Electric tug energy efficiency management method based on large model

Abstract

The invention discloses an electric tug energy efficiency management method based on a large model, and the method comprises the following steps: S1, energy dynamic distribution optimization: carrying out the optimization of energy dynamic distribution based on the large model according to the real-time load of an electric tug; s2, charging strategy optimization: according to the price gradient of the power grid, the charging time and the charging electric quantity of the electric tug are optimized; s3, safety protection of the battery system: monitoring the temperature, voltage and current of the battery in real time, and performing early warning protection on the battery; s4, safety guarantee of the propulsion system: monitoring operation data of the propulsion system in real time, and performing protection, fault monitoring and fault diagnosis on the propulsion system; s5, safety redundancy of the power supply system: monitoring and adjusting the electric energy quality of the DC power distribution system, and supplying emergency power to the AC power distribution system; according to the method, accurate power distribution, intelligent charging management, efficient safety protection and reliable power supply guarantee are achieved, and the energy efficiency and operation safety of the electric tug are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to an energy efficiency management method for an electric tugboat based on a large model. Background Art

[0002] In recent years, significant progress has been made in energy efficiency management technology for electric tugboats, both domestically and internationally. In terms of dynamic energy distribution, simulation modeling and optimization algorithms are being used to delve into energy management systems. For example, China Shipbuilding Power (Group) Co., Ltd. has successfully implemented 1000V DC integrated electric propulsion technology to improve energy efficiency. Regarding charging strategy optimization, foreign ports are adopting charging strategies based on real-time load forecasting, while domestic ports are exploring fast-charging technologies to reduce the impact of charging on operational efficiency. In terms of lithium battery system safety and protection technology, lithium iron phosphate batteries have become mainstream, with the development of active cooling and passive protection technologies to improve battery safety. Propulsion and power supply system safety assurance is also gradually moving towards intelligence, leveraging sensor networks and real-time monitoring systems to improve reliability and redundancy.

[0003] However, current technologies still face challenges in adapting to complex working conditions, intelligent charging equipment, and efficient charging of multiple tugboats. Specifically, existing technologies have the following shortcomings: 1) Dynamic energy distribution: Existing energy management systems are mostly optimized based on preset parameters, making it difficult to adapt to fluctuations in energy demand under complex working conditions in real time, and their dynamic optimization capabilities are poor; the coupling between propulsion, energy storage, and charging equipment systems is poor, and insufficient coordination leads to low energy distribution efficiency; and the impact of environmental factors such as temperature and humidity on battery performance is not fully considered, which reduces overall energy efficiency. 2) Charging strategy optimization: Current charging equipment has a low level of intelligence and mostly has a fixed power output, which cannot dynamically adjust charging parameters based on battery status; the charging interfaces and protocols of different ports and tugboat manufacturers are incompatible, and there is a lack of unified charging standards, which limits the versatility and flexibility of charging equipment; when the port is busy, the charging time of electric tugboats is long, which becomes a bottleneck restricting their continuous operation. 3) Lithium Battery System Safety Protection: Batteries are at risk of thermal runaway when exposed to high temperatures or overcharge, and existing protection technologies are insufficient to cope with extreme operating conditions. Battery status monitoring systems lack real-time performance and accuracy, making it difficult to predict the remaining battery life and health status. Existing technologies primarily focus on passive protection, such as cooling systems and overcharge protection, and lack proactive intervention to preemptively mitigate potential risks. 4) Propulsion System Safety Assurance: Existing sensors have limited measurement accuracy in complex sea conditions, impacting propulsion system control effectiveness. Some electric tugboat propulsion systems lack sufficient redundancy, making failure of key components prone to serious safety incidents. Propulsion system control strategies are often based on traditional algorithms, with limited intelligence and a lack of adaptive capabilities to cope with unexpected operating conditions. 5) Power Supply System Safety Redundancy: Existing redundant designs rely on complex circuits, increasing system maintenance complexity and failure rates. Power supply system fault diagnosis technology is immature, making it difficult to quickly locate and repair problems. The power supply system suffers from energy loss during energy distribution and conversion, resulting in inefficient energy management. Summary of the Invention

[0004] To solve the above problems, the present invention proposes an energy efficiency management method for electric tugboats based on a large model. This method realizes precise power distribution, intelligent charging management, efficient safety protection and reliable power supply guarantee, improves the energy efficiency and operational safety of electric tugboats, and provides technical support for the widespread application of electric tugboats in port operations and other fields.

