Potential energy recovery system and method based on lithium iron phosphate energy storage battery

Abstract

The invention discloses a potential energy recovery system and method based on a lithium iron phosphate energy storage battery, particularly relates to the technical field of ship energy recovery, and aims to solve the problems that potential energy frequently generated by hoisting and traction equipment in ship operation is difficult to effectively manage, and the potential energy is difficult to recycle in an existing scheme. The invention relates to a brake energy recovery system, which solves the problems of energy waste and safety risk caused by insufficient system reliability and energy management efficiency in a severe marine environment, and comprises a brake energy recovery unit and an energy storage system unit, and the brake energy recovery unit comprises a three-phase alternating current motor, a motor variable frequency driver, a brake fuse and a power supply busbar. The energy storage system unit comprises an energy storage fuse, a charging isolation switch, a battery management system and a lithium iron phosphate energy storage battery; by dynamically adjusting the charging current and optimizing energy management, the charging efficiency and the system response capability in a low-temperature environment are improved, and the stability and the safety in ship operation are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of ship energy recovery, and more specifically, to a potential energy recovery system and method based on a lithium iron phosphate energy storage battery. Background Art

[0002] In the field of ships, potential energy management is particularly important, especially in systems such as lifting equipment (such as cranes) and traction equipment (such as winches and anchor winches). These equipment will generate a large amount of potential energy during operation, especially in cargo loading and unloading, rescue and other operations. The descent and load release of the equipment will release a large amount of potential energy. How to effectively manage and utilize this energy is directly related to the overall efficiency, reliability and safety of the ship system. At present, there are two main potential energy treatment solutions commonly used in the field of ships: local consumption type and feedback to the main grid type. The local consumption type converts excess potential energy into heat energy and consumes it through the braking unit. Although the structure is simple, this method cannot recycle and reuse potential energy, resulting in energy waste and increasing the operating cost of the ship. In addition, the marine environment is complex and changeable, and key components in the braking system, such as braking resistors, braking inverters and cooling systems, are prone to failure, reducing the reliability of the system. On the other hand, the feedback to the main grid type feeds back excess electrical energy to the ship's main grid through the inverter system, which improves the utilization efficiency of potential energy. However, the instability and volatility of the ship's main power grid make this solution subject to the risk of power shock, causing power grid failure and even paralysis of the main power grid, seriously affecting the safe navigation of the ship and the normal operation of the equipment. In addition, the operating environment of ship equipment is extremely special. It is exposed to harsh conditions such as salt spray corrosion, high humidity and high vibration for a long time, which requires high reliability and maintainability of the potential energy processing system. The adaptability and reliability of existing technologies in these environments need to be improved to ensure that ship equipment can operate safely and reliably in various sea conditions. Especially in deep-sea operating environments, the lifting equipment and traction equipment on the ship need to be operated frequently, generating a large amount of potential energy. This potential energy should be recovered and stored in lithium iron phosphate energy storage batteries. The low temperature environment of the deep-sea environment will reduce the electrochemical reaction rate of lithium iron phosphate batteries, resulting in low charging efficiency and prolonged charging time. It will also increase the internal resistance of the battery, thereby increasing energy loss during charging. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, the present invention provides a potential energy recovery system and method based on lithium iron phosphate energy storage battery, which improves the charging efficiency and system responsiveness in low temperature environment by dynamically adjusting the charging current and optimizing energy management, thereby ensuring the stability and safety of ship operations.

[0004] When ships are operating in the deep sea, they often face harsh conditions such as extreme temperatures, salt spray corrosion, high humidity and high vibration. These environmental factors put forward requirements for the stability and reliability of the potential energy recovery system. Under low temperature conditions, the electrochemical reaction rate of lithium iron phosphate batteries decreases significantly, resulting in reduced charging efficiency and prolonged charging time. In addition, low temperature will increase the internal resistance of the battery, further leading to energy loss. When the equipment is operating at sea for a long time, it will be corroded by seawater salt spray, causing short circuits and failures of electrical equipment. The high-vibration offshore operating environment will also affect the stability of battery connections, resulting in poor contact or battery damage. For high-frequency cargo loading and unloading, the lifting equipment and traction equipment need to be operated frequently, generating a large amount of potential energy. These devices frequently convert potential energy into electrical energy during the process of load reduction and release, requiring multiple Energy recovery and charging operations are performed repeatedly, so the system's responsiveness and energy management capabilities are high. The equipment operation is random, and the recovered energy has a large volatility, which will lead to instability in the battery charging current and voltage. The ship's main power grid will be affected by fluctuations during operation. This instability poses a challenge to the potential energy processing solution that feeds back to the main grid. When the potential energy is recovered to the main grid, it may cause power shock and cause grid instability. In severe cases, it may even cause the grid to collapse, affecting the ship's navigation safety and equipment operation. The traditional main grid feedback solution relies on the stability of the grid. Once there is a problem with the grid, the efficiency and safety of the potential energy recovery system will be greatly reduced. The ship's operating environment makes equipment maintenance inconvenient. Therefore, the potential energy recovery system must have automatic monitoring and fault prediction capabilities to reduce the need for manual maintenance.

