Fault detection and response method and system for energy storage device

By cleaning and feature extraction of the current, voltage and temperature data of the ship's energy storage device, establishing a monitoring model, performing fault analysis and PI control, the problem of insufficient fault detection and response speed is solved, and detection accuracy and safety are improved. Reduces maintenance costs and maintenance complexity.

CN118739611BActive Publication Date: 2024-11-29HUNAN XILAIKE ENERGY STORAGE TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411209897.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-29
Estimated Expiration
2044-08-30

AI Technical Summary

Technical Problem

The fault detection technology of ship energy storage devices has limitations, and it is impossible to achieve high-precision detection, insufficient response speed, lack of unified standards and specifications, resulting in maintenance difficulties and safety hazards. The existing fault reconstruction system is costly, complex and difficult to be harsh. Run stably in the environment.

Method used

By collecting current, voltage and temperature data of ship energy storage devices, data cleaning and feature extraction, parameter monitoring models are established, fault analysis and detection are carried out, power adjustment is used to realize internal fault processing, and monitoring data is displayed through visual interface and call the police.

Benefits of technology

Improve the accuracy and efficiency of fault detection, reduce maintenance time and cost, enhance the reliability and safety of ship energy storage devices, realize remote monitoring and automated alarms, and minimize the safety of faults for ship operation and crew. Influence.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118739611B_ABST
    Figure CN118739611B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of ship energy storage fault processing, and discloses a fault detection and response method and system for an energy storage device. Firstly, data of current, voltage and temperature of a ship energy storage device are collected, and data cleaning, denoising and eigenvalue extraction are performed on the collected data. Secondly, a ship energy storage device parameter monitoring model is established through the processed data, and the ship energy storage device parameters are monitored and predicted. Then, the parameter monitoring model outputs the ship energy storage device monitoring data and prediction data, and the ship energy storage device is subjected to fault analysis and detection. Finally, the fault data is recorded and stored, and the monitored and predicted parameter data of the energy storage device are displayed through a visual screen. An alarm unit is set to alarm for faults that cannot be self-regulated, thereby realizing remote monitoring and automatic alarm.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of ship energy storage fault processing and discloses a fault detection and response method and system for an energy storage device. Background Art

[0002] There are some shortcomings in the development of fault detection and response of ship energy storage devices. At present, the fault detection technology of ship energy storage devices has certain limitations and cannot achieve high-precision detection of all potential faults. Some faults may take a long time to be detected, which affects the safety and reliability of the ship. When a fault occurs, the response speed of the ship energy storage device needs to be further improved. In some fault situations, the current response speed may not meet the needs of ship operation in emergency situations, resulting in safety hazards. At present, there is a lack of unified standards and specifications in the field of fault detection and response of ship energy storage devices. Different manufacturers and different models of equipment may adopt different fault detection and response solutions, which brings certain difficulties to ship maintenance and management. Once a fault occurs, ship maintenance personnel may lack clear fault diagnosis and maintenance guidance, resulting in the failure to deal with the fault in a timely and effective manner. Ship energy storage devices usually need to be integrated with other ship systems, but in actual applications, due to the differences between the systems, there are certain challenges in system integration.

[0003] For example, a Chinese patent application with publication number CN117118020A discloses a ship power station fault reconstruction system, which belongs to the field of ship power stations and solves the technical problem of how to reconstruct ship power station faults so that the faulty circuit can be repaired accurately and reliably. In this invention, different fault types are processed by a fault reconstruction module, including reconstruction of faulty energy storage battery packs, faulty circuit breakers and faulty branches. In the process of processing the target faulty branch, the transfer object of the target faulty branch is finally determined through multi-level analysis and calculation, or a maintenance signal is generated. The faulty branch of the ship power station can be reconstructed by conditional analysis, which is more reliable than the reconstruction method based on sample training prediction in the prior art, and is simpler and more convenient than the complex algorithm in the prior art. At the same time, in the process of confirming the transfer object of the target faulty branch, it is ensured that the important equipment and devices of the ship power station can operate normally and the safety of the ship operation is ensured.

[0004] The design of the system in the above patent requires complex hardware and software support, which will increase the cost and complexity of the ship power station. In addition, the maintenance and update of the system may also require additional investment, which may increase the operating cost of the system.