[0005] To achieve the above object, the present invention adopts the following technical solutions: A large-scale model-based energy efficiency management method for electric tugboats comprises the following steps: S1. Energy dynamic distribution optimization: Based on the real-time load of the electric tugboat, the energy dynamic distribution is optimized based on the large model; S2. Charging strategy optimization: Optimize the charging time and charging power of the electric tugboat according to the price gradient of the power grid; S3. Safety protection of battery system: real-time monitoring of battery temperature, voltage and current, and early warning protection of the battery; S4. Safety assurance of the propulsion system: real-time monitoring of the propulsion system's operating data, protection of the propulsion system, fault monitoring and fault diagnosis; S5. Safety redundancy of power supply system: monitor and adjust the power quality of DC distribution system, and provide emergency power supply to AC distribution system.

[0006] Preferably, the specific process of step S1 is: S11. Based on the large model, the total power of the electric tugboat in different operating scenarios is predicted and analyzed. Propulsion motor power Power with other devices The sum of ; S12. The large model learns the historical operation data of the electric tugboat and analyzes the optimal ratio of propulsion motor power to total power in real time. , Among them, historical operation data includes load weight, sailing speed, water current and wind direction; S13. Propulsion motor power allocated based on analysis , power allocated to other devices , dynamic adjustment value to achieve dynamic power allocation.

[0007] Preferably, step S1 also includes charging and discharging balancing of the battery pack, and the specific process is as follows: S14, the large model monitors the charge and discharge status of the battery pack in real time, assuming that the initial charge state of each battery pack is ;in, , representing 8 groups of batteries; S15: During the discharge process, the discharge current of each battery group is predicted based on the real-time load. and discharge time 1. Combined with the battery capacity , calculate the discharge time The state of charge of each battery group after 1 is calculated as follows: ,in, is the state of charge of the i-th group of batteries; S16. Execute the battery balancing algorithm to adjust the discharge current of each battery group to keep the state of charge of each battery group consistent and reduce the accumulation of performance differences between battery groups. When the state of charge of a battery group is found to be lower than the average value, calculate the reduction in the discharge current of this battery group based on the large model to achieve battery balancing management.

[0008] Preferably, the specific process of step S2 is: S21, slow charging mode, large model combined with the initial charge of the battery , battery capacity and slow charge current , predict the time required to fully charge in slow charging mode, the calculation formula is: ,in, The time required to fully charge in slow charging mode; S22, in fast charging mode, the large model monitors the battery temperature in real time ,Voltage and current , establish the charging current change function , by integrating the charging current change function, the time required to fully charge in fast charging mode is predicted. The calculation formula is: ,in, The time required to fully charge in fast charging mode; S23, charging process, assuming the electricity price during the off-peak period is , the peak period electricity price is , Combined with the electricity price information and charging data of the power grid during peak and valley periods, the charging capacity of the electric tugboat is monitored in real time. The charging capacity during the valley period is , the charging amount during peak hours is , calculate the total cost of charging the tugboat ; S24. Based on the large-scale model, the relationship between grid load and tugboat charging power and electricity price differences are analyzed through optimization algorithms to dynamically adjust tugboat charging power. The historical electric tugboat power demand data is analyzed to determine the optimal charging capacity during off-peak hours. , to minimize charging costs.