[0005] In order to cope with the above situation and achieve the above purpose, the present invention provides the following technical solutions:

[0006] A potential energy recovery system based on a lithium iron phosphate energy storage battery comprises a braking energy recovery unit and an energy storage system unit. The braking energy recovery unit comprises a three-phase AC motor, a motor frequency conversion drive, a braking fuse and a power supply busbar. The energy storage system unit comprises an energy storage fuse, a charging isolation switch, a battery management system and a lithium iron phosphate energy storage battery. The three-phase AC motor is connected to the motor frequency conversion drive. The motor frequency conversion drive is connected to the power supply busbar through the braking fuse and is connected to the battery management system through the charging isolation switch. The battery management system controls the current to enter the lithium iron phosphate energy storage battery according to a temperature compensation charging current model, a charging depth optimization model, a dynamic energy distribution model and a real-time fault prediction model, stores the electric energy generated by potential energy recovery, and monitors the battery status and charging process in real time. The temperature compensation charging current model is based on the current ambient temperature, the nominal operating temperature and the charging efficiency parameters monitored in real time. The charging current is adjusted according to the charging efficiency ratio at the current temperature and the degree to which the temperature deviates from the optimal temperature. In the temperature compensation charging current model, the charging current adjustment formula is:

[0007]

[0008] Where: T is the real-time monitored ambient temperature, I charge (T) is the charging current of the battery at temperature T, T opt is the optimal battery temperature, I nominal is the ideal charging current at the optimal battery temperature, η charge (T) is the charging efficiency of the battery at temperature T, η max is the highest charging efficiency of the battery under optimal conditions, γ is the charging efficiency sensitivity adjustment coefficient, which is set according to demand, and α is the temperature sensitivity coefficient, which is obtained through experimental data.

[0009] As a further solution of the present invention, in the temperature compensation charging current model of the battery management system, the dynamic response of the temperature change rate to the charging current is optimized exponentially according to the current temperature change rate. The dynamic response formula of the battery charging current is:

[0010]

[0011] Where: I charge (T, ΔT) is the dynamic response value of the battery charging current at temperature T, is the temperature change per unit time.

[0012] As a further solution of the present invention, in the battery management system, the current temperature deviation is obtained by an exponential function to correct the initial value of the charging efficiency sensitivity adjustment coefficient in the charging current adjustment formula. The charging efficiency sensitivity adjustment coefficient is obtained by the formula:

[0013]

[0014] Wherein: γ0 is the initial charging efficiency sensitivity adjustment coefficient, which is obtained through historical data, δ is the adjustment coefficient, and n is the nonlinear index. δ and n are determined through experiments.

[0015] As a further solution of the present invention, in the battery management system, the acquisition method of the temperature sensitivity coefficient is determined by judging whether the temperature deviation exceeds the set threshold. If the temperature deviation is within the set threshold, the initial temperature sensitivity coefficient is corrected using a linear adjustment method. The correction formula of the temperature sensitivity coefficient is:

[0016]

[0017] Where: α0 is the initial temperature sensitivity coefficient, obtained through historical data, λ is the linear adjustment coefficient, obtained through experimental data analysis;

[0018] When the temperature deviation exceeds the set threshold, the nonlinear adjustment method is used to correct the initial temperature sensitivity coefficient. The correction formula of the temperature sensitivity coefficient is:

[0019]

[0020] Where: is the nonlinear adjustment coefficient, which is obtained through experimental data analysis; m is the nonlinear adjustment index, which is obtained through experimental data analysis; ΔT is the set temperature deviation threshold between the current temperature and the optimal temperature, which is set according to actual needs.

[0021] As a further solution of the present invention, in the battery management system, the charging depth optimization model optimizes the charging depth according to the current battery state and ambient temperature. In the charging depth optimization model, the charging depth formula is:

[0022]

[0023] Where: D charge is the depth of charge, between 0 and 1, D max is the maximum allowable charging depth, t is the current moment, V battery (t) is the current battery voltage, V max is the maximum allowable voltage of the battery, and β is the temperature adjustment coefficient, which is obtained through experiments.

[0024] As a further solution of the present invention, in the battery management system, the dynamic energy allocation model dynamically allocates energy according to the task priority and the system available power. The power formula for task allocation at the current moment is:

[0025]

[0026] Where: P alloc (t) is the power allocated to the current task at the current moment, P total is the total available power of the system, W task (t) is the priority weight of the current task at the current moment, ∑W task (t) is the sum of the priority weights of all tasks at the current moment.

[0027] As a further solution of the present invention, in the battery management system, the real-time fault prediction model constructs a high-dimensional input variable based on the real-time monitored battery voltage, battery current, battery temperature, ambient temperature, charging state, charging rate and charging depth, and uses this high-dimensional input variable as the input of the machine learning model to predict the probability of a fault occurring at the current moment in real time. The expression of this high-dimensional input variable is:

[0028] X(t)=[x1(t),x2(t),x3(t),x4(t),x5(t),x6(t),x7(t)]

[0029] Where: X(t) is the high-dimensional input variable of the machine learning model, x1(t) is the battery voltage input indicator, x2(t) is the battery current input indicator, x3(t) is the battery temperature input indicator, x4(t) is the ambient temperature input indicator, x5(t) is the battery charge state input indicator, x6(t) is the charging rate input indicator, x7(t) is the charging depth input indicator, and the input indicators are the real-time monitoring value of the current indicator, the ratio of the difference between the historical average value and the standard deviation of the indicator.

