A method for optimizing intelligent charging and discharging strategies for ship batteries

Abstract

The present invention discloses a method for optimizing an intelligent charging and discharging strategy for ship batteries, which specifically relates to the technical field of battery management. The method collects propulsion power data, auxiliary equipment power data, and environmental disturbance parameters generated during ship operation to construct a high-frequency time-series operating condition input sequence, adopts a multi-scale dynamic modeling algorithm to establish a load nonlinear evolution model, and generates a disturbance perception prediction sequence. The method combines the historical charge and discharge state records of the target battery with the current current, voltage, and temperature sensor data to construct a heterogeneous state feature matrix, and then evaluates the charge state and health state of the battery. According to the evaluation results of the charge state and health state of the battery, an energy scheduling constraint map is constructed to generate a multidimensional strategy candidate set. The optimal strategy path is selected from the multidimensional strategy candidate set, and the target charge and discharge control instructions are output to achieve comprehensive optimization control of dynamic perception, state drive, and strategy adaptation of the ship battery.

Description

Technical Field

[0001] The present invention relates to the technical field of battery management, and more specifically, to a method for optimizing intelligent charging and discharging strategies for ship batteries. Background Art

[0002] Existing ship battery energy management methods mostly rely on static load prediction and fixed threshold control strategies, usually assuming that navigation conditions change slowly and external disturbances are negligible.

[0003] In actual operation, propulsion load, auxiliary equipment load and environmental factors fluctuate at high frequency and nonlinearly, making it difficult for existing ship battery energy management methods to respond to power mutations in a timely manner and accurately reflect the remaining energy and reliability of the battery. They are unable to maintain accuracy in complex navigation scenarios, reducing the efficiency of the power system and accelerating battery degradation.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method for optimizing intelligent charging and discharging strategies of ship batteries to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for optimizing intelligent charging and discharging strategies for ship batteries, comprising the following steps:

[0008] S1: Collect real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data generated during ship operation to construct a high-frequency time-series operating condition input sequence;

[0009] S2: Based on the high-frequency time-series operating condition input sequence, a multi-scale dynamic modeling algorithm is used to establish a nonlinear load evolution model and output a disturbance perception prediction sequence;

[0010] S3: Obtain the historical charge and discharge status records of the target battery, and construct a heterogeneous state feature matrix based on the current, voltage, and temperature signals of the target battery during the current voyage.

[0011] S4: Evaluate the current state of charge and health status of the target battery based on the heterogeneous state feature matrix;

[0012] S5: Based on the disturbance perception prediction sequence, battery state of charge, and health status evaluation results, an energy scheduling constraint map is constructed to generate a multi-dimensional strategy candidate set.

[0013] S6: Select the optimal strategy path from the multi-dimensional strategy candidate set and output the target charge and discharge control instructions.

[0014] In a preferred embodiment, S1 is specifically:

[0015] Synchronously collect real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data generated by the ship during operation at the same sampling frequency;

[0016] Perform data alignment processing on real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data;

[0017] The real-time propulsion power data, auxiliary equipment power data and environmental disturbance parameter data after data alignment are integrated in sequence according to the same timestamp to construct a high-frequency time series operating condition input sequence.

[0018] In a preferred embodiment, S2 is specifically:

[0019] The high-frequency time series operating condition input sequence is decomposed in the time domain according to three preset time windows: short time scale, medium time scale and long time scale, to obtain three subsequences;

[0020] For each subsequence, a corresponding nonlinear dynamic sub-model is established, and the load evolution curve is fitted by regression analysis method to output the load change prediction increment at each time scale;

[0021] The prediction increments at three time scales are weighted and synthesized according to the predetermined fusion weights to obtain the disturbance-aware prediction sequence.

[0022] In a preferred embodiment, S3 is specifically:

[0023] Obtain the historical charge and discharge status records of the target battery over multiple historical navigation cycles;

[0024] Collect the real-time current signal, voltage signal and temperature signal of the target battery during the current navigation process;

[0025] The historical charge and discharge status records are jointly mapped with the real-time current signal, voltage signal, and temperature signal according to the time consistency standard to extract the operating feature vectors under multiple time segments;

[0026] All running feature vectors are combined to form a heterogeneous state feature matrix.

