustment strategy for the intelligent oil distribution tank is formulated, including the oil distribution ratio between cavities, the oil supply start and stop time, the oil transfer rate, etc. All adjustment strategies that meet the matching logic of the current state of each cavity and the oil quantity demand curve are integrated to form a set containing multiple basic oil supply adjustment schemes, i.e. a first space of oil supply adjustment.

[0020] Step S400: According to the oil supply distribution balance threshold, the first space of oil supply adjustment is balanced and optimized to obtain a second space of oil supply adjustment.

[0021] Specifically, each oil supply adjustment scheme (denoted as S scheme, S is a positive integer) is extracted from the first space of oil supply adjustment, based on the cavity state feature sequence, the oil quantity change of multiple tank cavities after the implementation of the scheme is simulated, and the cavity oil quantity change curve is fitted. At multiple times, the cavity oil quantity is read to form a cavity oil quantity sequence at each time, and the standard deviation (first oil quantity standard deviation) and mean (first oil quantity mean) of the first time cavity oil quantity sequence are calculated. The ratio of the two is the first oil quantity balance degree and is included in the oil quantity balance S sequence. The difference between 1 and each oil quantity balance degree in the sequence is calculated to obtain the oil supply balance S sequence, and the mean of the sequence is taken to obtain the S oil supply distribution balance coefficient. If the coefficient is greater than or equal to the oil supply distribution balance threshold, the S scheme is added to the second space of oil supply adjustment, and the balanced and optimized calculation of the first space of oil supply adjustment is completed.

[0022] Step S500: Based on the vehicle operation scheme, the second space of oil supply adjustment is evaluated and analyzed for optimization according to the oil supply scheduling evaluation model to obtain a third space of oil supply adjustment.

[0023] Specifically, based on the vehicle operation scheme of the target vehicle, each fuel supply adjustment scheme in the second space is simulated for fuel supply process on the target vehicle, respectively, to obtain a plurality of corresponding fuel supply scheduling simulation data; the fuel supply scheduling simulation data is input into a fuel supply scheduling evaluation model (the model includes fuel supply continuity, fuel supply safety, fuel supply loss, and other fuel supply scheduling evaluation multi-indexes), and a plurality of fuel supply scheduling evaluation sequences are output; a fuel supply scheduling evaluation constraint is constructed according to the above fuel supply scheduling evaluation multi-indexes, and the plurality of fuel supply scheduling evaluation sequences are checked through the constraint to obtain a plurality of evaluation checking results; the fuel supply adjustment scheme meeting the constraint requirement is selected according to the evaluation checking result, and the schemes are integrated to form a third fuel supply adjustment space.

[0024] Step S600: Based on the fuel supply distribution balance threshold and the fuel supply scheduling evaluation model, a plurality of reproduction joint optimizations are performed according to the third fuel supply adjustment space to determine a fuel supply adjustment optimization result, and the target vehicle is controlled for fuel supply by the intelligent oil distribution tank.

[0025] Specifically, based on the fuel supply distribution balance threshold and the fuel supply scheduling evaluation model, the weight distribution is performed according to the fuel supply scheduling evaluation multi-indexes to establish a fuel supply adjustment reproduction value analysis model, the model is used to analyze and reproduce the reproduction value of each fuel supply adjustment scheme in the third fuel supply adjustment space, the fuel supply adjustment reproduction optimization first domain is selected by combining the fuel supply distribution balance threshold and the fuel supply scheduling evaluation model, the fuel supply adjustment reproduction optimization Hth domain is obtained by the predetermined reproduction optimization number (H times) in this way, the third fuel supply adjustment space and each reproduction optimization domain are integrated into a fourth fuel supply adjustment space; then the schemes in the fourth space are sorted according to the fuel supply continuity, safety and loss in a predetermined number, to obtain a first set, a second set and a third set of fuel supply adjustment optimization results, and the intersection of the three sets is analyzed to generate a fuel supply adjustment optimization result; finally, the target vehicle is controlled for fuel supply by the intelligent oil distribution tank according to the result.

[0026] In one possible implementation, step S100 further includes: Step S110: predicting the oil demand of the vehicle operation scheme to obtain an oil demand set.

[0027] Step S120: constructing an oil demand coordinate system with time as the horizontal coordinate axis and demand oil as the vertical coordinate axis, and fitting a curve of the oil demand set according to the oil demand coordinate system to generate the oil demand curve.

[0028] Specifically, the random forest regression algorithm is used to realize the following steps: first, feature variables are extracted from the vehicle operation scheme, including the slope, length, expected speed, load weight, weather conditions of the driving section, and the actual fuel consumption under the same or similar working conditions in history is taken as the label data to construct the training data set; then the random forest regression model is trained, and the overfitting risk is reduced through the ensemble learning of multiple decision trees, and the model output is the predicted fuel consumption in different time periods; finally, the prediction results of the model for each time period of the current vehicle operation scheme are sorted into the fuel demand set. This algorithm can effectively handle the interaction of multiple features and improve the accuracy of fuel demand prediction.

[0029] A two-dimensional fuel demand coordinate system is built with time parameters (such as minutes, hours) as the horizontal coordinate axis and the demand fuel (such as liters) corresponding to the time as the vertical coordinate axis; then each data point (containing time information and corresponding demand fuel) in the fuel demand set is accurately mapped into the coordinate system, and a curve fitting method (least squares fitting) is used to fit these discrete data points, obtaining a curve that can smoothly reflect the trend of fuel demand change with time, i.e. the fuel demand curve.

[0030] In one possible implementation, step S200 further includes: Step S210: Multi-dimensional monitoring of the plurality of tank cavities is performed to obtain a plurality of cavity monitoring sets.

[0031] Step S220: Data cleaning is performed on the plurality of cavity monitoring sets to generate the plurality of cavity state feature sequences.

