Automatic intelligent voltage adjusting method for improving electrical performance of LNG (liquefied natural gas) ship

Abstract

The invention discloses an automatic intelligent voltage regulation method for improving the electrical performance of an LNG ship, and the method comprises the steps: carrying out the preprocessing of real-time data after a power system enters a working state, transmitting the preprocessed data to a control system PID module, converting the data into a voltage regulation signal after the data is processed by the control system PID module, and transmitting the voltage regulation signal to an AVR system module, an algorithm model is preset in a PID module of a control system, the algorithm model is obtained by collecting historical data from an LNG ship power system, preprocessing the collected historical data, building the algorithm model through a long-short term memory neural network and a convolutional neural network and training the algorithm model, and the algorithm model is obtained through the algorithm model. The algorithm model feeds back and adjusts the voltage through intelligent prediction and multiple iteration processing, so that the output voltage reaches or approaches the standard voltage to realize stable balance. According to the method, the deep learning optimization algorithm is adopted, automatic adjustment of the LNG ship power system is achieved, oscillation and faults of the power system are reduced, and the overall performance of the ship is improved.

Description

Technical Field

[0001] This invention relates to the field of marine electrical systems technology, and in particular to a method for automatically and intelligently regulating voltage to improve the electrical performance of LNG carriers. Background Technology

[0002] Automatic Voltage Regulator (AVR) systems play a crucial role in the power systems of LNG carriers, primarily maintaining the stability of the main generator output voltage. This is especially important on LNG carriers with frequent load fluctuations and complex power systems. Modern AVRs possess rapid response capabilities and precise voltage regulation functions, effectively suppressing busbar voltage fluctuations and flicker, ensuring the normal operation of critical equipment such as cargo pumps and propulsion systems. Furthermore, AVRs can enable multi-unit parallel control, data communication, and remote operation and maintenance, providing technical support for the efficient and safe operation of LNG carriers. They can also be integrated with power plant automation systems to improve overall energy efficiency and system stability.

[0003] While AVR systems bring stability to the electrical systems of LNG carriers, their application also presents certain challenges. Firstly, AVR equipment is expensive, and the commissioning process is complex, requiring a high level of technical expertise from designers. Secondly, system parameters significantly impact the regulation effect; improper circuit design can lead to voltage over-adjustment or oscillation. Furthermore, digital AVR systems rely on stable communication links; loss of connection with the upper-level control system can affect performance. During system modification or upgrades, relevant tests and certifications from classification societies are required, increasing the project implementation cycle and cost. These factors must be fully considered and mitigated in practical applications. Summary of the Invention

[0004] To address the shortcomings of the existing technology, this invention provides an automatic intelligent voltage adjustment method for improving the electrical performance of LNG ships. By employing a deep learning optimization algorithm, it achieves rapid automatic adjustment of the LNG ship's power system, reduces power system oscillations and faults, and improves the overall performance of the ship.

[0005] To achieve the above-mentioned objectives, the present invention provides the following technical solution:

[0006] An automatic intelligent voltage regulation method for improving the electrical performance of an LNG carrier, the LNG carrier including an electrical system, the electrical system including an IAS system, a control system PID module and an AVR system module, the IAS system including multiple sensors installed on the ship, the method comprising the following steps:

[0007] S1. Collect historical data from the LNG ship's power system and preprocess the collected historical data. The historical data includes input data and output data. The input data includes input voltage and excitation current. The output data includes output voltage. The preprocessing includes filtering and standardization.

[0008] S2. The processed historical data is used to build a deep optimization algorithm model through a long short-term memory neural network and a convolutional neural network. Then, the deep optimization algorithm model is trained by inputting historical data, and the trained deep optimization algorithm model is used as the preset algorithm of the PID module of the control system.

[0009] S3. Turn on the power system to enter the working state, collect data in real time through sensors and preprocess the real-time data through the IAS system;

[0010] S4. The pre-processed data is transmitted to the PID module of the control system. After being processed by the PID module of the control system, it is converted into an adjustable voltage signal and transmitted to the AVR system module.

[0011] The S5 and AVR systems output adjustable voltage based on the received adjustable voltage signal, enabling the power system to achieve stable voltage output.

[0012] Furthermore, the control system PID module includes a PID (proportional-integral-derivative) controller, and the AVR system module includes an amplifier module, an exciter module, a generator module, and a voltage sensor module. The PID controller is used to receive the signal fed back by the voltage sensor module and to give an adjustment signal after calculation by a deep optimization algorithm model, and to transmit the adjustment signal to the amplifier module. The set voltage is the standard voltage for the operation of the electrical equipment.

[0013] The amplifier module is used to receive the error signal transmitted by the PID controller, amplify the error signal, and transmit it to the exciter module.

[0014] The exciter module includes an exciter for receiving signals transmitted from the amplifier module and adjusting the excitation current according to the signals;

[0015] The generator module is used to receive excitation current and regulate the output voltage;

[0016] The voltage sensor module is used to detect the voltage output by the generator module and feed the signal back to the PID controller.

