Temperature and humidity control method for marine energy storage container

Abstract

The invention discloses a temperature and humidity control method for a marine energy storage container, and relates to the technical field of container temperature and humidity control, and the method comprises the following steps: monitoring the temperature and humidity in the container in real time, and obtaining the real-time environment parameters of the environment in the container through a sensor; through real-time monitoring, an intelligent algorithm and multi-level control, the system dynamically adjusts the temperature and humidity, and the accuracy and the response speed are improved. Different from traditional static setting, the system is combined with sensor data and a prediction model to cope with environment and load changes in advance, temperature and humidity are prevented from exceeding the standard, and equipment faults are reduced. The energy waste is reduced, the energy consumption distribution is optimized, the overall energy efficiency is improved, the cost is reduced, and the safe and stable operation of the equipment is ensured by a regionalized control and global optimization strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of container temperature and humidity control, and in particular to a method for controlling the temperature and humidity of a marine energy storage container. Background Art

[0002] With the continuous development of new energy technologies, especially the increasing application of lithium batteries in the field of ships, all-electric propulsion technology and energy storage systems for ships have developed rapidly. In order to meet the energy needs of modern seagoing ships, a large number of lithium battery packs and supporting electrical equipment are concentrated in the container battery packs on ships. These battery packs and equipment operate in high-sea environments, and the challenges they need to face include changes in temperature and humidity, vibration, and long-term safety of battery packs. Lithium batteries are particularly sensitive to changes in environmental temperature and humidity. Excessive temperature or humidity will lead to intensified electrochemical reactions inside the battery, which will in turn cause battery leakage, corrosion and other problems, seriously affecting the performance and life of the battery, and may even cause safety hazards such as fire. Therefore, how to effectively control the temperature and humidity in the ship container to ensure that the battery pack and electrical equipment operate in a suitable environment has become an important topic in new energy technologies for ships.

[0003] The prior art has the following deficiencies:

[0004] In the prior art, the temperature and humidity control system of marine energy storage containers usually adopts a simple adjustment mechanism based on a preset temperature and humidity range. However, this approach ignores the dynamic characteristics of temperature and humidity fluctuations, especially in harsh marine environments, where rapid changes in temperature and humidity may exceed the adjustment capabilities of traditional temperature and humidity control systems. Once drastic temperature and humidity fluctuations occur (for example, failure of the temperature control system due to sudden climate change or equipment failure), lithium batteries may be exposed to extreme environmental conditions, causing abnormal intensification of internal electrochemical reactions. At this time, a sharp increase in gas pressure inside the battery may trigger a thermal runaway reaction, causing battery leakage, fire, or even explosion, posing serious safety hazards to ships and crew members.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method for controlling temperature and humidity of a ship energy storage container. Through the combination of real-time monitoring, intelligent algorithms and multi-level control, the system can dynamically adjust the temperature and humidity to improve accuracy and response speed. Different from the traditional static setting, the solution combines sensor data with the prediction model to adjust the control strategy in real time, respond to environmental changes and equipment load fluctuations in advance, avoid excessive temperature and humidity, and reduce equipment failures. By adopting regionalized temperature and humidity control and global optimization strategies, the system can accurately adjust the temperature and humidity requirements of each area, reduce energy waste, and improve overall energy efficiency by optimizing energy consumption distribution, thereby reducing operating costs, ensuring safe and stable operation of equipment, and meeting the energy management needs of ships to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for controlling temperature and humidity of a marine energy storage container, comprising the following steps:

[0008] Monitor the temperature and humidity in the container in real time, and obtain the real-time environmental parameters of the environment in the container through sensors;

[0009] Set temperature and humidity control thresholds. Based on the operating requirements of lithium batteries and electrical equipment, set appropriate temperature and humidity ranges, and adjust the set thresholds based on real-time data in the container to cope with dynamically changing environmental conditions;

[0010] According to the deviation between the real-time monitoring data and the set threshold, the temperature and humidity control equipment is adjusted to keep the temperature and humidity in the container within a safe range at all times;

[0011] When the temperature and humidity in the container fluctuate sharply, the working state of the control equipment is adjusted in advance in combination with the prediction algorithm of environmental changes to prevent excessive fluctuations in temperature and humidity from causing harm to lithium batteries and electrical equipment;

[0012] Based on the pattern of temperature and humidity fluctuations, an adaptive control algorithm is used to optimize and adjust the equipment according to the historical temperature and humidity change rules to improve the responsiveness and accuracy of the temperature and humidity control system and ensure the safe operation of battery packs and electrical equipment under extreme conditions.

[0013] Preferably, the temperature and humidity in the container are monitored in real time, and the specific steps of obtaining the real-time environmental parameters of the environment in the container through sensors are as follows:

[0014] First, the sensor will continuously collect environmental data inside the container through its own measurement mechanism;

[0015] Once the sensor acquires the raw environmental data, these analog signals are converted into digital signals through a built-in analog-to-digital converter;

[0016] When the digital signals are successfully transmitted to the data receiving unit, these data will enter the real-time data storage module;

[0017] As time goes by, the sensors continue to collect new environmental data periodically, updating the parameters in the existing data store in real time.

[0018] Preferably, the temperature and humidity control thresholds are set, based on the operating requirements of the lithium battery and electrical equipment, the appropriate temperature and humidity range is set, and the set thresholds are adjusted according to the real-time data in the container to cope with the dynamic changes in environmental conditions. The specific steps are as follows:

[0019] At this stage, an initial temperature and humidity control range is first determined based on the working requirements of lithium batteries and electrical equipment;

[0020] The real-time monitoring system continuously obtains temperature and humidity data inside the container through sensors, providing a basis for subsequent threshold adjustments;

[0021] In order to cope with the severe weather and complex environmental conditions that ships may encounter when sailing at sea, the system dynamically adjusts the control range of temperature and humidity through real-time analysis of temperature and humidity data in the container;

[0022] Continuous evaluation and feedback must be provided throughout the entire process of real-time monitoring and threshold setting of container temperature and humidity.

[0023] Preferably, according to the deviation between the real-time monitoring data and the set threshold, the temperature and humidity control equipment is adjusted to keep the temperature and humidity in the container within a safe range. The specific steps are as follows:

[0024] Compare the real-time temperature and humidity data obtained by the sensor with the previously set thresholds;

[0025] When a deviation between the temperature and humidity and the set threshold is detected, the working state of the temperature and humidity control device is adjusted according to the size and direction of the deviation;

[0026] In order to improve the intelligent level of temperature and humidity regulation, an adaptive adjustment mechanism is adopted to adjust the control equipment more finely according to historical data, environmental change patterns and current workload;

[0027] While adjusting the temperature and humidity control equipment, the environmental data inside the container is continuously monitored, and the adjustment strategy is further optimized based on new data feedback.

