A ship diesel engine fault detection method, device, equipment and storage medium

Abstract

The embodiment of the specification discloses a ship diesel engine fault detection method, device, equipment and storage medium, and relates to the technical field of fault detection processing. The scheme comprises the following steps: obtaining multiple groups of to-be-detected vibration signals of a ship diesel engine; decomposing the multiple groups of to-be-detected vibration signals of the ship diesel engine by using a symplectic geometry modal decomposition algorithm; obtaining a to-be-detected image set after fusion by using a multi-modal fusion algorithm; calculating the similarity between a target to-be-detected image in the to-be-detected image set and an image in a standard image set; determining whether the target to-be-detected image corresponds to a fault of the ship diesel engine; and comparing the to-be-detected image obtained by combining the symplectic geometry modal decomposition algorithm and the multi-modal fusion algorithm with the standard image, so that accurate and efficient fault detection of the diesel engine can be realized.

Description

Technical Field

[0001] This application relates to the field of fault detection technology, and in particular to a method, apparatus, equipment and storage medium for detecting faults in marine diesel engines. Background Technology

[0002] Marine diesel engines play a vital role in modern industry, their high efficiency, wide application, and reliability making them an important power source for ships. However, due to their long-term operation in harsh environments, marine diesel engines are prone to malfunctions. Failure to detect and address these malfunctions promptly can lead to significant economic losses or even personal injury or death. Therefore, timely fault detection of marine diesel engines is crucial.

[0003] In related technologies, faults in marine diesel engines can be detected through signal analysis and deep learning models. However, due to the complexity of marine diesel engine signals and the difficulty in selecting them, as well as the high computational complexity of deep learning models, these technologies are not feasible. Summary of the Invention

[0004] This specification provides an embodiment of a method for detecting faults in marine diesel engines, in order to solve the problems existing in the prior art of detecting faults in marine diesel engines using signal analysis and deep learning models.

[0005] To solve the above-mentioned technical problems, the embodiments in this specification are implemented as follows:

[0006] Firstly, the embodiments of this specification provide a method for detecting faults in a marine diesel engine, including:

[0007] Acquire multiple sets of vibration signals to be measured from a marine diesel engine;

[0008] The multiple sets of vibration signals to be measured are decomposed using the symplectic geometric mode decomposition algorithm to obtain several modal signals;

[0009] The multimodal fusion algorithm is used to fuse the signals of several modalities to obtain a set of images to be tested;

[0010] Determine the first normal similarity between the target image in the image set to be tested and the first normal image in the standard image set, and the first abnormal similarity between the target image in the image set and the first abnormal image in the standard image set;

[0011] When it is determined that the first normal similarity is less than the first abnormal similarity, it is determined that the marine diesel engine corresponding to the target image to be tested has a fault.

[0012] Secondly, the embodiments of this specification provide a marine diesel engine fault detection device, comprising:

[0013] The acquisition module is used to acquire multiple sets of vibration signals to be measured from the marine diesel engine;

[0014] The decomposition module is used to decompose the multiple sets of vibration signals to be measured using the symplectic geometric mode decomposition algorithm to obtain several modal signals;

[0015] The fusion module is used to fuse several modal signals using a multimodal fusion algorithm to obtain a set of images to be tested;

[0016] The first determining module is used to determine the first normal similarity between the target image to be tested in the image set to be tested and the first normal image in the standard image set, and the first abnormal similarity between the target image to be tested and the first abnormal image in the standard image set.

[0017] The second determining module is used to determine that the marine diesel engine corresponding to the target image under test has a fault when the first normal similarity is less than the first abnormal similarity.

[0018] Thirdly, the embodiments of this specification provide a marine diesel engine fault detection device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the marine diesel engine fault detection method in Scheme 1.

[0019] Fourthly, the embodiments of this specification provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the marine diesel engine fault detection method in Scheme 1.