[0032] Specifically, for the plurality of tank cavities of the intelligent oil distribution tank, corresponding monitoring equipment (such as fuel level sensors, pressure sensors, temperature sensors, etc.) is deployed to monitor each cavity in multiple dimensions, including real-time fuel level, oil level, internal oil pressure, oil temperature, and flow of the oil supply pipeline; parameter data is continuously collected at a set time interval (such as every second or every minute), and each cavity's parameter data at different monitoring times is sorted in chronological order to form a data set containing time stamps and corresponding parameter values, i.e. the plurality of cavity monitoring sets.

[0033] For the centralized raw data of each cavity monitoring, first, abnormal value detection is performed, and by setting a reasonable threshold range (such as upper and lower limits of oil quantity, normal range of pressure, etc.), jump values and values beyond the range caused by sensor failure, transmission interference, etc. are identified and excluded; for missing values that occur during data collection, linear interpolation or adjacent time value filling method is used for supplement; then the processed monitoring parameters (such as oil quantity, pressure, temperature, etc.) are standardized, and data of different orders of magnitude are converted to a unified interval; finally, the parameters of each cavity are integrated in time sequence to form a cavity state feature sequence that can clearly reflect the real-time state change of the cavity.

[0034] In one possible implementation manner, step S400 further includes: Step S410: extracting a first oil supply adjustment scheme according to the oil supply adjustment first space, S being a positive integer.

[0035] Step S420: based on the cavity state feature sequence, fitting the oil quantity change of the plurality of tank cavities according to the first S oil supply adjustment scheme to obtain an oil quantity change curve of each cavity.

[0036] Step S430: performing multi-time oil quantity equalization calculation according to the oil quantity change curve of each cavity to obtain an oil quantity equalization S sequence.

[0037] Step S440: calculating the difference between 1 and each oil quantity equalization degree in the oil quantity equalization S sequence to obtain an oil supply equalization S sequence, and performing mean value calculation on the oil supply equalization S sequence to obtain an S oil supply distribution equalization coefficient.

[0038] Step S450: if the S oil supply distribution equalization coefficient is greater than or equal to the oil supply distribution equalization threshold value, adding the first S oil supply adjustment scheme to the second oil supply adjustment space.

[0039] Specifically, from the obtained first oil supply adjustment space, each oil supply adjustment scheme contained therein is extracted in sequence one by one, and each extracted scheme is sequentially marked as a first S oil supply adjustment scheme, wherein S is a positive integer, used to distinguish different oil supply adjustment schemes, and to provide a basis for subsequent equalization calculation optimization for each scheme.

[0040] According to the state data such as the real-time oil quantity and the liquid level change rate of each tank cavity recorded in the cavity state feature sequence, and according to the adjustment rules such as the oil quantity distribution proportion, the transmission start time and the flow control parameter of each cavity in the Sth oil supply adjustment scheme, the time sequence fitting algorithm (least square method) is used to simulate and calculate the oil quantity value of each tank cavity at different time nodes, the oil quantity data at each time point obtained by calculation is taken as the fitting point, the curve fitting tool (polynomial fitting) is used to generate the curve with time as the horizontal axis and oil quantity as the vertical axis, and finally the oil quantity dynamic change trajectory of each tank cavity under the scheme, that is, the cavity oil quantity change curve, is obtained.

[0041] For the obtained cavity oil quantity change curve, a plurality of key time nodes (such as every fixed time interval or important time of oil supply scheduling) are selected, the oil quantity data of all tank cavities at each node is read to form a cavity oil quantity sequence at each time; taking the cavity oil quantity sequence at the first time as an example, the standard deviation (i.e. the first oil quantity standard deviation) and the mean value (i.e. the first oil quantity mean value) of the sequence are calculated, the ratio of the first oil quantity standard deviation to the first oil quantity mean value is determined as the first oil quantity balance degree, and the first oil quantity balance degree is added to the oil quantity balance S sequence; the cavity oil quantity sequences at other times are processed in this way, and the oil quantity balance degree corresponding to each time is calculated, and finally the oil quantity balance S sequence containing a plurality of time oil quantity balance degrees is integrated and formed.

[0042] For the obtained oil quantity balance S sequence, the difference between 1 and each oil quantity balance degree in the sequence is calculated in sequence, for example, if an oil quantity balance degree in the sequence is 0.15, then 1-0.15=0.85 is calculated, and all such differences are integrated to form the oil supply balance S sequence; then the arithmetic average of all values in the oil supply balance S sequence is calculated, and the average value obtained is the Sth oil supply distribution balance coefficient, which is used to measure the comprehensive performance of the Sth oil supply adjustment scheme in the oil quantity distribution balance.

[0043] The Sth oil supply distribution balance coefficient calculated is compared with the preset oil supply distribution balance threshold value, if the coefficient is greater than or equal to the oil supply distribution balance threshold value, it indicates that the Sth oil supply adjustment scheme has reached the set standard in the oil quantity distribution balance, and meets the basic requirement of entering the next stage of optimization, then the Sth oil supply adjustment scheme is included in the oil supply adjustment second space as one of the optional schemes for subsequent scheduling evaluation and analysis optimization.

[0044] In a possible implementation manner, the step S430 further includes: Step S431: Multi-time oil quantity reading is performed on the cavity oil quantity change curve to obtain a cavity oil quantity sequence at each time.

[0045] Step S432: Extracting a first time cavity oil quantity sequence from the cavity oil quantity sequences at each time, and calculating the standard deviation of the first time cavity oil quantity sequence to obtain a first oil quantity standard deviation.

[0046] Step S433: Calculating the mean value of the first time cavity oil quantity sequence to obtain a first oil quantity mean value.

[0047] Step S434: Taking the ratio of the first oil quantity standard deviation and the first oil quantity mean value as a first oil quantity balance degree, and adding the first oil quantity balance degree to the oil quantity balance sequence.

[0048] Specifically, for the obtained oil quantity change curve of each oil tank cavity, a plurality of time points (such as different oil supply stage time points, fixed time interval points, etc.) are selected, and the oil quantity value of each oil tank cavity at each time point is read respectively, the real-time oil quantity data of all oil tank cavities at the same time point is arranged into a group of data according to the cavity number or a predetermined order, forming a cavity oil quantity sequence corresponding to the time, and finally obtaining a plurality of time points and their respective corresponding real-time oil quantity of all cavities at each time.