[0030] A potential energy recovery method based on a lithium iron phosphate energy storage battery, using the above-mentioned potential energy recovery system based on a lithium iron phosphate energy storage battery, comprises the following steps:

[0031] Step 1, initialization parameter setting: start the system, initialize various model parameters, and set the initial values ​​of key parameters according to experimental data;

[0032] Step 2, real-time monitoring data collection: real-time monitoring and collection of ambient temperature, battery temperature, battery voltage, battery current, and recording the current charging state, charging rate, and charging depth of the lithium iron phosphate energy storage battery;

[0033] Step 3, temperature compensated charging current calculation: According to the temperature compensated charging current model, the charging current adjustment formula is calculated using the real-time monitored ambient temperature and the nominal operating temperature to obtain the charging current of the battery at the current temperature, and further combined with the temperature change rate to obtain the dynamic response value of the charging current;

[0034] Step 4, charging efficiency sensitivity adjustment: using real-time temperature data, calculate the charging efficiency sensitivity adjustment coefficient according to an exponential function;

[0035] Step 5, temperature sensitivity coefficient adjustment: determine whether the current temperature deviation exceeds the set threshold. If the temperature deviation is within the set threshold, use the linear adjustment formula. If the temperature deviation exceeds the set threshold, use the nonlinear adjustment formula.

[0036] Step 6, charging depth optimization: Based on the real-time monitored battery status and ambient temperature, calculate and optimize the charging depth, and dynamically adjust the maximum charging depth according to the battery life and cycle number;

[0037] Step 7, dynamic energy allocation: Calculate the current task allocation rate based on the total available power of the system and the priority weight of the task, and adjust the task priority and allocated power in real time;

[0038] Step 8, real-time fault prediction: construct a high-dimensional input variable X(t), input the high-dimensional input variable into the trained machine learning model, predict the probability of a fault at the current moment in real time, and adjust the system operation according to the prediction result;

[0039] Step 9, system feedback and adjustment: monitor the battery charging process in real time, and adjust various parameters according to the feedback results. When abnormal conditions occur and the predicted probability of failure exceeds the set threshold, take corresponding preventive measures immediately.

[0040] As a further scheme of the present invention, in step 9, the fault occurrence rate output by the real-time fault prediction model exceeds the set safety threshold, and the defensive measures taken by the system include reducing the charging current, switching to the backup mode and issuing an alarm. The fault prediction probability is higher than the set safety threshold, and the battery charging current is immediately reduced by a specified percentage. The fault prediction probability is higher than the high-risk set threshold, and the system enters an over-low power operation mode and switches to the backup mode. The basic functions of the system are maintained by the backup power supply. If the fault prediction probability continues to be higher than the threshold setting time, an alarm is issued to the operator through the system's alarm mechanism.

[0041] As a further solution of the present invention, in step 9, the abnormal conditions that occur include abnormal increase in battery temperature, abnormal fluctuation in battery voltage, total system power overload, and abnormal or failed data sensor:

[0042] When the battery temperature exceeds the safe working threshold, the charging current is reduced linearly or nonlinearly according to the temperature rise. When the battery temperature exceeds the set high temperature threshold, the cooling system is immediately activated to reduce the battery temperature to a safe range. When the battery temperature exceeds the critical value, charging is temporarily stopped. When the battery voltage fluctuation exceeds the set threshold, the charging rate is reduced, and the battery internal resistance test and battery aging assessment are performed.

[0043] If the battery voltage continues to fluctuate for more than the set time, it will switch to low load mode;

[0044] When the total system power overload exceeds the set available threshold, the power allocation of secondary tasks will be postponed and reduced. When the system power exceeds the set threshold for severe overload, the backup energy storage equipment will be activated.

[0045] If a group of data from the data sensor is abnormal or the signal is lost, it will automatically switch to the redundant sensor. If multiple data are abnormal at the same time or the signal is lost, the charging current and power output will be reduced based on historical data and empirical parameters. In the case of data abnormality and signal loss, the battery temperature rise rate exceeds the set threshold or the voltage fluctuation exceeds the set threshold, the system will issue an emergency shutdown command.

[0046] With regard to solving the technical problems raised by the background technology, the technical effects of the present invention are as follows: the present invention can stably operate in harsh environments such as extreme temperature, salt spray corrosion, high humidity and high vibration by dynamically adjusting the charging current, optimizing energy management, and real-time fault prediction and response mechanism. In particular, the temperature compensation charging current model significantly improves the charging efficiency in low temperature environments and reduces energy loss; the charging depth optimization model and the dynamic energy allocation model improve the responsiveness of the system and ensure the energy management efficiency in high-frequency and high-volatility operations; the real-time fault prediction model enables the system to identify and respond to potential fault risks in advance, and effectively avoids safety issues caused by grid instability or equipment failure by automatically adjusting the charging current and starting the standby mode, significantly improving the stability, safety and energy utilization efficiency of ship operations, reducing maintenance requirements and reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a system block diagram of the present invention;

[0048] Figure 2 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solution in the present invention. Obviously, the described technical solution is only a part of the present invention but not all of it. Based on the technical solution in the present invention, all other technical solutions obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0050] like Figure 1 As shown, a potential energy recovery system based on a lithium iron phosphate energy storage battery proposed in the present invention includes a braking energy recovery unit and an energy storage system unit. The braking energy recovery unit includes a three-phase AC motor, a motor frequency conversion drive, a braking fuse and a power supply busbar. The energy storage system unit includes an energy storage fuse, a charging isolation switch, a battery management system and a lithium iron phosphate energy storage battery. The three-phase AC motor is connected to the motor frequency conversion drive, and the motor frequency conversion drive is connected to the power supply busbar through the braking fuse, and is connected to the battery management system through the charging isolation switch. The battery management system controls the current to enter the lithium iron phosphate energy storage battery according to the temperature compensation charging current model, the charging depth optimization model, the dynamic energy distribution model and the real-time fault prediction model, stores the electric energy generated by potential energy recovery, and monitors the battery status and charging process in real time. The temperature compensation charging current model is based on the current ambient temperature, the nominal operating temperature and the charging efficiency parameters monitored in real time. The charging current is adjusted according to the charging efficiency ratio at the current temperature and the degree to which the temperature deviates from the optimal temperature. In the temperature compensation charging current model, the charging current adjustment formula is:

[0051]

[0052] Where: T is the real-time monitored ambient temperature, L charge (T) is the charging current of the battery at temperature T, T opt is the optimal battery temperature, I nominal is the ideal charging current at the optimal battery temperature, η charge (T) is the charging efficiency of the battery at temperature T, η max is the highest charging efficiency of the battery under optimal conditions, γ is the charging efficiency sensitivity adjustment coefficient, which is set according to demand, and α is the temperature sensitivity coefficient, which is obtained through experimental data.

