A method and system for protecting the operation of a ship's electric propulsion system

Abstract

The present invention discloses a method and system for operating protection of a ship electric propulsion system. By generating a time series signal set from the real-time operation data set of the ship electric propulsion system, and then constructing multiple fault monitoring models through the HSMM algorithm, different time series signals can be processed respectively, enhancing the system's monitoring ability for multi-dimensional faults; through the membership function, the operation state of the system is fuzzified, which can effectively realize the fuzzy evaluation of the operation state of the ship electric propulsion system, enabling reasonable judgments and decisions to be made even in the face of some inaccurate or incomplete data. Compared with the traditional simple threshold determination, the fuzzy rule can make more reasonable judgments in the state transition stage, reduce misjudgments caused by fuzzy boundaries, improve the accuracy of fault monitoring, and further, according to the fault evaluation results, the most suitable fault protection scheme can be matched to ensure that the ship electric propulsion system is protected in a targeted and effective manner.

Description

Technical Field

[0001] The present invention relates to the technical field of condition monitoring, and particularly to a method and system for protecting the operation of a ship electric propulsion system. Background Art

[0002] A ship electric propulsion system is a ship propulsion system that uses an electric motor to drive the ship's propeller or other propulsion devices, rather than a traditional internal combustion engine or steam turbine. In a ship electric propulsion system, the main engine or generator generates electrical energy, which is then transmitted to the electric motor through a power transmission system, and the electric motor then drives the propeller or other propulsion devices. Due to its characteristics of high efficiency, environmental protection, and energy conservation, the ship electric propulsion system has become the mainstream of ship power plants. However, due to the complexity of its structure and the harshness of its working environment (such as high humidity, high temperature, vibration, etc.), the ship electric propulsion system fails frequently, seriously affecting the normal operation of the ship and the safety of the crew. Therefore, timely and accurate fault monitoring and diagnosis of the ship electric propulsion system are crucial for ensuring the safe operation of the ship and improving the work efficiency of the crew.

[0003] The existing condition monitoring of ship electric propulsion systems detects faults in the electric propulsion system through real-time parameters. However, due to the complexity of the structure of the ship electric propulsion system and the large amount of operation data, detecting faults in the electric propulsion system only by setting thresholds is prone to strong singularity and low accuracy, and it is impossible to comprehensively evaluate the state of the ship electric propulsion system. Summary of the Invention

[0004] The present invention provides a method and system for protecting the operation of a ship electric propulsion system to improve the comprehensiveness of fault prediction of the ship electric propulsion system and improve the operation stability of the ship electric propulsion system.

[0005] To solve the above technical problems, an embodiment of the present invention provides a method for protecting the operation of a ship electric propulsion system, including:

[0006] Obtain the real-time operation data set of the ship electric propulsion system, preprocess the real-time operation data set, and obtain a time series signal set;

[0007] Based on the time series signal set and the HSMM algorithm, construct a number of first fault monitoring models, and optimize each first fault monitoring model based on the ant colony algorithm to obtain a number of second fault monitoring models;

[0008] Obtain the hidden state sequence of the second fault monitoring model, generate a corresponding initial membership function based on each hidden state sequence, and perform fuzzy processing on the initial membership function to obtain a target membership function;

[0009] Determine the operating state of the ship's electric propulsion system based on the target membership function and preset fuzzy rules;

[0010] When the operating state is abnormal, defuzzify the operating state to obtain the operation evaluation result of the electric propulsion system;

[0011] Match a fault protection scheme based on the operation evaluation result, and adjust the operating parameters of the ship's electric propulsion system based on the fault protection scheme to protect the operation of the ship's electric propulsion system.

[0012] The present invention generates a time series signal set through the real-time operation data set of the ship's electric propulsion system, and then constructs multiple fault monitoring models through the HSMM (Hidden Semi-Markov Model) algorithm, which can process different time series signals respectively, enhancing the system's monitoring ability for multi-dimensional faults. At the same time, the optimization of the ant colony algorithm can automatically adjust the parameters of the model to ensure that the model can maintain high accuracy in a dynamic environment, avoiding the failure of fault monitoring caused by overfitting or underfitting of the model. In addition, by using the membership function to fuzzify the system operating state, an effective fuzzy evaluation of the operating state of the ship's electric propulsion system can be realized, enabling reasonable judgments and decisions to be made even in the face of some inaccurate or incomplete data. Compared with traditional simple threshold determination, fuzzy rules can make more reasonable judgments in the state transition stage, reducing misjudgments caused by fuzzy boundaries, improving the accuracy of fault monitoring, and further being able to match the most suitable fault protection scheme according to the fault evaluation result to ensure targeted and effective protection of the ship's electric propulsion system.

[0013] Further, the obtaining of the real-time operation data set of the ship's electric propulsion system and the preprocessing of the real-time operation data set include:

[0014] Obtain the real-time operation data set of the ship's electric propulsion system, and perform filtering processing and normalization processing on the real-time operation data set; the real-time operation data set includes current data, voltage data, rotation speed data, vibration data, and temperature data;

[0015] Set the window length based on the operation mode of the ship's electric propulsion system, and divide the data in the real-time operation data set based on the window length to obtain a time series signal set.

[0016] After filtering processing, the present invention removes high-frequency noise or interference signals, ensuring the smoothness and accuracy of data. At the same time, the data is normalized to a unified range, making different data sources comparable, avoiding the influence of the dimension differences of different data on model processing, and setting the window length according to different operating modes, which can optimize data division, making fault monitoring more accurate. Furthermore, through time window division, real-time data can be converted into independent time series signals, enabling each signal to be analyzed independently, which is convenient for subsequent model processing.

