Ship waste heat recovery method and device, electronic equipment and storage medium

Abstract

The invention relates to a ship waste heat recovery method and device, electronic equipment and a storage medium, and belongs to the technical field of ship energy recovery, and the ship waste heat recovery method comprises the steps that real-time engine operation state data and real-time waste heat source data of a target ship are obtained; based on the preprocessed real-time engine operation state data and the real-time waste heat source data, the temperature change gradient, the energy flow stability index, the exhaust temperature deviation and the load change rate of the target ship are determined; based on the temperature change gradient and the energy flow stability index of the target ship, the action probability of the multiple waste heat recovery modes is determined, and based on the exhaust temperature deviation and the load change rate of the target ship, the weight coefficients of the multiple waste heat recovery modes are determined; and determining the waste heat recovery mode of the target ship based on the action probabilities and the weight coefficients of the multiple waste heat recovery modes. While the ship waste heat recovery efficiency is guaranteed, the ship waste heat recovery flexibility is improved.

Description

Technical Field

[0001] This invention relates to the field of marine energy recovery technology, and in particular to a method, apparatus, electronic device, and storage medium for recovering waste heat from ships. Background Technology

[0002] With the deepening of the green shipping concept, ship waste heat recovery technology, as a key means to improve energy efficiency and reduce carbon emissions, is receiving increasing attention from the industry. Currently, most mainstream waste heat recovery systems adopt the Organic Rankine Cycle (ORC) architecture, which uses waste heat from main engine exhaust or cooling water to drive the working fluid circulation for power generation. While this technology exhibits good thermodynamic performance under steady-state conditions, in actual navigation, the ship's operating environment is complex and variable. Engine loads often fluctuate drastically due to operations such as departure, speed changes, and steering, leading to unstable heat source parameters and posing a severe challenge to the adaptability and control accuracy of the waste heat recovery system.

[0003] Waste heat recovery systems based on fixed control strategies struggle to cope with wide-range, highly dynamic load variations. Existing systems typically operate in only a single mode, which can lead to problems such as working fluid flow mismatch and a sudden drop in expander efficiency at low loads, resulting in low energy recovery rates. Conversely, during sudden load surges, response lag can cause system overpressure or surge, threatening operational safety.

[0004] Therefore, improving the flexibility and efficiency of ship waste heat recovery solutions has become an urgent technical problem to be solved. Summary of the Invention

[0005] In view of this, it is necessary to provide a method, apparatus, electronic equipment and storage medium for recovering waste heat from ships in order to solve the problems of low flexibility and efficiency of existing waste heat recovery schemes from ships.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a method for recovering waste heat from ships, comprising:

[0007] Acquire real-time engine operating status data and real-time waste heat source data of the target vessel. The engine operating status data includes engine speed and load power, and the waste heat source data includes main engine exhaust temperature, cooling water inlet and outlet temperature difference, and ambient seawater temperature. Based on the preprocessed real-time engine operating status data and real-time waste heat source data, the temperature change gradient, energy flow stability index, exhaust temperature deviation and load change rate of the target ship are determined. The temperature change gradient represents the temperature change gradient of the main engine exhaust temperature, the energy flow stability index represents the stability of the main engine load, the exhaust temperature deviation represents the deviation of the main engine exhaust temperature from the temperature threshold, and the load change rate represents the rate of change of load power within a preset time window. The probability of operation of multiple waste heat recovery modes is determined based on the temperature change gradient and energy flow stability index of the target ship. The weighting coefficients of multiple waste heat recovery modes are determined based on the exhaust temperature deviation and load change rate of the target ship. The multiple waste heat recovery modes include full load optimization mode, low load economic mode and dynamic response mode. The full load optimization mode aims to achieve the maximum thermoelectric conversion efficiency, the low load economic mode aims to balance pump power consumption and power generation revenue, and the dynamic response mode adjusts the waste heat recovery cycle operation parameters based on the heat source change trend. Based on the operational probabilities and weighting coefficients of multiple waste heat recovery modes, the waste heat recovery mode of the target ship is determined.

[0008] In one possible implementation, the preprocessing of the real-time engine operating status data and real-time waste heat source data includes: Sliding window midpoint filtering and discrete wavelet transform are applied to real-time engine operating status data and real-time waste heat source data.

[0009] In one possible implementation, determining the temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate of the target ship based on preprocessed real-time engine operating status data and real-time waste heat source data includes: The mean absolute value of the first difference of the preprocessed main engine exhaust temperature data is determined as the temperature change gradient of the target ship. The reciprocal of the ratio between the standard deviation and the mean of the load power data is determined as the energy flow stability index of the target ship. The deviation of the main engine exhaust temperature from the temperature threshold is defined as the exhaust temperature deviation of the target ship. The rate of change of load power within a preset time window is defined as the load change rate of the target ship.

[0010] In one possible implementation, determining the operational probability of multiple waste heat recovery modes based on the temperature change gradient and energy flow stability index of the target ship includes: The temperature change gradient and energy flow stability of the target ship are used as inputs to the action prediction model, and the action probabilities of multiple waste heat recovery modes output by the action prediction model are obtained. The action prediction model is trained on a dual-depth Q network using the historical temperature change gradient and historical energy flow stability index of the target ship as samples and the historical waste heat recovery mode of the target ship as labels.