[0027] In a preferred embodiment, S4 is specifically:

[0028] For the operating characteristic vector in each time segment, extract the current characteristic component, voltage characteristic component and temperature characteristic component in the current navigation cycle;

[0029] The current characteristic component, voltage characteristic component and temperature characteristic component are jointly processed according to the preset characteristic calculation rules, and the battery state of charge estimation results and battery health status estimation results for the corresponding time segments are generated respectively through multi-parameter combination calculation;

[0030] The battery state of charge estimation results and battery health state estimation results under all time segments are sequentially integrated to generate the battery state of charge evaluation output sequence and battery health state evaluation output sequence of the current target battery.

[0031] In a preferred embodiment, S5 is specifically:

[0032] Based on the battery state of charge assessment output sequence and the battery health status assessment output sequence, combined with the disturbance perception prediction sequence, energy scheduling constraint nodes are defined;

[0033] In the order of time series, each energy scheduling constraint node is connected in sequence through directed edges to form an energy scheduling constraint graph;

[0034] For the energy scheduling constraint graph, by traversing the node paths, the control paths that meet the propulsion power requirements and the critical load power requirements are listed, and the charging and discharging schemes corresponding to each control path are recorded as strategy candidates;

[0035] All strategy candidates are aggregated to form a multi-dimensional strategy candidate set.

[0036] In a preferred embodiment, S6 is specifically:

[0037] For each control path in the multi-dimensional strategy candidate set, the feasibility of the path is judged based on the propulsion power demand and key load power demand in the current navigation cycle, and the control paths with power default nodes or thermal safety boundary violations in the energy scheduling constraint map are excluded;

[0038] For the remaining feasible control paths, path scoring is performed based on the preset comprehensive evaluation indicators;

[0039] Select the control path with the highest path score and determine the charge and discharge strategy corresponding to the control path as the optimal strategy path;

[0040] Generate target charge and discharge control instructions based on the optimal strategy path.

[0041] The technical effects and advantages of the intelligent charging and discharging strategy optimization method for ship batteries of the present invention are as follows:

[0042] By collecting propulsion power data, auxiliary equipment power data and environmental disturbance parameters during ship operation, the actual navigation conditions can be fully reflected; by constructing a high-frequency time-series operating condition input sequence and adopting a multi-scale dynamic modeling algorithm, accurate prediction of nonlinear load changes can be achieved; combining historical charge and discharge state records with current current, voltage and temperature sensor information, a heterogeneous state feature matrix is ​​constructed to enhance the dimension and depth of battery state assessment; the heterogeneous state feature matrix is ​​used to assess the battery state of charge and health status, improving the accuracy of judging the current available capacity and reliability of the battery; based on the disturbance perception prediction sequence and the assessment results of the battery state of charge and health status, an energy scheduling constraint map is constructed, which can flexibly adjust the strategy search range according to actual changes and enhance the adaptability of strategy generation; finally, the optimal path is selected through multi-dimensional candidate strategies to output control instructions, ensuring that the battery life is extended while meeting the power demand, thereby improving the intelligence level and operation efficiency of the ship energy management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a schematic diagram of a method for optimizing intelligent charging and discharging strategies for ship batteries according to the present invention. DETAILED DESCRIPTION

[0044] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0045] Example

[0046] Figure 1 The present invention provides a method for optimizing intelligent charging and discharging strategies for ship batteries, which includes the following steps:

[0047] S1: Collect real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data generated during ship operation to construct a high-frequency time-series operating condition input sequence;

[0048] S2: Based on the high-frequency time-series operating condition input sequence, a multi-scale dynamic modeling algorithm is used to establish a nonlinear load evolution model and output a disturbance perception prediction sequence;

[0049] S3: Obtain the historical charge and discharge status records of the target battery, and construct a heterogeneous state feature matrix based on the current, voltage, and temperature signals of the target battery during the current voyage.

[0050] S4: Evaluate the current state of charge and health status of the target battery based on the heterogeneous state feature matrix;

[0051] S5: Based on the disturbance perception prediction sequence, battery state of charge, and health status evaluation results, an energy scheduling constraint map is constructed to generate a multi-dimensional strategy candidate set.

[0052] S6: Select the optimal strategy path from the multi-dimensional strategy candidate set and output the target charge and discharge control instructions.