[0005] As a special working environment, ship power stations may be affected by factors such as humidity, salt spray, and vibration. The fault reconstruction system needs to be able to operate stably and reliably in such a harsh environment, which may be a challenge. Ship power stations will face various complex fault conditions, including multiple faults at the same time or cross faults, etc. The system may need more powerful algorithms and logic to handle these complex situations. If the ship is already equipped with other types of power station fault diagnosis systems, then the new fault reconstruction system needs to be compatible with the existing system and can be seamlessly integrated. This may require some additional engineering work. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In order to solve the above technical problems, the main purpose of the present invention is to provide a fault detection and response method for an energy storage device, comprising:

[0008] S1. Collect the data of current, voltage and temperature of the ship energy storage device, and perform data cleaning, denoising and feature value extraction on the collected data;

[0009] S2. Establish a ship energy storage device parameter monitoring model through the processed data, monitor and predict the ship energy storage device parameters, fit the loss value, and optimize the parameter monitoring model;

[0010] The parameter monitoring model includes a current monitoring model, a voltage monitoring model and a temperature monitoring model. The current monitoring model is as follows:

[0011]

[0012]

[0013] Among them, I is the current value of the ship energy storage device transmission line, E is the output voltage value of the ship energy storage device, R is the line resistance, is the current flowing through the line resistance, is the hidden layer weight of the i-th group of current, is the current value of the transmission line of the i-th group of ship energy storage devices, is the current monitoring value of the energy storage device, is the current deviation value, n is any positive integer, i is an ordinal number, 1, 2, 3, ..., n;

[0014] The voltage monitoring model calculation expression is as follows:

[0015]

[0016]

[0017] Among them, U is the voltage value of the power transmission line of the ship energy storage device, is the voltage monitoring value of the energy storage device, is the hidden layer weight of the jth group voltage, is the voltage value of the power transmission line of the jth group of ship energy storage devices, is the voltage deviation value, j is the ordinal number, which takes the value as 1, 2, 3, ..., n;

[0018] S3. The parameter monitoring model outputs monitoring data and prediction data of the ship energy storage device, and performs fault analysis and detection on the ship energy storage device;

[0019] S4. Receive fault analysis data through the fault response module and judge the fault. If the energy storage device has an external fault, the system will alarm externally. If the energy storage device has an internal fault, the internal fault unit of the energy storage device will be judged.

[0020] S5. The internal fault unit of the energy storage device is processed by adjusting the power, and the active power and reactive power are adjusted by PI control. If the internal fault unit of the energy storage device cannot be processed by adjusting the power, a fault warning is issued;

[0021] S6. Record and store fault data, display the monitored and predicted parameter data of the energy storage device through a visual screen, and set an alarm unit to alarm for faults that cannot be self-regulated.

[0022] As a preferred solution of a method for fault detection and response of an energy storage device of the present invention, wherein:

[0023] The voltage sensor is used to collect the voltage when the energy storage device is running;

[0024] The current sensor is used to collect the current when the energy storage device is running;

[0025] The temperature sensor is used to collect the temperature of the energy storage device when it is running;

[0026] The voltage parameters, current parameters and temperature parameters of the energy storage device are energy storage data parameters.

[0027] As a preferred solution of a method for fault detection and response of an energy storage device of the present invention, wherein:

[0028] The data cleaning includes removing abnormal values ​​and processing missing values ​​of the collected data of current, voltage and temperature of the ship energy storage device;

[0029] Data collected through the de-noising process and subject to electromagnetic interference and equipment failure;

[0030] Extracting a feature vector from the data after data cleaning and denoising, the feature vector including a statistical value, a frequency domain feature and a time domain feature;

[0031] Feature extraction is used to transform raw data into a more informative and discriminable form.

[0032] As a preferred solution of a method for fault detection and response of an energy storage device of the present invention, wherein:

[0033] The parameter monitoring model is established by using the processed parameter data of the ship energy storage device, and the parameter monitoring model is used to monitor the parameters of the ship energy storage device and predict the parameter change trend of the ship energy storage device, and fit the predicted value by setting a loss function;

[0034] As a preferred solution of a method for fault detection and response of an energy storage device of the present invention, wherein:

[0035] The loss value is used to determine whether the predicted value is a valid value. If it is a valid value, the valid value is input as a reference value into the optimization function for optimizing the parameter monitoring model;

[0036] The loss function, the calculation expression is as follows:

[0037]

[0038] in, is the loss value, is the actual output parameter value of the energy storage device, predicting output parameter values ​​for the energy storage device;

[0039] If the loss value is close to 0, it means that the parameter monitoring model has good prediction performance;

[0040] The optimization function calculation expression is as follows:

[0041]

[0042] in, is the optimized value output by the optimization function, λ is the compensation constant value, is the p-th power of the monitoring parameter input by the qth group, is the pth power of the normal value of the qth group of output parameters, p is an ordinal number taking the value 1, 2, 3, ..., N, q is an ordinal number taking the value 1, 2, 3, ..., N, is the total error of the input monitoring parameters.