[0017] Further, constructing a number of first fault monitoring models based on the time series signal set and the HSMM algorithm includes:

[0018] Setting hidden states and corresponding hidden state duration distributions for the time series signals in the time series signal set respectively based on the operating state of the ship electric propulsion system;

[0019] Constructing a first fault detection model based on the HSMM algorithm and the time series signals, where the first fault detection model includes a hidden state duration distribution, a hidden state transition matrix, and an observation probability distribution.

[0020] By combining the HSMM algorithm with the modeling of the time series signal set, the present invention can obtain a refined fault monitoring model. Through the hidden semi-Markov model (HSMM) combined with time series data, hidden state duration, transition matrix, and observation probability distribution, it can comprehensively describe the operation and fault modes of the ship electric propulsion system, thereby improving the reliability of fault detection, enhancing the adaptability and generalization ability of the model, and enabling it to perform effective fault diagnosis and prediction under different operating environments and conditions.

[0021] Further, optimizing each first fault monitoring model based on the ant colony algorithm to obtain a number of second fault monitoring models includes:

[0022] Initializing the ant colony size and search space based on the ant colony algorithm, and initializing the parameters of the first fault monitoring model;

[0023] Performing ant colony search iteratively based on the ant colony size and search space, and updating the parameters of the first fault monitoring model;

[0024] Evaluating the fitness of the updated first fault detection model based on the fitness function in each iteration until the fitness or the number of iterations reaches a preset condition, stopping the iteration, and outputting the second fault detection model.

[0025] Through the ant colony algorithm, the present invention can adjust the search strategy according to the fitness of each ant to achieve dynamic adaptive optimization. At the same time, the ant colony algorithm has good global search ability and can stably and effectively optimize the parameters of the fault monitoring model when facing multi-modal or complex objective functions.

[0026] Further, the steps of obtaining the hidden state sequence of the second fault monitoring model, generating the corresponding initial membership function based on each hidden state sequence, and performing fuzzy processing on the initial membership function to obtain the target membership function include:

[0027] Based on each second fault monitoring model, obtain the hidden state sequence at each time point and record the probability distribution corresponding to each hidden state;

[0028] Calculate the probability value of the hidden state sequence based on the probability distribution corresponding to each hidden state, and generate the initial membership function corresponding to each second fault monitoring model based on the probability value;

[0029] Map the initial membership function to the fuzzy set based on the fuzzy function to obtain the target membership function.

[0030] In the present invention, as the probability distribution of the hidden state is converted into the membership function, the system can more carefully capture the subtle changes in the operating state, thereby early warning potential faults. And through fuzzy processing and the generation of the target membership function, the system can still perform effective reasoning and decision-making in the face of incomplete information, improving the fault monitoring accuracy of the ship electric propulsion system.

[0031] Further, when the operating state is abnormal, the steps of performing defuzzification processing on the operating state to obtain the operation evaluation result of the ship electric propulsion system include:

[0032] When the operating state is abnormal, calculate the weighted average value of the target membership function based on the centroid method to obtain the operation evaluation result, and the operation evaluation result includes the system state and the fault type.

[0033] In the present invention, through defuzzification processing, a clear system state and fault type can be extracted from the fuzzy target membership function, and through defuzzification processing using the centroid method, the accuracy of fault detection is improved, and the response ability of the system to abnormal situations is enhanced.

[0034] Further, the steps of matching the fault protection scheme based on the operation evaluation result and adjusting the operation parameters of the ship electric propulsion system based on the fault protection scheme to protect the operation of the ship electric propulsion system include:

[0035] Match a fault protection scheme in a preset policy library based on the fault type and the system state;

[0036] Obtain a control strategy based on the fault protection scheme, and adjust the operating parameters of the ship electric propulsion system based on the control strategy to protect the operation of the ship electric propulsion system.

[0037] By combining the system evaluation results, automatically matching and executing a fault protection scheme, the ship electric propulsion system can quickly respond when a fault occurs and take appropriate control measures, which not only ensures the safety of the ship, but also improves the intelligence and adaptability of the system, providing a strong guarantee for the long-term stable operation of the ship electric propulsion system.

[0038] In a second aspect, the present invention provides a ship electric propulsion system operation protection system, including: a data acquisition module, a monitoring model construction module, a fuzzy module, an evaluation module, a defuzzification module, and a maintenance module;

[0039] The data acquisition module is used to obtain a real-time operation data set of the ship electric propulsion system, preprocess the real-time operation data set, and obtain a time series signal set;

[0040] The monitoring model construction module is used to construct a number of first fault monitoring models based on the time series signal set and the HSMM algorithm, and optimize each first fault monitoring model based on the ant colony algorithm to obtain a number of second fault monitoring models;

[0041] The fuzzy module is used to obtain the hidden state sequence of the second fault monitoring model, generate a corresponding initial membership function based on each hidden state sequence, and perform fuzzy processing on the initial membership function to obtain a target membership function;

[0042] The evaluation module is used to determine the operation state of the ship electric propulsion system based on the target membership function and a preset fuzzy rule;

[0043] The defuzzification module is used to perform defuzzification processing on the operation state when the operation state is abnormal to obtain an operation evaluation result of the electric propulsion system;

[0044] The maintenance module is used to match a fault protection scheme based on the operation evaluation result, and adjust the operating parameters of the ship electric propulsion system based on the fault protection scheme to protect the operation of the ship electric propulsion system.

[0045] Further, the monitoring model construction module is used for:

[0046] Set hidden states and corresponding hidden state duration distributions for the time series signals in the time series signal set respectively based on the operating state of the ship electric propulsion system;

[0047] Construct a first fault detection model based on the HSMM algorithm and the time series signals, where the first fault detection model includes a hidden state duration distribution, a hidden state transition matrix, and an observation probability distribution.