[0053] S1: Collect real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data generated during ship operation to construct a high-frequency time-series operating condition input sequence, including:

[0054] Synchronously collect real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data generated by the ship during operation at the same sampling frequency;

[0055] During a vessel's actual voyage, multiple types of sensors are used to synchronously collect real-time power data from the propulsion system, auxiliary equipment, and environmental disturbance parameters at the same sampling frequency. Specifically, power measurement sensors installed on the vessel's propulsion shaft collect real-time power consumption data from the propulsion system during navigation. Dedicated power measurement sensors located throughout the vessel's main auxiliary equipment, such as radar, communications equipment, and navigation instruments, synchronously collect real-time power consumption data from auxiliary equipment during navigation. Environmental parameter monitoring sensors installed on the hull or deck collect real-time data on external environmental disturbance parameters, such as wind speed, direction, wave height, current velocity, and ambient temperature. These sensors synchronously sample data at the same sampling frequency to ensure that each data point is aligned on a unified timeline.

[0056] Perform data alignment processing on real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data;

[0057] A timestamp-matching-based alignment process is used to establish a unified timestamp. The collected ship propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data are matched to the timestamps. If a sensor data point does not accurately match the corresponding timestamp, it is filled in by interpolating the data from adjacent time points. The data interpolation method used is linear interpolation, which uses the values ​​of the two closest collected data points before and after the missing data point to ensure data integrity and continuity.

[0058] The real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data after data alignment are sequentially integrated according to the same timestamp to construct a high-frequency time series operating condition input sequence;

[0059] The data corresponding to each unified timestamp constitutes a unified operating condition data point. Each operating condition data point contains the propulsion power data value, the auxiliary equipment power data value, and the values ​​of various environmental disturbance parameters. All operating condition data points are arranged in a unified time sequence, and ultimately a high-frequency time-series operating condition input sequence is constructed. For example, if the power value of the ship's propulsion system, the power value of the entire auxiliary equipment, and the corresponding environmental disturbance data such as wind speed, wind direction, and wave height are obtained at a certain moment, these data are recorded simultaneously as a complete operating condition data point at that moment; and the subsequent moment data is continuously processed according to the same method to gradually form a complete high-frequency time-series operating condition input sequence.

[0060] S2: Based on the high-frequency time-series operating condition input sequence, a multi-scale dynamic modeling algorithm is used to establish a nonlinear load evolution model and output a disturbance perception prediction sequence, including:

[0061] The high-frequency time series operating condition input sequence is decomposed in the time domain according to three preset time windows: short time scale, medium time scale and long time scale, to obtain three subsequences;

[0062] The short time scale is used to capture subtle changes in the ship's propulsion power, auxiliary equipment power, and environmental disturbance parameters under short-term mutation conditions. The medium time scale is used to analyze the periodic fluctuation characteristics during the ship's operation. The long time scale is used to reflect the ship's long-term operation trend and load variation patterns. Specifically, the high-frequency time series input sequence is gradually divided using the sliding window method. For example, the short time scale window corresponds to ship navigation data of a few seconds to a few minutes, the medium time scale window corresponds to navigation data of tens of minutes to a few hours, and the long time scale window corresponds to navigation data of several hours to dozens of hours. The data within each scale window is completely extracted to form the corresponding subsequence.

[0063] For each subsequence, a corresponding nonlinear dynamic sub-model is established, and the load evolution curve is fitted by regression analysis method to output the load change prediction increment at each time scale;

[0064] A nonlinear dynamic sub-model is established for each sub-sequence obtained from the time domain decomposition to predict load change trends. The nonlinear dynamic sub-model used is a multivariate nonlinear regression model, in which the independent variables are the ship propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data within the corresponding sub-sequence, and the dependent variable is the predicted power change increment at a future moment in the load evolution curve. For each sub-sequence, data normalization preprocessing is first performed to eliminate dimensional differences between the variables. A multivariate nonlinear regression analysis algorithm is applied to train the preprocessed sub-sequence data, and a nonlinear load evolution curve is obtained through least squares fitting. The predicted increment of the load evolution curve is calculated by predicting the power value difference between a specific future moment and the current moment based on the known historical data and the nonlinear regression model, forming a short-time scale predicted increment, a medium-time scale predicted increment, and a long-time scale predicted increment.