[0043] As a preferred solution of a method for fault detection and response of an energy storage device of the present invention, wherein:

[0044] Output the monitoring data of the ship energy storage device through the parameter monitoring model, the monitoring data includes the current, voltage and temperature of the ship energy storage device;

[0045] The fault analysis unit is used to analyze energy storage system faults, including system external faults and internal unit faults;

[0046] The system external faults include transmission line faults and step-up transformer faults;

[0047] The internal unit faults include abnormal output voltage, abnormal output current and abnormal temperature impedance point faults of the ship energy storage device;

[0048] The fault processing unit is used to receive the fault location and output a fault processing signal. If a fault occurs, the fault response unit controls the output power of the energy storage device through PI control voltage control signal and current control signal, thereby controlling the fault.

[0049] As a preferred solution of a method for fault detection and response of an energy storage device of the present invention, wherein:

[0050] The fault response unit is used to receive a fault processing signal. The fault response unit includes a first voltage control signal and a second voltage control signal. The calculation expression of the first voltage control signal is as follows:

[0051]

[0052] in, is the first voltage control signal, is the d-axis component of the voltage of the ship energy storage device, is the PI control parameter, is the PI control parameter, is the d-axis component of the reference current, is the actual current d-axis component, t is the control timing;

[0053] The calculation expression of the second voltage control signal is as follows:

[0054]

[0055] in, is the second voltage control signal, is the q-axis component of the ship energy storage device voltage, is the q-axis component of the reference current, is the q-axis component of the actual current.

[0056] As a preferred solution of a method for fault detection and response of an energy storage device of the present invention, wherein:

[0057] Setting up a user interface to display the status and trend of various parameters of the energy storage device in real time;

[0058] Generate regular failure analysis reports and performance evaluation reports through reports;

[0059] If the ship energy storage device cannot handle the fault by automatically adjusting parameters, an alarm is issued through the alarm unit.

[0060] A fault detection and response system for an energy storage device, comprising:

[0061] A sensor module, including a voltage sensor, a current sensor, and a temperature sensor;

[0062] The processing module includes a data cleaning unit, a normalization unit and a feature extraction unit. The data cleaning unit is used to pre-process the collected energy storage data parameters. The normalization unit is used to perform format-unified processing on the pre-processed energy storage data parameters. The feature extraction unit is used to perform feature extraction on the energy storage data parameters after the format-unified processing.

[0063] A monitoring module, including a parameter monitoring model, a loss fitting unit and an optimization model unit. The parameter monitoring model is used to monitor the parameters of the energy storage device. The loss fitting unit is used to calculate the predicted value and the actual loss value. The optimization model unit is used to optimize the parameter monitoring model in real time.

[0064] A fault detection module, comprising a fault analysis unit for analyzing a fault of the energy storage device, a fault processing unit for processing the fault of the energy storage device, and a fault response unit for responding to a result of processing the fault;

[0065] An alarm module, used for receiving the fault that cannot be self-regulated output by the fault response unit and issuing an alarm;

[0066] The tuning module is used to optimize the parameter monitoring model to mitigate the impact of faults on the ship system;

[0067] A storage module for storing fault data and self-adjustment logs;

[0068] Visualization module, used to display ship energy storage device parameters, ship energy storage device fault parameters and fault processing data;

[0069] User Interface and Visualization includes an intuitive, user-friendly interface that allows vessel maintenance personnel to easily view monitoring results, fault conditions, and response recommendations given by the system.

[0070] A computer device includes a memory for storing instructions and a processor for executing the instructions, so that the device implements a fault detection and response method for an energy storage device.

[0071] A computer-readable storage medium stores a computer program, which, when executed, implements a fault detection and response method for an energy storage device.

[0072] Beneficial effects of the present invention:

[0073] The present invention improves the accuracy and efficiency of fault detection by real-time monitoring and analyzing data, predicts potential faults, and takes responsive measures, thereby reducing maintenance time and costs.