[0048] Furthermore, the monitoring model construction module is further configured to:

[0049] Initialize the ant colony size and search space based on the ant colony algorithm, and initialize the parameters of the first fault monitoring model;

[0050] Iteratively perform ant colony search based on the ant colony size and search space, and update the parameters of the first fault monitoring model;

[0051] Evaluate the fitness of the updated first fault detection model based on the fitness function in each iteration until the fitness or the number of iterations reaches a preset condition, stop the iteration, and output the second fault detection model. Description of the Drawings

[0052] Figure 1 It is a schematic flowchart of a method for protecting the operation of a ship electric propulsion system provided in an embodiment of the present invention;

[0053] Figure 2 It is a schematic structural diagram of a system for protecting the operation of a ship electric propulsion system provided in an embodiment of the present invention. Detailed Embodiments

[0054] The following combines the drawings and embodiments to further describe in detail the specific embodiments of the present invention. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0055] The terms "first" and "second" in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0056] References to "embodiments" in this specification mean that the particular features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0057] Embodiment 1

[0058] Refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for protecting the operation of a ship electric propulsion system provided in an embodiment of the present invention. An embodiment of the present invention provides a method for protecting the operation of a ship electric propulsion system, including steps 101 to 106, as follows:

[0059] Step 101: Obtain a real-time operation dataset of the ship electric propulsion system, preprocess the real-time operation dataset, and obtain a time series signal set;

[0060] In this embodiment, the obtaining of the real-time operation dataset of the ship electric propulsion system and the preprocessing of the real-time operation dataset include:

[0061] Obtain a real-time operation dataset of the ship electric propulsion system, and perform filtering processing and normalization processing on the real-time operation dataset; the real-time operation dataset includes current data, voltage data, rotational speed data, vibration data, and temperature data;

[0062] Set a window length based on the operation mode of the ship electric propulsion system, and divide the data in the real-time operation dataset based on the window length to obtain a time series signal set.

[0063] In this embodiment, the real-time operation dataset contains sensor data from various monitoring points of the ship electric propulsion system, such as current (A), voltage (V), rotational speed (rpm), vibration (mm / s), temperature (°C), etc. These data are usually collected in the form of a time series, and the data may deviate due to noise or sensor errors.

[0064] In this embodiment, various types of data in the real-time operation dataset are subjected to filtering processing and normalization processing.

[0065] In this embodiment, methods such as a low-pass filter or a median filter are used to filter out high-frequency noise to ensure that the signal is more in line with the actual physical characteristics. After filtering processing, high-frequency noise or interference signals are removed, ensuring the smoothness and accuracy of the data.

[0066] In this embodiment, the maximum and minimum values of each sensor data are normalized to between 0 and 1 (for example, using maximum value normalization) to ensure that all signals are within the same scale range. The normalized data eliminates the dimensional differences between different types of data, making subsequent analysis and modeling more consistent and stable.

[0067] In this embodiment, the operating modes of the ship's electric propulsion system include: normal operation, low-load operation, high-load operation, etc. Different operating modes have different effects on various performance indicators of the system (such as current, voltage, etc.). Therefore, according to the actual operating mode and application requirements of the ship's electric propulsion system, an appropriate window length (for example, 10 seconds, 1 minute, etc.) is set to ensure that each time window contains sufficient historical data to identify potential fault modes.

[0068] In another alternative embodiment, the system response speed can be determined according to the operating mode. If the system response is relatively stable and the signal changes slowly, a longer window length (such as 10 seconds, 30 seconds, or even 1 minute) can be selected. If the system has a fast dynamic response (such as during startup, shutdown, etc.), a shorter time window should be selected to capture the characteristics of rapidly changing signals (such as 1 second, 3 seconds).

[0069] In another alternative embodiment, the sampling frequency of the signal can be obtained according to the operating mode, and then the window length can be determined based on the sampling frequency of the signal. For example, if the sampling frequency of the signal is high (collecting data multiple times per second), a shorter time window can be selected to capture detailed information. If the sampling frequency is low, the window length can be appropriately extended.

[0070] In this embodiment, the preprocessed real-time data is divided into multiple small windows in chronological order, and the data within the window is input as a time series signal for subsequent fault monitoring and analysis.

[0071] In this embodiment of the city, after filtering, high-frequency noise or interference signals are removed, ensuring the smoothness and accuracy of the data. At the same time, the data is normalized to a unified range, making different data sources comparable, avoiding the impact of dimensional differences of different data on model processing, and setting the window length according to different operating modes can optimize data division, making fault monitoring more accurate. Furthermore, through time window division, real-time data can be converted into independent time series signals, enabling each signal to be analyzed independently, which is convenient for subsequent model processing.

[0072] Step 102: Construct a number of first fault monitoring models based on the time series signal set and the HSMM algorithm, and optimize each first fault monitoring model based on the ant colony algorithm to obtain a number of second fault monitoring models;

[0073] In this embodiment, constructing a number of first fault monitoring models based on the time series signal set and the HSMM algorithm includes:

[0074] Setting hidden states and corresponding hidden state duration distributions for the time series signals in the time series signal set respectively based on the operating states of the ship's electric propulsion system;

[0075] Constructing a first fault detection model based on the HSMM algorithm and the time series signals, where the first fault detection model includes a hidden state duration distribution, a hidden state transition matrix, and an observation probability distribution.

[0076] In this embodiment, since the time series signal set includes time series signals of various types of data, a fault monitoring model needs to be constructed separately for each different time series signal.

[0077] In this embodiment, for each different time series signal, hidden states are defined according to the operating mode of the ship's electric propulsion system.

[0078] In this embodiment, the hidden states include a normal state, a fault warning state, and a fault state. Among them, the normal state indicates that the system is running smoothly without faults; the fault warning state indicates that the system may have faults and there are certain abnormalities; the fault state indicates that the system has a fault and needs intervention.