[0009] Preferably, the specific process of step S3 is: S31, the battery temperature data is transmitted to the large model in real time through the temperature sensor, and the large model analyzes the battery temperature data in real time, and sets the critical temperature for battery thermal runaway to be , when the battery temperature When the battery is in a state of thermal runaway, the blocking protection mechanism is immediately activated, and the connection between batteries is cut off through the intelligent fuse or electronic switch; during the thermal runaway process, the heat conduction equation is used to , combined with real-time monitored battery temperature data, to predict thermal runaway risks in advance; is the battery material density; is the specific heat capacity of the battery material; is thermal conductivity; is the internal heat generation rate of the battery; S32, collect and monitor the voltage and current of the single battery in real time. For overvoltage fault, the normal operating voltage range of the battery is , when the voltage of the single battery is monitored in real time satisfy When the battery is judged to have an overvoltage fault, the connection between the batteries is cut off through the intelligent fuse or electronic switch; for overcurrent fault, the rated current of the battery is set to , when the current of the single battery is monitored in real time satisfy When the battery is judged to have an overcurrent fault, the connection between the batteries is cut off through the intelligent fuse or electronic switch; S33, build Rint model, battery terminal voltage With current , battery internal resistance and open circuit voltage The relationship is , using the data analysis and learning capabilities of the large model, the model parameters are analyzed by the least squares method to determine the battery health status and faults; The data of group terminal voltage and corresponding current are used to find the objective function smallest The value is calculated as follows: ,in, is the terminal voltage of the jth group of batteries; is the current of the jth group of batteries; right Ask about The derivative of and set it to 0: , solve the equation to get the estimated value of the battery internal resistance R.

[0010] Preferably, the specific process of step S4 is: S41, permanent magnet propulsion motor overload protection: real-time monitoring of the operating power of the permanent magnet propulsion motor and rated power ,when When the permanent magnet propulsion motor is judged to be overloaded, the large model immediately activates the motor protection function and cuts off the power supply in milliseconds to protect the permanent magnet propulsion motor and the entire propulsion system from damage; is the overload factor, The large model dynamically adjusts the overload coefficient according to the real-time operating status and historical data of the permanent magnet propulsion motor. ; S42. Propulsion system fault monitoring: The propulsion system, based on a programmable controller, transmits the status data of the electric propulsion equipment to the large model. When the monitored status data exceeds the normal range, the electric propulsion equipment is determined to be operating abnormally and an alarm signal is immediately issued. The status data includes the current, voltage, and speed of the propulsion motor. S43. Fault diagnosis of propulsion system: Build a diagnostic model based on fault data in historical data, and pre-learn the operating data of the motor under different fault conditions. When the speed difference of the motor exceeds the threshold, the diagnostic model combines other motor parameters monitored in real time, matches and analyzes them in the knowledge base, and obtains the fault diagnosis result of the motor.

[0011] Preferably, in step S5, the specific process of monitoring and adjusting the power quality of the DC power distribution system is: S51, real-time monitoring of the actual voltage of the DC bus in the DC power distribution system , rated voltage And the voltage fluctuation range allowable value ; S52, when When , the large model starts the regulation mechanism and controls the DC bus voltage output based on the voltage regulation algorithm of proportional-integral-differential control. The calculation formula is: ,in, is the DC bus voltage output; is the proportionality coefficient; is the integration time constant; is the differential time constant; is the voltage deviation, ; is the DC output time; for Voltage value at the moment; For time; S53, the large model dynamically adjusts the 、 、 The value of is used to control the power regulation device in the DC distribution system to stabilize the DC bus voltage within the allowable range and improve the quality of the output power.

[0012] Preferably, in step S5, the specific process of providing emergency power supply to the AC power distribution system is as follows: S54, monitor the operating status of the AC power distribution system in real time. When the AC power fails, control the emergency power supply to supply power to the propulsion system and key equipment. Assume that the capacity of the emergency power supply is , the output voltage is , the total power demand of the propulsion system and key equipment is , the duration that the emergency power supply can continue to supply power ; S55, the emergency power supply is equipped with an intelligent charging device and control system. The large model automatically adjusts the output power of the emergency power supply according to the real-time changes in the ship's power demand; considering the charging and discharging efficiency of the emergency power supply , the actual power supply , actual continuous power supply time .

[0013] After adopting the above technical solution, the present invention has the following beneficial effects: 1. The present invention adopts a dynamic energy distribution mechanism to adapt to energy fluctuations in complex working conditions in real time, strengthen the coordination of propulsion, energy storage and charging equipment, comprehensively consider environmental factors, and improve the dynamic optimization of energy distribution and overall energy efficiency.