[0017] Based on the above technical solution, the present invention has the following advantages:

[0018] 1. This invention integrates advanced artificial intelligence and deep learning to predict possible faults and excitation current fluctuations, thereby adjusting the output voltage value, providing early warning and taking measures to reduce the probability of faults occurring;

[0019] 2. Through intelligent detection and control, this invention achieves higher precision voltage regulation by using advanced algorithms and sensor detection, which can reduce voltage fluctuations, improve the stability of the power system, and thus ensure the normal operation of various electrical equipment on LNG ships;

[0020] 3. This invention can reduce maintenance costs: Through self-diagnosis and fault prediction functions, potential problems can be detected in advance, preventive maintenance can be carried out, and responses to changes in power load and fault conditions can be made more quickly, ensuring that the voltage is stable within the preset range, reducing the failure rate, reducing the equipment wear rate and energy waste rate, and reducing the operating cost of LNG ships.

[0021] 4. This invention can increase security. Through real-time adaptive analysis, the intelligent AVR system can quickly identify and respond to different situations, and can also identify and handle abnormal situations in a timely manner, ensuring the safety of the power system and avoiding safety accidents caused by power failures. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the workflow of the present invention.

[0023] Figure 2 This is a schematic diagram of the PID module of the control system of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention is described below with reference to specific embodiments shown in the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0025] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0026] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms and should not be construed as indicating or implying relative importance. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0027] In the description of this invention, unless otherwise specified and limited, it should be noted that the terms "installation", "connection" and "linking" should be interpreted broadly. For example, they can refer to mechanical connection or internal connection between two components. They can be direct connection or indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0028] To better understand the technical solution of the present invention, the present invention will be described in detail below with reference to specific embodiments.

[0029] An automatic intelligent voltage regulation method for improving the electrical performance of an LNG carrier, the LNG carrier including an electrical system, the electrical system including an IAS system, a control system PID module and an AVR system module, the IAS system including multiple sensors installed on the ship, the method comprising the following steps:

[0030] S1. Collect historical data from the LNG ship's power system and preprocess the collected historical data. The historical data includes input data and output data. The input data includes input voltage and excitation current. The output data includes output voltage. The preprocessing includes filtering and standardization.

[0031] S2. The processed historical data is used to build a deep optimization algorithm model through a long short-term memory neural network and a convolutional neural network. Then, the deep optimization algorithm model is trained by inputting historical data, and the trained deep optimization algorithm model is used as the preset algorithm of the PID module of the control system.

[0032] S3. Turn on the power system to enter the working state, collect data in real time through sensors and preprocess the real-time data through the IAS system;

[0033] S4. The pre-processed data is transmitted to the PID module of the control system. After being processed by the PID module of the control system, it is converted into an adjustable voltage signal and transmitted to the AVR system module.

[0034] The S5 and AVR systems output adjustable voltage based on the received adjustable voltage signal, enabling the power system to achieve stable voltage output.

[0035] In practical operation, the detailed working process of this application is as follows: First, after the power system enters the working state, the IAS system (Integrated Automation System) collects real-time data through sensors and preprocesses the collected real-time data. This process includes filtering and standardization of the raw data to ensure that the subsequent control module obtains high-quality information input. The preprocessed real-time data information can be recognized and utilized by the PID module of the control system. The preprocessed data is transmitted to the PID module of the control system. Initially, the PID module of the control system provides a predicted adjustment signal to the AVR system module through a deep optimization algorithm model. The AVR system module adjusts the voltage and outputs the voltage according to the received adjustment signal. The output voltage data is collected and the data signal is fed back to the PID module of the control system. The PID module of the control system compares the output voltage with the set voltage and generates an error signal. Depending on the situation of the error signal, such as... Figure 1 As shown: 1. An error signal indicates that the output voltage has reached or is close to the set voltage, that is, the difference between the output voltage and the set voltage does not exceed the preset error threshold. At this time, the PID module of the control system no longer outputs an adjustment signal, and the AVR system module maintains the output voltage unchanged; 2. An error signal indicates that the output voltage has not reached or is close to the set voltage, that is, the difference between the output voltage and the set voltage exceeds the preset error threshold. The deep optimization algorithm model generates and outputs the corresponding adjustment signal to the AVR system module. The AVR system module adjusts the voltage and outputs the voltage according to the received adjustment signal, collects the output voltage data and feeds the data signal back to the PID module of the control system. The PID module of the control system compares the output voltage with the set voltage. After multiple iterations, the output voltage finally reaches or is close to the set voltage.