[0049] From the obtained cavity oil quantity sequence at each time, the cavity oil quantity sequence corresponding to any one time is selected as the first time cavity oil quantity sequence, which contains the real-time oil quantity data of the plurality of oil tank cavities of the intelligent oil separation tank at that time; then, according to the calculation method of the standard deviation in statistics, all oil quantity data in the first time cavity oil quantity sequence are calculated, that is, the difference between each oil quantity data in the sequence and the average value of the sequence is first calculated, then the average value of the squares of these differences is calculated, and finally the square root is taken, and the result obtained is the first oil quantity standard deviation, which is used to reflect the dispersion degree of the oil quantity data of each cavity at that time.

[0050] For the extracted first time cavity oil quantity sequence (containing the real-time oil quantity data of the plurality of oil tank cavities of the intelligent oil separation tank at that time), the sum of the real-time oil quantity values of all cavities in the sequence is calculated, and then the sum is divided by the number of cavities, and the result obtained by the arithmetic mean calculation is the first oil quantity mean value, which is used to reflect the average level of the oil quantity of each oil tank cavity at that time.

[0051] The obtained first oil quantity standard deviation is divided by the obtained first oil quantity mean value, and the obtained ratio is defined as the first oil quantity balance degree, which is used to quantitatively represent the balance degree of the oil quantity distribution among the plurality of oil tank cavities at the first time; then, the calculated first oil quantity balance degree is included in the oil quantity balance sequence as a component of the sequence, providing basic data for the calculation of the subsequent oil supply distribution balance coefficient.

[0052] In one possible implementation, step S500 further comprises: Step S510: Based on the vehicle operation scheme, simulate fuel supply for the target vehicle according to each fuel supply adjustment scheme in the second fuel supply adjustment space respectively to obtain a plurality of fuel supply scheduling simulation data.

[0053] Step S520: Input the plurality of fuel supply scheduling simulation data into the fuel supply scheduling evaluation model to obtain a plurality of fuel supply scheduling evaluation sequences, wherein the fuel supply scheduling evaluation model comprises a fuel supply scheduling evaluation multi-index, and the fuel supply scheduling evaluation multi-index comprises fuel supply continuity, fuel supply safety and fuel supply loss.

[0054] Step S530: According to the fuel supply scheduling evaluation multi-index, construct a fuel supply scheduling evaluation constraint, and verify the plurality of fuel supply scheduling evaluation sequences according to the fuel supply scheduling evaluation constraint to obtain a plurality of evaluation verification results.

[0055] Step S540: According to the plurality of evaluation verification results, screen the second fuel supply adjustment space to generate a third fuel supply adjustment space.

[0056] Specifically, a simulation environment is built relying on the driving route, working condition load, and predicted duration and other parameters contained in the vehicle operation scheme; for each fuel supply adjustment scheme in the second fuel supply adjustment space, the fuel supply sequence of each tank cavity, the flow control parameter, the valve opening and closing logic and the like set by the scheme are input into the simulation environment; through a simulation software, the dynamic process of fuel supply of each cavity according to the scheme under different driving stages (such as starting, accelerating, constant speed, and decelerating) of the target vehicle is simulated, and data such as fuel supply pressure, flow stability, residual oil amount of each cavity at each time, fuel supply interruption frequency and duration, and oil transfer loss amount are recorded in real time; the complete recorded data corresponding to each scheme is integrated into a set of fuel supply scheduling simulation data, and finally a plurality of fuel supply scheduling simulation data corresponding to all schemes are obtained.

[0057] A fuel supply scheduling evaluation model is constructed, which adopts a random forest algorithm, takes fuel supply continuity, fuel supply safety and fuel supply loss as output indexes, selects fuel supply interruption frequency, longest duration of single interruption, pressure abnormal fluctuation frequency, overpressure duration, oil evaporation amount, and transmission leakage amount in the simulation fuel supply process as input features, trains the model through historical fuel supply data, so that the model can output evaluation coefficients (the coefficient range is 0-1, and the closer to 1, the better the performance) of the corresponding three indexes according to the input feature data. Subsequently, the obtained plurality of fuel supply scheduling simulation data are respectively input into the random forest model, the model analyzes and calculates the features in each simulation data, outputs a fuel supply scheduling evaluation sequence containing fuel supply continuity coefficient, fuel supply safety coefficient and fuel supply loss coefficient, and finally obtains a plurality of fuel supply scheduling evaluation sequences corresponding to each fuel supply adjustment scheme.

[0058] According to the oil supply scheduling evaluation multi-index (oil supply continuity, oil supply safety, and oil supply loss), combined with the operation requirements of the target vehicle and the performance standards of the oil supply system, specific constraint conditions are set for each index, such as ensuring that the oil supply continuity does not exceed a preset threshold, ensuring that the oil supply safety does not have the risk of overpressure or leakage, and controlling the oil supply loss within a certain proportion, thereby constructing a complete oil supply scheduling evaluation constraint; then, the index coefficients contained in each sequence in the multiple oil supply scheduling evaluation sequences are compared with the corresponding constraint conditions one by one, and it is judged whether each sequence meets all the constraint conditions. If all the constraint conditions are met, the evaluation check result is "satisfy"; if any one of the constraint conditions is not met, the evaluation check result is "not satisfy", and finally multiple evaluation check results corresponding to the multiple oil supply scheduling evaluation sequences are obtained.

[0059] According to the obtained multiple evaluation check results, all the oil supply regulation schemes in the second space are screened, and those corresponding evaluation check results are "satisfy the oil supply scheduling evaluation constraint". These schemes that meet the conditions are integrated together to form a new third space of oil supply regulation, so as to ensure that the schemes in the space can meet the preset evaluation standard in terms of oil supply scheduling.

[0060] In one possible implementation manner, step S600 further includes: Step S610: based on the oil supply distribution balance threshold and the oil supply scheduling evaluation model, multiple reproduction optimizations are performed according to the third space of oil supply regulation, and a fourth space of oil supply regulation is established.