[0065] The prediction increments at the three time scales are weighted and synthesized according to the predetermined fusion weights to obtain the disturbance perception prediction sequence;

[0066] The load change prediction increments obtained at these three time scales are weighted and synthesized according to predetermined fusion weights to produce the disturbance-aware prediction sequence. Specifically, the preset fusion weights are determined based on statistical analysis of historical navigation data and error assessment. Short-timescale prediction increments are given a relatively higher weight because they are more sensitive to immediate changes. Medium-timescale prediction increments are given the second highest weight because they account for both transient and trend changes. Long-timescale prediction increments are given a relatively lower weight because they reflect long-term trend changes. The specific calculation method is: multiply the short-timescale prediction increment by the corresponding larger weight, the medium-timescale prediction increment by the second largest weight, and the long-timescale prediction increment by the smaller weight. These three weighted results are then summed to form the disturbance-aware prediction sequence. For example, during sudden changes in navigation conditions, short-timescale prediction increments contribute more significantly, allowing the disturbance-aware prediction sequence to respond quickly to load changes. During long, stable navigation, long-timescale prediction increments contribute more significantly, allowing the disturbance-aware prediction sequence to smoothly reflect long-term trends. It can take into account the prediction characteristics at different time scales, enhance the flexibility and adaptability of the prediction, and overall improve the accuracy and reliability of disturbance perception prediction, providing prediction basis and decision-making support for the optimization of ship battery charging and discharging strategies.

[0067] S3: Obtain the historical charge and discharge status records of the target battery, combine the current, voltage, and temperature signals of the target battery during the current voyage, and construct a heterogeneous state feature matrix, including:

[0068] Obtain the historical charge and discharge status records of the target battery over multiple historical navigation cycles;

[0069] The historical charge and discharge status record is a complete historical data set obtained through real-time monitoring of the target battery's charge and discharge processes during multiple previous voyages. A dedicated historical data recording module installed in the battery management system continuously records the target battery's charge current, discharge current, voltage level, and temperature changes of the battery cells and the entire battery pack at a uniform sampling frequency during each historical voyage cycle. The historical charge and discharge status record also includes long-term tracking parameters such as battery capacity decay curves, battery health indicators, and the number of charge and discharge cycles during the historical voyage cycle.

[0070] Collect the real-time current signal, voltage signal and temperature signal of the target battery during the current navigation process;

[0071] During the vessel's voyage, the current, voltage, and temperature signals of the target battery are collected in real time. High-precision current sensors installed within the battery management system measure the target battery's charge or discharge current during the current voyage cycle. Voltage sensors measure the current voltage of the battery pack and individual cells in real time. A temperature sensor array monitors the temperature distribution within the battery cells and the entire battery pack. The sensor's measurement accuracy and sampling frequency are consistent with historical data collection methods to ensure data comparability and consistency. This high-precision, multi-point measurement method comprehensively reflects the real-time internal battery status, effectively improving the accuracy and reliability of battery status estimation.

[0072] The historical charge and discharge status records are jointly mapped with the real-time current signal, voltage signal, and temperature signal according to the time consistency standard to extract the operating feature vectors under multiple time segments;

[0073] The historical charge and discharge status records obtained in multiple historical navigation cycles are jointly mapped with the current signals, voltage signals and temperature signals collected in real time during the current navigation process. First, the historical navigation data and the current navigation data are aligned to the same time scale according to the unified time consistency standard. A synchronous mapping method based on a unified timestamp is adopted, that is, the timestamps of each sampling point of the real-time acquisition signal in the current navigation cycle are first determined, and then the corresponding or similar historical charge and discharge data points are searched in the historical data according to the timestamps for matching. If there is no completely consistent timestamp in the historical data, the nearest neighbor interpolation method is used for data filling, that is, the two historical data points closest to the current sampling point in time are selected, and the historical values ​​corresponding to the real-time sampling points are calculated by linear interpolation to complete the time matching of historical data and real-time data.

[0074] Based on the data processed by the joint mapping, the operating feature vectors for multiple time segments are extracted. Each time segment is defined as a window of a certain length, such as a few minutes or tens of minutes. Within each time segment, characteristic parameters such as the mean value of the current signal, the maximum and minimum values ​​of the current signal, the mean and fluctuation amplitude of the voltage signal, and the mean and rising and falling trend of the temperature signal are extracted. The fluctuation amplitude of the voltage signal is the difference between the maximum and minimum voltage values ​​within the time segment; the rising and falling trend of the temperature signal is obtained by comparing the starting and ending temperature values ​​of the time segment. The extracted characteristic parameters are combined to form an operating feature vector corresponding to the time segment.

[0075] All running feature vectors are combined to form a heterogeneous state feature matrix;

[0076] All the running feature vectors obtained in different time segments are sequentially combined and arranged to form a heterogeneous state feature matrix. Each row of the heterogeneous state feature matrix represents a specific time segment, and each column represents the specific feature parameters uniformly extracted in each time segment.