[0028] Preferably, when the temperature and humidity in the container fluctuate sharply, the working state of the control device is adjusted in advance in combination with the prediction algorithm of environmental changes to prevent excessive fluctuations in temperature and humidity from causing harm to lithium batteries and electrical equipment. The specific steps are as follows;

[0029] First, obtain the real-time temperature and humidity data in the container. Assume that the sensor sampling period is Δt. Each collected data contains the instantaneous value of temperature and humidity. Next, by using the time series analysis method, calculate the change trend of temperature and humidity data over the past period of time. By calculating the trend slope, the change rate of temperature and humidity is obtained. The calculation expression is as follows:

[0030]

[0031] Where ΔT represents the change in temperature in the container within the time interval Δt, that is, the temperature difference from time t to time t+Δt, T(t) is the temperature value inside the container at time t, ΔH is the change in humidity in the container within the time interval Δt, that is, the humidity difference from time t to time t+Δt, H(t) is the humidity value inside the container at time t, is the rate of temperature change, is the rate of change of humidity;

[0032] After identifying the trend of temperature and humidity changes through the above analysis, the weighted regression model is then used to predict the temperature and humidity changes in the future. When predicting the future value of temperature and humidity changes, the model performs weighted calculations on the recent historical data to obtain the future temperature and humidity change forecast. The calculation expression is as follows:

[0033] In the formula, is the predicted temperature value at the future time point t+Δt, w i is the weight coefficient, T(t-iΔt) represents the temperature data before the past i time points, the unit time interval is Δt, n is the total number of time points, α is the weight coefficient of the temperature change rate, is the predicted humidity value at the future time point t+Δt, H(t-iΔt) represents the humidity data before the past i time points, the unit time interval is Δt, and β is the weight coefficient of the humidity change rate;

[0034] According to the temperature and humidity change trend obtained by the prediction algorithm, the working state of the temperature and humidity control equipment is adjusted in advance according to the preset safety threshold. The calculation expression is as follows:

[0035]

[0036]

[0037] Where U cool (t) is the temperature control instruction, It is the proportional gain part, which is used to control the response intensity during the temperature adjustment process. maxis the maximum safe threshold of temperature, It is the temperature integral control part, Represents the accumulation of temperature deviations over a period of time, K i is the integral gain, which controls the influence of past deviations on the current control strategy. It is the temperature data before the predicted temperature j time points in the future, with a unit time interval of Δt. is the temperature differential gain, K d is the differential gain coefficient, U humid (t) is the humidity control instruction, It is the humidity proportional control part, which is used to control the response intensity during the humidity adjustment process. max is the maximum safe threshold of humidity, It is the humidity integral control part. Represents the accumulation of humidity deviations over a period of time. is the humidity differential gain;

[0038] After implementing the adjustment strategy, the temperature and humidity changes are continuously tracked, and the control effect is fed back and optimized in real time. Specifically, the control strategy is optimized through a dynamic optimization algorithm. The calculation expression is as follows: In the formula, f opt is the optimization objective function, T target is the target temperature value, H target is the set target humidity value, A and B are weighted coefficients, A controls the priority of temperature adjustment, and B controls the priority of humidity adjustment.

[0039] Preferably, according to the temperature and humidity fluctuation mode, an adaptive control algorithm is used to optimize equipment adjustment in combination with historical change rules to improve the response speed and accuracy of the temperature and humidity control system and ensure the safe operation of battery packs and electrical equipment under extreme conditions. The specific steps are as follows:

[0040] First, the historical temperature and humidity data are analyzed to extract the pattern characteristics of temperature and humidity fluctuations. By statistically modeling the temperature and humidity changes over a period of time, the laws and periodic characteristics of environmental changes are identified. After extracting the historical temperature and humidity fluctuation patterns, the frequency components of temperature and humidity fluctuations are calculated and defined as the periodic change frequency of temperature and humidity. The calculation expression is as follows:

[0041]

[0042]

[0043] In the formula, ω T is the frequency component of the temperature data, T(t l) is the temperature value at the lth moment in the historical data, t l is the lth time point t, is the mean of the temperature data, T period is the time period of temperature fluctuation, N is the total number of time points, ω H is the frequency component of humidity data, H(t l ) is the humidity value at the lth moment in the historical data, is the mean of the humidity data, H period is the time period of humidity fluctuation;

[0044] After obtaining the periodic fluctuation characteristics of temperature and humidity, based on the frequency information of periodic fluctuations and combined with changes in the external environment, the temperature and humidity change trend at a certain moment in the future is predicted, and the periodic fluctuations of historical data are predicted using a fitting function. The calculation expression is as follows:

[0045]

[0046] Where, T pred (t) is the predicted temperature value, which means the predicted temperature value at time point t. pred (t) is the humidity prediction value, which means the humidity value predicted at time point t;

[0047] After predicting the future temperature and humidity, compare it with the real-time monitored environmental data and calculate the temperature and humidity error. The calculation expression is as follows: ΔT(t) = T measured (t)-T pred (t), ΔH(t)=H measured (t)-H pred (t), where ΔT(t) is the temperature error, ΔH(t) is the humidity error, and T measured (t) is the real-time temperature data, H measured (t) is the real-time humidity data;

[0048] The error obtained through calculation is used to optimize the adjustment force of the equipment through adaptive control algorithm. The specific adjustment control amount calculation expression is as follows:

[0049]

[0050] Where U T (t) is the adjustment amount calculated by the PID control algorithm based on the temperature error, U H (t) is the adjustment amount calculated by the PID control algorithm based on the humidity error, K P is the proportional gain, K I is the integral gain, K d is the differential gain;

[0051] After calculating the control quantity I T (t) and I H (t), the working state of the equipment is adjusted in real time according to the control quantity to ensure that the temperature and humidity in the container are maintained within a safe range. At the same time, the effect of the control strategy is evaluated through continuous real-time feedback, and the control strategy is optimized according to the new real-time temperature and humidity data. The calculation expression is as follows:

[0052]

[0053] Where, T max and T min are the maximum and minimum temperature respectively, H max and H min are the maximum and minimum humidity values ​​respectively, E is the dynamic adjustment coefficient, R is the adjustment coefficient of the integral gain, Z is the adjustment coefficient of the differential gain, and K P (t) is the proportional gain at time point t, K I (t) is the integral gain at time point t, K d (t) is the differential gain at time point t.