[0079] In this embodiment, under each hidden state, the characteristics of the signals may be different, so it is necessary to set based on the actual operating state.

[0080] In this embodiment, one of the core characteristics of HSMM is the ability to model the duration of hidden states. Each hidden state not only has a transition probability (the probability of transitioning from one hidden state to another), but also includes a duration distribution, that is, the length of time the system stays in a hidden state. For each hidden state, its duration distribution can be estimated based on historical data (such as signal fluctuations before and after a fault occurs). Usually, statistical methods such as the Gamma distribution and the exponential distribution are used to fit the duration of hidden states.

[0081] As a specific example of the embodiment of the present invention, assume that in the "fault warning" state, the ship's electric propulsion system may be in this state for a period of time (for example, several minutes or several hours), while in the "normal" state, the duration may be longer. According to historical data (such as fluctuations in sensor data and changes in operating modes), the duration distributions under different hidden states can be calculated.

[0082] In this embodiment, the structure of the first fault monitoring model includes a hidden state duration distribution, a hidden state transition matrix, and an observation probability distribution.

[0083] In this embodiment, the hidden state transition matrix represents the probabilities of transitioning between different hidden states. For example, there may be a relatively low transition probability from the "normal state" to the "fault warning state", while there may be a relatively high transition probability from the "fault warning state" to the "fault state".

[0084] In this embodiment, the transition matrix is a matrix of size N*N, where N is the number of hidden states, and each element P(i,j) represents the probability of transitioning from hidden state 𝑖 to hidden state 𝑗.

[0085] In this embodiment, the observation probability distribution represents the probability distribution of the observed data (i.e., time series signals) generated by the system under each hidden state. The generation process of the observed data can be modeled using a Gaussian distribution, a polynomial distribution, etc. For example, under the "fault state", the observed value of the current signal may be relatively high, while under the "normal state", the fluctuation of the current signal is relatively small.

[0086] In this embodiment, according to the actual situation of the ship's electric propulsion system, an initial probability distribution is set for each hidden state (such as "normal", "fault warning", "fault"), thereby constructing a first fault monitoring model. And the first fault monitoring model is trained with historical time series data (including signals such as current, voltage, and temperature) to use the Expectation-Maximization (EM) algorithm to estimate the hidden state transition matrix, the hidden state duration distribution, and the observation probability distribution.

[0087] In this embodiment, using the Hidden Semi-Markov Model (HSMM) can take into account the duration characteristics of the hidden states, and can more accurately describe the performance of the ship's electric propulsion system in different states. Especially when there are latent faults or transitional states, it can identify potential faults in advance and avoid system failures during operation.

[0088] By combining the HSMM algorithm with the modeling of the time series signal set, the present invention can obtain a refined fault monitoring model. By combining the Hidden Semi-Markov Model (HSMM) with time series data, hidden state durations, transition matrices, and observation probability distributions, it can comprehensively describe the operation and fault modes of the ship's electric propulsion system, thereby improving the reliability of fault detection, enhancing the adaptability and generalization ability of the model, and enabling effective fault diagnosis and prediction under different operating environments and conditions.

[0089] In this embodiment, optimizing each of the first fault monitoring models based on the ant colony algorithm to obtain a number of second fault monitoring models, including:

[0090] Initializing the ant colony size and the search space based on the ant colony algorithm, and initializing the parameters of the first fault monitoring model;

[0091] Based on the ant colony size and the search space, perform ant colony search iteratively to update the parameters of the first fault monitoring model;

[0092] In each iteration, evaluate the fitness of the updated first fault detection model based on the fitness function until the fitness or the number of iterations reaches a preset condition, stop the iteration, and output the second fault detection model.

[0093] In this embodiment, initialize the parameters of the ant colony algorithm, namely the ant colony size and the search space. Since the basic idea of the ant colony algorithm is to simulate the process of ants foraging in nature, the number of ants and the exploration process will affect the optimization effect. In this process, first, the size of the ant colony needs to be set, that is, the number of ants participating in the optimization. Usually, the selected range of the number of ants is from dozens to hundreds.

[0094] In this embodiment, the search space is the parameter space that the ant colony algorithm needs to search.

[0095] In this embodiment, the search space mainly includes the following parameters: the hidden state transition matrix, the hidden state duration distribution, and the observation probability distribution. The setting of the search space determines the parameter range that the ant colony needs to explore in each iteration.

[0096] In this embodiment, for each ant, its solution needs to be randomly initialized, that is, given an initial value of the hidden state transition matrix, the duration distribution, and the observation probability distribution. These initial values should be reasonable to ensure that the ant colony can effectively explore the optimization space. Thus, each ant will search according to the quality (i.e., fitness) of the current solution and select a possible path (i.e., update the parameters).

[0097] In this embodiment, when updating the parameters, the ant's choice of path depends on the fitness information of the previous iteration, with probability. For a solution with high fitness, the ant is more likely to choose this path, thus strengthening the search of this path. During the process of the ant choosing a path, it will release pheromone on the path. The concentration of the pheromone is proportional to the fitness of the path. The path with high fitness will release more pheromone, attracting more ants to choose this path.

[0098] In this embodiment, after each iteration, the ant updates the pheromone concentration of the path according to the fitness function. The pheromone update formula is:

[0099] (1)

[0100] Where, is the pheromone evaporation factor, is the concentration of the pheromone on the path, is the pheromone left by each ant on this path.

[0101] In this embodiment, ants will explore in the local space and share pheromones globally to promote global search.

[0102] In this embodiment, in each iteration, ants will evaluate the quality of the current solution according to the fitness function.