[0011] In one possible implementation, determining the weighting coefficients for multiple waste heat recovery modes based on the exhaust temperature deviation and load change rate of the target ship includes: Based on the exhaust temperature deviation and load change rate of the target ship, and the preset weighting rules, the weight coefficients of multiple waste heat recovery modes are determined. The preset weighting rules include the weight coefficients of multiple waste heat recovery modes corresponding to different exhaust temperature deviations and load change rates.

[0012] In one possible implementation, determining the waste heat recovery mode of the target ship based on the action probabilities and weighting coefficients of multiple waste heat recovery modes includes: If the weighting coefficient of the target waste heat recovery mode is greater than or equal to the weighting coefficient threshold, the target waste heat recovery mode is determined as the waste heat recovery mode of the target ship. The target waste heat recovery mode is any waste heat recovery mode among multiple waste heat recovery modes. When the weighting coefficients of multiple waste heat recovery modes are all less than the weighting coefficient threshold, random sampling is performed based on the action probability of the waste heat recovery mode to determine the waste heat recovery mode of the target ship.

[0013] In one possible implementation, the method further includes: After determining the waste heat recovery mode of the target ship, the flow rate of the organic working fluid pump, the opening of the expander speed regulating valve, and the effective heat transfer area of ​​the plate heat exchanger are adjusted based on the waste heat recovery mode of the target ship.

[0014] On the other hand, the present invention also provides a ship waste heat recovery device, comprising: The acquisition module is used to acquire real-time engine operating status data and real-time waste heat source data of the target ship. The engine operating status data includes engine speed and load power, and the waste heat source data includes main engine exhaust temperature, cooling water inlet and outlet temperature difference and ambient seawater temperature. The first determination module is used to determine the temperature change gradient, energy flow stability index, exhaust temperature deviation and load change rate of the target ship based on the preprocessed real-time engine operating status data and real-time waste heat source data. The temperature change gradient represents the temperature change gradient of the main engine exhaust temperature, the energy flow stability index represents the stability of the main engine load, the exhaust temperature deviation represents the deviation of the main engine exhaust temperature from the temperature threshold, and the load change rate represents the rate of change of load power within a preset time window. The second determining module is used to determine the probability of action of multiple waste heat recovery modes based on the temperature change gradient and energy flow stability index of the target ship, and to determine the weight coefficients of multiple waste heat recovery modes based on the exhaust temperature deviation and load change rate of the target ship. The multiple waste heat recovery modes include full load optimization mode, low load economic mode and dynamic response mode. The full load optimization mode aims to achieve the maximum thermoelectric conversion efficiency, the low load economic mode aims to balance pump power consumption and power generation revenue, and the dynamic response mode adjusts the waste heat recovery cycle operation parameters based on the heat source change trend. The third determination module is used to determine the waste heat recovery mode of the target ship based on the action probability and weighting coefficient of multiple waste heat recovery modes.

[0015] In a second aspect, the present invention also provides an electronic device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the ship waste heat recovery method described in any of the above implementations.

[0016] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps of the ship waste heat recovery method described in any of the above implementations.

[0017] The beneficial effects of this invention are as follows: The ship waste heat recovery method, device, electronic equipment, and storage medium provided by this invention determine the temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate of the target ship by using real-time engine operating status data and real-time waste heat source data. This allows for real-time monitoring of the target ship's waste heat recovery status, thereby determining the operation probability and weighting coefficients of multiple waste heat recovery modes, and ultimately determining the waste heat recovery mode for the target ship. This invention dynamically adjusts the waste heat recovery mode of the target ship using real-time engine operating status data and real-time waste heat source data, thus enabling the selection of the waste heat recovery mode that best suits the current waste heat recovery status, rather than relying on a single operating model. This ensures the efficiency of waste heat recovery. Furthermore, the ability to adjust the waste heat recovery mode based on real-time engine operating status data and real-time waste heat source data also improves the flexibility of ship waste heat recovery. In short, this invention improves the flexibility of ship waste heat recovery while ensuring its efficiency. Attached Figure Description

[0018] Figure 1 A schematic flowchart of an embodiment of the waste heat recovery method for ships provided by the present invention; Figure 2 A schematic diagram of an embodiment of the overall architecture of the ship waste heat recovery system provided by the present invention; Figure 3 A schematic flowchart of an embodiment of the adaptive pattern decision-making and strategy generation process provided by the present invention; Figure 4 A schematic diagram of an embodiment of the multi-level interaction relationship and data flow of the dynamic control of waste heat recovery cycle operating parameters provided by the present invention; Figure 5A flowchart illustrating an embodiment of the multi-module collaborative switching and system status monitoring process provided by the present invention; Figure 6 A schematic diagram of an embodiment of the ship waste heat recovery device provided by the present invention; Figure 7 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0021] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] This invention provides a method, apparatus, electronic device, and storage medium for recovering waste heat from ships, which will be described below.

[0024] Figure 1 This is a schematic flowchart of an embodiment of the ship waste heat recovery method provided by the present invention, as shown below. Figure 1 As shown, ship waste heat recovery methods include: S101. Obtain real-time engine operating status data and real-time waste heat source data of the target vessel. The engine operating status data includes engine speed and load power, and the waste heat source data includes main engine exhaust temperature, cooling water inlet and outlet temperature difference, and ambient seawater temperature.