[0020] One embodiment of this specification achieves the following beneficial effects: Multiple sets of vibration signals from a marine diesel engine are decomposed using a symplectic geometric mode decomposition algorithm, fused using a multimodal fusion algorithm to obtain a set of images to be tested, the similarity between the target image in the set of images to be tested and the images in the standard image set is calculated, and it is determined whether the marine diesel engine corresponding to the target image to be tested has a fault. By comparing the image to be tested obtained by combining the symplectic geometric mode decomposition algorithm and the multimodal fusion algorithm with the standard image, accurate and efficient fault detection of the diesel engine can be achieved. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1This is a flowchart illustrating a method for detecting faults in a marine diesel engine, as provided in an embodiment of this specification.

[0023] Figure 2 A schematic diagram of a multimodal fusion image provided in an embodiment of this specification;

[0024] Figure 3 This is a schematic diagram illustrating the comparison between the image set to be tested and the standard image set provided in the embodiments of this specification.

[0025] Figure 4 This is a schematic diagram of the structure of a marine diesel engine fault detection device provided in the embodiments of this specification;

[0026] Figure 5 This is a structural schematic diagram of a marine diesel engine fault detection device provided in the embodiments of this specification. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of one or more embodiments of this specification.

[0028] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0029] The following is a detailed description of a marine diesel engine fault detection method provided in the embodiments of the specification, in conjunction with the accompanying drawings.

[0030] Figure 1 This is a flowchart illustrating a method for detecting faults in a marine diesel engine, as provided in an embodiment of this specification. Figure 1 As shown, the process may include the following steps:

[0031] Step 110: Acquire multiple sets of vibration signals to be measured from the marine diesel engine.

[0032] In the embodiments of this specification, an acceleration sensor is used to collect vibration signals of the ship's diesel engine under operating conditions. Vibration signals within a preset time period are used as a group, and multiple groups of vibration signals under different operating conditions can be collected.

[0033] Step 120: Decompose the multiple sets of vibration signals to be measured using the symplectic geometric mode decomposition algorithm to obtain several modal signals.

[0034] In the embodiments of this specification, fault feature enhancement is achieved by employing symplectic geometric mode decomposition to eliminate the influence of noise on the signal. The acquired one-dimensional signal is x = {x1, x2, x3, ... x...} n Let n be the length of the one-dimensional signal. According to Tukens' theorem, x can be constructed as a matrix X, which is:

[0035]

[0036] Where d is the embedding dimension, t is the time delay factor, m is the number of rows in the constructed matrix, and m = n - (d-1)t.

[0037] Autocorrelation analysis of the constructed matrix X yields the Hamiltonian matrix A, where A = X. T X and T are matrix transposes. Matrix M is constructed using matrix A. Matrix M is:

[0038]

[0039] After constructing matrix M, construct symplectic orthogonal matrix Q. The relationship between matrix Q and matrix M is as follows:

[0040]

[0041] Where B is an upper triangular matrix and R is a real matrix.

[0042] Matrix Q is obtained through symplectic geometric similarity transformation, and coefficient matrix W is constructed using eigenvector matrix Q and matrix X.

[0043] Where i = [0, 1, 2, ..., d].

[0044] The single-component Z can be obtained from the coefficient matrix W and the eigenvector matrix Q. i ,

[0045] Z i =Q i W i Z = Z1 + Z2 + ... + Z k ,

[0046] For matrix Z i The transformation yields a one-dimensional time series Y. i y k It is Y i One of the data points, y k for:

[0047]

[0048] where k is the index of the k-th element in y; p is the counting variable in the summation iteration process; d* = min(m, d), which is the minimum value between the number of rows and the embedding dimension; m* = max(m, d), that is, the maximum value between the number of rows and the embedding dimension; when m < d, then z* = z ij , when m > d, z* = z ji , z ij (1 ≤ i ≤ d, 1 ≤ j ≤ m) are the elements of matrix Z i .

[0049] Performing angular averaging on each matrix to obtain a one-dimensional time series, thereby generating d groups of initial single-signal components Y = [Y1, Y2,..., Y d , that is, several modal signals.