[0103] In this embodiment, a fitness function is constructed based on model accuracy, fault detection rate, and false alarm rate. Among them, the model accuracy is to calculate the error between the predicted fault state and the actual fault state, such as the mean square error (MSE) or other regression error metrics. The fault detection rate indicates whether the system fault can be accurately detected. The false alarm rate is used to measure whether the model will wrongly report a non-fault state as a fault.

[0104] As a specific example of the embodiment of the present invention, the fitness function is:

[0105] (2)

[0106] Where F is the fitness, and are weight coefficients respectively, is the detection accuracy, is the false alarm rate.

[0107] In this embodiment, the iterative process will continue until any of the following conditions is met: reaching the preset maximum number of iterations. In several iterations, the value of the fitness function does not change significantly, indicating that the optimization has reached a local optimal solution.

[0108] In this embodiment, after multiple iterations, the optimal second fault monitoring model is output, which includes an optimized hidden state transition matrix, hidden state duration distribution, and observation probability distribution. This model has significantly improved accuracy and stability in fault detection compared to the initial first fault monitoring model and can better adapt to different operating states of the ship's electric propulsion system.

[0109] In this embodiment, the ant colony algorithm can adjust the search strategy according to the fitness of each ant to achieve dynamic adaptive optimization. At the same time, the ant colony algorithm has good global search ability and can stably and effectively optimize the parameters of the fault monitoring model when facing multi-modal or complex objective functions.

[0110] Step 103: Obtain the hidden state sequences of the second fault monitoring model, generate corresponding initial membership functions based on the respective hidden state sequences, and perform fuzzy processing on the initial membership functions to obtain target membership functions;

[0111] In this embodiment, obtaining the hidden state sequence of the second fault monitoring model, generating corresponding initial membership functions based on the respective hidden state sequences, and performing fuzzification processing on the initial membership functions to obtain target membership functions includes:

[0112] Based on each second fault monitoring model, obtain the hidden state sequences at each time point, and record the probability distribution corresponding to each hidden state;

[0113] Calculate the probability value of the hidden state sequence based on the probability distribution corresponding to each hidden state, and generate the initial membership function corresponding to each second fault monitoring model based on the probability value;

[0114] Map the initial membership function to a fuzzy set based on the fuzzification function to obtain the target membership function.

[0115] In this embodiment, the second fault monitoring model is a model optimized by the ant colony algorithm, including information such as a hidden state transition matrix, a hidden state duration distribution, and an observation probability distribution. Through this model, the hidden state sequence of the ship's electric propulsion system can be obtained.

[0116] In this embodiment, the system state data corresponding to each time point is obtained through the time series signal set.

[0117] In this embodiment, using the optimized second fault monitoring model, the real-time operation data is inferred through the HSMM algorithm to obtain the hidden state at each moment. The hidden state is obtained by decoding the observed time series signal and represents the possible internal state of the system at a certain moment.

[0118] For each time point , calculate the probability that the system is in a certain hidden state, and the result is a hidden state sequence:

[0119] (3)

[0120] Wherein, is the hidden state of the system at time .

[0121] In this embodiment, for each time point , the hidden state has a corresponding probability , which represents the probability that the system is in this hidden state at this moment. Based on the probability distribution corresponding to the hidden state, the probability value of the hidden state sequence can be calculated. That is, at each moment, the probability of the hidden state occurring is used to describe the current state uncertainty of the system. For each hidden state , its probability value is used to generate the membership function.

[0122] In this embodiment, through the membership function in fuzzy logic, the degree to which an event or state belongs to a certain fuzzy set can be represented. The general value range of the membership function is [0, 1], representing the membership degree of a certain state.

[0123] In this embodiment, based on the hidden state and its probability distribution, the membership value can be calculated. Specifically:

[0124] (4)

[0125] where represents the hidden state of the normalized membership value.

[0126] In this embodiment, the hidden state sequence and the corresponding membership values are combined to generate an initial membership function. The initial membership function represents the membership values of different hidden state sequences.

[0127] In this embodiment, the initial membership function is mapped to a fuzzy set to obtain the target membership function, and the initial membership function is fuzzified and mapped into the fuzzy set. The purpose of fuzzification is to convert the original numerical data into a fuzzy set.

[0128] In this embodiment, various fuzzification functions can be used, such as triangular, trapezoidal, normal distribution and other functions, to map the membership function of the hidden state into the fuzzy set. For example, the triangular membership function is used to define the membership relationship of different hidden states in the fuzzy set. The membership degree of each hidden state will be mapped to a fuzzy set according to the selected fuzzification function. These fuzzy sets can be classified according to the operating state of the ship's electric propulsion system, such as three fuzzy sets of "normal", "minor fault" and "serious fault".

[0129] As a specific example of the embodiment of the present invention, the triangular membership function or the trapezoidal membership function is used as the fuzzification function, and the initial membership values are distributed to different fuzzy sets according to the fuzzy rules:

[0130] Normal operating state: The closer the initial membership value is to 1, the more stable the system is.

[0131] Minor fault state: The initial membership value is in the middle range (for example, 0.3 - 0.7), indicating that there is a certain deviation in the system but it does not reach the fault standard.

[0132] Serious fault state: The initial membership value is close to 0, and the system is in an abnormal state.

[0133] Preset fuzzy rules. If the initial membership degree is higher than 0.8, it belongs to the "normal operation state"; if the initial membership degree is between 0.3 and 0.8, it belongs to the "slight anomaly state"; if the initial membership degree is lower than 0.3, it belongs to the "severe fault state".

[0134] In this embodiment, for the hidden state sequence of each signal , calculate the membership degree value corresponding to the state , where j represents the state category (normal, abnormal, faulty), so as to obtain the fuzzification result in matrix form: Among them, each column corresponds to the fuzzy membership degrees of "normal", "slight anomaly", and "severe fault" respectively.