[0025] It should be noted that the waste heat recovery method for ships provided by this invention can be applied to energy recovery scenarios for equipment, especially waste heat recovery scenarios for ships.

[0026] First, the ship's control equipment (such as onboard desktop or portable computers) can acquire real-time engine operating status data and real-time waste heat source data of the target ship, such as engine speed, load power, main engine exhaust temperature, cooling water inlet and outlet temperature difference, and ambient seawater temperature, providing data basis for subsequent waste heat recovery decisions.

[0027] S102. Based on the preprocessed real-time engine operating status data and real-time waste heat source data, determine the temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate of the target ship. The temperature change gradient represents the temperature change gradient of the main engine exhaust temperature, the energy flow stability index represents the stability of the main engine load, the exhaust temperature deviation represents the deviation of the main engine exhaust temperature from the temperature threshold, and the load change rate represents the rate of change of load power within a preset time window.

[0028] It should be noted that after acquiring real-time engine operating status data and real-time waste heat source data, these data can be preprocessed. Then, using the preprocessed data, the temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate of the target ship can be determined, further clarifying the waste heat utilization status of the target ship. The temperature change gradient represents the temperature change gradient of the main engine exhaust temperature; the energy flow stability index represents the stability of the main engine load; the exhaust temperature deviation represents the deviation of the main engine exhaust temperature from a temperature threshold; and the load change rate represents the rate of change of load power within a preset time window.

[0029] S103. Based on the temperature change gradient and energy flow stability index of the target ship, determine the operation probability of multiple waste heat recovery modes, and based on the exhaust temperature deviation and load change rate of the target ship, determine the weight coefficient of multiple waste heat recovery modes. Multiple waste heat recovery modes include full load optimization mode, low load economic mode and dynamic response mode. The full load optimization mode aims to achieve the maximum thermoelectric conversion efficiency, the low load economic mode aims to balance pump power consumption and power generation revenue, and the dynamic response mode adjusts the waste heat recovery cycle operation parameters based on the heat source change trend.

[0030] It should be noted that after determining the temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate of the target vessel, the activation probability of multiple waste heat recovery modes can be determined based on the temperature change gradient and energy flow stability index. Furthermore, the weighting coefficients of these multiple waste heat recovery modes can be determined based on the exhaust temperature deviation and load change rate, providing support for the selection of the waste heat recovery mode for the target vessel. These multiple waste heat recovery modes include a full-load optimization mode, a low-load economic mode, and a dynamic response mode. The full-load optimization mode aims to achieve maximum thermoelectric conversion efficiency; the low-load economic mode aims to balance pump power consumption and power generation revenue; and the dynamic response mode adjusts the waste heat recovery cycle operating parameters based on the heat source change trend.

[0031] S104. Based on the action probability and weighting coefficient of multiple waste heat recovery modes, determine the waste heat recovery mode of the target ship.

[0032] It should be noted that: Finally, after determining the operation probability and weight coefficient of multiple waste heat recovery modes, the waste heat recovery mode of the target ship can be determined by weighted fusion, thereby realizing the waste heat recovery of the target ship.

[0033] In summary, the waste heat recovery method for ships provided by this invention determines the temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate of the target ship by using real-time engine operating status data and real-time waste heat source data. This allows for real-time monitoring of the waste heat recovery status of the target ship, thereby determining the operation probability and weighting coefficients of multiple waste heat recovery modes, and ultimately determining the waste heat recovery mode for the target ship. This invention dynamically adjusts the waste heat recovery mode of the target ship using real-time engine operating status data and real-time waste heat source data, enabling the selection of the waste heat recovery mode that best suits the current waste heat recovery status rather than relying on a single operating model. This ensures the efficiency of waste heat recovery. Furthermore, the ability to adjust the waste heat recovery mode based on real-time engine operating status data and real-time waste heat source data also improves the flexibility of ship waste heat recovery. Therefore, this invention improves the flexibility of ship waste heat recovery while ensuring its efficiency.

[0034] In some embodiments of the present invention, the preprocessing of the real-time engine operating status data and real-time waste heat source data includes: Sliding window midpoint filtering and discrete wavelet transform are applied to real-time engine operating status data and real-time waste heat source data.

[0035] It should be noted that when preprocessing real-time engine operating status data and real-time waste heat source data, sliding window value filtering can be applied to the real-time engine operating status data and real-time waste heat source data to eliminate impulse noise caused by electromagnetic interference or mechanical vibration. Then, the filtered signal can be decomposed into multiple scales through discrete wavelet transform to balance time domain resolution and frequency domain resolution.

[0036] In some embodiments of the present invention, determining the temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate of the target ship based on preprocessed real-time engine operating status data and real-time waste heat source data includes: The mean absolute value of the first difference of the preprocessed main engine exhaust temperature data is determined as the temperature change gradient of the target ship. The reciprocal of the ratio between the standard deviation and the mean of the load power data is determined as the energy flow stability index of the target ship. The deviation of the main engine exhaust temperature from the temperature threshold is defined as the exhaust temperature deviation of the target ship. The rate of change of load power within a preset time window is defined as the load change rate of the target ship.