[0061] Step S620: according to a predetermined number, the fourth space of oil supply regulation is subjected to oil supply continuity sorting optimization to establish a first set of oil supply regulation optimization.

[0062] Step S630: according to the predetermined number, the fourth space of oil supply regulation is subjected to oil supply safety sorting optimization to establish a second set of oil supply regulation optimization.

[0063] Step S640: according to the predetermined number, the fourth space of oil supply regulation is subjected to oil supply loss sorting optimization to establish a third set of oil supply regulation optimization.

[0064] Step S650: the first set of oil supply regulation optimization, the second set of oil supply regulation optimization, and the third set of oil supply regulation optimization are subjected to intersection analysis to generate the oil supply regulation optimization result.

[0065] Specifically, genetic algorithm is used for multiple reproduction optimization. First, the weight distribution of multiple indexes (oil supply continuity, oil supply safety, and oil supply loss) is used to construct the fitness function (i.e., the oil supply adjustment reproduction value analysis model) according to the oil supply scheduling evaluation, and the schemes in the third space of oil supply adjustment are taken as the initial population. The schemes with higher fitness are selected by the selection operator, the oil supply parameters (such as allocation ratio and scheduling opportunity) of the selected schemes are crossed by the crossover operator, and part of the parameters are randomly adjusted by the mutation operator to generate new schemes to form the first reproduction group of oil supply adjustment. The first reproduction group is checked for balance according to the oil supply distribution balance threshold, and the schemes meeting the standard are retained to form the first reproduction optimization group, which is then evaluated and screened by the oil supply scheduling evaluation model to obtain the first domain of oil supply adjustment reproduction optimization. The above reproduction and screening process is repeated H times to obtain the Hth domain. Finally, the initial third space of oil supply adjustment and each reproduction optimization domain are integrated to establish the fourth space of oil supply adjustment.

[0066] A predetermined number K is set, and the oil supply continuity of each oil supply adjustment scheme in the fourth space of oil supply adjustment is evaluated. During the evaluation, the total interruption time, the longest single interruption time, and the interruption frequency per unit time are extracted as three core indexes, and the weighted calculation is performed according to the weights of 50%, 30%, and 20% respectively (for example, the total interruption time of a certain scheme corresponds to 80 points, the longest single interruption time corresponds to 90 points, and the interruption frequency corresponds to 85 points, and the weighted score is 80 x 50% + 90 x 30% + 85 x 20% = 84 points). The weighted score is the comprehensive score of oil supply continuity, and the score range is 0-100 points. The higher the score, the better the continuity. Subsequently, all schemes are sorted in descending order according to the comprehensive score, and the top K schemes are selected to form the first set of oil supply adjustment optimization.

[0067] A predetermined number K is set, and the oil supply safety of each oil supply adjustment scheme in the fourth space of oil supply adjustment is evaluated. During the evaluation, the time length of pressure exceeding the safety range, the number of leakage warnings, and the number of explosion-proof device triggers are selected as three core indexes, and the quantitative calculation is performed according to the weights of 0%, 35%, and 25% respectively (for example, the time length of pressure exceeding the range of a certain scheme corresponds to 90 points, the number of leakage warnings corresponds to 85 points, and the number of explosion-proof triggers corresponds to 95 points, and the weighted score is 90 x 40% + 85 x 35% + 95 x 25% = 89.5 points). The weighted score is the comprehensive score of oil supply safety, and the score range is 0-100 points. The higher the score, the better the safety. Subsequently, all schemes are sorted in descending order according to the comprehensive score, and the top K schemes are selected to form the second set of oil supply adjustment optimization.

[0068] A predetermined number K is set, and each fuel supply adjustment scheme in the fourth space of the fuel supply adjustment is first evaluated for fuel supply loss. In the evaluation, three core indicators, namely the amount of oil evaporation loss, the amount of leakage loss during transmission, and the amount of residual oil after the end of fuel supply, are selected, and the actual values of the indicators are compared with the preset maximum acceptable loss value to convert into a single score of 0-100 points (the smaller the loss amount, the higher the score). Then, the comprehensive score is calculated according to the weights of 40% for evaporation loss, 35% for leakage loss, and 25% for residual oil (for example, a certain scheme has an evaporation loss score of 90 points, a leakage loss score of 85 points, and a residual oil score of 80 points, and the comprehensive score is 90 x 40% + 85 x 35% + 80 x 25% = 85.75 points). Then, all the schemes are ranked from high to low according to the comprehensive score (i.e., from low to high in terms of fuel supply loss), and the top K schemes are selected to form the third set of fuel supply adjustment optimization.

[0069] First, the schemes in the three sets are listed with unique identifiers (such as scheme numbers), and then the intersection of the three sets is calculated using set operation algorithms, that is, the schemes that appear in the top K in the fuel supply continuity optimization, the top K in the fuel supply safety optimization, and the top K in the fuel supply loss optimization are selected. These schemes together constitute the fuel supply adjustment optimization result, ensuring that they are at the optimal level in the three key indicators.

[0070] In one possible implementation, step S610 further includes: Step S611: According to the fuel supply scheduling evaluation multi-index, the weight distribution is allocated, and a fuel supply adjustment breeding value analysis model is established.

[0071] Step S612: According to the fuel supply distribution balance threshold, the fuel supply scheduling evaluation model, and the fuel supply adjustment breeding value analysis model, the third space of the fuel supply adjustment is bred and optimized to obtain a first domain of the fuel supply adjustment breeding optimization.

[0072] Step S613: According to the fuel supply distribution balance threshold, the fuel supply scheduling evaluation model, and the fuel supply adjustment breeding value analysis model, the first domain of the fuel supply adjustment breeding optimization is further bred and optimized to obtain an Hth domain of the fuel supply adjustment breeding optimization, where H is a predetermined breeding optimization number.