[0074] The artificial intelligence-based system of the present invention also improves the ability to identify different types of faults by learning historical data and pattern recognition, thereby further improving the reliability and safety of the ship energy storage device.

[0075] The present invention realizes remote monitoring and automatic alarm, notifies relevant personnel in time and enables them to take necessary actions, thereby minimizing the impact of faults on ship operation and crew safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0077] Figure 1 A flow chart of a fault detection and response method for an energy storage device of the present invention;

[0078] Figure 2 A diagram showing the composition of a fault detection and response system for an energy storage device of the present invention;

[0079] Figure 3 The present invention is a schematic diagram of a fault detection and response system for an energy storage device for self-regulating and controlling a fault of the energy storage device. DETAILED DESCRIPTION

[0080] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0081] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0082] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0083] Embodiment 1

[0084] like Figure 1 As shown, a fault detection and response method for an energy storage device includes:

[0085] S1. Collect the data of current, voltage and temperature of the ship energy storage device, and perform data cleaning, denoising and feature value extraction on the collected data;

[0086] Among them, the voltage sensor is used to collect voltage parameters when the energy storage device is running;

[0087] The current sensor is used to collect current parameters when the energy storage device is running;

[0088] The temperature sensor is used to collect temperature parameters of the energy storage device during operation;

[0089] The voltage parameter, current parameter and temperature parameter of the energy storage device are energy storage data parameters;

[0090] Furthermore, data cleaning includes removing outliers and processing missing values ​​from the collected data of current, voltage and temperature of ship energy storage devices to ensure the accuracy and reliability of subsequent analysis;

[0091] The collected data is affected by electromagnetic interference, equipment failure or sensor error, so it needs to be denoised. Methods include filters, wavelet transforms and other techniques to smooth the data and remove noise.

[0092] Extract feature vectors from the cleaned and denoised data, which include statistical values, frequency domain features, time domain features, etc. Feature extraction is used to convert raw data into a more informative and distinguishable form so that subsequent fault diagnosis and prediction models can process more effectively.

[0093] S2. Establish a ship energy storage device parameter monitoring model through the processed data, monitor and predict the ship energy storage device parameters, fit the loss value, and optimize the parameter monitoring model;

[0094] A parameter monitoring model is established through the processed parameter data of the ship energy storage device. The parameter monitoring model is used to monitor the parameters of the ship energy storage device and predict the parameter change trend of the ship energy storage device, and fit the predicted value by setting a loss function;

[0095] If the loss value is less than the minimum prediction threshold, the predicted value is a valid value, which is used as a reference value to input into the optimization function of the optimization parameter monitoring model. If the loss value is greater than the maximum prediction threshold, the predicted value is an invalid value.

[0096] The parameter monitoring model includes a current monitoring model, a voltage monitoring model, and a temperature monitoring model. The current monitoring model is as follows:

[0097]

[0098]

[0099] Among them, I is the current value of the ship energy storage device transmission line, E is the output voltage value of the ship energy storage device, R is the line resistance, is the current flowing through the line resistance, is the hidden layer weight of the i-th group of current, is the current value of the transmission line of the i-th group of ship energy storage devices, is the current monitoring value of the energy storage device, is the current deviation value, n is any positive integer, i is an ordinal number, 1, 2, 3, ..., n;

[0100] The voltage monitoring model calculation expression is as follows:

[0101]

[0102]

[0103] Among them, U is the voltage value of the power transmission line of the ship energy storage device, is the voltage monitoring value of the energy storage device, is the hidden layer weight of the jth group voltage, is the voltage value of the power transmission line of the jth group of ship energy storage devices, is the voltage deviation value, j is the ordinal number, which takes the value as 1, 2, 3, ..., n;

[0104] Based on the monitoring of the current and voltage of different lines of the energy storage device, the ability to identify different types of faults can be improved, thereby further improving the reliability and safety of the ship's energy storage device.

[0105] The loss value is used to determine whether the predicted value is a valid value. If it is a valid value, the valid value is input as a reference value into the optimization function for optimizing the parameter monitoring model;

[0106] The loss function, the calculation expression is as follows:

[0107]

[0108] in, is the loss value, is the actual output parameter value of the energy storage device, predicting output parameter values ​​for the energy storage device;

[0109] If the loss value is close to 0, it means that the parameter monitoring model has good prediction performance;

[0110] The optimization function calculation expression is as follows:

[0111]

[0112] in, is the optimized value output by the optimization function, λ is the compensation constant value, is the p-th power of the monitoring parameter input by the qth group, is the pth power of the normal value of the qth group of output parameters, p is an ordinal number taking the value 1, 2, 3, ..., N, q is an ordinal number taking the value 1, 2, 3, ..., N, is the total error of the input monitoring parameters.