[0050] Step 130: Using a multi-modal fusion algorithm to fuse several of the modal signals to obtain a set of images to be measured.

[0051] In the embodiments of this specification, through a multi-modal fusion algorithm, the data points in several obtained modal signals are fused onto an image to obtain an image to be measured corresponding to the vibration signal to be measured.

[0052] Step 140: Determine the first normal similarity between the target image to be measured in the set of images to be measured and the first normal image in the standard image set, and the first abnormal similarity between the target image to be measured and the first abnormal image in the standard image set.

[0053] Step 150: When it is determined that the first normal similarity is less than the first abnormal similarity, determine that there is a fault in the marine diesel engine corresponding to the target image to be measured.

[0054] In the embodiments of this specification, a normal image can be an image corresponding to the vibration signal after the normal operation of a marine diesel engine, and an abnormal image can be an image corresponding to the vibration signal after the fault operation of a marine diesel engine.

[0055] Compare the similarity between the target image to be measured in the set of images to be measured and the normal image in the standard image set to obtain the normal similarity, and compare the similarity between the target image to be measured in the set of images to be measured and the abnormal image in the standard image set to obtain the abnormal similarity.

[0056] If the normal similarity is less than the abnormal similarity, it indicates that there is a fault in the operating state of the marine diesel engine corresponding to the target image to be measured. If the normal similarity is greater than the abnormal similarity, it indicates that the operating state of the marine diesel engine corresponding to the target image to be measured is normal.

[0057] In practical applications, by comparing the similarity of each target image in the image set to be tested with normal and abnormal images in the standard image set, the operating status of the marine diesel engine under different working conditions can be obtained.

[0058] It should be understood that the order of some steps in the methods described in one or more embodiments of this specification may be interchanged according to actual needs, or some steps may be omitted or deleted.

[0059] In the embodiments of this specification, the symplectic geometric mode decomposition algorithm is used to decompose multiple sets of vibration signals to be tested from a marine diesel engine. After fusion using a multimodal fusion algorithm, a set of images to be tested is obtained. The similarity between the target image in the set of images to be tested and the images in the standard image set is calculated to determine whether there is a fault in the marine diesel engine corresponding to the target image. By comparing the image to be tested obtained by combining the symplectic geometric mode decomposition algorithm and the multimodal fusion algorithm with the standard image, accurate and efficient fault detection of the diesel engine can be achieved.

[0060] based on Figure 1 In addition to the method described in the embodiments of this specification, some specific implementation schemes of the method are also provided, which will be described below.

[0061] To reduce computational load and improve computational efficiency, optionally, the multimodal fusion algorithm described in the embodiments of this specification is used to fuse several modal signals to obtain a set of images to be tested, which may specifically include:

[0062] Based on the adaptive maximum spectral entropy method, a target mode signal is selected from the plurality of mode signals;

[0063] The target modal signals are fused using a multimodal fusion algorithm to obtain a set of images to be tested.

[0064] In the embodiments of this specification, the adaptive maximum spectral entropy method can calculate the spectral entropy of each modal signal after Fourier transform and adaptively select the maximum spectral entropy.

[0065] By comparing the entropy values ​​of different modal signals, the modal signal containing the most information or the least uncertainty is selected as the target modal signal. The target modal signals are then fused into a fused image, which contains complementary information from different modal signals, improving the comprehensiveness and accuracy of the information and reducing redundant data that needs to be filtered and processed during the process.

[0066] Each set of vibration signals to be tested is decomposed to obtain several modal signals. An adaptive maximum spectral entropy method is used to select a predetermined number of modal signals as target modal signals from the corresponding modal signals of each set of vibration signals to be tested. A multimodal fusion algorithm is then used to fuse the target modal signals corresponding to each set of vibration signals to be tested, resulting in the transformed image of each set of vibration signals to be tested. All images to be tested are then combined into a set of images to be tested.