[0014] 2. The charging strategy optimization of the present invention dynamically adjusts parameters according to the battery status based on a large model, unifies charging standards, solves interface protocol compatibility issues, optimizes charging strategies in busy ports, and shortens charging time.

[0015] 3. The safety protection of the battery system of the present invention focuses on battery protection, addresses the risk of thermal runaway, builds a monitoring system based on a large model, predicts battery life and health, explores proactive measures, and avoids potential safety hazards.

[0016] 4. The safety of the propulsion system of the present invention uses a large model to optimize the design of the propulsion system, increase redundancy, and improve the adaptability and safety of responding to sudden working conditions.

[0017] 5. The safety redundancy of the power supply system of the present invention uses large model technology to simplify redundant circuit design, reduce maintenance difficulty and failure, develop efficient fault diagnosis technology, optimize energy distribution and conversion, and improve the energy management efficiency of the power supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Flowchart of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, a large-scale model-based electric tugboat energy efficiency management method includes the following steps: S1. Energy dynamic distribution optimization: Based on the real-time load of the electric tugboat, the energy dynamic distribution is optimized based on the large model; The specific process of step S1 is: S11. Based on the large model, the total power of the electric tugboat in different operating scenarios is predicted and analyzed. Propulsion motor power Power with other devices The sum of ; S12. The large model learns the historical operation data of the electric tugboat and analyzes the optimal ratio of propulsion motor power to total power in real time. , Among them, historical operation data includes load weight, sailing speed, water current and wind direction; S13. Propulsion motor power allocated based on analysis , power allocated to other devices , dynamic adjustment value, realizing dynamic power allocation; Step S1 also includes battery pack charge and discharge balancing, and the specific process is as follows: S14, the large model monitors the charge and discharge status of the battery pack in real time, assuming that the initial charge state of each battery pack is ;in, , representing 8 groups of batteries; S15: During the discharge process, the discharge current of each battery group is predicted based on the real-time load. and discharge time 1. Combined with the battery capacity , calculate the discharge time The state of charge of each battery group after 1 is calculated as follows: ,in, is the state of charge of the i-th group of batteries; S16. Execute a battery balancing algorithm to adjust the discharge current of each battery group to maintain consistent state of charge across all battery groups, thereby reducing the accumulation of performance differences between battery groups. When the state of charge of a battery group is found to be lower than the average, calculate the reduction in discharge current of the battery group based on the large model to implement battery balancing management. S2. Charging strategy optimization: Optimize the charging time and charging power of the electric tugboat according to the price gradient of the power grid; The specific process of step S2 is: S21, slow charging mode, large model combined with the initial charge of the battery , battery capacity and slow charge current , predict the time required to fully charge in slow charging mode, the calculation formula is: ,in, The time required to fully charge in slow charging mode; S22, in fast charging mode, the large model monitors the battery temperature in real time ,Voltage and current , establish the charging current change function , by integrating the charging current change function, the time required to fully charge in fast charging mode is predicted. The calculation formula is: ,in, The time required to fully charge in fast charging mode; S23, charging process, assuming the electricity price during the off-peak period is , the peak period electricity price is , Combined with the electricity price information and charging data of the power grid during peak and valley periods, the charging capacity of the electric tugboat is monitored in real time. The charging capacity during the valley period is , the charging amount during peak hours is , calculate the total cost of charging the tugboat ; S24. Based on the large-scale model, the relationship between grid load and tugboat charging power and electricity price differences are analyzed through optimization algorithms to dynamically adjust tugboat charging power. The historical electric tugboat power demand data is analyzed to determine the optimal charging capacity during off-peak hours. , to minimize charging costs; S3. Safety protection of battery system: real-time monitoring of battery temperature, voltage and current, and early warning protection of the battery; The specific process of step S3 is: S31, the battery temperature data is transmitted to the large model in real time through the temperature sensor, and the large model analyzes the battery temperature data in real time, and sets the critical temperature for battery thermal runaway to be , when the battery temperature When the battery is in a state of thermal runaway, the blocking protection mechanism is immediately activated, and the connection between