[0113] S3. The parameter monitoring model outputs monitoring data and prediction data of the ship energy storage device, and performs fault analysis and detection on the ship energy storage device;

[0114] Output the monitoring data of the ship energy storage device through the parameter monitoring model, the monitoring data includes the current, voltage and temperature of the ship energy storage device;

[0115] S4. Receive fault analysis data through the fault response module and judge the fault. If the energy storage device has an external fault, the system will alarm externally. If the energy storage device has an internal fault, the internal fault unit of the energy storage device will be judged.

[0116] The fault analysis unit is used to analyze the energy storage system faults, including system external faults and internal unit faults;

[0117] Furthermore, external system faults include transmission line faults, step-up transformer faults, etc. External system faults may lead to over-modulation phenomena, etc.

[0118] Internal unit failures include abnormal output voltage, abnormal output current, abnormal temperature, impedance point failure, etc. of the ship energy storage device;

[0119] The fault processing unit receives the fault location and outputs a fault processing signal. If a fault occurs, the fault response unit controls the voltage control signal and the current control signal through PI, thereby controlling the output power of the energy storage device and controlling the fault;

[0120] S5. The internal fault unit of the energy storage device is processed by adjusting the power, and the active power and reactive power are adjusted by PI control. If the internal fault unit of the energy storage device cannot be processed by adjusting the power, a fault warning is issued;

[0121] The fault response unit is used to receive a fault processing signal. The fault response unit includes a first voltage control signal and a second voltage control signal. The calculation expression of the first voltage control signal is as follows:

[0122]

[0123] in, is the first voltage control signal, is the d-axis component of the voltage of the ship energy storage device, is the PI control parameter, is the PI control parameter, is the d-axis component of the reference current, is the actual current d-axis component, t is the control timing;

[0124] The second voltage control signal, the calculation expression is as follows:

[0125]

[0126] in, is the second voltage control signal, is the q-axis component of the ship energy storage device voltage, is the q-axis component of the reference current, is the q-axis component of the actual current;

[0127] like Figure 3 As shown, is the first voltage control signal, is the second voltage control signal, is the d-axis component of the voltage of the ship energy storage device, is the q-axis component of the ship energy storage device voltage, is the actual value of the d-axis current, is the actual value of q-axis current;

[0128] The voltage control signal is obtained by space vector pulse width modulation SVPWM to control the switch of IGBT, and finally control the output of active power and reactive power of the ship energy storage device. By controlling the output of active power and reactive power of the ship energy storage device, the voltage, current and temperature of the ship energy storage device fault are responded to.

[0129] The d-axis and q-axis are the dq rotating coordinate system;

[0130] S6. Record and store fault data, display the monitored and predicted parameter data of the energy storage device through a visual screen, and set an alarm unit to alarm for faults that cannot be self-regulated.

[0131] Set up a user interface or dashboard to display the status and trends of various parameters of the energy storage device in real time, helping operators quickly understand the health status of the device;

[0132] Generate regular fault analysis reports and performance evaluation reports through reports to provide basis and support for management decisions;

[0133] If the ship energy storage device cannot handle the fault by automatically adjusting parameters, an alarm will be issued through the alarm unit.

[0134] Embodiment 2

[0135] like Figure 2 As shown, a fault detection and response system for an energy storage device includes:

[0136] The sensor module includes a voltage sensor, a current sensor and a temperature sensor.

[0137] The processing module includes a data cleaning unit, a normalization unit and a feature extraction unit. The data cleaning unit is used to preprocess the collected energy storage data parameters, the normalization unit is used to unify the format of the preprocessed energy storage data parameters, and the feature extraction unit is used to extract features from the energy storage data parameters after the unified format processing.

[0138] The monitoring module includes a parameter monitoring model, a loss fitting unit and an optimization model unit. The parameter monitoring model is used to monitor the parameters of the energy storage device, the loss fitting unit is used to calculate the predicted value and the actual loss value, and the optimization model unit is used to optimize the parameter monitoring model in real time.