[0067] Specifically, the six optimal modal signals are selected as the target modal signals. From the d initial single-signal components Y, six optimal modal signals Y' = [Y'1, Y'2, Y'3, Y'4, Y'5, Y'6] are selected, using the following formula:

[0068]

[0069] Among them, F i (k) are the coefficients after the Fourier transform, Y i (n) is the input signal. For complex terms, argmax(S) i ) is the index of the largest numerical value.

[0070] The data points in each mode of the obtained Y' = [Y'1, Y'2, Y'3, Y'4, Y'5, Y'6] are fused using a multimodal fusion algorithm. The multimodal fusion formula is as follows:

[0071]

[0072] Where G = [1,2,3,4,5,6], G is the Gth mode, r G (i) represents the radius of the i-th data point in the G-th mode on the polar coordinate axis, Y' Gi Let Y' be the amplitude at the i-th point of the G-th mode Y. Gmin Y' is the minimum amplitude of a one-dimensional time-domain signal with G modes. Gmax Let θ be the maximum amplitude of a one-dimensional time-domain signal with G modes. G (i) represents the angle of clockwise rotation of the Gth mode by 60°, φ G (i) represents the counterclockwise rotation angle of the Gth mode along 60°, and g is the amplification factor.

[0073] To quickly and accurately determine the current operating status of the diesel engine, optionally, before determining the first normal similarity between the target image in the image set to be tested and the first normal image in the standard image set as described in the embodiments of this specification, the method may include:

[0074] Acquire multiple sets of normal vibration signals and multiple sets of abnormal vibration signals of the marine diesel engine;

[0075] The multiple sets of normal vibration signals are decomposed using the symplectic geometric mode decomposition algorithm to obtain several normal mode signals;

[0076] The multiple sets of abnormal vibration signals are decomposed using the symplectic geometric mode decomposition algorithm to obtain several abnormal mode signals;

[0077] A multimodal fusion algorithm is used to fuse several normal modal signals to obtain a normal image set;

[0078] A multimodal fusion algorithm is used to fuse several of the aforementioned anomalous modal signals to obtain an anomalous image set;

[0079] The normal image set and the abnormal image set are combined to obtain the standard image set.

[0080] In the embodiments described in this specification, a standard image set is pre-constructed to form a benchmark for comparative analysis.

[0081] Each group of normal vibration signals is decomposed to obtain several normal modal signals. An adaptive maximum spectral entropy method is used to select a predetermined number of normal modal signals from these signals as target normal modal signals. A multimodal fusion algorithm is then used to fuse the target normal modal signals corresponding to each group of normal vibration signals to obtain the transformed normal image for each group. All normal images are then combined into a normal image set.

[0082] Each group of abnormal vibration signals is decomposed to obtain several abnormal mode signals. An adaptive maximum spectral entropy method is used to select a predetermined number of abnormal mode signals as target abnormal mode signals from these signals. A multi-modal fusion algorithm is then used to fuse the target abnormal mode signals corresponding to each group of abnormal vibration signals, resulting in an abnormal image for each group after transformation. All abnormal images are then combined into an abnormal image set.

[0083] The generated normal and abnormal images are combined to form a complete standard image set. This standard image set contains vibration characteristic images of diesel engines under normal and abnormal conditions, providing a basis for subsequent comparative analysis.

[0084] Figure 2 This is a schematic diagram of a multimodal fusion image provided in an embodiment of this specification.

[0085] like Figure 2 As shown, a is a normal image after multimodal fusion, and b is an abnormal image after multimodal fusion. Multiple normal images form a normal image set, and multiple abnormal images form an abnormal image set.

[0086] In practical applications, abnormal vibration signals of different fault types can be acquired, multiple abnormal image sets of different fault types can be established, and the corresponding fault type can be determined by similarity comparison.