[0054] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0055] Through the combination of real-time monitoring, intelligent algorithms and multi-level control, the present invention enables the system to make timely adjustments based on the dynamic changes of temperature and humidity, significantly improving the accuracy and response speed of temperature and humidity control. Unlike traditional temperature and humidity adjustment methods, the solution combines sensor data with prediction models so that temperature and humidity adjustment no longer relies on static set values, but can adjust the control strategy in real time according to environmental fluctuations and equipment load. For example, through machine learning and intelligent prediction algorithms, the system can identify the potential impact of external climate changes, equipment load fluctuations and other factors on environmental temperature and humidity in advance, so as to take measures in advance to prevent temperature and humidity from exceeding the safe range and avoid equipment damage or battery failure. This real-time feedback and dynamic adjustment mechanism ensures that the temperature and humidity are always maintained at the optimal state in complex environments, greatly reducing the equipment failure rate.

[0056] The present invention uses multi-level control and optimization strategies to make temperature and humidity regulation not only more accurate, but also optimize resource utilization and improve the energy efficiency of the system. During the implementation process, the system adopts a temperature and humidity adjustment method based on regional division, so that the temperature and humidity requirements of each area are independently controlled, thereby avoiding the impact of temperature and humidity fluctuations on other areas. This refined management method can be dynamically adjusted according to the actual needs of different areas to avoid unnecessary energy waste. At the same time, combined with the global optimization algorithm, the system can dynamically balance the energy consumption of each area, reasonably allocate the load of the temperature and humidity control equipment, and maximize the overall energy efficiency of the system. In this way, not only the safe operation of the equipment is guaranteed, but also the energy consumption is reduced, and the overall economic benefits of the temperature and humidity control system are improved, which meets the needs of modern ship energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0058] Figure 1 The present invention is a method flow chart of a method for controlling temperature and humidity of a marine energy storage container. DETAILED DESCRIPTION

[0059] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0060] The present invention provides Figure 1 A temperature and humidity control method for a marine energy storage container is shown, comprising the following steps:

[0061] Monitor the temperature and humidity in the container in real time, and obtain the real-time environmental parameters of the environment in the container through sensors;

[0062] Real-time monitoring of the temperature and humidity inside the container, and obtaining the real-time environmental parameters of the environment inside the container through sensors. The specific steps are as follows:

[0063] First, the sensor will continuously collect environmental data inside the container through its own measurement mechanism (such as thermocouples, infrared temperature sensors or humidity capacitance sensors, etc.);

[0064] These sensors convert external environmental information into digital signals through physical changes (such as changes in electrical signals caused by temperature changes or changes in capacitance caused by humidity changes), reflecting temperature, humidity and other environmental parameters (such as air pressure, air flow rate, etc.) in real time. In this process, the sensor continuously samples at specific time intervals, converting environmental data into digital information in real time for subsequent processing systems. At this time, the sensor is in monitoring mode, and the acquisition frequency is usually set by the system to ensure that the data can accurately reflect the dynamic changes of the environment.

[0065] Once the sensor acquires the raw environmental data, these analog signals (temperature, humidity and other parameters) are converted into digital signals through the built-in analog-to-digital converter (ADC);

[0066] Signal conversion is essential because digital signals facilitate subsequent transmission, processing and analysis. The converted digital data will be sent to the data receiving unit through a communication interface (such as serial communication, I2C, CAN bus, etc.). These data transmission processes are very important. It is necessary to ensure that the signal is not disturbed during the transmission process to avoid data loss, delay or error, and ensure that the system can accurately obtain real-time environmental data.

[0067] When the digital signals are successfully transmitted to the data receiving unit, these data will enter the real-time data storage module;

[0068] This data will be stored for a short period of time for immediate reading, processing and analysis. In some advanced systems, some preprocessing will be performed, such as simple noise filtering or removal of extreme data (such as outliers when sensors fail). The purpose of this step is to ensure that the data is stored efficiently and available at any time so that control decisions can be made based on real-time monitoring data. During the storage process, the system will set an appropriate cache time to ensure that the data is not lost and to provide sufficient data support for subsequent data processing.

[0069] As time goes by, the sensors continue to collect new environmental data periodically, updating the parameters in the existing data storage in real time;

[0070] These new data will replace the old data or in some cases perform data synthesis (such as time-weighted averaging, filtering, etc.). During the update process, the real-time monitoring system will continuously exchange data with the control system. Through the feedback link, the system can make corresponding environmental control decisions based on the current temperature and humidity data. At this time, the speed and accuracy of data updates determine the response speed of the temperature and humidity control system. Effective data updates and timely feedback ensure that the system can adapt to rapid changes in the environment and maintain the temperature and humidity in the container within the set range by adjusting the working status of the equipment.

[0071] Set temperature and humidity control thresholds. Based on the operating requirements of lithium batteries and electrical equipment, set appropriate temperature and humidity ranges, and adjust the set thresholds based on real-time data in the container to cope with dynamically changing environmental conditions;

[0072] Set the temperature and humidity control thresholds, set the appropriate temperature and humidity range based on the operating requirements of lithium batteries and electrical equipment, and adjust the set thresholds according to the real-time data in the container to cope with dynamically changing environmental conditions. The specific steps are as follows:

[0073] At this stage, an initial temperature and humidity control range is first determined based on the working requirements of lithium batteries and electrical equipment;

[0074] The safe operating temperature of lithium batteries is usually set at 15℃ to 35℃, and the humidity is controlled between 40% and 60%. In order to ensure the long life and high performance of the battery, these ranges are designed as safe areas to protect the battery from extreme environmental influences. The temperature and humidity requirements of electrical equipment are usually more relaxed, but they also need to prevent overheating or overhumidification. This initial range is set based on the long-term experimental data of the battery and equipment and the manufacturer's requirements, and is a static set value. The key to this step is to ensure that the set range can ensure the basic operating safety of the equipment and prevent failures under normal conditions.

[0075] The real-time monitoring system continuously obtains temperature and humidity data inside the container (such as temperature, humidity, air pressure and other environmental parameters) through sensors, providing a basis for subsequent threshold adjustments;

[0076] At this stage, the control system will dynamically adjust the initially set temperature and humidity thresholds based on real-time monitoring data. For example, if the real-time monitoring detects that the ambient temperature is too high or the humidity is too high, the control system will immediately calculate and fine-tune the control thresholds to adapt to the current environment. The adjustment of the thresholds can take into account factors such as historical data trends, equipment load changes, and external weather conditions. This step ensures that the temperature and humidity control system can respond flexibly as the environment changes, avoiding temperature and humidity exceeding the safe range due to drastic climate changes or equipment failures.