[0073] Step S614: The third space of the fuel supply adjustment, the first domain of the fuel supply adjustment breeding optimization,..., and the Hth domain of the fuel supply adjustment breeding optimization are added to the fourth space of the fuel supply adjustment.

[0074] Specifically, according to the oil supply scheduling, the multiple indexes (oil supply continuity, oil supply safety, and oil supply loss) are evaluated to assign weights, the weight of oil supply continuity is set as a, the weight of oil supply safety is set as b, and the weight of oil supply loss is set as c (a+b+c=1), and an oil supply adjustment breeding value analysis model is constructed according to the formula "oil supply adjustment breeding value coefficient = oil supply continuity weight × oil supply continuity coefficient + oil supply safety weight × oil supply safety coefficient - oil supply loss weight × oil supply loss coefficient", which can calculate the breeding value coefficient of each oil supply adjustment scheme through the index coefficients and their corresponding weights, so as to serve as a quantitative evaluation basis for the breeding value of the scheme.

[0075] The genetic algorithm is adopted, the scheme of adjusting the third space of oil supply is taken as the initial population, the fitness (i.e. the breeding value coefficient, the formula is "oil supply continuity weight × continuity coefficient + oil supply safety weight × safety coefficient - oil supply loss weight × loss coefficient") of each scheme is calculated through the oil supply adjustment breeding value analysis model, part of the schemes are selected as parents according to the fitness, the offspring schemes are generated through single-point crossover (such as exchanging the oil supply time period distribution parameters of different schemes) and random mutation (such as adjusting the cavity oil supply proportion in a small range), to form the first breeding population of oil supply adjustment; then the first breeding population is screened according to the oil distribution balance threshold, the schemes whose oil distribution balance coefficients meet the standard are retained to form the first breeding optimization population; finally, the schemes of the population are input into the oil supply scheduling evaluation model, the schemes that meet the standard are integrated into the first domain of breeding optimization of oil supply adjustment through the multi-index (continuity, safety, and loss) constraint verification.

[0076] The same genetic algorithm process as that for obtaining the first domain of breeding optimization of oil supply adjustment is adopted, the first domain of breeding optimization of oil supply adjustment is taken as the initial population, the breeding value coefficients (i.e. the fitness) of the schemes in the domain are calculated through the oil supply adjustment breeding value analysis model, and the parent schemes are selected according to the coefficients; the crossover operation (such as exchanging the cavity oil supply switching logic parameters of different schemes) and the mutation operation (such as randomly adjusting the fluctuation range parameters of the oil supply flow) are performed on the parents to generate a new scheme population; the new scheme population is screened for balance according to the oil distribution balance threshold, and the schemes whose oil distribution balance coefficients meet the standard are retained; the screened schemes are evaluated and verified through the oil supply scheduling evaluation model according to the multiple indexes (oil supply continuity, safety, and loss), and the schemes that meet the standard form the second domain of breeding optimization of oil supply adjustment; the above algorithm process is repeated until the predetermined H times of breeding optimization are completed, and finally the Hth domain of breeding optimization of oil supply adjustment is obtained.

[0077] All the fuel supply adjustment schemes in the third space and all the fuel supply adjustment schemes in the first to Hth reproduction optimization domains obtained through multiple reproduction optimization are integrated into a same set, which is a fourth space, thereby realizing the collection of effective schemes generated by reproduction optimization in each stage and providing a comprehensive scheme basis for subsequent sorting optimization.

[0078] In one possible implementation manner, step S612 further includes: Step S6121: performing reproduction value analysis on each fuel supply adjustment scheme in the third space according to the fuel supply adjustment reproduction value analysis model, to obtain a fuel supply adjustment reproduction value set.

[0079] Step S6122: performing reproduction on the third space according to the fuel supply adjustment reproduction value set, to obtain a first reproduction group of fuel supply adjustment.

[0080] Step S6123: performing balance calculation optimization on the first reproduction group of fuel supply adjustment according to the fuel supply distribution balance threshold, to obtain a first reproduction optimization group.

[0081] Step S6124: performing scheduling evaluation analysis optimization on the first reproduction optimization group according to the fuel supply scheduling evaluation model, to obtain a first domain of fuel supply adjustment reproduction optimization.

[0082] Specifically, the fuel supply adjustment reproduction value analysis model is used to perform reproduction value analysis on each fuel supply adjustment scheme included in the third space. During the analysis, the weight distribution of the fuel supply scheduling evaluation multi-index (fuel supply continuity, fuel supply safety, and fuel supply loss) set in the model is combined, the performance coefficients of each scheme on these indexes are calculated, and then the reproduction value coefficients of each scheme are obtained through the calculation formula (fuel supply continuity weight x continuity coefficient + fuel supply safety weight x safety coefficient - fuel supply loss weight x loss coefficient) set in the model. The reproduction value coefficients of all schemes are integrated to form a fuel supply adjustment reproduction value set.

[0083] First, the reproduction proportion is determined according to the reproduction value coefficients of each scheme in the fuel supply adjustment reproduction value set, for example, the coefficients are divided into three levels of high, medium and low, and the corresponding reproduction quantity proportion is 5:3:2. Then, the corresponding schemes are selected from the third space of fuel supply adjustment. The high-value coefficient scheme is generated with 5 offspring through multi-point crossover (such as exchanging cavity fuel distribution parameters at different times) and adaptive mutation (adjusting the mutation probability according to the coefficient, the higher the coefficient, the lower the mutation probability), the medium-value coefficient scheme is generated with 3 offspring through single-point crossover and fixed probability mutation, and the low-value coefficient scheme is generated with 2 offspring through simple crossover. Finally, all the generated offspring schemes are integrated to form a first reproduction group of fuel supply adjustment.

[0084] Traverse each oil supply adjustment scheme in the first breeding group, based on the sequence of state characteristics of each cavity, fit the oil volume change of multiple tank cavities under each scheme to obtain the oil volume change curve of each cavity; read the oil volume data at multiple times from these curves to form the cavity oil volume sequence at each time, calculate the standard deviation and mean value of the cavity oil volume sequence at each time, and take the ratio of the standard deviation and the mean value as the oil volume balance at that time to form the oil volume balance sequence; calculate the supply balance sequence by the difference between 1 and each oil volume balance in the sequence, and take the mean value as the oil supply distribution balance coefficient of the scheme; compare the coefficient with the oil supply distribution balance threshold, retain the scheme whose coefficient is greater than or equal to the threshold, and integrate to form the first breeding optimization group.