batteries is cut off through the intelligent fuse or electronic switch; during the thermal runaway process, the heat conduction equation is used to , combined with real-time monitored battery temperature data, to predict thermal runaway risks in advance; is the battery material density; is the specific heat capacity of the battery material; is thermal conductivity; is the internal heat generation rate of the battery; S32, collect and monitor the voltage and current of the single battery in real time. For overvoltage fault, the normal operating voltage range of the battery is , when the voltage of the single battery is monitored in real time satisfy When the battery is judged to have an overvoltage fault, the connection between the batteries is cut off through the intelligent fuse or electronic switch; for overcurrent fault, the rated current of the battery is set to , when the current of the single battery is monitored in real time satisfy When the battery is judged to have an overcurrent fault, the connection between the batteries is cut off through the intelligent fuse or electronic switch; S33, build Rint model, battery terminal voltage With current , battery internal resistance and open circuit voltage The relationship is , using the data analysis and learning capabilities of the large model, the model parameters are analyzed by the least squares method to determine the battery health status and faults; The data of group terminal voltage and corresponding current are used to find the objective function smallest The value is calculated as follows: ,in, is the terminal voltage of the jth group of batteries; is the current of the jth group of batteries; right Ask about The derivative of and set it to 0: , solve the equation to get the estimated value of the battery internal resistance R; S4. Safety assurance of the propulsion system: real-time monitoring of the propulsion system's operating data, protection of the propulsion system, fault monitoring and fault diagnosis; The specific process of step S4 is: S41, permanent magnet propulsion motor overload protection: real-time monitoring of the operating power of the permanent magnet propulsion motor and rated power ,when When the permanent magnet propulsion motor is judged to be overloaded, the large model immediately activates the motor protection function and cuts off the power supply in milliseconds to protect the permanent magnet propulsion motor and the entire propulsion system from damage; is the overload factor, The large model dynamically adjusts the overload coefficient according to the real-time operating status and historical data of the permanent magnet propulsion motor. ; S42. Propulsion system fault monitoring: The propulsion system, based on a programmable controller, transmits the status data of the electric propulsion equipment to the large model. When the monitored status data exceeds the normal range, the electric propulsion equipment is determined to be operating abnormally and an alarm signal is immediately issued. The status data includes the current, voltage, and speed of the propulsion motor. S43. Propulsion system fault diagnosis: Build a diagnostic model based on historical fault data. Pre-learn the motor's operating data under different fault conditions. When the motor's speed difference exceeds a threshold, the diagnostic model combines other motor parameters monitored in real time with matching and analysis in the knowledge base to obtain the motor's fault diagnosis results. S5. Safety redundancy of power supply system: monitor and adjust the power quality of DC power distribution system and provide emergency power supply to AC power distribution system; In step S5, the specific process of monitoring and adjusting the power quality of the DC power distribution system is as follows: S51, real-time monitoring of the actual voltage of the DC bus in the DC power distribution system , rated voltage And the voltage fluctuation range allowable value ; S52, when When , the large model starts the regulation mechanism and controls the DC bus voltage output based on the voltage regulation algorithm of proportional-integral-differential control. The calculation formula is: ,in, is the DC bus voltage output; is the proportionality coefficient; is the integration time constant; is the differential time constant; is the voltage deviation, ; is the DC output time; for Voltage value at the moment; For time; S53, the large model dynamically adjusts the 、 、 The value of the DC bus voltage is controlled to control the power regulation device in the DC power distribution system, so as to stabilize the DC bus voltage within the allowable range and improve the quality of the output power. In step S5, the specific process of providing emergency power supply to the AC power distribution system is as follows: S54, monitor the operating status of the AC power distribution system in real time. When the AC power fails, control the emergency power supply to supply power to the propulsion system and key equipment. Assume that the capacity of the emergency power supply is , the output voltage is , the total power demand of the propulsion system and key equipment is , the duration that the emergency power supply can continue to supply power ; S55, the emergency power supply is equipped with an intelligent charging device and control system. The large model automatically adjusts the output power of the emergency power supply according to the real-time changes in the ship's power demand; considering the charging and discharging efficiency of the emergency power supply , the actual power supply , actual continuous power supply time .