[0053] The present invention uses lithium iron phosphate energy storage batteries as storage media to recycle system potential energy, effectively giving play to the advantages of the two potential energy treatment schemes of local consumption type and feedback to the main grid type, while avoiding the shortcomings of the two schemes. Specifically, lithium iron phosphate batteries have the advantages of high safety performance, high energy density, long cycle life, environmental sustainability, etc. Using this battery as a potential energy recovery storage medium can reduce the system usage restrictions caused by the failure of a single device in the braking unit, reduce energy waste, and expand the system's endurance and usage time. At the same time, the energy storage device of this scheme has no direct power path to the main grid, effectively avoiding the safety and system failure hazards such as power shock caused by potential energy feedback to the main grid, improving the safety of the system, and reducing the operating costs of the enterprise. The system proposed by the present invention includes a braking energy recovery unit and an energy storage system unit. The braking energy recovery unit includes a three-phase AC motor, a motor frequency conversion driver, a brake fuse, and a power supply busbar. The three-phase AC motor, with a motor frequency conversion driver downstream, is a working potential energy conversion device or device. The motor variable frequency drive, with a three-phase AC motor upstream and a brake fuse downstream, is a device or apparatus that rectifies the AC generated by the three-phase AC motor into DC. The brake fuse has a fusible fuse inside. Its upstream is the motor variable frequency drive and its downstream is the power supply busbar. It is a device or apparatus that plays an overcurrent isolation protection role between the motor variable frequency drive and the power supply busbar. The power supply busbar, with a brake fuse of the brake energy recovery unit upstream and an energy storage fuse of the energy storage system downstream, is a copper bar that receives the electric energy of the brake energy recovery unit and provides electric energy to the energy storage system unit. The working process of brake energy recovery is as follows: when the three-phase AC motor is dragged by heavy objects or other equipment, the AC generated by it is rectified into DC by the motor variable frequency drive, and then the DC power is sent to the power supply busbar through the brake fuse. The energy storage system unit includes an energy storage fuse, a charging isolation switch, a battery management system, and a lithium iron phosphate energy storage battery. The energy storage fuse has a fusible fuse inside. Its upstream is the power supply busbar and its downstream is the charging isolation switch. It is a device or device that isolates and protects the energy storage system unit from overcurrent. The charging isolation switch, whose upstream is the energy storage fuse and whose downstream is the battery management system, is a device or device that controls and isolates the energy storage system unit from charging. The battery management system, whose upstream is the energy storage fuse and whose downstream is the lithium iron phosphate energy storage battery, is a device or device that monitors the lithium iron phosphate energy storage battery. The lithium iron phosphate energy storage battery contains several groups of energy storage battery packs. Its upstream is the energy storage battery management system, which is the final device or device that receives and stores the electric energy generated by the potential energy recovery unit. The working principle of the fuse is: when the current flowing through the fuse is too large, the fuse will generate a lot of heat due to the excessive current, thereby melting the fuse in the fuse to achieve the isolation protection of its upstream and downstream equipment / systems / devices.

[0054] It should be noted that in the temperature compensation charging current model of the battery management system, the dynamic response of the temperature change rate to the charging current is optimized exponentially according to the current temperature change rate. The dynamic response formula of the battery charging current is:

[0055]

[0056] Where: I charge (T, ΔT) is the dynamic response value of the battery charging current at temperature T, is the temperature change per unit time.

[0057] By introducing exponential adjustment of the temperature change rate, the temperature-compensated charging current model can respond more quickly to dynamic changes in ambient temperature and optimize the charging current, especially when the temperature fluctuates drastically, effectively reducing the decline in battery charging efficiency and energy loss, and improving the stability and safety of the system under extreme conditions.

[0058] It should be noted that in the battery management system, the current temperature deviation is obtained through an exponential function to correct the initial value of the charging efficiency sensitivity adjustment coefficient in the charging current adjustment formula. The formula for obtaining the charging efficiency sensitivity adjustment coefficient is:

[0059]

[0060] Wherein: γ0 is the initial charging efficiency sensitivity adjustment coefficient, which is obtained through historical data, δ is the adjustment coefficient, and n is the nonlinear index. δ and n are determined through experiments.

[0061] By using an exponential function to correct the charging efficiency sensitivity adjustment coefficient, the battery management system can adjust the charging current more accurately, especially when the temperature deviates from the optimal range, making the system more responsive to temperature changes, thereby improving charging efficiency, reducing energy loss, and enhancing the system's stability and adaptability under adverse temperature conditions.

[0062] It should be noted that in the battery management system, the method for obtaining the temperature sensitivity coefficient is determined by judging whether the temperature deviation exceeds the set threshold. If the temperature deviation is within the set threshold, the linear adjustment method is used to correct the initial temperature sensitivity coefficient. The correction formula of the temperature sensitivity coefficient is:

[0063]

[0064] Where: α0 is the initial temperature sensitivity coefficient, obtained through historical data, λ is the linear adjustment coefficient, obtained through experimental data analysis;

[0065] When the temperature deviation exceeds the set threshold, the nonlinear adjustment method is used to correct the initial temperature sensitivity coefficient. The correction formula of the temperature sensitivity coefficient is:

[0066]

[0067] Where: is the nonlinear adjustment coefficient, which is obtained through experimental data analysis; m is the nonlinear adjustment index, which is obtained through experimental data analysis; ΔT is the set temperature deviation threshold between the current temperature and the optimal temperature, which is set according to actual needs.