[0077] In order to cope with the severe weather and complex environmental conditions that ships may encounter when sailing at sea, the system dynamically adjusts the control range of temperature and humidity through real-time analysis of temperature and humidity data in the container;

[0078] When the system detects a sudden drop in external temperature, the control system will automatically adjust the lower limit of temperature and humidity to cope with the dramatic change in the environment; if the humidity is too high, the system will appropriately adjust the upper limit of the humidity control range to prevent the battery from being affected by excessive humidity. In addition, the system will also optimize according to the temperature and humidity change rules in different time periods or navigation areas, making temperature and humidity control more flexible and accurate, thereby improving the system's adaptability in various environments.

[0079] Throughout the process of real-time monitoring and threshold setting of container temperature and humidity, continuous evaluation and feedback must be provided;

[0080] Whenever the system makes a threshold adjustment, it compares it with the current environmental data to confirm whether the adjustment is effective. Through the feedback mechanism, the system can automatically evaluate whether the threshold needs to be further optimized to ensure that the temperature and humidity control system can respond quickly to environmental changes in harsh offshore environments. For example, when the temperature approaches the upper limit, the system may activate an early warning mechanism to prompt the operator to adjust the equipment. Through this real-time evaluation and feedback, the system can continuously optimize itself and automatically adjust the temperature and humidity control thresholds when faced with different weather conditions, thereby effectively protecting the safe operation of lithium batteries and electrical equipment.

[0081] According to the deviation between the real-time monitoring data and the set threshold, the temperature and humidity control equipment is adjusted to keep the temperature and humidity in the container within a safe range at all times;

[0082] According to the deviation between the real-time monitoring data and the set threshold, adjust the temperature and humidity control equipment to keep the temperature and humidity in the container within a safe range. The specific steps are as follows:

[0083] Compare the real-time temperature and humidity data obtained by the sensor with the previously set thresholds;

[0084] By comparing the current environmental data in the container with the upper and lower limits of the safety range, the system can quickly identify deviations in temperature and humidity. The size of the deviation directly determines the adjustment range of the subsequent control equipment. For example, if the current temperature is higher than the set upper threshold, the system will immediately trigger the temperature control equipment (such as air conditioning or cooling equipment); if the humidity exceeds the set range, the humidity control equipment (such as a dehumidifier or humidifier) ​​will start accordingly. This step is the basis for temperature and humidity regulation, ensuring that the system can respond to environmental changes in real time and always maintain the suitability of the environment.

[0085] When a deviation between the temperature and humidity and the set threshold is detected, the working state of the temperature and humidity control device is adjusted according to the size and direction of the deviation;

[0086] If the temperature exceeds the set upper limit, the air conditioning system will increase the cooling power to reduce the temperature inside the container; if the temperature is lower than the set lower limit, the system will start the on-board heating device to heat and restore the temperature to a safe range. In terms of humidity control, if the humidity exceeds the upper limit, the dehumidifier will increase its working intensity; on the contrary, if the humidity is too low, the humidity regulator will turn on the humidification function to increase the air humidity. The adjustment of these control devices depends on the system's rapid calculation of real-time deviations to ensure timely and accurate temperature and humidity adjustment.

[0087] In order to improve the intelligent level of temperature and humidity regulation, an adaptive adjustment mechanism is adopted to adjust the control equipment more finely according to historical data, environmental change patterns and current workload;

[0088] If the system finds that the temperature of the container fluctuates greatly over a period of time, it may adjust the air conditioning operation strategy, such as increasing the pre-cooling or pre-heating time to adapt to external environmental changes in advance. The system will not only respond to instantaneous deviations, but also consider long-term environmental fluctuation trends to reduce the negative impact of frequent adjustments on battery packs and equipment. In addition, the intelligent control system may use algorithms (such as PID control algorithms) to automatically optimize the adjustment range to make temperature and humidity adjustments smoother and avoid energy waste or equipment loss caused by excessive adjustments.

[0089] While adjusting the temperature and humidity control equipment, continuously monitor the environmental data inside the container and further optimize the adjustment strategy based on new data feedback;

[0090] This means that even if the environmental data improves after the initial adjustment, the system will still regularly check whether the temperature and humidity are stable within the safe range. If the environment in the container continues to change, the system will adjust the equipment again based on the new real-time data. This step ensures the self-adjustment ability of the temperature and humidity control system through a continuous feedback mechanism to adapt to different environmental conditions. Especially in the dynamic marine environment, the continuous monitoring and adjustment capabilities of the temperature and humidity control system can effectively avoid potential damage to lithium batteries and electrical equipment caused by environmental fluctuations.

[0091] When the temperature and humidity in the container fluctuate sharply, the working state of the control equipment is adjusted in advance in combination with the prediction algorithm of environmental changes to prevent excessive fluctuations in temperature and humidity from causing harm to lithium batteries and electrical equipment;

[0092] When the temperature and humidity in the container fluctuate sharply, the working state of the control equipment is adjusted in advance in combination with the prediction algorithm of environmental changes to prevent excessive fluctuations in temperature and humidity from causing harm to lithium batteries and electrical equipment. The specific steps are as follows;

[0093] First, obtain the real-time temperature and humidity data in the container. Assume that the sensor sampling period is Δt. Each collected data contains the instantaneous value of temperature and humidity. Next, by using the time series analysis method, calculate the change trend of temperature and humidity data over the past period of time. By calculating the trend slope, the change rate of temperature and humidity is obtained. The calculation expression is as follows:

[0094]

[0095] Where ΔT represents the change in temperature in the container within the time interval Δt, that is, the temperature difference from time t to time t+Δt, T(t) is the temperature value inside the container at time t, ΔH is the change in humidity in the container within the time interval Δt, that is, the humidity difference from time t to time t+Δt, H(t) is the humidity value inside the container at time t, is the rate of temperature change, is the rate of change of humidity;

[0096] By calculating the change rate of temperature and humidity, the change amount of temperature and humidity in each sampling period is calculated and divided by the sampling period Δt, and the change rate per unit time is obtained, which is used to represent the fluctuation speed of temperature and humidity inside the container.