[0085] Based on the vehicle operation scheme, simulate the oil supply operation of each oil supply adjustment scheme in the first breeding optimization group, collect the corresponding oil supply scheduling simulation data, including the number of oil supply interruptions, the frequency of pressure abnormalities, and the oil volume loss; input these data into the oil supply scheduling evaluation model to calculate the scores of each scheme in the three indicators of oil supply continuity, oil supply safety, and oil supply loss; according to the preset evaluation constraints (such as the oil supply continuity score not less than 80 points, the oil supply safety not less than 85 points, and the loss score not less than 75 points), check the evaluation results of each scheme, retain the schemes that meet all indicators, and integrate to form the oil supply adjustment breeding optimization first domain.

[0086] In the second embodiment, based on the same inventive concept as the oil volume distribution balance method of the intelligent oil distribution tank in the foregoing embodiments, as shown in Figure 2 The present application provides an oil volume distribution balance system for an intelligent oil distribution tank, and the system and method embodiments in the present application are based on the same inventive concept. The system comprises: An oil volume demand curve establishing module 10 is configured to predict the oil volume demand based on the vehicle operation scheme of the target vehicle, and establish an oil volume demand curve.

[0087] A real-time sensing module 20 is configured to perform real-time sensing on the intelligent oil distribution tank of the target vehicle, and obtain a sequence of state characteristics of each cavity. The intelligent oil distribution tank is provided with multiple tank cavities.

[0088] An oil supply adjustment module 30 is configured to perform oil supply adjustment on the intelligent oil distribution tank based on the sequence of state characteristics of each cavity and the oil volume demand curve, and obtain an oil supply adjustment first space.

[0089] An equilibrium calculation and optimization module 40 is configured to perform equilibrium calculation and optimization on the oil supply adjustment first space according to an oil supply distribution balance threshold, and obtain an oil supply adjustment second space.

[0090] The scheduling evaluation analysis optimization module 50 is configured to perform scheduling evaluation analysis optimization on the oil supply adjustment second space based on the vehicle operation scheme according to the oil supply scheduling evaluation model, and obtain an oil supply adjustment third space.

[0091] The oil supply adjustment optimization result determination module 60 is configured to perform multiple reproduction joint optimization on the oil supply adjustment third space based on the oil supply distribution balance threshold and the oil supply scheduling evaluation model, determine an oil supply adjustment optimization result, and perform oil supply management and control on the target vehicle in combination with the intelligent oil distribution tank.

[0092] Further, the system is also used to implement the following functions: The oil supply adjustment first space is extracted, S is a positive integer; based on the cavity state feature sequence, oil quantity change fitting is performed on the plurality of tank cavities according to the oil supply adjustment S scheme, and a cavity oil quantity change curve is obtained; multi-time oil quantity balance calculation is performed according to the cavity oil quantity change curve, and an oil quantity balance S sequence is obtained; difference calculation is performed on 1 and each oil quantity balance degree in the oil quantity balance S sequence, and an oil supply balance S sequence is obtained, and a S oil supply distribution balance coefficient is obtained by mean value calculation on the oil supply balance S sequence; if the S oil supply distribution balance coefficient is greater than or equal to the oil supply distribution balance threshold, the oil supply adjustment S scheme is added to the oil supply adjustment second space.

[0093] Further, the system is also used to implement the following functions: Multi-time oil quantity reading is performed on the cavity oil quantity change curve, and a cavity oil quantity sequence at each time is obtained; a first-time cavity oil quantity sequence is extracted according to the cavity oil quantity sequence at each time, and a first oil quantity standard deviation is obtained by standard deviation calculation on the first-time cavity oil quantity sequence; a first oil quantity mean value is obtained by mean value calculation on the first-time cavity oil quantity sequence; the ratio of the first oil quantity standard deviation to the first oil quantity mean value is denoted as a first oil quantity balance degree, and the first oil quantity balance degree is added to the oil quantity balance S sequence.

[0094] Further, the system is also used to implement the following functions: Based on the vehicle operation scheme, the target vehicle is simulated fuel supply according to each fuel supply adjustment scheme in the second fuel supply adjustment space respectively, and a plurality of fuel supply scheduling simulation data is obtained; the plurality of fuel supply scheduling simulation data is input into the fuel supply scheduling evaluation model, and a plurality of fuel supply scheduling evaluation sequences is obtained, the fuel supply scheduling evaluation model includes fuel supply scheduling evaluation multi-index, the fuel supply scheduling evaluation multi-index includes fuel supply continuity, fuel supply safety and fuel supply loss; according to the fuel supply scheduling evaluation multi-index, a fuel supply scheduling evaluation constraint is constructed, and the plurality of fuel supply scheduling evaluation sequences is verified according to the fuel supply scheduling evaluation constraint, and a plurality of evaluation verification results is obtained; the fuel supply adjustment third space is screened according to the plurality of evaluation verification results, and the fuel supply adjustment third space is generated.

[0095] Further, the system is also used to implement the following functions: Based on the fuel supply distribution balance threshold and the fuel supply scheduling evaluation model, the fuel supply adjustment fourth space is established by performing multiple reproduction optimization according to the fuel supply adjustment third space; the fuel supply adjustment optimization first set is established by performing fuel supply continuity ordering optimization on the fuel supply adjustment fourth space according to the predetermined number; the fuel supply adjustment optimization second set is established by performing fuel supply safety ordering optimization on the fuel supply adjustment fourth space according to the predetermined number; the fuel supply adjustment optimization third set is established by performing fuel supply loss ordering optimization on the fuel supply adjustment fourth space according to the predetermined number; the fuel supply adjustment optimization first set, the fuel supply adjustment optimization second set and the fuel supply adjustment optimization third set are intersected and analyzed to generate the fuel supply adjustment optimization result.