[0139] The fault detection module includes a fault analysis unit for analyzing the fault of the energy storage device, a fault processing unit for processing the fault of the energy storage device, and a fault response unit for responding to the result of processing the fault.

[0140] The alarm module is used for receiving the fault that cannot be self-adjusted output by the fault response unit and issuing an alarm.

[0141] The tuning module is used to optimize the parameter monitoring model to mitigate the impact of faults on the ship system.

[0142] The storage module is used to store fault data and self-adjustment logs.

[0143] The visualization module is used to display the ship energy storage device parameters, ship energy storage device fault parameters and fault handling data.

[0144] User Interface and Visualization includes an intuitive, user-friendly interface that allows vessel maintenance personnel to easily view monitoring results, fault conditions, and response recommendations given by the system.

[0145] Embodiment 3

[0146] A computer device includes a memory for storing instructions and a processor for executing the instructions, so that the device implements a fault detection and response method for an energy storage device.

[0147] Embodiment 4

[0148] A computer-readable storage medium stores a computer program, which, when executed, implements a fault detection and response method for an energy storage device.

[0149] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only two embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible, for example, the size, scale, structure, shape and ratio of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc., without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. Any "device plus function" clause is intended to cover the structure of the execution function described in this article, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiment. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0150] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).

[0151] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, the development effort will be a routine task of design, fabrication, and production without undue experimentation.

[0152] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A fault detection and response method for an energy storage device, characterized in that: include: S1. Collect the data of current, voltage and temperature of the ship energy storage device, and perform data cleaning, denoising and feature value extraction on the collected data; S2. Establish a ship energy storage device parameter monitoring model through the processed data, monitor and predict the ship energy storage device parameters, fit the loss value, and optimize the parameter monitoring model; The parameter monitoring model includes a current monitoring model, a voltage monitoring model and a temperature monitoring model. The current monitoring model is as follows: ; ; Among them, I is the current value of the ship energy storage device transmission line, E is the output voltage value of the ship energy storage device, R is the line resistance, is the current flowing through the line resistance, is the hidden layer weight of the i-th group of current, is the current value of the transmission line of the i-th group of ship energy storage devices, is the current monitoring value of the energy storage device, is the current deviation value, n is any positive integer, i is an ordinal number, 1, 2, 3, ..., n; The voltage monitoring model calculation expression is as follows: ; ; Among them, U is the voltage value of the power transmission line of the ship energy storage device, is the voltage monitoring value of the energy storage device, is the hidden layer weight of the jth group voltage, is the voltage value of the power transmission line of the jth group of ship energy storage devices, is the voltage deviation value, j is the ordinal number, which takes the value as 1, 2, 3, ..., n; S3. The parameter monitoring model outputs monitoring data and prediction data of the ship energy storage device, and performs fault analysis and detection on the ship energy storage device; The loss value is used to determine whether the predicted value is a valid value. If it is a valid value, the valid value is input as a reference value into the optimization function for optimizing the parameter monitoring model; The loss function, the calculation expression is as follows: ; in, is the loss value, is the actual output parameter value of the energy storage device, predicting output parameter values ​​for the energy storage device; If the loss value is close to 0, it means that the parameter monitoring model has good prediction performance; The optimization function calculation expression is as follows: ; in, is the optimized value output by the optimization function, λ is the compensation constant value, is the p-th power of the monitoring parameter input by the qth group, is the pth power of the normal value of the qth group of output parameters, p is an ordinal number taking the value 1, 2, 3, ..., N, q is an ordinal number taking the value 1, 2, 3, ..., N, is the total error of input monitoring parameters; Output the monitoring data of the ship energy storage device through the parameter monitoring model, the monitoring data includes the current, voltage and temperature of the ship energy storage device; The fault analysis unit is used to analyze energy storage system faults, including system external faults and internal unit faults; The system external faults include transmission line faults and step-up transformer faults; The internal unit faults include abnormal output voltage, abnormal output current and abnormal temperature impedance point faults of the ship energy storage device; The fault processing unit is used to receive the fault location and output a fault processing signal. If a fault occurs, the fault response unit controls the output power of the energy storage device through PI control of the voltage control signal and the current control signal, thereby controlling the fault; S4. Receive fault analysis data through the fault response module and judge the fault. If the energy storage device has an external fault, the system will alarm externally. If the energy storage device has an internal fault, the internal fault unit of the energy storage device will be judged. S5. The internal fault unit of the energy storage device is processed by adjusting the power, and the active power and reactive power are adjusted by PI control. If the internal fault unit of the energy storage device cannot be processed by adjusting the power, a fault warning is issued; S6. Record and store fault data, display the monitored and predicted parameter data of the energy storage device through a visual screen, and set an alarm unit to alarm for faults that cannot be self-regulated.