[0087] Optionally, the description in the embodiments of this specification of determining that the marine diesel engine corresponding to the target image to be tested has a fault when the first normal similarity is less than the first abnormal similarity may specifically include:

[0088] Determine the second normal similarity between the target image in the image set to be tested and the second normal image in the normal image set, and the second abnormal similarity between the target image in the image set and the second abnormal image in the abnormal image set;

[0089] The first normal similarity is compared with the second normal similarity to obtain the target normal similarity;

[0090] The first anomaly similarity is compared with the second anomaly similarity to obtain the target anomaly similarity;

[0091] When the normal similarity of the target is determined to be less than the abnormal similarity of the target, it is determined that the marine diesel engine corresponding to the target image to be tested has a fault.

[0092] In the embodiments of this specification, the normal image set may include several normal images, and the target image to be tested is compared with each normal image in the normal image set to obtain the corresponding normal similarity.

[0093] An anomalous image set can include several anomalous images. The target image to be tested is compared with each anomalous image in the anomalous image set to obtain the corresponding anomalous similarity.

[0094] The smaller of the first and second normal similarities is taken as the target normal similarity, and the minimum normal similarity after comparison with normal images in the normal image set is selected as the target normal similarity.

[0095] The smaller of the first and second anomaly similarities is taken as the target anomaly similarity, and the smallest anomaly similarity after comparison with the anomaly images in the anomaly image set is selected as the target anomaly similarity.

[0096] By comparing the minimum normal similarity with the minimum abnormal similarity, if the target normal similarity is greater than the target abnormal similarity, it can be considered that the ship diesel engine state represented by the target image under test is more similar to the normal state. Therefore, it is determined that the ship diesel engine operating state corresponding to the target image under test is normal.

[0097] If the normal similarity of the target is less than the abnormal similarity of the target, it can be considered that the similarity between the ship diesel engine state represented by the target image under test and the abnormal state is higher. Therefore, it is determined that the ship diesel engine operating state corresponding to the target image under test has a fault.

[0098] Specifically, the formula for calculating the similarity between the image to be tested and the standard image is as follows:

[0099]

[0100] Where N is the pixel matrix of the standard image N, Let M be the average value of the N-pixel matrix of the standard image, and M be the pixel matrix of the M-pixel image to be tested. Let be the average value of M pixels in the image to be tested, i be the i-th standard image, and j be the j-th image to be tested.

[0101] In fault detection, selecting a smaller normal similarity as the target normal similarity means that it is more sensitive to the difference between the target image under test and the normal state. Even small differences may be regarded as potential fault signs, which helps to avoid missing faults.

[0102] Comparing multiple similarity values ​​can reduce misjudgments caused by the inaccuracy of a single comparison result. For example, if a normal image has a low similarity to the target image due to noise or other interference factors, while another normal image shows a high similarity, then taking the smaller value can avoid misjudgments caused by noise interference.

[0103] Figure 3 This is a schematic diagram illustrating the comparison between the image set to be tested and the standard image set provided in the embodiments of this specification.

[0104] like Figure 3 As shown, the image to be tested is compared with the normal image set and the abnormal image set in the standard image set to obtain the corresponding normal similarity and abnormal similarity.

[0105] By introducing multiple normal and abnormal images for comparison, and by comparing similarity to obtain more accurate judgment results, the accuracy and reliability of fault diagnosis are improved. Furthermore, by comparing with different sets of abnormal images, the fault type of the marine diesel engine can be determined.

[0106] In practical applications, the symplectic geometric mode decomposition algorithm is used to decompose multiple sets of vibration signals to be tested from a marine diesel engine. Based on the adaptive maximum spectral entropy method, a target mode signal is selected from several modal signals. The modal signals are fused using a multimodal fusion algorithm to obtain a set of images to be tested. The similarity between any target image in the set of images to be tested and normal and abnormal images in the standard image set is calculated. The minimum normal similarity and the minimum abnormal similarity are compared to determine whether there is a fault in the marine diesel engine corresponding to the target image. By combining the symplectic geometric mode decomposition algorithm with the multimodal fusion algorithm to obtain the image to be tested and comparing it with the standard image, adaptive multimodal signal selection is achieved. The computational complexity is low, and complex signals can be analyzed at multiple scales, thus enabling accurate and efficient fault detection of diesel engines.