[0037] It should be noted that when determining the temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate of the target ship based on the pre-processed real-time engine operating status data and real-time waste heat source data, the mean of the absolute values ​​of the first-order differences of the pre-processed main engine exhaust temperature data can be determined as the temperature change gradient of the target ship, the reciprocal of the ratio between the standard deviation and the mean of the load power data can be determined as the energy flow stability index of the target ship, the deviation of the main engine exhaust temperature from the temperature threshold can be determined as the exhaust temperature deviation of the target ship, and the load power change rate within the preset time window can be determined as the load change rate of the target ship.

[0038] In some embodiments of the present invention, determining the operational probability of multiple waste heat recovery modes based on the temperature change gradient and energy flow stability index of the target ship includes: The temperature change gradient and energy flow stability of the target ship are used as inputs to the action prediction model, and the action probabilities of multiple waste heat recovery modes output by the action prediction model are obtained. The action prediction model is trained on a dual-depth Q network using the historical temperature change gradient and historical energy flow stability index of the target ship as samples and the historical waste heat recovery mode of the target ship as labels.

[0039] It should be noted that when determining the operational probabilities of multiple waste heat recovery modes based on the target ship's temperature change gradient and energy flow stability index, the target ship's temperature change gradient and energy flow stability can be used as inputs to the operational prediction model, yielding the operational probabilities of multiple waste heat recovery modes output by the model. The operational prediction model can be trained on a dual-depth Q-network using historical data. During training, the historical temperature change gradient and historical energy flow stability index of the target ship are used as samples, and the historical waste heat recovery modes of the target ship are used as labels.

[0040] In some embodiments of the present invention, determining the weighting coefficients of multiple waste heat recovery modes based on the exhaust temperature deviation and load change rate of the target ship includes: Based on the exhaust temperature deviation and load change rate of the target ship, and the preset weighting rules, the weight coefficients of multiple waste heat recovery modes are determined. The preset weighting rules include the weight coefficients of multiple waste heat recovery modes corresponding to different exhaust temperature deviations and load change rates.

[0041] It should be noted that when determining the weighting coefficients of multiple waste heat recovery modes based on the exhaust temperature deviation and load change rate of the target vessel, the weighting coefficients of multiple waste heat recovery modes can be determined according to the exhaust temperature deviation and load change rate of the target vessel, as well as the preset weighting rules. The preset weighting rules include the weighting coefficients of multiple waste heat recovery modes corresponding to different exhaust temperature deviations and load change rates. That is, according to the preset weighting rules, the weighting coefficients of multiple waste heat recovery modes corresponding to a given exhaust temperature deviation and load change rate can be directly queried.

[0042] In some embodiments of the present invention, determining the waste heat recovery mode of the target ship based on the action probability and weighting coefficient of multiple waste heat recovery modes includes: If the weighting coefficient of the target waste heat recovery mode is greater than or equal to the weighting coefficient threshold, the target waste heat recovery mode is determined as the waste heat recovery mode of the target ship. The target waste heat recovery mode is any waste heat recovery mode among multiple waste heat recovery modes. When the weighting coefficients of multiple waste heat recovery modes are all less than the weighting coefficient threshold, random sampling is performed based on the action probability of the waste heat recovery mode to determine the waste heat recovery mode of the target ship.

[0043] It should be noted that when determining the waste heat recovery mode of a target vessel based on the operation probabilities and weighting coefficients of multiple waste heat recovery modes, if the weighting coefficient of any waste heat recovery mode is greater than or equal to a weighting coefficient threshold (e.g., 0.75), then that waste heat recovery mode can be determined as the waste heat recovery mode of the target vessel. If the weighting coefficients of multiple waste heat recovery modes are all less than the weighting coefficient threshold, then random sampling can be performed based on the operation probabilities of the waste heat recovery modes to determine the waste heat recovery mode of the target vessel.

[0044] In some embodiments of the present invention, the method further includes: After determining the waste heat recovery mode of the target ship, the flow rate of the organic working fluid pump, the opening of the expander speed regulating valve, and the effective heat transfer area of ​​the plate heat exchanger are adjusted based on the waste heat recovery mode of the target ship.

[0045] It should be noted that after determining the waste heat recovery mode of the target ship, the flow rate of the organic working fluid pump, the opening of the expander speed regulating valve, and the effective heat transfer area of ​​the plate heat exchanger can be adjusted according to the target of the waste heat recovery mode of the target ship.

[0046] Combination Figure 2 The overall architecture of the ship waste heat recovery system proposed in this invention includes a distributed sensor network, a multi-source operating condition sensing and feature extraction module, an adaptive mode decision-making and strategy generation unit, a dynamic parameter control actuator, a multi-module collaborative switching and status monitoring subsystem, and an energy efficiency assessment and lifespan prediction functional module. These modules are interconnected via an industrial-grade communication bus, forming a closed-loop control architecture that enables fully automated management from data acquisition to intelligent decision-making and precise execution.

[0047] The specific steps for recovering waste heat from ships include: 1. Real-time acquisition of ship engine operating status parameters and waste heat source characteristic data.