[0097] After identifying the trend of temperature and humidity changes through the above analysis, a weighted regression model (such as weighted least squares, Weighted Least Squares, WLS) is then used to predict the temperature and humidity changes in the future. When predicting the future value of temperature and humidity changes, the model performs a weighted calculation on the recent historical data (temperature and humidity change rate) to obtain the future temperature and humidity change prediction. The calculation expression is as follows:

[0098] In the formula, is the predicted temperature value at the future time point t+Δt, w i is the weight coefficient, T(t-iΔt) represents the temperature data before the past i time points, the unit time interval is Δt, n is the total number of time points, α is the weight coefficient of the temperature change rate, which represents the impact of the temperature change rate on future temperature prediction, is the predicted humidity value at the future time point t+Δt, H(t-iΔt) represents the humidity data before the past i time points, with the unit time interval being Δt, and β is the weight coefficient of the humidity change rate, which represents the impact of the humidity change rate on future humidity prediction;

[0099] w i It is the weight coefficient of the historical data point, which is used to indicate the importance of each historical data point when predicting future temperature and humidity values. Its function is to dynamically adjust the impact of past data on future predictions according to the changing characteristics of time and environment. Usually, the most recent temperature and humidity data (data closer to the current moment) are given a higher weight, while data farther from the current moment are given a lower weight. Through this weighting strategy, the system can respond more sensitively to recent changes in temperature and humidity, avoid over-reliance on long-term data, thereby improving the accuracy and real-time nature of the prediction, and ensuring that the temperature and humidity control system can adjust the equipment in a timely manner to prevent environmental fluctuations from causing potential safety risks to lithium batteries and electrical equipment.

[0100] According to the temperature and humidity change trend obtained by the prediction algorithm, the working state of the temperature and humidity control equipment is adjusted in advance according to the preset safety threshold. The calculation expression is as follows:

[0101]

[0102]

[0103] Where U coo l(t) is the temperature control instruction, which means adjusting the intensity of air conditioning and other equipment to adjust the temperature inside the container. It is the proportional gain part, which is used to control the response intensity during the temperature adjustment process. max is the maximum safe threshold of temperature, It is the temperature integral control part, Represents the accumulation of temperature deviations over a period of time, K i is the integral gain, which controls the influence of past deviations on the current control strategy. (t+jΔt) is the temperature data before the predicted temperature at the jth time point in the future, with the unit time interval being Δt. is the temperature differential gain, K d is the differential gain factor, which controls the effect of the rate of temperature change and helps prevent over-response to temperature fluctuations. humid (t) is the humidity control instruction, which means adjusting the working intensity of the humidifier or dehumidifier to adjust the humidity in the container. It is the humidity proportional control part, which is used to control the response intensity during the humidity adjustment process. max is the maximum safe threshold of humidity, It is the humidity integral control part. Represents the accumulation of humidity deviations over a period of time. is the humidity differential gain;

[0104] After implementing the adjustment strategy, the temperature and humidity changes are continuously tracked, and the control effect is fed back and optimized in real time. Specifically, the control strategy is optimized through a dynamic optimization algorithm (such as a genetic algorithm or a particle swarm optimization algorithm, PSO). The calculation expression is as follows:

[0105] In the formula, f opt is the optimization objective function, T target It is the target temperature value, which is usually set according to the optimal operating temperature of lithium batteries and electrical equipment. target It is the target humidity value, which is usually set according to the optimal operating environment of the equipment and the safety requirements of the lithium battery. A and B are weighted coefficients. A controls the priority of temperature adjustment, and B controls the priority of humidity adjustment.

[0106] According to the temperature and humidity fluctuation pattern, an adaptive control algorithm is used to optimize and adjust the equipment according to the historical temperature and humidity change rules to improve the responsiveness and accuracy of the temperature and humidity control system and ensure the safe operation of battery packs and electrical equipment under extreme conditions;

[0107] According to the temperature and humidity fluctuation pattern, the adaptive control algorithm is used in combination with the historical change law to optimize the equipment adjustment, improve the response speed and accuracy of the temperature and humidity control system, and ensure the safe operation of battery packs and electrical equipment under extreme conditions. The specific steps are as follows:

[0108] First, the historical temperature and humidity data are analyzed to extract the pattern characteristics of temperature and humidity fluctuations. By statistically modeling the temperature and humidity changes over a period of time, the laws and periodic characteristics of environmental changes are identified. After extracting the historical temperature and humidity fluctuation patterns, the frequency components of temperature and humidity fluctuations are calculated and defined as the periodic change frequency of temperature and humidity. The calculation expression is as follows:

[0109]

[0110] In the formula, ω T is the frequency component of the temperature data, T(t l ) is the temperature value at the lth moment in the historical data, t l is the lth time point t, is the mean of the temperature data, T period is the time period of temperature fluctuation, N is the total number of time points, ω H is the frequency component of humidity data, H(t l ) is the humidity value at the lth moment in the historical data, is the mean of the humidity data, H period is the time period of humidity fluctuation;

[0111] After obtaining the periodic fluctuation characteristics of temperature and humidity, the next step is to use these characteristics to predict the future temperature and humidity. Based on the frequency information of periodic fluctuations and combined with changes in the external environment, the trend of temperature and humidity changes at a certain moment in the future is predicted. Fitting functions such as weighted least squares or exponentially weighted average are used to predict the periodic fluctuations of historical data. The calculation expression is as follows:

[0112]

[0113] Where, T pred (t) is the predicted temperature value, which means the predicted temperature value at time point t. pred (t) is the humidity prediction value, which means the humidity value predicted at time point t;

[0114] After predicting the future temperature and humidity, compare it with the real-time monitored environmental data and calculate the temperature and humidity errors. These errors reflect the difference between the current temperature and humidity and the predicted values. The calculation expression is as follows: ΔT(t) = T measured (t)-T pred (t), ΔH(t)=H measured (t)-H pred (t), where ΔT(t) is the temperature error, ΔH(t) is the humidity error, and T measured (t) is the real-time temperature data, H measured (t) is the real-time humidity data;

[0115] The error obtained through calculation is used to optimize the adjustment strength of the equipment through adaptive control algorithms (such as PID control). The specific adjustment control amount calculation expression is as follows:

[0116]

[0117] Where U T (t) is the adjustment amount calculated by the PID control algorithm based on the temperature error (i.e., the difference between the current temperature and the predicted temperature), U H (t) is the adjustment amount calculated by the PID control algorithm based on the humidity error (i.e., the difference between the current humidity and the predicted humidity), K P is the proportional gain, K I is the integral gain, K d is the differential gain;

[0118] After calculating the control quantity U T (t) and U H (t), the working state of the equipment is adjusted in real time according to the control quantity to ensure that the temperature and humidity in the container are maintained within a safe range. At the same time, the effect of the control strategy is evaluated through continuous real-time feedback, and the control strategy is optimized according to the new real-time temperature and humidity data. The calculation expression is as follows:

[0119]