[0107] Figure 4 This is a schematic diagram of the structure of a marine diesel engine fault detection device proposed in the embodiments of this specification.

[0108] The marine diesel engine fault detection device described in the embodiments of this specification may include:

[0109] The acquisition module 402 is used to acquire multiple sets of vibration signals to be measured from the marine diesel engine;

[0110] The decomposition module 404 is used to decompose the multiple sets of vibration signals to be measured using the symplectic geometric mode decomposition algorithm to obtain several modal signals.

[0111] The fusion module 406 is used to fuse several modal signals using a multimodal fusion algorithm to obtain a set of images to be tested;

[0112] The first determining module 408 is used to determine the first normal similarity between the target image to be tested in the image set to be tested and the first normal image in the standard image set, and the first abnormal similarity between the target image to be tested and the first abnormal image in the standard image set.

[0113] The second determining module 410 is used to determine that the marine diesel engine corresponding to the target image under test has a fault when the first normal similarity is less than the first abnormal similarity.

[0114] Optionally, the method described in the embodiments of this specification for fusing several modal signals using a multimodal fusion algorithm to obtain a set of images to be tested may specifically include:

[0115] Based on the adaptive maximum spectral entropy method, a target mode signal is selected from the plurality of mode signals;

[0116] The target modal signals are fused using a multimodal fusion algorithm to obtain a set of images to be tested.

[0117] Optionally, before determining the first normal similarity between the target image in the image set to be tested and the first normal image in the standard image set as described in the embodiments of this specification, the apparatus may include:

[0118] The acquisition module is used to acquire multiple sets of normal vibration signals and multiple sets of abnormal vibration signals of the marine diesel engine;

[0119] The decomposition module is used to decompose the multiple sets of normal vibration signals using the symplectic geometric mode decomposition algorithm to obtain several normal mode signals; and to decompose the multiple sets of abnormal vibration signals using the symplectic geometric mode decomposition algorithm to obtain several abnormal mode signals.

[0120] The fusion module is used to fuse several normal modal signals using a multimodal fusion algorithm to obtain a normal image set; and to fuse several abnormal modal signals using a multimodal fusion algorithm to obtain an abnormal image set.

[0121] The third determining module is used to combine the normal image set and the abnormal image set to obtain the standard image set.

[0122] Optionally, the description in the embodiments of this specification of determining that the marine diesel engine corresponding to the target image to be tested has a fault when the first normal similarity is less than the first abnormal similarity may specifically include:

[0123] Determine the second normal similarity between the target image in the image set to be tested and the second normal image in the normal image set, and the second abnormal similarity between the target image in the image set and the second abnormal image in the abnormal image set;

[0124] The first normal similarity is compared with the second normal similarity to obtain the target normal similarity;

[0125] The first anomaly similarity is compared with the second anomaly similarity to obtain the target anomaly similarity;

[0126] When the normal similarity of the target is determined to be less than the abnormal similarity of the target, it is determined that the marine diesel engine corresponding to the target image to be tested has a fault.

[0127] Based on the same idea, this specification also provides devices corresponding to the above methods in its embodiments.

[0128] Figure 5 This is a structural schematic diagram of a marine diesel engine fault detection device provided as an embodiment of this specification. Figure 5As shown in the embodiments of this specification, a marine diesel engine fault detection device includes a memory 530, a processor 510, and a computer program 520 stored in the memory. The processor 510 executes the computer program 520 to implement the marine diesel engine fault detection method described in any of the above embodiments.

[0129] The embodiments of this specification provide a marine diesel engine fault detection device, which may include a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the marine diesel engine fault detection method described in any of the above embodiments.

[0130] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the marine diesel engine fault detection method described in any of the above embodiments.