[0135] In this embodiment, for the fuzzy membership degree matrix of all signals perform weighted fusion to obtain the target membership degree function. Specifically:

[0136] (5)

[0137] Among them, is the weight of signal , reflecting the importance of different signals in evaluating the system state. The weight can be set through historical data or expert experience. represents the fused target membership degree function, which is ultimately used to evaluate the operation state of the system.

[0138] Step 104: Determine the operation state of the ship's electric propulsion system based on the target membership degree function and the preset fuzzy rules;

[0139] In this embodiment, by converting the probability distribution of the hidden state into a membership degree function, the system can more finely capture the subtle changes in the operation state, thereby warning of potential faults in advance. And through the fuzzification process and the generation of the target membership degree function, the system can still perform effective reasoning and decision-making in the face of incomplete information, improving the accuracy of fault monitoring of the ship's electric propulsion system.

[0140] Step 105: When the operation state is abnormal, perform defuzzification processing on the operation state to obtain the operation evaluation result of the electric propulsion system;

[0141] In this embodiment, further, when the operation state is abnormal, performing defuzzification processing on the operation state to obtain the operation evaluation result of the ship's electric propulsion system includes:

[0142] When the operation state is abnormal, calculate the weighted average value of the target membership degree function based on the centroid method to obtain the operation evaluation result, and the operation evaluation result includes the system state and the fault type.

[0143] In this embodiment, the centroid method calculates a weighted average according to the membership degrees of each fuzzy set in the target membership function and the system state values represented by them. Specifically:

[0144] (6)

[0145] Among them, is the membership function value of the state in the fuzzy set (i.e., the membership degree of this state), is each state value (such as different fault types, system operation modes, etc.), is the centroid value, representing the system state value obtained after defuzzification.

[0146] In this embodiment, matching a fault protection scheme based on the operation evaluation result, and adjusting the operation parameters of the ship electric propulsion system based on the fault protection scheme to perform operation protection on the ship electric propulsion system includes:

[0147] Matching a fault protection scheme in a preset policy library based on the fault type and the system state;

[0148] Obtaining a control strategy based on the fault protection scheme, and adjusting the operation parameters of the ship electric propulsion system based on the control strategy to perform operation protection on the ship electric propulsion system.

[0149] In this embodiment, the system state reflects the overall operation condition of the current ship electric propulsion system, such as "normal", "minor fault", "severe fault", etc. The fault type describes the possible fault types in the system, such as "voltage anomaly", "current overload", "overhigh temperature", etc.

[0150] By combining the system evaluation result, the present invention automatically matches and executes a fault protection scheme. The ship electric propulsion system can quickly respond when a fault occurs and take appropriate control measures, which not only ensures the safety of the ship, but also improves the intelligence and adaptability of the system, providing a strong guarantee for the long-term stable operation of the ship electric propulsion system.

[0151] Step 106: Matching a fault protection scheme based on the operation evaluation result, and adjusting the operation parameters of the ship electric propulsion system based on the fault protection scheme to perform operation protection on the ship electric propulsion system.

[0152] In this embodiment, matching a fault protection scheme based on the operation evaluation result, and adjusting the operation parameters of the ship electric propulsion system based on the fault protection scheme to perform operation protection on the ship electric propulsion system includes: ​

[0153] Match a fault protection scheme in a preset policy library based on the fault type and the system state;

[0154] Obtain a control strategy based on the fault protection scheme, and adjust the operating parameters of the ship's electric propulsion system based on the control strategy to protect the operation of the ship's electric propulsion system.

[0155] In this embodiment, the preset policy library contains protection schemes for different fault types and system states. This policy library is designed through experience, historical data, and expert knowledge to ensure effective protection and adjustment when the system fails. According to the fault type and system state obtained from the operation evaluation results, the system will search for the corresponding fault protection scheme in the preset policy library. The policy library can provide protection schemes at different levels according to different fault types, system states, and their severity.

[0156] In this embodiment, when the fault type is "too low voltage" and the system state is "minor fault", the "current limiting" or "automatic boost" protection strategy may be matched. When the fault type is "current overload" and the system state is "severe fault", the "power off" or "speed limit" protection strategy may be matched.

[0157] In this embodiment, after determining the fault protection scheme, extract the control strategy related to this scheme. The control strategy includes how to adjust the operating parameters of the ship's electric propulsion system to minimize the impact of the fault and restore normal operation. For the "current overload" fault, the control strategy may be to reduce the power output, limit the current load, etc. For the "too high temperature" fault, the control strategy may be to turn on the cooling system, adjust the working frequency of the equipment, etc. According to the selected control strategy, the system will automatically or manually adjust the operating parameters of the electric propulsion system to ensure that the system can continue to operate when a fault occurs, or quickly return to the normal state.

[0158] By combining the system evaluation results, automatically matching and executing the fault protection scheme, the ship's electric propulsion system can quickly respond when a fault occurs and take appropriate control measures, which not only ensures the safety of the ship, but also improves the intelligence and adaptability of the system, providing a strong guarantee for the long-term stable operation of the ship's electric propulsion system.

[0159] In this embodiment, a time series signal set is generated from the real-time operation data set of the ship electric propulsion system. Then, multiple fault monitoring models are constructed through the HSMM algorithm, which can process different time series signals respectively, enhancing the system's monitoring ability for multi-dimensional faults. At the same time, the optimization of the ant colony algorithm can automatically adjust the parameters of the models to ensure that the models can maintain high accuracy in a dynamic environment, avoiding the failure of fault monitoring caused by overfitting or underfitting of the models. In addition, by using the membership function to perform fuzzy processing on the system operation state, an effective fuzzy evaluation of the operation state of the ship electric propulsion system can be achieved. This enables reasonable judgments and decisions to be made even in the face of some inaccurate or incomplete data. Compared with traditional simple threshold determination, fuzzy rules can make more reasonable judgments in the state transition stage, reducing misjudgments caused by fuzzy boundaries, improving the accuracy of fault monitoring, and further matching the most appropriate fault protection scheme according to the fault evaluation results to ensure targeted and effective protection of the ship electric propulsion system.