[0120] Where, T max and T min are the maximum and minimum temperature respectively, H max and H min are the maximum and minimum humidity values ​​respectively, E is the dynamic adjustment coefficient, which is used to adjust the proportional gain according to the size of the real-time temperature and humidity error and the control requirements, R is the adjustment coefficient of the integral gain, which determines the importance of the integral term in the control strategy, Z is the adjustment coefficient of the differential gain, which is used to adjust the influence of the differential term, and K P(t) is the proportional gain at time point t, which is used to determine the response intensity of the system to temperature and humidity errors, K I (t) is the integral gain at time point t, which is used to eliminate the persistent small deviations so that the system can maintain near the target value for a long time. K d (t) is the differential gain at time point t, which is used to suppress the oscillation or over-adjustment of the system and adjust the control amount based on the rate of change of temperature and humidity errors;

[0121] Implementation method 1: By building a multi-point sensor network system, the environmental parameters in the marine energy storage container are monitored in real time, and the temperature and humidity are intelligently adjusted in combination with the early warning mechanism. The core of this method is to provide continuous and comprehensive environmental data collection through the sensor network, ensuring that the system can accurately understand the temperature and humidity conditions in each area of ​​the container, and respond intelligently based on the deviation between the real-time data and the set threshold.

[0122] First, the sensor network is distributed in multiple areas of the container, including key locations such as near lithium battery packs, electrical equipment areas, and air circulation areas. Each sensor continuously monitors temperature and humidity data and transmits the data to a centralized control system. The control system collects environmental information transmitted by the sensor in real time through an integrated data acquisition unit. This process ensures that the system fully understands the temperature and humidity conditions at different locations in the container, avoiding monitoring blind spots caused by uneven environmental distribution or unreasonable sensor locations in traditional solutions.

[0123] After acquiring real-time data, the control system will compare this data with the preset safety thresholds. The set temperature and humidity thresholds are based on the working requirements of lithium batteries and the tolerance of electrical equipment. Usually, lithium batteries require the temperature range to be maintained between 15°C and 35°C, and the humidity to be controlled between 40% and 60%. When the system detects that the temperature and humidity data exceed this range, it immediately triggers the early warning mechanism and sends a warning message to the crew or operator to take measures in advance to avoid safety hazards caused by excessive fluctuations in temperature and humidity. The early warning information not only includes the size of the temperature and humidity deviation, but also can determine the potential causes and response strategies of the problem based on the specific location and real-time data fed back by the sensor.

[0124] Once the system detects a deviation in temperature and humidity, the control system will automatically adjust air conditioners, dehumidifiers, humidifiers and other equipment. Taking air conditioning as an example, if the temperature exceeds the set safety range, the air conditioning's cooling function will be activated, or heating will be adjusted according to actual needs; if the humidity exceeds the preset range, the dehumidifier will start to reduce the humidity in the air and ensure that lithium batteries and electrical equipment are protected from damage by high humidity. At the same time, in order to improve control accuracy, the adjustment strategies of air conditioners and dehumidifiers are optimized based on dynamic changes monitored in real time. For example, if the temperature and humidity in the container fluctuate greatly, the control system may prevent excessive changes by starting the air conditioner or dehumidification equipment in advance, thereby reducing energy waste caused by frequent start and stop of equipment.

[0125] In order to further improve the regulation efficiency, this implementation method introduces an environmental prediction algorithm and a pre-adjustment mechanism. The system collects external meteorological data (such as wind speed, temperature changes, etc.) and combines historical data to model and predict the laws of temperature and humidity fluctuations inside the container. Based on these predictions, the system can identify environmental changes that may affect temperature and humidity control in advance, and start the corresponding control equipment in advance. For example, when a sudden change in the climate at sea is expected, the system can start the air conditioning and dehumidification equipment before the external environment changes drastically, thereby reducing the impact on the battery pack. This advance prediction and response mechanism effectively improves the system's ability to cope with complex marine environments and avoids potential risks to lithium batteries caused by temperature and humidity fluctuations.

[0126] Through the combination of multi-sensor networks and intelligent early warning mechanisms, this implementation can efficiently respond to complex changes in the environment inside and outside the container, ensuring that lithium batteries and electrical equipment operate in a safe and stable environment, while significantly improving the system's degree of automation and intelligent response capabilities.

[0127] Implementation method 2: Using machine learning technology, combined with real-time temperature and humidity data collected by sensors, intelligently predict and dynamically adjust the temperature and humidity fluctuations in the container. Compared with the traditional rule-based control method, machine learning can automatically discover the temperature and humidity change rules based on historical data, and automatically adjust the control strategy according to the current environmental changes, achieving more accurate and efficient temperature and humidity regulation.

[0128] During the implementation process, a large amount of historical data is first required for training. The machine learning model will learn the laws of temperature and humidity changes by analyzing the changing trends of temperature and humidity under different environmental conditions. These data include external meteorological data, historical temperature and humidity data inside the container, battery load conditions, and ship navigation status. Based on these historical data, the system can establish a model between temperature and humidity and environmental changes through algorithms. This model can not only predict the changing trends of temperature and humidity, but also identify some potential abnormal patterns, such as temperature and humidity changes caused by climate change and equipment failure.

[0129] By updating these models in real time, the system can continuously adjust the temperature and humidity control strategy. For example, if the system detects that the external temperature is about to rise, and based on historical data, it is inferred that the temperature and humidity inside the container will also change accordingly, the machine learning model can start the air conditioning equipment in advance to cool down. At the same time, when the humidity is too high, the system will also start the dehumidifier in advance for drying based on the humidity trend predicted by the model. In this process, the machine learning algorithm can automatically optimize the control strategy based on the real-time temperature and humidity data, making the temperature and humidity control more accurate.

[0130] In addition, the machine learning system also has the functions of self-learning and self-optimization. After each temperature and humidity adjustment, the system will collect new data and evaluate the effectiveness of the adjustment strategy through a feedback mechanism. If the system finds that some predictions or adjustment methods are not accurate enough, it will automatically adjust and optimize. As the system continues to run and data accumulates, the machine learning model can gradually improve the accuracy of predictions and the efficiency of temperature and humidity control, thereby reducing manual intervention and improving the automation and intelligence level of the system.

[0131] By introducing machine learning technology, the second implementation method can effectively improve the flexibility and accuracy of temperature and humidity adjustment, avoid the lag and errors that may exist in traditional control methods, and provide a more intelligent and efficient temperature and humidity control solution for marine energy storage containers.

[0132] Implementation method 3: A multi-level temperature and humidity control strategy is adopted, which aims to manage the temperature and humidity in different areas of the container in layers to ensure that each area can be controlled most appropriately according to its specific needs. This solution mainly improves the accuracy and response speed of temperature and humidity adjustment by combining regional temperature and humidity management with global optimization strategy.