[0096] Further, the system is also used to implement the following functions: The fuel supply adjustment reproduction value analysis model is established by performing weight distribution according to the fuel supply scheduling evaluation multi-index; the fuel supply adjustment fourth space is obtained by performing reproduction optimization on the fuel supply adjustment third space according to the fuel supply distribution balance threshold, the fuel supply scheduling evaluation model and the fuel supply adjustment reproduction value analysis model; the fuel supply adjustment reproduction optimization first domain is obtained by continuing to perform reproduction optimization on the fuel supply adjustment third space according to the fuel supply distribution balance threshold, the fuel supply scheduling evaluation model and the fuel supply adjustment reproduction value analysis model; the fuel supply adjustment reproduction optimization H domain is obtained, H is a predetermined reproduction optimization number; the fuel supply adjustment third space, the fuel supply adjustment reproduction optimization first domain,..., and the fuel supply adjustment reproduction optimization H domain are added to the fuel supply adjustment fourth space.

[0097] Further, the system is also used to implement the following functions: According to the oil supply adjustment breeding value analysis model, breeding values of each oil supply adjustment scheme in the oil supply adjustment third space are analyzed to obtain an oil supply adjustment breeding value set; according to the oil supply adjustment breeding value set, the oil supply adjustment first breeding population is obtained by breeding in the oil supply adjustment third space; according to the oil supply distribution balance threshold, the breeding optimization first population is obtained by balance calculation optimization of the oil supply adjustment first breeding population; and according to the oil supply scheduling evaluation model, the oil supply adjustment breeding optimization first domain is obtained by scheduling evaluation analysis optimization of the breeding optimization first population.

[0098] Further, the system is also used to implement the following functions: The oil demand set is obtained by predicting the oil demand of the vehicle operation scheme; the oil demand coordinate system is constructed by taking time as the horizontal coordinate axis and taking the demand oil as the vertical coordinate axis, and the oil demand curve is generated by curve fitting the oil demand set according to the oil demand coordinate system.

[0099] Further, the system is also used to implement the following functions: The multi-dimensional monitoring of the plurality of oil tank cavities is performed to obtain a cavity monitoring set; and the cavity state feature sequence is generated by data cleaning the cavity monitoring set.

[0100] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. Moreover, the above-mentioned specific embodiments of the present application are described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0101] The above only describes the preferred embodiments of the present application and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0102] The present application is only an exemplary description of the present application, and should be considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalents, the present application is intended to include these modifications and changes.

Claims

1. An oil distribution equalization method for an intelligent oil distribution tank, characterized by, The method comprises: According to the vehicle operation scheme of the target vehicle, an oil demand curve is established; The intelligent oil distribution tank of the target vehicle is sensed in real time to obtain a cavity state feature sequence, and the intelligent oil distribution tank is provided with a plurality of oil tank cavities; Based on the cavity state feature sequence, the intelligent oil distribution tank is adjusted according to the oil demand curve to obtain a first space of oil supply adjustment; According to the oil distribution balance threshold, the first space of oil supply adjustment is balanced and optimized to obtain a second space of oil supply adjustment; Based on the vehicle operation scheme, the second space of oil supply adjustment is evaluated and analyzed according to an oil supply scheduling evaluation model to obtain a third space of oil supply adjustment; Based on the oil distribution balance threshold and the oil supply scheduling evaluation model, the third space of oil supply adjustment is subjected to multiple reproduction joint optimization to determine an oil supply adjustment optimization result, and the target vehicle is controlled in combination with the intelligent oil distribution tank.

2. The oil amount distribution equalization method of the intelligent oil distribution tank according to claim 1, characterized by, According to the oil distribution balance threshold, the first space of oil supply adjustment is balanced and optimized to obtain a second space of oil supply adjustment, which comprises: An Sth oil supply adjustment scheme is extracted from the first space of oil supply adjustment, S being a positive integer; Based on the cavity state feature sequence, the oil volume change of the plurality of oil tank cavities is fitted according to the Sth oil supply adjustment scheme to obtain a cavity oil volume change curve; According to the cavity oil volume change curve, multi-time oil volume balance calculation is performed to obtain an Sth oil volume balance sequence; The difference between 1 and each oil volume balance degree in the Sth oil volume balance sequence is calculated to obtain an Sth oil supply balance sequence, and the Sth oil supply balance sequence is subjected to mean value calculation to obtain an Sth oil distribution balance coefficient; If the Sth oil distribution balance coefficient is greater than or equal to the oil distribution balance threshold, the Sth oil supply adjustment scheme is added to the second space of oil supply adjustment.

3. The oil amount distribution equalization method of the intelligent oil distribution tank according to claim 2, characterized by, According to the cavity oil volume change curve, multi-time oil volume balance calculation is performed to obtain an Sth oil volume balance sequence, which comprises: The multi-time oil volume of the cavity oil volume change curve is read to obtain a cavity oil volume sequence at each time; A first-time cavity oil volume sequence is extracted from the cavity oil volume sequence at each time, and standard deviation calculation is performed on the first-time cavity oil volume sequence to obtain a first oil volume standard deviation; The first-time cavity oil volume sequence is subjected to mean value calculation to obtain a first oil volume mean value; The ratio of the first oil volume standard deviation to the first oil volume mean value is denoted as a first oil volume balance degree, and the first oil volume balance degree is added to the Sth oil volume balance sequence.