[0160] Please refer to Figure 2 , Figure 2 FIG. is a schematic structural diagram of an operation protection system for a ship electric propulsion system provided by an embodiment of the present invention, including: a data acquisition module 201, a monitoring model construction module 202, a fuzzy module 203, an evaluation module 204, a defuzzification module 205, and a maintenance module 206;

[0161] The data acquisition module 201 is configured to obtain the real-time operation data set of the ship electric propulsion system, and preprocess the real-time operation data set to obtain a time series signal set;

[0162] The monitoring model construction module 202 is configured to construct a number of first fault monitoring models based on the time series signal set and the HSMM algorithm, and optimize each first fault monitoring model based on the ant colony algorithm to obtain a number of second fault monitoring models;

[0163] The fuzzy module 203 is configured to obtain the hidden state sequence of the second fault monitoring model, generate a corresponding initial membership function based on each hidden state sequence, and perform fuzzy processing on the initial membership function to obtain a target membership function;

[0164] The evaluation module 204 is configured to determine the operation state of the ship electric propulsion system based on the target membership function and preset fuzzy rules;

[0165] The defuzzification module 205 is configured to perform defuzzification processing on the operation state when the operation state is abnormal to obtain an operation evaluation result of the electric propulsion system;

[0166] The maintenance module 206 is configured to match a fault protection scheme based on the operation evaluation result, and adjust the operation parameters of the ship electric propulsion system based on the fault protection scheme, so as to perform operation protection on the ship electric propulsion system.

[0167] In this embodiment, the data acquisition module is configured to:

[0168] Obtain a real-time operation data set of the ship electric propulsion system, and perform filtering processing and normalization processing on the real-time operation data set; the real-time operation data set includes current data, voltage data, rotation speed data, vibration data, and temperature data;

[0169] Set a window length based on the operation mode of the ship electric propulsion system, and divide the data in the real-time operation data set based on the window length to obtain a time series signal set.

[0170] In this embodiment, the monitoring model construction module is configured to:

[0171] Set hidden states and corresponding hidden state duration distributions for the time series signals in the time series signal set respectively based on the operation state of the ship electric propulsion system;

[0172] Construct a first fault detection model based on the HSMM algorithm and the time series signals, where the first fault detection model includes a hidden state duration distribution, a hidden state transition matrix, and an observation probability distribution.

[0173] In this embodiment, the monitoring model construction module is further configured to:

[0174] Initialize the ant colony size and search space based on the ant colony algorithm, and initialize the parameters of the first fault monitoring model;

[0175] Iteratively perform ant colony search based on the ant colony size and search space to update the parameters of the first fault monitoring model;

[0176] Evaluate the fitness of the updated first fault detection model based on the fitness function in each iteration until the fitness or the number of iterations reaches a preset condition, stop the iteration, and output a second fault detection model.

[0177] In this embodiment, the fuzzy module is configured to:

[0178] Obtain the hidden state sequences at each time point based on each second fault monitoring model respectively, and record the probability distributions corresponding to the respective hidden states;

[0179] Calculate the probability value of the hidden state sequence based on the probability distribution corresponding to each hidden state, and generate an initial membership function corresponding to each second fault monitoring model based on the probability value;

[0180] Map the initial membership function to a fuzzy set based on a fuzzification function to obtain a target membership function.

[0181] In this embodiment, the defuzzification module is used for:

[0182] When the operating state is abnormal, calculate the weighted average value of the target membership function based on the centroid method to obtain an operation evaluation result, where the operation evaluation result includes a system state and a fault type.

[0183] In this embodiment, the maintenance module includes:

[0184] Match a fault protection scheme in a preset policy library based on the fault type and the system state;

[0185] Obtain a control strategy based on the fault protection scheme, and adjust the operating parameters of the ship electric propulsion system based on the control strategy to perform operating protection on the ship electric propulsion system.

[0186] In an embodiment of the present invention, a terminal device is further provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned method for operating protection of a ship electric propulsion system is implemented.

[0187] In an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the above-mentioned method for operating protection of a ship electric propulsion system.

[0188] Exemplarily, the computer program can be divided into one or more modules. One or more modules are stored in the memory and executed by the processor to complete the present invention. One or more modules can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the terminal device.

[0189] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor, a memory, and a display. Those skilled in the art can understand that the above components are only examples of the terminal device and do not constitute a limitation on the terminal device. It may include more or fewer components than those described, or combine certain components, or different components. For example, the terminal device may further include input / output devices, network access devices, a bus, etc.

[0190] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal device and connects various parts of the entire terminal device through various interfaces and circuits.

[0191] The memory can be used to store computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and by calling the data stored in the memory, the processor realizes various functions of the terminal device. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, a text conversion function, etc.); the data storage area may store data created according to the use of the mobile phone (such as audio data, text message data, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0192] Among them, when the module for protecting the operation of the ship electric propulsion system is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0193] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, it is pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for protecting the operation of a ship's electric propulsion system, characterized in that, Including: Obtain a real-time operation data set of a ship electric propulsion system, preprocess the real-time operation data set, and obtain a time series signal set; Construct a number of first fault monitoring models based on the time series signal set and the HSMM algorithm, and optimize each first fault monitoring model based on the ant colony algorithm to obtain a number of second fault monitoring models; Obtain the hidden state sequences of the second fault monitoring models, generate corresponding initial membership functions based on each hidden state sequence, and perform fuzzy processing on the initial membership functions to obtain target membership functions; Determine the operation state of the ship electric propulsion system based on the target membership function and preset fuzzy rules; When the operation state is abnormal, perform defuzzification processing on the operation state to obtain an operation evaluation result of the electric propulsion system; Match a fault protection scheme based on the operation evaluation result, and adjust the operation parameters of the ship electric propulsion system based on the fault protection scheme to perform operation protection on the ship electric propulsion system.