[0131] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for... Figure 5 As the device shown is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0132] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0133] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0134] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0135] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0136] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0137] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0138] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0139] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0140] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0141] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0142] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0143] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0144] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0146] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for detecting faults in marine diesel engines, characterized in that, include: Multiple sets of vibration signals to be measured from a marine diesel engine are acquired. These multiple sets of vibration signals are obtained by collecting vibration signals of the marine diesel engine under operating conditions using an accelerometer. Vibration signals within a preset time period are used as a group to collect multiple sets of vibration signals under different operating conditions. The multiple sets of vibration signals to be measured are decomposed using the symplectic geometric mode decomposition algorithm to obtain several modal signals; A multimodal fusion algorithm is used to fuse several modal signals to obtain a set of images to be tested. Specifically, this includes: selecting a target modal signal from the several modal signals based on the adaptive maximum spectral entropy method; fusing the target modal signal using the multimodal fusion algorithm to obtain the set of images to be tested; the adaptive maximum spectral entropy method involves calculating the spectral entropy of each modal signal after Fourier transform and adaptively selecting the largest spectral entropy; by comparing the entropy values ​​of different modal signals, selecting the modal signal containing the most information or the least uncertainty as the target modal signal, and fusing the target modal signal into a single image. The resulting image contains complementary information from different modal signals. Each group of vibration signals to be tested is decomposed into several modal signals. An adaptive maximum spectral entropy method is used to select a predetermined number of modal signals as target modal signals from these modal signals for each group of vibration signals to be tested. A multimodal fusion algorithm is then used to fuse the target modal signals corresponding to each group of vibration signals to be tested, resulting in the transformed image of each group of vibration signals to be tested. All images to be tested are combined into a set of images to be tested. Specifically, the optimal six modal signals are selected as target modal signals, resulting in d initial single-signal components. Six optimal modal signals were selected. The formula is: ； in, These are the coefficients after the Fourier transform. For input signal, For complex terms, argmax(S) i ) represents the index of the largest numerical value; The result Data points from each modality are fused using a multimodal fusion algorithm. The multimodal fusion formula is as follows: ， in, G is the Gth mode. For the Gth mode, the th The radius of each data point on the polar coordinate axis For the Gth mode The The amplitude at each point, Let G be the minimum amplitude of a one-dimensional time-domain signal with G modes. Let G be the maximum amplitude of a one-dimensional time-domain signal with G modes. For the Gth mode along Rotate the angle clockwise. For the Gth mode along The counterclockwise rotation angle, where g is the magnification factor; Multiple sets of normal vibration signals and multiple sets of abnormal vibration signals of the marine diesel engine are acquired; the multiple sets of normal vibration signals are decomposed using a symplectic geometric mode decomposition algorithm to obtain several normal mode signals; the multiple sets of abnormal vibration signals are decomposed using a symplectic geometric mode decomposition algorithm to obtain several abnormal mode signals; the several normal mode signals are fused using a multimodal fusion algorithm to obtain a normal image set; the several abnormal mode signals are fused using a multimodal fusion algorithm to obtain an abnormal image set; the normal image set and the abnormal image set are combined to obtain a standard image set; a first normal similarity is determined by comparing the target image to be tested in the image set with a first normal image in the standard image set, and a first abnormal similarity is determined by comparing the target image to be tested with a first abnormal image in the standard image set; When it is determined that the first normal similarity is less than the first abnormal similarity, it is determined that the marine diesel engine corresponding to the target image under test has a fault. Specifically, this includes: determining the second normal similarity between the target image under test in the image set and the second normal image in the normal image set, and the second abnormal similarity between the target image under test and the second abnormal image in the abnormal image set; comparing the first normal similarity with the second normal similarity to obtain the target normal similarity; comparing the first abnormal similarity with the second abnormal similarity to obtain the target abnormal similarity; when it is determined that the target normal similarity is less than the target abnormal similarity, it is determined that the marine diesel engine corresponding to the target image under test has a fault.