[0068] By judging whether the temperature deviation exceeds the set threshold, the battery management system can dynamically select a linear or nonlinear adjustment method to correct the temperature sensitivity coefficient. For smaller temperature deviations, the linear adjustment method ensures the stability and charging efficiency of the system; while for larger temperature deviations that exceed the threshold, the nonlinear adjustment method provides a more sensitive response to prevent temperature anomalies from adversely affecting the charging process. This method optimizes the adaptability of the system under different temperature conditions, effectively improves charging efficiency, reduces energy loss, and enhances the stability and safety of the system.

[0069] It should be noted that in the battery management system, the charging depth optimization model optimizes the charging depth according to the current battery status and ambient temperature. In the charging depth optimization model, the charging depth formula is:

[0070]

[0071] Where: D charge is the depth of charge, between 0 and 1, D max is the maximum allowable charging depth, t is the current moment, V battery (t) is the current battery voltage, V max is the maximum allowable voltage of the battery, and β is the temperature adjustment coefficient, which is obtained through experiments.

[0072] Through the charging depth optimization model, the battery management system can dynamically adjust the charging depth according to the current battery status and ambient temperature to ensure that the battery reaches the optimal charging state at different temperatures. The model monitors voltage and temperature in real time to avoid overcharging or undercharging, improve battery charging efficiency and life, reduce energy loss, and ensure the stability and reliability of the system under various environmental conditions.

[0073] It should be noted that in the battery management system, the dynamic energy allocation model dynamically allocates energy according to the task priority and the system available power. The power formula for task allocation at the current moment is:

[0074]

[0075] Where: P alloc (t) is the power allocated to the current task at the current moment, P totalis the total available power of the system, W task (t) is the priority weight of the current task at the current moment, ∑W task (t) is the sum of the priority weights of all tasks at the current moment.

[0076] Through the dynamic energy allocation model, the battery management system can optimize energy allocation in real time according to the priority of the task and the available power of the system. This model ensures that critical tasks are given priority to obtain sufficient energy support, while balancing the energy requirements between tasks to avoid resource waste and overload. This method improves the operating efficiency of the system and the reliability of task execution, especially in the case of limited resources or heavy tasks, ensuring the stability and overall performance of the system.

[0077] It should be noted that in the battery management system, the real-time fault prediction model constructs a high-dimensional input variable based on the real-time monitored battery voltage, battery current, battery temperature, ambient temperature, charging state, charging rate and charging depth. This high-dimensional input variable is used as the input of the machine learning model to predict the probability of a fault at the current moment in real time. The expression of this high-dimensional input variable is:

[0078] X(t)=[x1(t),x2(t),x3(t),x4(t),t5(t),x6(t),x7(t)]

[0079] Where: X(t) is the high-dimensional input variable of the machine learning model, x1(t) is the battery voltage input indicator, x2(t) is the battery current input indicator, x3(t) is the battery temperature input indicator, x4(t) is the ambient temperature input indicator, x5(t) is the battery charge state input indicator, x6(t) is the charging rate input indicator, x7(t) is the charging depth input indicator, and the input indicators are the real-time monitoring value of the current indicator, the ratio of the difference between the historical average value and the standard deviation of the indicator.

[0080] By constructing high-dimensional input variables based on real-time monitoring data and inputting them into the machine learning model for fault prediction, the battery management system can evaluate the probability of failure under current conditions in real time. This method comprehensively analyzes multiple key indicators such as battery voltage, current, temperature, ambient temperature, etc., and considers the deviation between the real-time changes of these indicators and historical trends, thereby improving the accuracy and timeliness of fault prediction. In this way, the system can proactively take preventive measures before a fault occurs, such as adjusting the charging current or switching to backup mode, effectively avoiding potential battery damage and system failures, and ensuring the stable operation of the system and the safety of the equipment. At the same time, the model reduces the need to rely on manual inspection and improves the overall operation and maintenance efficiency.

[0081] like Figure 2As shown, the present invention proposes a potential energy recovery method based on a lithium iron phosphate energy storage battery, which uses the above-mentioned potential energy recovery system based on a lithium iron phosphate energy storage battery, and includes the following steps:

[0082] Step 1, initialization parameter setting: start the system, initialize various model parameters, and set the initial values ​​of key parameters according to experimental data;

[0083] Step 2, real-time monitoring data collection: real-time monitoring and collection of ambient temperature, battery temperature, battery voltage, battery current, and recording the current charging state, charging rate, and charging depth of the lithium iron phosphate energy storage battery;

[0084] Step 3, temperature compensated charging current calculation: According to the temperature compensated charging current model, the charging current adjustment formula is calculated using the real-time monitored ambient temperature and the nominal operating temperature to obtain the charging current of the battery at the current temperature, and further combined with the temperature change rate to obtain the dynamic response value of the charging current;

[0085] Step 4, charging efficiency sensitivity adjustment: using real-time temperature data, calculate the charging efficiency sensitivity adjustment coefficient according to an exponential function;

[0086] Step 5, temperature sensitivity coefficient adjustment: determine whether the current temperature deviation exceeds the set threshold. If the temperature deviation is within the set threshold, use the linear adjustment formula. If the temperature deviation exceeds the set threshold, use the nonlinear adjustment formula.