2. The operation protection method of a ship electric propulsion system according to claim 1, characterized in that The obtaining of the real-time operation data set of the ship electric propulsion system and the preprocessing of the real-time operation data set include: Obtain a real-time operation data set of the ship electric propulsion system, and perform filtering processing and normalization processing on the real-time operation data set; the real-time operation data set includes current data, voltage data, rotational speed data, vibration data, and temperature data; Set a window length based on the operation mode of the ship electric propulsion system, and divide the data in the real-time operation data set based on the window length to obtain a time series signal set.

3. The operation protection method of a ship electric propulsion system according to claim 2, characterized in that The constructing of a number of first fault monitoring models based on the time series signal set and the HSMM algorithm includes: Set hidden states and corresponding hidden state duration distributions for the time series signals in the time series signal set respectively based on the operation state of the ship electric propulsion system; Construct a first fault detection model based on the HSMM algorithm and the time series signals, and the first fault detection model includes a hidden state duration distribution, a hidden state transition matrix, and an observation probability distribution.

4. A method for protecting the operation of a ship's electric propulsion system according to claim 3, characterized in that, The optimizing of each first fault monitoring model based on the ant colony algorithm to obtain a number of second fault monitoring models includes: Initialize the ant colony size and search space based on the ant colony algorithm, and initialize the parameters of the first fault monitoring model; Perform ant colony search iteratively based on the ant colony size and search space to update the parameters of the first fault monitoring model; Evaluate the fitness of the updated first fault detection model based on the fitness function in each iteration until the fitness or the number of iterations reaches a preset condition, stop the iteration, and output the second fault detection model.

5. The operation protection method for a ship electric propulsion system according to claim 4, characterized in that, The obtaining of the hidden state sequences of the second fault monitoring models, generating corresponding initial membership functions based on each hidden state sequence, and performing fuzzy processing on the initial membership functions to obtain target membership functions includes: Obtain the hidden state sequences at each time point based on each second fault monitoring model respectively, and record the probability distributions corresponding to each hidden state; Calculate the probability value of the hidden state sequence based on the probability distributions corresponding to each hidden state, and generate an initial membership function corresponding to each second fault monitoring model based on the probability value; Map the initial membership function to a fuzzy set based on a fuzzification function to obtain a target membership function.

6. The operation protection method of a ship electric propulsion system according to claim 5, characterized in that When the operating state is abnormal, perform defuzzification processing on the operating state to obtain an operating evaluation result of the ship's electric propulsion system, including: When the operating state is abnormal, calculate the weighted average value of the target membership function based on the centroid method to obtain an operating evaluation result, and the operating evaluation result includes the system state and the fault type.

7. The operation protection method of a ship electric propulsion system according to claim 6, characterized in that, Match a fault protection scheme based on the operating evaluation result, and adjust the operating parameters of the ship's electric propulsion system based on the fault protection scheme to perform operating protection on the ship's electric propulsion system, including: Match a fault protection scheme in a preset policy library based on the fault type and the system state; Obtain a control strategy based on the fault protection scheme, and adjust the operating parameters of the ship's electric propulsion system based on the control strategy to perform operating protection on the ship's electric propulsion system.

8. A ship electric propulsion system operation protection system, characterized in that, Include: A data acquisition module, a monitoring model construction module, a fuzzy module, an evaluation module, a defuzzification module, and a maintenance module; The data acquisition module is used to obtain a real-time operation data set of the ship's electric propulsion system, and preprocess the real-time operation data set to obtain a time series signal set; The monitoring model construction module is used to construct a number of first fault monitoring models based on the time series signal set and the HSMM algorithm, and optimize each first fault monitoring model based on the ant colony algorithm to obtain a number of second fault monitoring models; The fuzzy module is used to obtain the hidden state sequence of the second fault monitoring model, generate a corresponding initial membership function based on each hidden state sequence, and perform fuzzification processing on the initial membership function to obtain a target membership function; The evaluation module is used to determine the operating state of the ship's electric propulsion system based on the target membership function and preset fuzzy rules; The defuzzification module is used to perform defuzzification processing on the operating state when the operating state is abnormal to obtain an operating evaluation result of the electric propulsion system; The maintenance module is used to match a fault protection scheme based on the operating evaluation result, and adjust the operating parameters of the ship's electric propulsion system based on the fault protection scheme to perform operating protection on the ship's electric propulsion system.

9. The operation protection system of a ship electric propulsion system according to claim 8, characterized in that, The monitoring model construction module is used to: Set hidden states and corresponding hidden state duration distributions for the time series signals in the time series signal set based on the operating state of the ship's electric propulsion system; Construct a first fault detection model based on the HSMM algorithm and the time series signals, and the first fault detection model includes a hidden state duration distribution, a hidden state transition matrix, and an observation probability distribution.

10. A running protection system for a ship electric propulsion system according to claim 9, characterized in that, The monitoring model construction module is also used to: Initialize the ant colony size and search space based on the ant colony algorithm, and initialize the parameters of the first fault monitoring model; Based on the size of the ant colony and the search space, perform ant colony search iteratively to update the parameters of the first fault monitoring model; In each iteration, evaluate the fitness of the updated first fault detection model based on the fitness function until the fitness or the number of iterations reaches a preset condition, stop the iteration, and output the second fault detection model.

Images