[0077] S4: Evaluate the current state of charge and health status of the target battery based on the heterogeneous state feature matrix, including:

[0078] For the operating characteristic vector in each time segment, extract the current characteristic component, voltage characteristic component and temperature characteristic component in the current navigation cycle;

[0079] The current characteristic components include the current average value, the current maximum value, and the current minimum value; the voltage characteristic components include the voltage average value and the voltage fluctuation amplitude; and the temperature characteristic components include the temperature average value and the temperature change trend.

[0080] The current characteristic component, voltage characteristic component and temperature characteristic component are jointly processed according to the preset characteristic calculation rules, and the battery state of charge estimation results and battery health status estimation results for the corresponding time segments are generated respectively through multi-parameter combination calculation;

[0081] The characteristic calculation rules are determined through the analysis, summarization, and verification of extensive historical data, using mathematical relationships that comprehensively consider the internal physical and chemical characteristics of the battery. Specifically, the battery SOC estimation method is as follows: First, the average values ​​of the current characteristic components and the voltage characteristic components are jointly processed to estimate the initial SOC value of the current battery using the voltage integration method. This initial SOC value is then corrected using the temperature characteristic component. Specifically, when the average battery temperature is above a predetermined reference temperature, the initial SOC value is reduced to compensate; when the average temperature is below the reference temperature, the initial SOC value is appropriately increased to ensure the accuracy of the SOC estimation. The battery SOH estimation method uses the fluctuation amplitude of the voltage characteristic component, the maximum value of the current characteristic component, and the changing trend of the temperature characteristic component to generate a preliminary SOH estimate through a nonlinear combination calculation method. This preliminary SOH estimate is then dynamically corrected based on the health degradation characteristic curve of the battery over its historical voyage cycle to obtain an accurate SOH estimate.

[0082] The dynamic correction is specifically as follows: compare the preliminary health status estimation result with the theoretical health status value corresponding to the health degradation characteristic curve of the battery during the historical navigation cycle. If the preliminary health status estimation result is significantly higher than the theoretical health status value, it means that the preliminary health status estimation result needs to be lowered; if the preliminary health status estimation result is significantly lower than the theoretical health status value, it means that the preliminary health status estimation result needs to be moderately increased.

[0083] Based on the difference between the theoretical health status value and the preliminary health status estimate, a correction coefficient is calculated; the preliminary health status estimate is then multiplied and adjusted using the coefficient. For example, if the preliminary health status estimate is significantly higher than the theoretical health status value, the preliminary health status estimate is multiplied by a correction coefficient less than one; if the preliminary health status estimate is significantly lower than the theoretical health status value, the preliminary health status estimate is multiplied by a correction coefficient greater than one to obtain the final health status estimate.

[0084] Multi-parameter combined calculation can comprehensively evaluate the real-time status and long-term health status of the battery, significantly improving the comprehensiveness and reliability of status assessment.

[0085] Sequentially integrate the battery state of charge estimation results and battery health status estimation results under all time segments to generate the battery state of charge evaluation output sequence and battery health status evaluation output sequence of the current target battery;

[0086] The battery state-of-charge (SOC) estimates calculated for each time segment are arranged sequentially in their original chronological order to form a battery SOC evaluation output sequence. Similarly, the battery state-of-health (SOH) estimates calculated for each time segment are arranged sequentially in their original chronological order to form a battery health evaluation output sequence. This sequence integration clearly demonstrates the real-time and long-term trends of battery state over the course of the voyage, facilitating effective decision-making based on real-time and accurate data during battery charge and discharge strategy optimization.

[0087] S5: Based on the disturbance perception prediction sequence, battery state of charge, and health status evaluation results, an energy scheduling constraint map is constructed to generate a multi-dimensional strategy candidate set, including:

[0088] Based on the battery state of charge assessment output sequence and the battery health status assessment output sequence, combined with the disturbance perception prediction sequence, energy scheduling constraint nodes are defined;

[0089] Each specific time point is regarded as an energy scheduling constraint node. Each energy scheduling constraint node contains three types of constraints: battery state of charge constraints, battery health state constraints, and disturbance-aware prediction constraints. The battery state of charge constraints are defined as follows: the battery's allowable charge and discharge current range is determined based on the value of the battery state of charge evaluation output sequence at the time the energy scheduling constraint node is located; the battery health state constraints are defined as follows: the battery's maximum allowable charge and discharge power limit is determined based on the value of the battery health state evaluation output sequence at the corresponding time of the energy scheduling constraint node; the disturbance-aware prediction constraints are defined as follows: the power response conditions that must be met are determined based on the load change trend and amplitude predicted at the corresponding time in the disturbance-aware prediction sequence. The three types of constraints comprehensively reflect the battery's real-time status, long-term health, and load change requirements, ensuring the comprehensiveness and applicability of the energy scheduling node definition.