[0048] A distributed sensor network deployed along the ship's main engine exhaust pipes, cooling water circulation loop, power take-off shaft, and seawater inlet synchronously acquires key parameters such as main engine exhaust temperature, cooling water inlet and outlet temperature difference, engine speed, load power, and ambient seawater temperature. This sensor network covers waste heat sources, the power system, and the environment, and includes platinum resistance temperature sensors, piezoresistive pressure transmitters, electromagnetic flowmeters, photoelectric encoders, and digital temperature and humidity composite sensors. The sampling frequency is uniformly set to 10 Hz to ensure good data timeliness and representativeness. All sensors are connected to the central data acquisition unit via shielded twisted-pair cables, using the Modbus TCP protocol for timestamp synchronization to ensure millisecond-level alignment accuracy of multi-source data. The data acquisition unit incorporates a watchdog circuit and CRC check mechanism. When a single-point data anomaly or communication interruption is detected, a historical sliding window interpolation algorithm is automatically activated for data compensation to prevent global perception distortion due to local sensor failure.

[0049] 2. Construct a multi-source working condition perception and feature extraction module.

[0050] First, the raw data sequence acquired in step 1 is preprocessed: a sliding window mid-range filtering algorithm with a length of 15 sampling points is used to eliminate impulse noise caused by electromagnetic interference or mechanical vibration. Then, discrete wavelet transform is applied to the filtered signal for multi-scale decomposition. The wavelet basis function is db4, and the decomposition level is set to 4 levels to balance time-domain resolution and frequency-domain resolution. High-frequency components are extracted from the detail coefficients of the 3rd level as load fluctuation characteristics, and their energy proportion is defined as:

[0051] in, Indicates the first Layer Detail coefficients for each sampling point For the 4th floor Approximation coefficients for each sampling point and These represent the corresponding sequence lengths. Simultaneously, the mean absolute value of the first-order difference of the exhaust temperature sequence is calculated as the temperature gradient. The unit is degrees Celsius per second; and an energy flow stability index is introduced. , defined as the reciprocal of the ratio of the standard deviation of host load power to its mean, i.e. These are used to quantify the smoothness of energy input. The aforementioned characteristic quantities... , , Together, they form a three-dimensional feature vector of the working condition, which is then input into the subsequent decision-making module. The entire feature extraction process is completed in real time on the embedded processor, with a processing latency of no more than 50 milliseconds.

[0052] 3. Perform adaptive mode decision-making and strategy generation.

[0053] It integrates fuzzy logic control with deep reinforcement learning methods to collaboratively determine the current optimal operating mode. Figure 3 The decision-making framework consists of two parallel branches: a fuzzy logic controller receives normalized operating condition deviation variables, including exhaust temperature deviation. (Deviation from the set baseline value of 850 degrees Celsius), load change rate (Percentage change in load power per unit time) and ambient seawater temperature (Standardized to the 0-1 range); the fuzzy rule base has 9 preset IF-THEN rules, such as "if..." For high, and If the value is low, the weight of the full-load optimization mode is 0.9. After defuzzification using the centroid method, the selection weights of the three modes are output. Meanwhile, the deep reinforcement learning model employs a dual-deep Q-network structure. The state space is expanded from the aforementioned three-dimensional feature vectors to a sequence containing five historical states. The action space is {full-load optimization mode, low-load economic mode, dynamic response mode}. The reward function comprehensively considers instantaneous power recovery, system pressure safety margin, and control energy consumption, and is defined as follows: , For instantaneous power recovery, For system power, For system pressure safety margin, To control energy consumption, the model stores at least 10,000 interaction samples in an experience replay pool and updates parameters of the target network every 200 steps to improve training stability. The final decision-making employs a weighted fusion strategy: if the maximum weight of the fuzzy logic output exceeds 0.75, the mode is directly adopted; otherwise, random sampling is performed using the action probability distribution output by the deep Q-network to ensure exploratory decision-making is introduced in the fuzzy boundary region. The specific meanings of the three operating modes are as follows: Full load optimization mode is suitable when the host load power is greater than 80% of the rated value and... Under stable high-load conditions, the system prioritizes adjusting to the point of maximum thermoelectric conversion efficiency; the low-load economic mode is suitable for load power between 30% and 80% and temperature gradient. In the low to medium load range, it emphasizes the economic balance between pump power consumption and power generation revenue; the dynamic response mode is specifically designed for... or The design incorporates a load change scenario, activating a feedforward-feedback composite control strategy to predict heat source changes in advance and adjust actuator settings accordingly.

[0054] 4. Dynamically adjust the operating parameters of the waste heat recovery cycle.

[0055] Based on the operating mode selected in step 3, the flow rate of the organic working fluid pump, the opening of the expander speed regulating valve, and the effective heat transfer area of ​​the plate heat exchanger are adjusted in real time. Combined with... Figure 4 The control system employs a three-layer architecture: the top layer is the mode command generation layer, outputting target parameter setpoints; the middle layer is the coordination control layer, executing multi-variable decoupling and step feedforward compensation; and the bottom layer is the execution drive layer, directly controlling physical equipment. The organic working fluid pump uses a magnetically coupled, leak-free drive structure, equipped with a vector control frequency converter. The frequency adjustment range is 5 to 60 Hz, changing the pump speed, corresponding to a flow rate adjustment range of 2 to 25 cubic meters per hour. The expander speed regulating valve uses a pneumatic diaphragm actuator, with a short response time and a linear relationship between valve core stroke and opening. The plate heat exchanger consists of 128 stainless steel corrugated plates, and the effective heat transfer area is changed by a hydraulic cylinder pushing the movable end plate, with an adjustment range of 40% to 100% of the total heat transfer area. In full-load optimization mode, the system maximizes the working fluid flow and expander speed, constrained by an exhaust outlet temperature not lower than 180 degrees Celsius. In low-load economic mode, an energy efficiency ratio threshold is introduced. When the real-time COP falls below this value, the pump frequency is automatically reduced; in dynamic response mode, the feedforward channel is based on the load change rate. The system predicts the heat source power within the next 5 seconds and adjusts the pump frequency and valve opening in advance. The feedback channel uses a PID controller to track the deviation between the actual expander speed and the set value, and the integral time constant is dynamically tuned according to the current mode.