2. A method for fault detection and response of an energy storage device according to claim 1, characterized in that: The voltage sensor is used to collect the voltage when the energy storage device is running; The current sensor is used to collect the current when the energy storage device is running; The temperature sensor is used to collect the temperature of the energy storage device when it is running; The voltage parameters, current parameters and temperature parameters of the energy storage device are energy storage data parameters.

3. A fault detection and response method for an energy storage device according to claim 2, characterized in that: The data cleaning includes removing abnormal values ​​and processing missing values ​​of the collected data of current, voltage and temperature of the ship energy storage device; Data collected through the de-noising process and subject to electromagnetic interference and equipment failure; Extracting a feature vector from the data after data cleaning and denoising, the feature vector including a statistical value, a frequency domain feature and a time domain feature; Feature extraction is used to transform raw data into a more informative and discriminable form.

4. A method for fault detection and response of an energy storage device according to claim 3, characterized in that: The parameter monitoring model is established through the processed parameter data of the ship energy storage device. The parameter monitoring model is used to monitor the parameters of the ship energy storage device and predict the parameter change trend of the ship energy storage device, and fit the predicted value by setting the loss function.

5. A method for fault detection and response of an energy storage device according to claim 4, characterized in that: The fault response unit is used to receive a fault processing signal. The fault response unit includes a first voltage control signal and a second voltage control signal. The calculation expression of the first voltage control signal is as follows: ; in, is the first voltage control signal, is the d-axis component of the voltage of the ship energy storage device, is the PI control parameter, is the PI control parameter, is the d-axis component of the reference current, is the actual current d-axis component, t is the control timing; The calculation expression of the second voltage control signal is as follows: ; in, is the second voltage control signal, is the q-axis component of the ship energy storage device voltage, is the q-axis component of the reference current, is the q-axis component of the actual current.

6. A method for fault detection and response of an energy storage device according to claim 5, characterized in that: Setting up a user interface to display the status and trend of various parameters of the energy storage device in real time; Generate regular failure analysis reports and performance evaluation reports through reports; If the ship energy storage device cannot handle the fault by automatically adjusting parameters, an alarm is issued through the alarm unit.

7. A fault detection and response system for an energy storage device, used to implement a fault detection and response method for an energy storage device according to any one of claims 1 to 6, characterized in that: include: A sensor module, including a voltage sensor, a current sensor, and a temperature sensor; The processing module includes a data cleaning unit, a normalization unit and a feature extraction unit. The data cleaning unit is used to pre-process the collected energy storage data parameters. The normalization unit is used to perform format-unified processing on the pre-processed energy storage data parameters. The feature extraction unit is used to perform feature extraction on the energy storage data parameters after the format-unified processing. A monitoring module, including a parameter monitoring model, a loss fitting unit and an optimization model unit. The parameter monitoring model is used to monitor the parameters of the energy storage device. The loss fitting unit is used to calculate the predicted value and the actual loss value. The optimization model unit is used to optimize the parameter monitoring model in real time. A fault detection module, comprising a fault analysis unit for analyzing a fault of the energy storage device, a fault processing unit for processing the fault of the energy storage device, and a fault response unit for responding to a result of processing the fault; An alarm module, used for receiving the fault that cannot be self-adjusted output by the fault response unit and issuing an alarm; The tuning module is used to optimize the parameter monitoring model to mitigate the impact of faults on the ship system; A storage module for storing fault data and self-adjustment logs; The visualization module is used to display the ship energy storage device parameters, ship energy storage device fault parameters and fault handling data.

8. A computer device, characterized in that: include: A memory for storing instructions; A processor is used to execute the instruction so that the device implements a fault detection and response method for an energy storage device as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, a fault detection and response method for an energy storage device as described in any one of claims 1 to 6 is implemented.

Citation Information

Patent Citations

  • Ship power station fault reconstruction system

    CN117118020A

  • Fault diagnosis method

    CN117150414A

  • Marine engine room diagnosis method based on fault relation analysis

    CN117784765A