[0090] In the order of time series, each energy scheduling constraint node is connected in sequence through directed edges to form an energy scheduling constraint graph;

[0091] Each node is connected only one-way to the next node, forming a graph structure arranged in chronological order. Each directed edge represents the path of energy transfer from the current node to the next. The constraints represented by each node in the graph determine the transfer method and range of the node to the next node.

[0092] For the energy scheduling constraint graph, by traversing the node paths, the control paths that meet the propulsion power requirements and the critical load power requirements are listed, and the charging and discharging schemes corresponding to each control path are recorded as strategy candidates;

[0093] All node paths in the energy scheduling constraint graph are traversed using a depth-first search or breadth-first search method. The feasibility judgment criteria for each path are defined as follows: among all nodes on the path, the charge and discharge power range allowed by the battery must meet the propulsion power demand and the critical load power demand at the corresponding moment, and must not exceed the upper limit of the battery's allowable power or violate the safety boundary of the state of charge. For example, if there is a node in a certain path that predicts a sharp increase in load power, if the current battery health status does not allow this power level to be provided, the path is abandoned and the next path is traversed. Ultimately, all the charge and discharge control schemes corresponding to the paths that meet the above judgment criteria are retained and become valid strategy candidates.

[0094] Aggregate all strategy candidates to form a multi-dimensional strategy candidate set;

[0095] Control information for each valid control path, including the charge and discharge power level, timing, duration, and corresponding energy transfer direction, is recorded in a unified data structure. For example, a specific strategy candidate might include the current intensity at which charging begins at a certain moment, the power level and duration of discharge at the next moment, and how the battery adjusts power output over the next few moments to smoothly meet load demand. This multi-dimensional strategy candidate set provides a comprehensive set of solutions that comprehensively reflect multiple possible scenarios, enabling precise selection of the optimal strategy.

[0096] S6: Select the optimal strategy path from the multi-dimensional strategy candidate set and output the target charge and discharge control instructions, including:

[0097] For each control path in the multi-dimensional strategy candidate set, the feasibility of the path is judged based on the propulsion power demand and key load power demand in the current navigation cycle, and the control paths with power default nodes or thermal safety boundary violations in the energy scheduling constraint map are excluded;

[0098] For each control path, a node-by-node review and verification is conducted based on the ship's propulsion power requirements and critical load power requirements during the current navigation cycle. The criteria for judging path feasibility include: for each node in the path, checking whether the charge and discharge power provided by the battery at this node exceeds the node's pre-defined allowable power limit. If any node exceeds the allowable power limit, it is defined as a power default node; based on the battery temperature state parameters corresponding to the node, checking whether the battery may break through the predetermined battery thermal safety boundary conditions under the action of the node's charge and discharge power. If any node may cause the battery temperature to exceed the safe upper limit temperature value or fall below the allowable lower limit temperature value, it is defined as a thermal safety boundary violation node. Paths with power default nodes or thermal safety boundary violation nodes are excluded.

[0099] For the remaining feasible control paths, path scoring is performed based on the preset comprehensive evaluation indicators;

[0100] Comprehensive evaluation indicators include battery life loss, battery energy efficiency, load response sensitivity, and charge-discharge control stability. The specific calculation method is as follows: The battery life loss is determined by estimating the degree of cycle life loss caused by power fluctuations during path execution. Paths with less loss receive higher scores. The battery energy efficiency is determined by calculating the effective energy utilization rate during path execution. Paths with less energy loss receive higher scores. The load response sensitivity is determined by the timeliness and accuracy of the path's predicted response to disturbances. Paths with more sensitive and accurate responses receive higher scores. The charge-discharge control stability is determined by the smoothness of the charge and discharge power changes between adjacent nodes on the path. Paths with smoother changes receive higher scores. Each of these four evaluation indicators is assigned a score based on the path's specific performance. The path score is then determined by weighted summing the four scores. The weighting is determined through a combination of historical data analysis and expert experience to ensure comprehensive and accurate scoring.