[0056] 5. Enable multi-module collaborative switching and system status monitoring.

[0057] It includes a primary / backup module switching mechanism and full lifecycle health management functions. Combined with... Figure 5 The system is configured with a main Rankine cycle unit and a backup unit, which are rapidly switched via a solenoid valve assembly. When the main system's recovery efficiency drops by more than 15% for 10 consecutive seconds, or the expander vibration amplitude exceeds 8 mm / s, or the evaporator outlet superheat is below 5 degrees Celsius, it is determined that the main system performance has deteriorated or a component is malfunctioning, immediately triggering the switching logic: first, the main circulation working fluid pump is shut down; after a 500-millisecond delay, the backup circulation pump is started; simultaneously, the solenoid valve assembly is switched to the backup circuit. The entire process is completed within 2 seconds, ensuring uninterrupted power supply. System status monitoring is achieved by high-precision pressure transmitters and temperature sensors distributed at the inlet and outlet of the evaporator, condenser, liquid receiver, and expander. Pressure and temperature are detected, and data is uploaded to the safety monitoring PLC every 100 milliseconds. When the pressure at any node exceeds 1.2 times the design limit or the temperature exceeds the allowable range, graded protection is automatically activated: Level 1 is an audible and visual alarm, Level 2 is reduced load operation, and Level 3 is an emergency shutdown. In addition, the system integrates an energy efficiency assessment module, which calculates the waste heat recovery efficiency in real time based on a steady-state thermodynamic model. ( Waste heat output power, Waste heat input power), system performance coefficient ( The system's output power, The system's input power and unit power generation cost (RMB / kWh) are considered. The lifespan prediction module utilizes a long short-term memory neural network to process historical operating data from the past 30 days, including start-up / shutdown counts, cumulative over-temperature duration, and vibration spectrum characteristics, to predict the remaining service life of the expander bearings and working fluid pump seals. When the predicted value is below 300 hours, a preventative maintenance work order is generated. The entire system interfaces with the ship's energy management platform via a PROFIBUS-DP bus, supporting remote parameter configuration, fault code uploading, and collaborative scheduling command reception.

[0058] This invention constructs a closed-loop control architecture of "multi-source sensing - feature extraction - intelligent decision-making - dynamic regulation," integrating three major functional modules: a distributed sensor network, an intelligent algorithm module, and a dynamic regulation unit. This enables the real-time dynamic adaptation of the ship's waste heat recovery system to a wide range of varying operating conditions, including engine load variations and waste heat source fluctuations. The system can autonomously sense changes in multiple parameters such as main engine exhaust temperature, cooling water temperature difference, engine speed, load power, and ambient seawater temperature. Through wavelet transform, fuzzy logic, and deep reinforcement learning techniques, it extracts operating condition features and intelligently decides on the optimal operating mode. This allows for precise adjustment of the organic working fluid pump flow rate, expander regulating valve opening, and effective heat transfer area of ​​the heat exchanger. This fundamentally overcomes the inherent defects of traditional fixed control strategies, such as efficiency degradation and response lag under varying operating conditions, ensuring efficient and stable operation of the system across a wide range of operating conditions and significantly expanding the effective application scenarios of ship waste heat recovery technology.

[0059] This invention employs a multi-mode adaptive switching mechanism, subdividing the operation modes of the waste heat recovery system into a full-load optimization mode, a low-load economic mode, and a dynamic response mode, achieving a balance between energy efficiency and economic requirements across different load ranges. The full-load optimization mode prioritizes maximum energy recovery efficiency for high-load stable conditions; the low-load economic mode adapts to medium-low load ranges, emphasizing a balance between energy consumption and recovery benefits; and the dynamic response mode is specifically designed for rapidly changing load conditions, employing a feedforward-feedback composite control strategy to enhance system robustness. This mechanism transforms the traditional static operation process of a single mode into a dynamic mode switching process based on operating condition characteristics, effectively addressing the performance shortcomings of traditional systems under different loads and comprehensively improving the overall energy efficiency of the system under complex ship operating conditions.

[0060] This invention combines modular design with intelligent operation and maintenance methods. Through an independent backup recovery module and a coordinated switching structure for solenoid valve groups, it enhances the system's adaptability to sudden changes in operating conditions and component malfunctions under complex sea conditions. Simultaneously, it integrates energy efficiency assessment and long short-term memory neural network lifetime prediction functions, supporting the formulation of preventative maintenance strategies. Furthermore, it can interact with the ship's energy management platform via standard industrial communication protocols to achieve remote monitoring, fault diagnosis, and collaborative scheduling. This design not only solves the problems of low modularity and insufficient intelligent operation and maintenance in traditional systems but also provides reliable technical support for ship energy conservation and emission reduction, helping to upgrade ship energy management towards higher efficiency and intelligence.