[0133] First, this embodiment divides the interior of the container into multiple areas, including key areas such as areas near lithium battery packs, electrical equipment areas, and general storage areas. These areas are designed with their respective special needs in mind. For example, the area near the lithium battery pack has stricter requirements on temperature and humidity, while the general storage area has relatively loose requirements on temperature and humidity. In each area, independent temperature and humidity sensors and control devices are installed to ensure that the temperature and humidity of each area are always maintained within a safe range through local adjustment. This regionalized management method can avoid the problem of uneven environment in traditional centralized adjustment and improve the accuracy of temperature and humidity control.

[0134] On the basis of local adjustment, the system will also perform global optimization. Through integrated algorithms, such as particle swarm optimization or genetic algorithm, the system will optimize the scheduling of control equipment according to the real-time data and temperature and humidity fluctuations in each area. For example, if the temperature and humidity in a certain area fluctuate abnormally, the system will dynamically adjust the operating status of the temperature and humidity control equipment in that area, and allocate overall resources according to the temperature and humidity requirements of other areas to avoid excessive use of certain equipment or waste of resources. The optimization algorithm takes into account the workload, environmental factors and equipment status of all areas in the container to ensure the optimal effect of overall temperature and humidity control.

[0135] In addition, this implementation method also designs a multi-level feedback mechanism. The system will conduct self-evaluation based on the real-time monitoring data and the effect of optimization and adjustment, and further optimize the adjustment strategy based on the evaluation results. The results of each adjustment will be fed back to the system. Through the data feedback mechanism, the system will continuously adjust its control strategy to make the temperature and humidity adjustment more efficient. Through this multi-level control and optimization, the third implementation method can not only accurately control the temperature and humidity of each area in the container, but also achieve efficient allocation of resources through global optimization, thereby ensuring that lithium batteries and electrical equipment operate in a safe and stable environment.

[0136] This management system based on multi-level control and optimization strategies not only has strong adaptability and flexibility, but can also achieve precise adjustment under complex environmental changes, fully meeting the temperature and humidity requirements of different areas and equipment.

[0137] Through the combination of real-time monitoring, intelligent algorithms and multi-level control, the present invention enables the system to make timely adjustments based on the dynamic changes of temperature and humidity, significantly improving the accuracy and response speed of temperature and humidity control. Unlike traditional temperature and humidity adjustment methods, the solution combines sensor data with prediction models so that temperature and humidity adjustment no longer relies on static set values, but can adjust the control strategy in real time according to environmental fluctuations and equipment load. For example, through machine learning and intelligent prediction algorithms, the system can identify the potential impact of external climate changes, equipment load fluctuations and other factors on environmental temperature and humidity in advance, so as to take measures in advance to prevent temperature and humidity from exceeding the safe range and avoid equipment damage or battery failure. This real-time feedback and dynamic adjustment mechanism ensures that the temperature and humidity are always maintained at the optimal state in complex environments, greatly reducing the equipment failure rate.

[0138] The present invention uses multi-level control and optimization strategies to make temperature and humidity regulation not only more accurate, but also optimize resource utilization and improve the energy efficiency of the system. During the implementation process, the system adopts a temperature and humidity adjustment method based on regional division, so that the temperature and humidity requirements of each area are independently controlled, thereby avoiding the impact of temperature and humidity fluctuations on other areas. This refined management method can be dynamically adjusted according to the actual needs of different areas to avoid unnecessary energy waste. At the same time, combined with the global optimization algorithm, the system can dynamically balance the energy consumption of each area, reasonably allocate the load of the temperature and humidity control equipment, and maximize the overall energy efficiency of the system. In this way, not only the safe operation of the equipment is guaranteed, but also the energy consumption is reduced, and the overall economic benefits of the temperature and humidity control system are improved, which meets the needs of modern ship energy management.

[0139] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for controlling temperature and humidity of a marine energy storage container, characterized in that: The following steps are involved: Monitor the temperature and humidity in the container in real time, and obtain the real-time environmental parameters of the environment in the container through sensors; Set temperature and humidity control thresholds. Based on the operating requirements of lithium batteries and electrical equipment, set appropriate temperature and humidity ranges, and adjust the set thresholds based on real-time data in the container to cope with dynamically changing environmental conditions; According to the deviation between the real-time monitoring data and the set threshold, the temperature and humidity control equipment is adjusted to keep the temperature and humidity in the container within a safe range at all times; When the temperature and humidity in the container fluctuate sharply, the working state of the control equipment is adjusted in advance in combination with the prediction algorithm of environmental changes to prevent excessive fluctuations in temperature and humidity from causing harm to lithium batteries and electrical equipment; According to the temperature and humidity fluctuation pattern, an adaptive control algorithm is used to optimize and adjust the equipment according to the historical temperature and humidity change rules to improve the responsiveness and accuracy of the temperature and humidity control system and ensure the safe operation of battery packs and electrical equipment under extreme conditions; According to the deviation between the real-time monitoring data and the set threshold, adjust the temperature and humidity control equipment to keep the temperature and humidity in the container within a safe range. The specific steps are as follows: Compare the real-time temperature and humidity data obtained by the sensor with the previously set thresholds; When a deviation between the temperature and humidity and the set threshold is detected, the working state of the temperature and humidity control device is adjusted according to the size and direction of the deviation; In order to improve the intelligent level of temperature and humidity regulation, an adaptive adjustment mechanism is adopted to adjust the control equipment more finely according to historical data, environmental change patterns and current workload; While adjusting the temperature and humidity control equipment, the environmental data inside the container is continuously monitored, and the adjustment strategy is further optimized based on new data feedback.

2. The temperature and humidity control method of a marine energy storage container according to claim 1, characterized in that: Real-time monitoring of the temperature and humidity inside the container, and obtaining real-time environmental parameters of the environment inside the container through sensors. The specific steps are as follows: First, the sensor will continuously collect environmental data inside the container through its own measurement mechanism; Once the sensor acquires the raw environmental data, these analog signals are converted into digital signals through a built-in analog-to-digital converter; When the digital signals are successfully transmitted to the data receiving unit, these data will enter the real-time data storage module; As time goes by, the sensors continue to collect new environmental data periodically, updating the parameters in the existing data store in real time.

3. The temperature and humidity control method of a marine energy storage container according to claim 1, characterized in that: Set the temperature and humidity control thresholds, set the appropriate temperature and humidity range based on the operating requirements of lithium batteries and electrical equipment, and adjust the set thresholds according to the real-time data in the container to cope with dynamically changing environmental conditions. The specific steps are as follows: At this stage, an initial temperature and humidity control range is first determined based on the working requirements of lithium batteries and electrical equipment; The real-time monitoring system continuously obtains temperature and humidity data inside the container through sensors, providing a basis for subsequent threshold adjustments; In order to cope with the severe weather and complex environmental conditions that ships may encounter when sailing at sea, the system dynamically adjusts the control range of temperature and humidity through real-time analysis of temperature and humidity data in the container; Continuous evaluation and feedback must be provided throughout the entire process of real-time monitoring and threshold setting of container temperature and humidity.