[0101] The method for determining the battery life loss index is as follows:

[0102] The battery life loss index is determined by analyzing the cycle life loss caused by the charge and discharge power fluctuations of the target battery during the implementation of a certain control path:

[0103] The battery life loss calculation benchmark is determined based on the battery cycle life characteristic curve provided by the battery manufacturer or established through long-term historical test data. The battery cycle life characteristic curve describes the clear mathematical relationship between the degree of battery capacity attenuation and the charge and discharge depth and charge and discharge current intensity.

[0104] According to the charge and discharge power changes at each node at each moment in each specific control path, the corresponding charge and discharge depth and charge and discharge current intensity are determined respectively, and the specific capacity loss of the battery life caused by a single charge and discharge action at each node is calculated based on the battery cycle life characteristic curve.

[0105] The capacity depreciation caused by all nodes on the path is accumulated and summed up in sequence to obtain the total battery life loss degree under the control path.

[0106] To unify the scoring criteria, the life loss degree of all paths is processed using a unified normalization method. That is, the total battery life loss of each path is compared with the maximum value of the total loss of all paths, and the life loss degree score of the path is calculated based on this. The smaller the life loss degree of the path, the higher its score.

[0107] The battery energy utilization efficiency index is the ratio between the effective energy actually output by the battery and the total energy released by the battery during the implementation of the control path:

[0108] Determine the total amount of energy delivered by the battery during all discharge phases during the path implementation.

[0109] Based on the effective power demand of the actual load (propulsion system and key equipment) during the implementation of the route, the total amount of energy actually effectively utilized by the load is calculated.

[0110] The energy utilization efficiency is obtained by dividing the total amount of energy effectively utilized by the actual load by the total amount of energy output by the battery.

[0111] The energy efficiency index score is determined in a normalized manner, that is, the energy efficiency values ​​calculated for all paths are compared; paths with higher efficiency have higher scores, while paths with lower efficiency have lower scores.

[0112] The load response sensitivity index indicates the matching accuracy and response timeliness between the control action of the path and the load change demand in the disturbance perception prediction sequence:

[0113] The difference between the power demand given by the disturbance-aware prediction sequence and the actual power provided by the control path is explicitly calculated for each node. The smaller the difference, the more accurate the response.

[0114] Determine the timeliness of each node's response, that is, the delay between the power adjustment action provided in the path and the moment when the disturbance prediction changes. The shorter the delay, the more timely the response.

[0115] The power demand difference and delay time of each node are comprehensively weighted and calculated with appropriate weights to obtain the response sensitivity score of each node. The weight is determined by historical statistical analysis. That is, the more drastic the load changes in history, the higher the weight of response timeliness, and the more stable the load changes, the more significant the weight of accuracy.

[0116] The arithmetic mean of the response sensitivity scores of all nodes on the path is calculated to obtain the overall load response sensitivity index score of the path. A higher score indicates that the path responds more sensitively and accurately to load changes.

[0117] The charge and discharge control stability index indicates the degree of stability of the charge and discharge power changes between adjacent nodes on the path:

[0118] The absolute value of the difference between the charge and discharge power values ​​is explicitly calculated for each pair of adjacent nodes on the path. The smaller the value, the more stable the power change of the adjacent nodes.

[0119] The absolute values ​​of the power change differences of all adjacent nodes on the path are accumulated to obtain the total power change amplitude.

[0120] The total power variation of all paths is processed in a normalized manner. That is, the total power variation of each path is compared with the value with the largest variation among all paths. The path with a smaller variation has a higher score after normalization.

[0121] The normalized score is used as the final score of the path charge and discharge control stability index.

[0122] Select the control path with the highest path score and determine the charge and discharge strategy corresponding to the control path as the optimal strategy path;

[0123] The scoring results of all feasible paths are ranked from highest to lowest, and the path with the highest score is selected as the optimal strategic path. The reason for selecting the highest-scoring path is that it achieves the best balance among various aspects such as battery life preservation, efficient energy utilization, load response accuracy, and charge and discharge stability, and can best meet the actual operational needs of the ship and the battery status optimization goals.

[0124] Generate target charge and discharge control instructions based on the optimal strategy path;

[0125] For each specific time point on the optimal strategy path, parameters such as the corresponding battery charging or discharging power value, specific start and stop times, charge and discharge duration, and auxiliary control strategies (such as cooling system activation and charging current ramp-up) are set. Targeted charge and discharge control instructions can accurately and comprehensively guide the real-time charging and discharging actions of the ship's batteries during actual operation.