[0061] To better implement the ship waste heat recovery method in the embodiments of the present invention, based on the ship waste heat recovery method, correspondingly, as follows: Figure 6 As shown, this embodiment of the invention also provides a ship waste heat recovery device, the ship waste heat recovery device 600 comprising: The acquisition module 601 is used to acquire real-time engine operating status data and real-time waste heat source data of the target ship. The engine operating status data includes engine speed and load power, and the waste heat source data includes main engine exhaust temperature, cooling water inlet and outlet temperature difference and ambient seawater temperature. The first determining module 602 is used to determine the temperature change gradient, energy flow stability index, exhaust temperature deviation and load change rate of the target ship based on the preprocessed real-time engine operating status data and real-time waste heat source data. The temperature change gradient represents the temperature change gradient of the main engine exhaust temperature, the energy flow stability index represents the stability of the main engine load, the exhaust temperature deviation represents the deviation of the main engine exhaust temperature from the temperature threshold, and the load change rate represents the rate of change of load power within a preset time window. The second determining module 603 is used to determine the operation probability of multiple waste heat recovery modes based on the temperature change gradient and energy flow stability index of the target ship, and to determine the weight coefficient of multiple waste heat recovery modes based on the exhaust temperature deviation and load change rate of the target ship. The multiple waste heat recovery modes include full load optimization mode, low load economic mode and dynamic response mode. The full load optimization mode aims to achieve the maximum thermoelectric conversion efficiency, the low load economic mode aims to balance pump power consumption and power generation revenue, and the dynamic response mode adjusts the waste heat recovery cycle operation parameters based on the heat source change trend. The third determination module 604 is used to determine the waste heat recovery mode of the target ship based on the action probability and weight coefficient of multiple waste heat recovery modes.

[0062] The ship waste heat recovery device 600 provided in the above embodiments can realize the technical solutions described in the above ship waste heat recovery method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above ship waste heat recovery method embodiments, and will not be repeated here.

[0063] like Figure 7 As shown, the present invention also provides an electronic device 700. The electronic device 700 includes a processor 701, a memory 702, and a display 703. Figure 7 Only some components of the electronic device 700 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0064] In some embodiments, processor 701 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 702 or process data, such as the ship waste heat recovery method of the present invention.

[0065] In some embodiments, processor 701 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 701 may be local or remote. In some embodiments, processor 701 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0066] In some embodiments, memory 702 may be an internal storage unit of electronic device 700, such as a hard disk or memory of electronic device 700. In other embodiments, memory 702 may also be an external storage device of electronic device 700, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 700.

[0067] Furthermore, the memory 702 may include both internal storage units of the electronic device 700 and external storage devices. The memory 702 is used to store application software and various types of data installed on the electronic device 700.

[0068] In some embodiments, display 703 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 703 is used to display information from electronic device 700 and to display a visual user interface. Components 701-703 of electronic device 700 communicate with each other via a system bus.

[0069] In one embodiment, when processor 701 executes the ship waste heat recovery program in memory 702, the following steps can be implemented: Acquire real-time engine operating status data and real-time waste heat source data of the target vessel. The engine operating status data includes engine speed and load power, and the waste heat source data includes main engine exhaust temperature, cooling water inlet and outlet temperature difference, and ambient seawater temperature. Based on the preprocessed real-time engine operating status data and real-time waste heat source data, the temperature change gradient, energy flow stability index, exhaust temperature deviation and load change rate of the target ship are determined. The temperature change gradient represents the temperature change gradient of the main engine exhaust temperature, the energy flow stability index represents the stability of the main engine load, the exhaust temperature deviation represents the deviation of the main engine exhaust temperature from the temperature threshold, and the load change rate represents the rate of change of load power within a preset time window. The probability of operation of multiple waste heat recovery modes is determined based on the temperature change gradient and energy flow stability index of the target ship. The weighting coefficients of multiple waste heat recovery modes are determined based on the exhaust temperature deviation and load change rate of the target ship. The multiple waste heat recovery modes include full load optimization mode, low load economic mode and dynamic response mode. The full load optimization mode aims to achieve the maximum thermoelectric conversion efficiency, the low load economic mode aims to balance pump power consumption and power generation revenue, and the dynamic response mode adjusts the waste heat recovery cycle operation parameters based on the heat source change trend. Based on the operational probabilities and weighting coefficients of multiple waste heat recovery modes, the waste heat recovery mode of the target ship is determined.

[0070] It should be understood that when the processor 701 executes the ship waste heat recovery program in the memory 702, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0071] Furthermore, the embodiments of the present invention do not specifically limit the type of electronic device 700 mentioned. Electronic device 700 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, electronic device 700 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0072] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the ship waste heat recovery methods provided in the above-described method embodiments.