4. The oil amount distribution equalization method of the intelligent oil distribution tank according to claim 1, characterized by, Based on the vehicle operation scheme, the second space of oil supply adjustment is evaluated and analyzed according to an oil supply scheduling evaluation model to obtain a third space of oil supply adjustment, which comprises: Based on the vehicle operation scheme, each oil supply adjustment scheme in the second space of oil supply adjustment is subjected to simulated oil supply of the target vehicle to obtain a plurality of oil supply scheduling simulation data; inputting the plurality of oil supply scheduling simulation data into the oil supply scheduling evaluation model to obtain a plurality of oil supply scheduling evaluation sequences, the oil supply scheduling evaluation model comprising oil supply scheduling evaluation multi-indexes, the oil supply scheduling evaluation multi-indexes comprising oil supply continuity, oil supply safety and oil supply loss; according to the oil supply scheduling evaluation multi-indexes, constructing oil supply scheduling evaluation constraints, and verifying the plurality of oil supply scheduling evaluation sequences according to the oil supply scheduling evaluation constraints to obtain a plurality of evaluation verification results; screening the oil supply regulation second space according to the plurality of evaluation verification results to generate the oil supply regulation third space.

5. The oil amount distribution equalization method of the intelligent oil distribution tank according to claim 1, characterized by, based on the oil supply distribution balance threshold and the oil supply scheduling evaluation model, performing multiple reproduction joint optimization according to the oil supply regulation third space to determine the oil supply regulation optimization result, comprising: based on the oil supply distribution balance threshold and the oil supply scheduling evaluation model, performing multiple reproduction optimization on the oil supply regulation third space to establish an oil supply regulation fourth space; performing oil supply continuity ordering optimization on the oil supply regulation fourth space according to a predetermined number to establish an oil supply regulation optimization first set; performing oil supply safety ordering optimization on the oil supply regulation fourth space according to the predetermined number to establish an oil supply regulation optimization second set; performing oil supply loss ordering optimization on the oil supply regulation fourth space according to the predetermined number to establish an oil supply regulation optimization third set; performing intersection analysis on the oil supply regulation optimization first set, the oil supply regulation optimization second set and the oil supply regulation optimization third set to generate the oil supply regulation optimization result.

6. The oil amount distribution equalization method of the intelligent oil distribution tank according to claim 5, characterized by, based on the oil supply distribution balance threshold and the oil supply scheduling evaluation model, performing multiple reproduction optimization according to the oil supply regulation third space to establish an oil supply regulation fourth space, comprising: performing weight distribution according to oil supply scheduling evaluation multi-indexes to establish an oil supply regulation reproduction value analysis model; performing reproduction optimization on the oil supply regulation third space according to the oil supply distribution balance threshold, the oil supply scheduling evaluation model and the oil supply regulation reproduction value analysis model to obtain an oil supply regulation reproduction optimization first domain; continuing to perform reproduction optimization on the oil supply regulation reproduction optimization first domain according to the oil supply distribution balance threshold, the oil supply scheduling evaluation model and the oil supply regulation reproduction value analysis model to obtain an oil supply regulation reproduction optimization Hth domain, H being a predetermined reproduction optimization number; adding the oil supply regulation third space, the oil supply regulation reproduction optimization first domain, …, the oil supply regulation reproduction optimization Hth domain to the oil supply regulation fourth space.

7. The oil amount distribution equalization method of the intelligent oil distribution tank according to claim 6, characterized by, performing reproduction optimization on the oil supply regulation third space according to the oil supply distribution balance threshold, the oil supply scheduling evaluation model and the oil supply regulation reproduction value analysis model to obtain an oil supply regulation reproduction optimization first domain, comprising: performing reproduction value analysis on each oil supply regulation scheme in the oil supply regulation third space according to the oil supply regulation reproduction value analysis model to obtain an oil supply regulation reproduction value set; performing reproduction on the oil supply regulation third space according to the oil supply regulation reproduction value set to obtain an oil supply regulation first reproduction group; According to the oil supply distribution balance threshold, the oil supply adjustment first breeding group is balanced and optimized to obtain a breeding optimization first group; According to the oil supply scheduling evaluation model, the breeding optimization first group is scheduled and evaluated to obtain the oil supply adjustment breeding optimization first domain.

8. The oil amount distribution equalization method of the intelligent oil distribution tank according to claim 1, characterized by, According to the vehicle operation scheme of the target vehicle, oil demand prediction is performed to establish an oil demand curve, including: According to the vehicle operation scheme, oil demand prediction is performed to obtain an oil demand set; Taking time as the horizontal coordinate axis and demand oil as the vertical coordinate axis, an oil demand coordinate system is constructed, and curve fitting is performed on the oil demand set according to the oil demand coordinate system to generate the oil demand curve.

9. The oil amount distribution equalization method of the intelligent oil distribution tank according to claim 1, characterized by, The intelligent oil distribution tank of the target vehicle is sensed in real time to obtain a cavity state feature sequence, including: The multiple oil tank cavities are multi-dimensionally monitored to obtain a cavity monitoring set; The cavity monitoring set is data cleaned to generate the cavity state feature sequence.

10. An oil distribution equalization system for an intelligent oil distribution tank, characterized by, The system is used to implement the oil distribution balance method of the intelligent oil distribution tank according to any one of claims 1-9, and the system includes: An oil demand curve establishment module is configured to perform oil demand prediction according to a vehicle operation scheme of a target vehicle to establish an oil demand curve; A real-time sensing module is configured to sense the intelligent oil distribution tank of the target vehicle in real time to obtain a cavity state feature sequence, and the intelligent oil distribution tank is provided with multiple oil tank cavities; An oil supply adjustment module is configured to perform oil supply adjustment on the intelligent oil distribution tank according to the oil demand curve based on the cavity state feature sequence to obtain an oil supply adjustment first space; A balanced calculation optimization module is configured to perform balanced calculation optimization on the oil supply adjustment first space according to an oil supply distribution balance threshold to obtain an oil supply adjustment second space; A scheduling evaluation analysis optimization module is configured to perform scheduling evaluation analysis optimization on the oil supply adjustment second space according to an oil supply scheduling evaluation model based on the vehicle operation scheme to obtain an oil supply adjustment third space; An oil supply adjustment optimization result determination module is configured to perform multiple breeding joint optimizations according to the oil supply adjustment third space based on the oil supply distribution balance threshold and the oil supply scheduling evaluation model to determine an oil supply adjustment optimization result, and to perform oil supply management and control on the target vehicle in combination with the intelligent oil distribution tank.

Images