[0126] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0127] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0128] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0129] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0131] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0132] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0133] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0134] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0135] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for optimizing intelligent charging and discharging strategies for ship batteries, characterized in that: The steps include: S1: Collect real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data generated during ship operation to construct a high-frequency time-series operating condition input sequence; S2: Based on the high-frequency time-series operating condition input sequence, a multi-scale dynamic modeling algorithm is used to establish a nonlinear load evolution model and output a disturbance perception prediction sequence; S3: Obtain the historical charge and discharge status records of the target battery, and construct a heterogeneous state feature matrix based on the current, voltage, and temperature signals of the target battery during the current voyage. Obtain the historical charge and discharge status records of the target battery over multiple historical navigation cycles; Collect the real-time current signal, voltage signal and temperature signal of the target battery during the current navigation process; The historical charge and discharge status records are jointly mapped with the real-time current signal, voltage signal, and temperature signal according to the time consistency standard to extract the operating feature vectors under multiple time segments; All running feature vectors are combined to form a heterogeneous state feature matrix; S4: Evaluate the current state of charge and health status of the target battery based on the heterogeneous state feature matrix; For the operating characteristic vector in each time segment, extract the current characteristic component, voltage characteristic component and temperature characteristic component in the current navigation cycle; The current characteristic component, voltage characteristic component and temperature characteristic component are jointly processed according to the preset characteristic calculation rules, and the battery state of charge estimation results and battery health status estimation results for the corresponding time segments are generated respectively through multi-parameter combination calculation; Sequentially integrate the battery state of charge estimation results and battery health status estimation results under all time segments to generate the battery state of charge evaluation output sequence and battery health status evaluation output sequence of the current target battery; S5: Based on the disturbance perception prediction sequence, battery state of charge, and health status evaluation results, an energy scheduling constraint map is constructed to generate a multi-dimensional strategy candidate set. S6: Select the optimal strategy path from the multi-dimensional strategy candidate set and output the target charge and discharge control instructions.

2. A method for optimizing intelligent charging and discharging strategies for ship batteries according to claim 1, characterized in that: S1, specifically: Synchronously collect real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data generated by the ship during operation at the same sampling frequency; Perform data alignment processing on real-time propulsion power data, auxiliary equipment power data, and environmental disturbance parameter data; The real-time propulsion power data, auxiliary equipment power data and environmental disturbance parameter data after data alignment are integrated in sequence according to the same timestamp to construct a high-frequency time series operating condition input sequence.

3. A method for optimizing intelligent charging and discharging strategies for ship batteries according to claim 2, characterized in that: S2, specifically: The high-frequency time series operating condition input sequence is decomposed in the time domain according to three preset time windows: short time scale, medium time scale and long time scale, to obtain three subsequences; For each subsequence, a corresponding nonlinear dynamic sub-model is established, and the load evolution curve is fitted by regression analysis method to output the load change prediction increment at each time scale; The prediction increments at three time scales are weighted and synthesized according to the predetermined fusion weights to obtain the disturbance-aware prediction sequence.

4. A method for optimizing intelligent charging and discharging strategies for ship batteries according to claim 3, characterized in that: S5, specifically: Based on the battery state of charge assessment output sequence and the battery health status assessment output sequence, combined with the disturbance perception prediction sequence, energy scheduling constraint nodes are defined; In the order of time series, each energy scheduling constraint node is connected in sequence through directed edges to form an energy scheduling constraint graph; For the energy scheduling constraint graph, by traversing the node paths, the control paths that meet the propulsion power requirements and the critical load power requirements are listed, and the charging and discharging schemes corresponding to each control path are recorded as strategy candidates; All strategy candidates are aggregated to form a multi-dimensional strategy candidate set.

5. A method for optimizing intelligent charging and discharging strategies for ship batteries according to claim 4, characterized in that: S6, specifically: For each control path in the multi-dimensional strategy candidate set, the feasibility of the path is judged based on the propulsion power demand and key load power demand in the current navigation cycle, and the control paths with power default nodes or thermal safety boundary violations in the energy scheduling constraint map are excluded; For the remaining feasible control paths, path scoring is performed based on the preset comprehensive evaluation indicators; Select the control path with the highest path score and determine the charge and discharge strategy corresponding to the control path as the optimal strategy path; Generate target charge and discharge control instructions based on the optimal strategy path.

Images