[0073] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0074] The above provides a detailed description of the ship waste heat recovery method, apparatus, electronic equipment, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for recovering waste heat from ships, characterized in that, include: Acquire real-time engine operating status data and real-time waste heat source data of the target vessel. The engine operating status data includes engine speed and load power, and the waste heat source data includes main engine exhaust temperature, cooling water inlet and outlet temperature difference, and ambient seawater temperature. Based on the preprocessed real-time engine operating status data and real-time waste heat source data, the temperature change gradient, energy flow stability index, exhaust temperature deviation and load change rate of the target ship are determined. The temperature change gradient represents the temperature change gradient of the main engine exhaust temperature, the energy flow stability index represents the stability of the main engine load, the exhaust temperature deviation represents the deviation of the main engine exhaust temperature from the temperature threshold, and the load change rate represents the rate of change of load power within a preset time window. The probability of operation of multiple waste heat recovery modes is determined based on the temperature change gradient and energy flow stability index of the target ship. The weighting coefficients of multiple waste heat recovery modes are determined based on the exhaust temperature deviation and load change rate of the target ship. The multiple waste heat recovery modes include full load optimization mode, low load economic mode and dynamic response mode. The full load optimization mode aims to achieve the maximum thermoelectric conversion efficiency, the low load economic mode aims to balance pump power consumption and power generation revenue, and the dynamic response mode adjusts the waste heat recovery cycle operation parameters based on the heat source change trend. Based on the operational probabilities and weighting coefficients of multiple waste heat recovery modes, the waste heat recovery mode of the target ship is determined.

2. The ship waste heat recovery method according to claim 1, characterized in that, The preprocessing of the real-time engine operating status data and real-time waste heat source data includes: Sliding window midpoint filtering and discrete wavelet transform are applied to real-time engine operating status data and real-time waste heat source data.

3. The ship waste heat recovery method according to claim 1, characterized in that, The determination of the target ship's temperature change gradient, energy flow stability index, exhaust temperature deviation, and load change rate based on preprocessed real-time engine operating status data and real-time waste heat source data includes: The mean absolute value of the first difference of the preprocessed main engine exhaust temperature data is determined as the temperature change gradient of the target ship. The reciprocal of the ratio between the standard deviation and the mean of the load power data is determined as the energy flow stability index of the target ship. The deviation of the main engine exhaust temperature from the temperature threshold is defined as the exhaust temperature deviation of the target ship. The rate of change of load power within a preset time window is defined as the load change rate of the target ship.

4. The ship waste heat recovery method according to claim 1, characterized in that, The determination of the operational probability of multiple waste heat recovery modes based on the temperature change gradient and energy flow stability index of the target ship includes: The temperature change gradient and energy flow stability of the target ship are used as inputs to the action prediction model, and the action probabilities of multiple waste heat recovery modes output by the action prediction model are obtained. The action prediction model is trained on a dual-depth Q network using the historical temperature change gradient and historical energy flow stability index of the target ship as samples and the historical waste heat recovery mode of the target ship as labels.

5. The ship waste heat recovery method according to claim 1, characterized in that, The weighting coefficients for determining multiple waste heat recovery modes based on the exhaust temperature deviation and load change rate of the target ship include: Based on the exhaust temperature deviation and load change rate of the target ship, and the preset weighting rules, the weight coefficients of multiple waste heat recovery modes are determined. The preset weighting rules include the weight coefficients of multiple waste heat recovery modes corresponding to different exhaust temperature deviations and load change rates.

6. The ship waste heat recovery method according to claim 1, characterized in that, The determination of the waste heat recovery mode of the target ship based on the action probability and weighting coefficient of multiple waste heat recovery modes includes: If the weighting coefficient of the target waste heat recovery mode is greater than or equal to the weighting coefficient threshold, the target waste heat recovery mode is determined as the waste heat recovery mode of the target ship. The target waste heat recovery mode is any waste heat recovery mode among multiple waste heat recovery modes. When the weighting coefficients of multiple waste heat recovery modes are all less than the weighting coefficient threshold, random sampling is performed based on the action probability of the waste heat recovery mode to determine the waste heat recovery mode of the target ship.

7. The ship waste heat recovery method according to claim 1, characterized in that, The method further includes: After determining the waste heat recovery mode of the target ship, the flow rate of the organic working fluid pump, the opening of the expander speed regulating valve, and the effective heat transfer area of ​​the plate heat exchanger are adjusted based on the waste heat recovery mode of the target ship.

8. A waste heat recovery device for ships, characterized in that, include: The acquisition module is used to acquire real-time engine operating status data and real-time waste heat source data of the target ship. The engine operating status data includes engine speed and load power, and the waste heat source data includes main engine exhaust temperature, cooling water inlet and outlet temperature difference and ambient seawater temperature. The first determination module is used to determine the temperature change gradient, energy flow stability index, exhaust temperature deviation and load change rate of the target ship based on the preprocessed real-time engine operating status data and real-time waste heat source data. The temperature change gradient represents the temperature change gradient of the main engine exhaust temperature, the energy flow stability index represents the stability of the main engine load, the exhaust temperature deviation represents the deviation of the main engine exhaust temperature from the temperature threshold, and the load change rate represents the rate of change of load power within a preset time window. The second determining module is used to determine the probability of action of multiple waste heat recovery modes based on the temperature change gradient and energy flow stability index of the target ship, and to determine the weight coefficients of multiple waste heat recovery modes based on the exhaust temperature deviation and load change rate of the target ship. The multiple waste heat recovery modes include full load optimization mode, low load economic mode and dynamic response mode. The full load optimization mode aims to achieve the maximum thermoelectric conversion efficiency, the low load economic mode aims to balance pump power consumption and power generation revenue, and the dynamic response mode adjusts the waste heat recovery cycle operation parameters based on the heat source change trend. The third determination module is used to determine the waste heat recovery mode of the target ship based on the action probability and weighting coefficient of multiple waste heat recovery modes.

9. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the ship waste heat recovery method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the ship waste heat recovery method according to any one of claims 1 to 7.

Images