[0087] Step 6, charging depth optimization: Based on the real-time monitored battery status and ambient temperature, calculate and optimize the charging depth, and dynamically adjust the maximum charging depth according to the battery life and cycle number;

[0088] Step 7, dynamic energy allocation: Calculate the current task allocation rate based on the total available power of the system and the priority weight of the task, and adjust the task priority and allocated power in real time;

[0089] Step 8, real-time fault prediction: construct a high-dimensional input variable x(t), input the high-dimensional input variable into the trained machine learning model, predict the probability of a fault at the current moment in real time, and adjust the system operation according to the prediction result;

[0090] Step 9, system feedback and adjustment: monitor the battery charging process in real time, and adjust various parameters according to the feedback results. When abnormal conditions occur and the predicted probability of failure exceeds the set threshold, take corresponding preventive measures immediately.

[0091] The potential energy recovery method based on lithium iron phosphate energy storage battery proposed in the present invention realizes efficient management and dynamic adjustment of the potential energy recovery system in deep-sea operations of ships through a series of optimization steps. Through initialization parameter setting and real-time monitoring, the system can accurately grasp the operating status of the environment and the battery, and through models such as temperature compensation charging current, charging efficiency sensitivity adjustment, and temperature sensitivity coefficient adjustment, it ensures that the battery charging process is always in the best state under complex and changing environmental conditions. In addition, through charging depth optimization and dynamic energy allocation, the system can effectively utilize resources and improve energy management efficiency. The real-time fault prediction model further ensures the safety of the system. By identifying potential faults in advance and adjusting operations in time, the risk of system instability or equipment damage is avoided. Overall, this method significantly improves the stability, reliability and energy utilization efficiency of the system under extreme conditions, ensuring the safety and continuity of ship operations.

[0092] It should be noted that in step 9, the fault occurrence rate output by the real-time fault prediction model exceeds the set safety threshold. The defensive measures taken by the system include reducing the charging current, switching to the backup mode and issuing an alarm. If the fault prediction probability is higher than the set safety threshold, the battery charging current is immediately reduced by a specified percentage. If the fault prediction probability is higher than the high-risk set threshold, the system enters an overly low power operation mode and switches to the backup mode. The basic functions of the system are maintained by the backup power supply. If the fault prediction probability continues to be higher than the threshold setting time, an alarm is issued to the operator through the system's alarm mechanism.

[0093] Through the real-time fault prediction model, when the fault occurrence rate exceeds the safety threshold, the system takes measures such as reducing the charging current, switching to the backup mode and issuing an alarm, which can prevent potential faults in time and reduce system risks. This not only protects the battery and equipment from further damage, but also ensures the continuous operation of the system in emergency situations, and reminds operators to conduct inspections and maintenance through the alarm mechanism, which significantly improves the safety and stability of the system.

[0094] It should be noted that in step 9, the abnormal conditions that occur include abnormal increase in battery temperature, abnormal fluctuation in battery voltage, total system power overload, and abnormal or failed data sensors:

[0095] When the battery temperature exceeds the safe working threshold, the charging current is reduced linearly or nonlinearly according to the temperature rise. When the battery temperature exceeds the set high temperature threshold, the cooling system is immediately activated to reduce the battery temperature to a safe range. When the battery temperature exceeds the critical value, charging is temporarily stopped. When the battery voltage fluctuation exceeds the set threshold, the charging rate is reduced, and the battery internal resistance test and battery aging assessment are performed.

[0096] If the battery voltage continues to fluctuate for more than the set time, it will switch to low load mode;

[0097] When the total system power overload exceeds the set available threshold, the power allocation of secondary tasks will be postponed and reduced. When the system power exceeds the set threshold for severe overload, the backup energy storage equipment will be activated.

[0098] If a group of data from the data sensor is abnormal or the signal is lost, it will automatically switch to the redundant sensor. If multiple data are abnormal at the same time or the signal is lost, the charging current and power output will be reduced based on historical data and empirical parameters. In the case of data abnormality and signal loss, the battery temperature rise rate exceeds the set threshold or the voltage fluctuation exceeds the set threshold, the system will issue an emergency shutdown command.

[0099] In step 9, the system significantly improves the stability and safety of the potential energy recovery system in a complex offshore environment through a series of response measures for abnormal situations. For abnormally high battery temperature, the charging current is reduced linearly or nonlinearly, and the cooling system is started to quickly control the battery temperature within a safe range, avoiding battery damage caused by overheating. When the battery voltage fluctuation exceeds the set threshold, the battery failure caused by aging or internal problems is prevented by reducing the charging rate and performing a battery health check. When the total power of the system is overloaded, the impact of power overload on the system is effectively avoided by dynamically adjusting the task allocation and enabling the backup energy storage device. In addition, when the data sensor is abnormal or fails, the system automatically switches to the redundant sensor to ensure the continuity of the monitoring data; in the case of multiple sets of data abnormalities, the system actively reduces the charging current and power output based on historical data and empirical parameters to prevent operational failures caused by data loss or errors. If the abnormal situation deteriorates further, such as a sharp rise in battery temperature or severe voltage fluctuations, the system will issue an emergency shutdown command to protect the safety of equipment and personnel. Overall, these measures ensure the continuous operation, timely response and fault prevention of the system in extreme environments, greatly reducing the risk of system failures and accidents.