[0021] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention 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 the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for energy efficiency management of electric tugboat based on a large model, characterized in that: The following steps are involved: S1. Energy dynamic distribution optimization: Based on the real-time load of the electric tugboat, the energy dynamic distribution is optimized based on the large model; S2. Charging strategy optimization: Optimize the charging time and charging power of the electric tugboat according to the price gradient of the power grid; S3. Safety protection of battery system: real-time monitoring of battery temperature, voltage and current, and early warning protection of the battery; S4. Safety assurance of the propulsion system: real-time monitoring of the propulsion system's operating data, protection of the propulsion system, fault monitoring and fault diagnosis; S5. Safety redundancy of power supply system: monitor and adjust the power quality of DC distribution system, and provide emergency power supply to AC distribution system.

2. The method for energy efficiency management of an electric tugboat based on a large model according to claim 1, characterized in that: The specific process of step S1 is: S11. Based on the large model, the total power of the electric tugboat in different operating scenarios is predicted and analyzed. Propulsion motor power Power with other devices The sum of ; S12. The large model learns the historical operation data of the electric tugboat and analyzes the optimal ratio of propulsion motor power to total power in real time. , Among them, historical operation data includes load weight, sailing speed, water current and wind direction; S13. Propulsion motor power allocated based on analysis , power allocated to other devices , dynamic adjustment value to achieve dynamic power allocation.

3. The method for energy efficiency management of electric tugboat based on a large model according to claim 1, characterized in that: Step S1 also includes battery pack charge and discharge balancing, and the specific process is as follows: S14, the large model monitors the charge and discharge status of the battery pack in real time, assuming that the initial charge state of each battery pack is ;in, , representing 8 groups of batteries; S15: During the discharge process, the discharge current of each battery group is predicted based on the real-time load. and discharge time 1. Combined with the battery capacity , calculate the discharge time The state of charge of each battery group after 1 is calculated as follows: ,in, is the state of charge of the i-th group of batteries; S16. Execute the battery balancing algorithm to adjust the discharge current of each battery group to keep the state of charge of each battery group consistent and reduce the accumulation of performance differences between battery groups. When the state of charge of a battery group is found to be lower than the average value, calculate the reduction in the discharge current of this battery group based on the large model to achieve battery balancing management.

4. The method for energy efficiency management of an electric tugboat based on a large model according to claim 1, characterized in that: The specific process of step S2 is: S21, slow charging mode, large model combined with the initial charge of the battery , battery capacity and slow charge current , predict the time required to fully charge in slow charging mode, the calculation formula is: ,in, The time required to fully charge in slow charging mode; S22, in fast charging mode, the large model monitors the battery temperature in real time ,Voltage and current , establish the charging current change function , by integrating the charging current change function, the time required to fully charge in fast charging mode is predicted. The calculation formula is: ,in, The time required to fully charge in fast charging mode; S23, charging process, assuming the electricity price during the off-peak period is , the peak period electricity price is , Combined with the electricity price information and charging data of the power grid during peak and valley periods, the charging capacity of the electric tugboat is monitored in real time. The charging capacity during the valley period is , the charging amount during peak hours is , calculate the total cost of charging the tugboat ; S24. Based on the large-scale model, the relationship between grid load and tugboat charging power and electricity price differences are analyzed through optimization algorithms to dynamically adjust tugboat charging power. The historical electric tugboat power demand data is analyzed to determine the optimal charging capacity during off-peak hours. , to minimize charging costs.