2. A fault detection device for marine diesel engines, characterized in that, include: The acquisition module is used to acquire multiple sets of vibration signals to be tested from the marine diesel engine. The multiple sets of vibration signals to be tested are acquired by using an accelerometer to collect vibration signals under the operating conditions of the marine diesel engine. The vibration signals within a preset time period are used as a group to acquire multiple sets of vibration signals under different operating conditions. The decomposition module is used to decompose the multiple sets of vibration signals to be measured using the symplectic geometric mode decomposition algorithm to obtain several modal signals; The fusion module is used to fuse several modal signals using a multimodal fusion algorithm to obtain a set of images to be tested. Specifically, it includes: selecting a target modal signal from the several modal signals based on an adaptive maximum spectral entropy method; fusing the target modal signal using a multimodal fusion algorithm to obtain the set of images to be tested; the adaptive maximum spectral entropy method involves calculating the spectral entropy of each modal signal after Fourier transform and adaptively selecting the largest spectral entropy; by comparing the entropy values ​​of different modal signals, selecting the modal signal containing the most information or the least uncertainty as the target modal signal, and fusing the target modal signal into a single image. The fused image contains complementary information from different modal signals. Each group of vibration signals to be tested is decomposed into several modal signals. An adaptive maximum spectral entropy method is used to select a predetermined number of modal signals as target modal signals from these modal signals for each group of vibration signals to be tested. A multimodal fusion algorithm is used to fuse the target modal signals corresponding to each group of vibration signals to be tested, resulting in the transformed image of each group of vibration signals to be tested. All images to be tested are combined into a set of images to be tested. Specifically, the optimal 6 modal signals are selected as target modal signals, resulting in d initial single-signal components. Six optimal modal signals were selected. The formula is: ； in, These are the coefficients after the Fourier transform. For input signal, For complex terms, argmax(S) i ) represents the index of the largest numerical value; The result Data points from each modality are fused using a multimodal fusion algorithm. The multimodal fusion formula is as follows: ， in, G is the Gth mode. For the Gth mode, the th The radius of each data point on the polar coordinate axis For the Gth mode The The amplitude at each point, Let G be the minimum amplitude of a one-dimensional time-domain signal with G modes. Let G be the maximum amplitude of a one-dimensional time-domain signal with G modes. For the Gth mode along Rotate the angle clockwise. For the Gth mode along The counterclockwise rotation angle, where g is the magnification factor; The first determining module is used to acquire multiple sets of normal vibration signals and multiple sets of abnormal vibration signals of the marine diesel engine; decompose the multiple sets of normal vibration signals using a symplectic geometric mode decomposition algorithm to obtain several normal mode signals; decompose the multiple sets of abnormal vibration signals using a symplectic geometric mode decomposition algorithm to obtain several abnormal mode signals; fuse the several normal mode signals using a multimodal fusion algorithm to obtain a normal image set; fuse the several abnormal mode signals using a multimodal fusion algorithm to obtain an abnormal image set; combine the normal image set and the abnormal image set to obtain a standard image set; determine the first normal similarity between the target image to be tested in the image set and the first normal image in the standard image set, and the first abnormal similarity between the target image to be tested and the first abnormal image in the standard image set; The second determining module is used to determine that the marine diesel engine corresponding to the target image under test has a fault when the first normal similarity is less than the first abnormal similarity. Specifically, it includes: determining a second normal similarity between the target image under test in the image set and a second normal image in the normal image set, and a second abnormal similarity between the target image under test and a second abnormal image in the abnormal image set; comparing the first normal similarity with the second normal similarity to obtain a target normal similarity; comparing the first abnormal similarity with the second abnormal similarity to obtain a target abnormal similarity; and determining that the marine diesel engine corresponding to the target image under test has a fault when the target normal similarity is less than the target abnormal similarity.

3. A marine diesel engine fault detection device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method of claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method of claim 1.

Images