[0100] The present invention can stably operate in harsh environments such as extreme temperature, salt spray corrosion, high humidity and high vibration by dynamically adjusting the charging current, optimizing energy management, and implementing real-time fault prediction and response mechanisms. In particular, the temperature-compensated charging current model significantly improves the charging efficiency in low-temperature environments and reduces energy loss. The charging depth optimization model and the dynamic energy allocation model improve the responsiveness of the system and ensure the energy management efficiency in high-frequency and high-volatility operations. The real-time fault prediction model enables the system to identify and respond to potential fault risks in advance, and effectively avoids safety issues caused by grid instability or equipment failure by automatically adjusting the charging current and starting the standby mode, significantly improving the stability, safety and energy utilization efficiency of ship operations, reducing maintenance requirements and lowering operating costs.

[0101] The present invention has the advantages of reducing energy waste, lowering electricity costs, improving system safety, and improving enterprise economic benefits. Specifically, it is embodied in:

[0102] System safety: effectively avoids the risk of system downtime caused by brake unit failure and the risk of grid shock caused by feedback to the main grid. This system improves system reliability and safety by about 3%-5%.

[0103] Economic benefits: Based on the calculation that a 2000KW lifting equipment can recover 700KW of potential energy once a day, without considering the energy conversion loss, energy consumption can be reduced by 35%. Based on the average fuel consumption rate of diesel engines of 210g / KWh, fuel consumption can be reduced by 0.147 tons. Based on the diesel price of 6,000 yuan / ton, fuel expenditure can be saved by about 882 yuan.

[0104] Social benefits: Based on the calculation that a 2000KW lifting equipment can recover 700KW of potential energy once a day and the diesel engine emission factor of 3.15t CO2e / t, the energy consumption saved can reduce carbon emissions by 0.46t.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0106] Finally: The above description is only an explanation of the preferred implementation 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 protection scope of the present invention.

Claims

1. A potential energy recovery system based on lithium iron phosphate energy storage battery, characterized in that: It includes a braking energy recovery unit and an energy storage system unit. The braking energy recovery unit includes a three-phase AC motor, a motor frequency conversion drive, a braking fuse and a power supply busbar. The energy storage system unit includes an energy storage fuse, a charging isolation switch, a battery management system and a lithium iron phosphate energy storage battery. The three-phase AC motor is connected to the motor frequency conversion drive. The motor frequency conversion drive is connected to the power supply busbar through the braking fuse and connected to the battery management system through the charging isolation switch. The battery management system controls the current entering the lithium iron phosphate energy storage battery according to the temperature compensation charging current model, the charging depth optimization model, the dynamic energy distribution model and the real-time fault prediction model, stores the electric energy generated by potential energy recovery, and monitors the battery status and charging process in real time. The temperature compensation charging current model is based on the current ambient temperature, the nominal operating temperature and the charging efficiency parameters monitored in real time. The charging current is adjusted according to the charging efficiency ratio at the current temperature and the degree of temperature deviation from the optimal temperature. In the temperature compensation charging current model, the charging current adjustment formula is: Where: T is the real-time monitored ambient temperature, I charge (T) is the charging current of the battery at temperature T, T opt is the optimal battery temperature, I nominal is the ideal charging current at the optimal battery temperature, η charge (T) is the charging efficiency of the battery at temperature T, η max is the highest charging efficiency of the battery under optimal conditions, γ is the charging efficiency sensitivity adjustment coefficient, which is set according to demand, and α is the temperature sensitivity coefficient, which is obtained through experimental data.

2. A potential energy recovery system based on lithium iron phosphate energy storage battery according to claim 1, characterized in that: In the temperature compensation charging current model of the battery management system, the dynamic response of the temperature change rate to the charging current is optimized exponentially according to the current temperature change rate. The dynamic response formula of the battery charging current is: Where: I charge (T, ΔT) is the dynamic response value of the battery charging current at temperature T, is the temperature change per unit time.

3. A potential energy recovery system based on lithium iron phosphate energy storage battery according to claim 1, characterized in that: In the battery management system, the current temperature deviation is obtained through an exponential function to correct the initial value of the charging efficiency sensitivity adjustment coefficient in the charging current adjustment formula. The formula for obtaining the charging efficiency sensitivity adjustment coefficient is: Wherein: γ0 is the initial charging efficiency sensitivity adjustment coefficient, which is obtained through historical data, δ is the adjustment coefficient, and n is the nonlinear index. δ and n are determined through experiments.

4. A potential energy recovery system based on lithium iron phosphate energy storage battery according to claim 1, characterized in that: In the battery management system, the acquisition method of the temperature sensitivity coefficient is determined by judging whether the temperature deviation exceeds the set threshold. If the temperature deviation is within the set threshold, the linear adjustment method is used to correct the initial temperature sensitivity coefficient. The correction formula of the temperature sensitivity coefficient is: Where: α0 is the initial temperature sensitivity coefficient, obtained through historical data, λ is the linear adjustment coefficient, obtained through experimental data analysis; When the temperature deviation exceeds the set threshold, the nonlinear adjustment method is used to correct the initial temperature sensitivity coefficient. The correction formula of the temperature sensitivity coefficient is: Where: is the nonlinear adjustment coefficient, which is obtained through experimental data analysis; m is the nonlinear adjustment index, which is obtained through experimental data analysis; ΔT is the set temperature deviation threshold between the current temperature and the optimal temperature, which is set according to actual needs.

5. A potential energy recovery system based on lithium iron phosphate energy storage battery according to claim 1, characterized in that: In the battery management system, the charging depth optimization model optimizes the charging depth according to the current battery status and ambient temperature. In the charging depth optimization model, the charging depth formula is: Where: D charge is the depth of charge, between 0 and 1, D max is the maximum allowable charging depth, t is the current moment, V battery (t) is the current battery voltage, V max is the maximum allowable voltage of the battery, and β is the temperature adjustment coefficient, which is obtained through experiments.