5. The method for energy efficiency management of an electric tugboat based on a large model according to claim 1, characterized in that: The specific process of step S3 is: S31, the battery temperature data is transmitted to the large model in real time through the temperature sensor, and the large model analyzes the battery temperature data in real time, and sets the critical temperature for battery thermal runaway to be , when the battery temperature When the battery is in a state of thermal runaway, the blocking protection mechanism is immediately activated, and the connection between batteries is cut off through the intelligent fuse or electronic switch; during the thermal runaway process, the heat conduction equation is used to , combined with real-time monitored battery temperature data, to predict thermal runaway risks in advance; is the battery material density; is the specific heat capacity of the battery material; is thermal conductivity; is the internal heat generation rate of the battery; S32, collect and monitor the voltage and current of the single battery in real time. For overvoltage fault, the normal operating voltage range of the battery is , when the voltage of the single battery is monitored in real time satisfy When the battery is judged to have an overvoltage fault, the connection between the batteries is cut off through the intelligent fuse or electronic switch; for overcurrent fault, the rated current of the battery is , when the current of the single battery is monitored in real time satisfy When the battery is judged to have an overcurrent fault, the connection between the batteries is cut off through the intelligent fuse or electronic switch; S33, build Rint model, battery terminal voltage With current , battery internal resistance and open circuit voltage The relationship is , using the data analysis and learning capabilities of the large model, the model parameters are analyzed by the least squares method to determine the battery health status and faults; The data of group terminal voltage and corresponding current are used to find the objective function smallest The value is calculated as follows: ,in, is the terminal voltage of the jth group of batteries; is the current of the jth group of batteries; right Ask about The derivative of and set it to 0: , solve the equation to get the estimated value of the battery internal resistance R.

6. The method for energy efficiency management of an electric tugboat based on a large model according to claim 1, characterized in that: The specific process of step S4 is: S41, permanent magnet propulsion motor overload protection: real-time monitoring of the operating power of the permanent magnet propulsion motor and rated power ,when When the permanent magnet propulsion motor is judged to be overloaded, the large model immediately activates the motor protection function and cuts off the power supply in milliseconds to protect the permanent magnet propulsion motor and the entire propulsion system from damage; is the overload factor, The large model dynamically adjusts the overload coefficient according to the real-time operating status and historical data of the permanent magnet propulsion motor. ; S42. Propulsion system fault monitoring: The propulsion system, based on a programmable controller, transmits the status data of the electric propulsion equipment to the large model. When the monitored status data exceeds the normal range, the electric propulsion equipment is determined to be operating abnormally and an alarm signal is immediately issued. The status data includes the current, voltage, and speed of the propulsion motor. S43. Fault diagnosis of propulsion system: Build a diagnostic model based on fault data in historical data, and pre-learn the operating data of the motor under different fault conditions. When the speed difference of the motor exceeds the threshold, the diagnostic model combines other motor parameters monitored in real time, matches and analyzes them in the knowledge base, and obtains the fault diagnosis result of the motor.

7. The method for energy efficiency management of an electric tugboat based on a large model according to claim 1, characterized in that: In step S5, the specific process of monitoring and adjusting the power quality of the DC power distribution system is as follows: S51, real-time monitoring of the actual voltage of the DC bus in the DC power distribution system , rated voltage And the voltage fluctuation range allowable value ; S52, when When , the large model starts the regulation mechanism and controls the DC bus voltage output based on the voltage regulation algorithm of proportional-integral-differential control. The calculation formula is: ,in, is the DC bus voltage output; is the proportionality coefficient; is the integration time constant; is the differential time constant; is the voltage deviation, ; is the DC output time; for Voltage value at the moment; For time; S53, the large model dynamically adjusts the 、 、 The value of is used to control the power regulation device in the DC distribution system to stabilize the DC bus voltage within the allowable range and improve the quality of the output power.

8. The method for energy efficiency management of an electric tugboat based on a large model according to claim 1, characterized in that: In step S5, the specific process of providing emergency power supply to the AC power distribution system is as follows: S54, monitor the operating status of the AC power distribution system in real time. When the AC power fails, control the emergency power supply to supply power to the propulsion system and key equipment. Assume that the capacity of the emergency power supply is , the output voltage is , the total power demand of the propulsion system and key equipment is , the duration that the emergency power supply can continue to supply power ; S55, the emergency power supply is equipped with an intelligent charging device and control system. The large model automatically adjusts the output power of the emergency power supply according to the real-time changes in the ship's power demand; considering the charging and discharging efficiency of the emergency power supply , the actual power supply , actual continuous power supply time .

Images