[0036] By leveraging the analysis and prediction capabilities of the deep optimization algorithm model, an adjustment signal can be provided initially. Furthermore, when subsequent error signals indicate that the output voltage has not reached or is close to the set voltage, a more suitable adjustment signal is provided through prediction. This effectively reduces the number of feedback loop iterations during voltage regulation, significantly improving regulation efficiency. In practice, due to the continuous expansion of the database, the deep optimization algorithm model undergoes self-optimization and upgrades, adaptively adjusting to improve the regulation response speed and overall system robustness. It can provide more accurate predictions and voltage regulation signals, leading to increasingly higher regulation efficiency.

[0037] Ultimately, the system outputs a stable voltage to meet the high reliability and stability requirements of LNG ship electrical systems. Simultaneously, the entire system forms a closed-loop structure, with the output results fed back to the front-end control module via a feedback path, enabling real-time error correction and dynamic response control, thereby significantly improving the overall performance and intelligence level of the power system.

[0038] like Figure 2 As shown, the control system PID module includes a PID controller, and the AVR system module includes an amplifier module, an exciter module, a generator module, and a voltage sensor module.

[0039] The PID controller receives the signal fed back from the voltage sensor module and calculates an adjustment signal using a deep optimization algorithm model. The adjustment signal is then transmitted to the amplifier module. The set voltage is the standard operating voltage of the electrical equipment. The signal fed back from the voltage sensor module is the output voltage signal. After comparing it with the set voltage (the standard voltage of the electrical equipment), an error signal is generated. Based on this error signal, the deep optimization algorithm model can generate an adjustment signal and transmit it to the AVR system module.

[0040] The amplifier module is used to receive the error signal transmitted by the PID controller, representing a transfer function. It simulates the proportional gain and integral delay functions in a PID controller, possesses a certain dynamic response capability, and amplifies and transmits the error signal to the exciter module.

[0041] Exciter Module It includes an exciter, which receives the signal transmitted from the amplifier module and adjusts the excitation current according to the signal, further processes the amplifier module, and represents a transfer function model, which is two first-order systems in series, and approximates the dynamic characteristics of the actual exciter.

[0042] Generator Module The transmitted signal output is converted into the actual output of the system, which is used to receive the excitation current and adjust the output voltage, representing the dynamic response process of the synchronous generator voltage output;

[0043] Voltage sensor module The system detects the voltage output of the generator module and feeds the signal back to the PID controller. A simple first-order delay system is used to model the system, simulating the actual voltage measurement and feedback delay. Essentially, the control system receives a fluctuating harmonic signal as input on the left. The PID controller generates an output signal based on the input signal, creating a closed-loop signal. This output signal is then re-inputted to the left input signal, converting the system's output signal into a feedback loop that is sent back to the error calculation module. The error is then compared with the input signal for optimization and deep learning, forming a negative feedback closed-loop control system.

[0044] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them; although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications can still be made to the specific implementation of the invention or equivalent substitutions can be made to some technical features without departing from the spirit of the technical solutions of the present invention, and all such modifications and substitutions should be covered within the scope of the technical solutions claimed in the present invention.

Claims

1. A method for automatically and intelligently regulating voltage to improve the electrical performance of an LNG carrier, the LNG carrier including an electrical system, the electrical system including an IAS system, a control system PID module and an AVR system module, the IAS system including multiple sensors installed on the ship, characterized in that, The method includes the following steps: S1. Collect historical data from the LNG ship's power system and preprocess the collected historical data. The historical data includes input data and output data. The input data includes input voltage and excitation current. The output data includes output voltage. The preprocessing includes filtering and standardization. S2. The processed historical data is used to build a deep optimization algorithm model through a long short-term memory neural network and a convolutional neural network. Then, the deep optimization algorithm model is trained by inputting historical data, and the trained deep optimization algorithm model is used as the preset algorithm of the PID module of the control system. S3. Turn on the power system to enter the working state, collect data in real time through sensors and preprocess the real-time data through the IAS system; S4. The pre-processed data is transmitted to the PID module of the control system. After being processed by the PID module of the control system, it is converted into an adjustable voltage signal and transmitted to the AVR system module. The S5 and AVR systems output adjustable voltage based on the received adjustable voltage signal, enabling the power system to achieve stable voltage output.

2. The method for automatically and intelligently adjusting voltage to improve the electrical performance of LNG carriers according to claim 1, characterized in that, The control system PID module includes a PID controller, and the AVR system module includes an amplifier module, an exciter module, a generator module, and a voltage sensor module. The PID controller is used to receive the signal fed back by the voltage sensor module and to give the adjustment signal after calculation by the deep optimization algorithm model, and transmit the adjustment signal to the amplifier module. The set voltage is the standard voltage for the operation of the electrical equipment. The amplifier module is used to receive the error signal transmitted by the PID controller, amplify the error signal, and transmit it to the exciter module. The exciter module includes an exciter for receiving signals transmitted from the amplifier module and adjusting the excitation current according to the signals; The generator module is used to receive excitation current and regulate the output voltage; The voltage sensor module is used to detect the voltage output by the generator module and feed the signal back to the PID controller.

Images