6. A potential energy recovery system based on lithium iron phosphate energy storage battery according to claim 5, characterized in that: In the battery management system, the dynamic energy allocation model dynamically allocates energy according to the task priority and the system available power. The power formula for task allocation at the current moment is: Where: P alloc (t) is the power allocated to the current task at the current moment, P total is the total available power of the system, W task (t) is the priority weight of the current task at the current moment, ∑W task (t) is the sum of the priority weights of all tasks at the current moment.

7. A potential energy recovery system based on lithium iron phosphate energy storage battery according to claim 6, characterized in that: In the battery management system, the real-time fault prediction model constructs a high-dimensional input variable based on the real-time monitored battery voltage, battery current, battery temperature, ambient temperature, charging state, charging rate and charging depth. This high-dimensional input variable is used as the input of the machine learning model to predict the probability of a fault at the current moment in real time. The expression of this high-dimensional input variable is: X(t)=[x1(t), x2(t), x3(t), x4(t), x5(t), x6(t), x7(t)] Where: X(t) is the high-dimensional input variable of the machine learning model, x1(t) is the battery voltage input indicator, x2(t) is the battery current input indicator, x3(t) is the battery temperature input indicator, x4(t) is the ambient temperature input indicator, x5(t) is the battery charge state input indicator, x6(t) is the charging rate input indicator, x7(t) is the charging depth input indicator, and the input indicators are the real-time monitoring value of the current indicator, the ratio of the difference between the historical average value and the standard deviation of the indicator.

8. A potential energy recovery method based on a lithium iron phosphate energy storage battery, used to implement a potential energy recovery system based on a lithium iron phosphate energy storage battery according to any one of claims 1 to 7, characterized in that: The steps include: Step 1, initialization parameter setting: start the system, initialize various model parameters, and set the initial values ​​of key parameters according to experimental data; Step 2, real-time monitoring data collection: real-time monitoring and collection of ambient temperature, battery temperature, battery voltage, battery current, and recording the current charging state, charging rate, and charging depth of the lithium iron phosphate energy storage battery; Step 3, temperature compensated charging current calculation: According to the temperature compensated charging current model, the charging current adjustment formula is calculated using the real-time monitored ambient temperature and the nominal operating temperature to obtain the charging current of the battery at the current temperature, and further combined with the temperature change rate to obtain the dynamic response value of the charging current; Step 4, charging efficiency sensitivity adjustment: using real-time temperature data, calculate the charging efficiency sensitivity adjustment coefficient according to an exponential function; Step 5, temperature sensitivity coefficient adjustment: determine whether the current temperature deviation exceeds the set threshold. If the temperature deviation is within the set threshold, use the linear adjustment formula. If the temperature deviation exceeds the set threshold, use the nonlinear adjustment formula. Step 6, charging depth optimization: Based on the real-time monitored battery status and ambient temperature, calculate and optimize the charging depth, and dynamically adjust the maximum charging depth according to the battery life and cycle number; Step 7, dynamic energy allocation: Calculate the current task allocation rate based on the total available power of the system and the priority weight of the task, and adjust the task priority and allocated power in real time; Step 8, real-time fault prediction: construct a high-dimensional input variable X(t), input the high-dimensional input variable into the trained machine learning model, predict the probability of a fault at the current moment in real time, and adjust the system operation according to the prediction result; Step 9, system feedback and adjustment: monitor the battery charging process in real time, and adjust various parameters according to the feedback results. When abnormal conditions occur and the predicted probability of failure exceeds the set threshold, take corresponding preventive measures immediately.

9. A potential energy recovery method based on lithium iron phosphate energy storage battery according to claim 8, characterized in that: In step 9, the fault occurrence rate output by the real-time fault prediction model exceeds the set safety threshold. The defensive measures taken by the system include reducing the charging current, switching to the backup mode and issuing an alarm. If the fault prediction probability is higher than the set safety threshold, the battery charging current is immediately reduced by a specified percentage. If the fault prediction probability is higher than the high-risk set threshold, the system enters an overly low power operation mode and switches to the backup mode. The basic functions of the system are maintained by the backup power supply. If the fault prediction probability continues to be higher than the threshold setting time, an alarm is issued to the operator through the system's alarm mechanism.

10. A potential energy recovery method based on lithium iron phosphate energy storage battery according to claim 8, characterized in that: In step 9, the abnormal conditions that occur include abnormal increase in battery temperature, abnormal fluctuation in battery voltage, total system power overload, and abnormal or failed data sensors: When the battery temperature exceeds the safe working threshold, the charging current is reduced linearly or nonlinearly according to the temperature rise. When the battery temperature exceeds the set high temperature threshold, the cooling system is immediately activated to reduce the battery temperature to a safe range. When the battery temperature exceeds the critical value, charging is temporarily stopped. When the battery voltage fluctuation exceeds the set threshold, the charging rate is reduced, and the battery internal resistance test and battery aging assessment are performed. If the battery voltage continues to fluctuate for more than the set time, it will switch to low load mode; When the total system power overload exceeds the set available threshold, the power allocation of secondary tasks will be postponed and reduced. When the system power exceeds the set threshold for severe overload, the backup energy storage equipment will be activated. If a group of data from the data sensor is abnormal or the signal is lost, it will automatically switch to the redundant sensor. If multiple data are abnormal at the same time or the signal is lost, the charging current and power output will be reduced based on historical data and empirical parameters. In the case of data abnormality and signal loss, the battery temperature rise rate exceeds the set threshold or the voltage fluctuation exceeds the set threshold, the system will issue an emergency shutdown command.

Images