4. The temperature and humidity control method of a marine energy storage container according to claim 1, characterized in that: When the temperature and humidity in the container fluctuate sharply, the working state of the control equipment is adjusted in advance in combination with the prediction algorithm of environmental changes to prevent excessive fluctuations in temperature and humidity from causing harm to lithium batteries and electrical equipment. The specific steps are as follows; First, obtain the real-time temperature and humidity data in the container. Assume that the sensor sampling period is Δt. Each collected data contains the instantaneous value of temperature and humidity. Next, by using the time series analysis method, calculate the change trend of temperature and humidity data over the past period of time. By calculating the trend slope, the change rate of temperature and humidity is obtained. The calculation expression is as follows: , where ΔT represents the change in temperature in the container within the time interval Δt, that is, the temperature difference from time t to time t+Δt, T(t) is the temperature value inside the container at time t, ΔH is the change in humidity in the container within the time interval Δt, that is, the humidity difference from time t to time t+Δt, H(t) is the humidity value inside the container at time t, is the rate of temperature change, is the rate of change of humidity; After identifying the trend of temperature and humidity changes through the above analysis, the weighted regression model is then used to predict the temperature and humidity changes in the future. When predicting the future value of temperature and humidity changes, the model performs weighted calculations on the recent historical data to obtain the future temperature and humidity change forecast. The calculation expression is as follows: In the formula, is the predicted temperature value at the future time point t+Δt, w i is the weight coefficient, T(t-iΔt) represents the temperature data before the past i time points, the unit time interval is Δt, n is the total number of time points, α is the weight coefficient of the temperature change rate, is the predicted humidity value at the future time point t+Δt, H(t-iΔt) represents the humidity data before the past i time points, the unit time interval is Δt, and β is the weight coefficient of the humidity change rate; According to the temperature and humidity change trend obtained by the prediction algorithm, the working state of the temperature and humidity control equipment is adjusted in advance according to the preset safety threshold. The calculation expression is as follows: Where U cool (t) is the temperature control instruction, It is the proportional gain part, which is used to control the response intensity during the temperature adjustment process. max is the maximum safe threshold of temperature, K i It is the temperature integral control part, Represents the accumulation of temperature deviations over a period of time, K i is the integral gain, which controls the influence of past deviations on the current control strategy. It is the temperature data before the predicted temperature j time points in the future, with a unit time interval of Δt. is the temperature differential gain, K d is the differential gain coefficient, U humid (t) is the humidity control instruction, It is the humidity proportional control part, which is used to control the response intensity during the humidity adjustment process. max is the maximum safe threshold of humidity, Δt is the humidity integral control part, Represents the accumulation of humidity deviations over a period of time. is the humidity differential gain; After implementing the adjustment strategy, the temperature and humidity changes are continuously tracked, and the control effect is fed back and optimized in real time. Specifically, the control strategy is optimized through a dynamic optimization algorithm. The calculation expression is as follows: In the formula, f opt is the optimization objective function, T target is the target temperature value, H target is the set target humidity value, A and B are weighted coefficients, A controls the priority of temperature adjustment, and B controls the priority of humidity adjustment.

5. The temperature and humidity control method of a marine energy storage container according to claim 1, characterized in that: According to the temperature and humidity fluctuation pattern, the adaptive control algorithm is used in combination with the historical change law to optimize the equipment adjustment, improve the response speed and accuracy of the temperature and humidity control system, and ensure the safe operation of battery packs and electrical equipment under extreme conditions. The specific steps are as follows: First, the historical temperature and humidity data are analyzed to extract the pattern characteristics of temperature and humidity fluctuations. By statistically modeling the temperature and humidity changes over a period of time, the laws and periodic characteristics of environmental changes are identified. After extracting the historical temperature and humidity fluctuation patterns, the frequency components of temperature and humidity fluctuations are calculated and defined as the periodic change frequency of temperature and humidity. The calculation expression is as follows: In the formula, ω T is the frequency component of the temperature data, T(t l ) is the temperature value at the lth moment in the historical data, t l is the lth time point t, is the mean of the temperature data, T period is the time period of temperature fluctuation, N is the total number of time points, ω H is the frequency component of humidity data, H(t l ) is the humidity value at the lth moment in the historical data, is the mean of the humidity data, H period is the time period of humidity fluctuation; After obtaining the periodic fluctuation characteristics of temperature and humidity, based on the frequency information of periodic fluctuations and combined with changes in the external environment, the temperature and humidity change trend at a certain moment in the future is predicted, and the periodic fluctuations of historical data are predicted using a fitting function. The calculation expression is as follows: Where, T pred (t) is the predicted temperature value, which means the predicted temperature value at time point t. pred (t) is the humidity prediction value, which means the humidity value predicted at time point t; After predicting the future temperature and humidity, compare it with the real-time monitored environmental data and calculate the temperature and humidity error. The calculation expression is as follows: ΔT(t) = T measured (t)-T pred (t), ΔH(t)=H measured (t)-H pred (t), where ΔT(t) is the temperature error, ΔH(t) is the humidity error, and T measured (t) is the real-time temperature data, H measured (t) is the real-time humidity data; The error obtained through calculation is used to optimize the adjustment force of the equipment through adaptive control algorithm. The specific adjustment control amount calculation expression is as follows: Where U T (t) is the adjustment amount calculated by the PID control algorithm based on the temperature error, U H (t) is the adjustment amount calculated by the PID control algorithm based on the humidity error, K P is the proportional gain, K I is the integral gain, K d is the differential gain; After calculating the control quantity U T (t) and U H (t), the working state of the equipment is adjusted in real time according to the control quantity to ensure that the temperature and humidity in the container are maintained within a safe range. At the same time, the effect of the control strategy is evaluated through continuous real-time feedback, and the control strategy is optimized according to the new real-time temperature and humidity data. The calculation expression is as follows: Where, T max and T min are the maximum and minimum temperature respectively, H max and H min are the maximum and minimum humidity values ​​respectively, E is the dynamic adjustment coefficient, R is the adjustment coefficient of the integral gain, Z is the adjustment coefficient of the differential gain, and K P (t) is the proportional gain at time point t, K I (t) is the integral gain at time point t, K d (t) is the differential gain at time point t.

Images